AIICS

Fredrik Heintz

All Publications

Hide abstracts BibTeX entries
2024
[132] Henrik Carlsen, Bjorn Nykvist, Somya Joshi and Fredrik Heintz. 2024.
Chasing artificial intelligence in shared socioeconomic pathways.
One Earth, 7(1):18–22. CELL PRESS.
DOI: 10.1016/j.oneear.2023.12.015.
Note: Funding Agencies|Mistra Geopolitics research program [2016/11]

The development of artificial intelligence has likely reached an inflection point, with significant implications for how research needs to address emerging technologies and how they drive long-term socioeconomic development of importance for climate change scenarios.

2023
[131] Linda Mannila and Fredrik Heintz. 2023.
Introducing programming and computational thinking in grades 1–9: Sweden in an international context.
In Jonas Hallström, Marc J. de Vries, editors, Programming and computational thinking in technology education: Swedish and international perspectives, pages 60–88. Brill Academic Publishers. ISBN: 9789004687912.
Find book at a swedish library/Hitta boken i ett svenskt bibliotek: https://libris.kb.se/bib/1jpx587nzql432l...

In this chapter, we situate Sweden in an international context focusing on how programming and computational thinking have been introduced into primary and lower-secondary education (grades 1–9 in the Swedish system). Our review shows that the strategies used in different countries have their own pros and cons, and there is no clear evidence establishing that one method is preferable. Moreover, due to a lack of clear guidelines, decisions on how programming is taught, by whom, and when, are commonly made at school level, also in Sweden. This freedom, or burden, to locally decide on how to implement the curriculum has left teachers in a difficult position, where they are to fulfil the requirements of the curriculum without proper training, time, and competence needed. This has naturally had a negative impact on how programming and computational thinking have been and are introduced at schools. Based on the review we provide six recommendations, which posit that to succeed, a much more systematic and holistic approach is needed, addressing the needs of teachers, students, and schools.

[130] Resmi Ramachandranpillai, Md Fahim Sikder and Fredrik Heintz. 2023.
Fair Latent Deep Generative Models (FLDGMs) for Syntax-Agnostic and Fair Synthetic Data Generation.
In , pages 1938–1945.
DOI: 10.3233/FAIA230484.
Fulltext: https://doi.org/10.3233/FAIA230484

Deep Generative Models (DGMs) for generating synthetic data with properties such as quality, diversity, fidelity, and privacy is an important research topic. Fairness is one particular aspect that has not received the attention it deserves. One difficulty is training DGMs with an in-process fairness objective, which can disturb the global convergence characteristics. To address this, we propose Fair Latent Deep Generative Models (FLDGMs) as enablers for more flexible and stable training of fair DGMs, by first learning a syntax-agnostic, model-agnostic fair latent representation (low dimensional) of the data. This separates the fairness optimization and data generation processes thereby boosting stability and optimization performance. Moreover, data generation in the low dimensional space enhances the accessibility of models by reducing computational demands. We conduct extensive experiments on image and tabular domains using Generative Adversarial Networks (GANs) and Diffusion Models (DMs) and compare them to the state-of-the-art in terms of fairness and utility. Our proposed FLDGMs achieve superior performance in generating high-quality, high-fidelity, and high-diversity fair synthetic data compared to the state-of-the-art fair generative models.

[129] Katarina Sperling, Linnéa Stenliden, Jörgen Nissen and Fredrik Heintz. 2023.
Behind the Scenes of Co-designing AI and LA in K-12 Education.
Postdigital Science and Education, ??(??):????.
DOI: 10.1007/s42438-023-00417-5.
Publication status: Epub ahead of print
fulltext:print: https://liu.diva-portal.org/smash/get/di...

This article explores the complex challenges of co-designing an AI- and learning analytics (LA)-integrated learning management system (LMS). While co-design has been proposed as a human-centred design approach for scaling AI and LA adoption, our understanding of how these design processes play out in real-life settings remains limited. This study is based on ethnographic fieldwork in primary and secondary schools and employs a relational materialist approach to trace, visualise, and analyse the increasingly complex and transformative relations between a growing number of actors. The findings shed light on the intricate ecosystem in which AI and LA are being introduced and on the marketisation of K-12 education. Instead of following a rational and sequential approach that can be easily executed, the co-design process emerged as a series of events, shifting from solely generating ideas with teachers to integrating and commercialising the LMS into a school market with an already high prevalence of educational technology (EdTech). AI and LA in education, co-design and data-driven schooling served as negotiating ideas, boundary objects, which maintained connectivity between actors, despite limited AI and LA implementation and the development of a stand-alone app. Even though teachers and students were actively involved in the design decisions, the co-design process did not lead to extensive adoption of the LMS nor did it sufficiently address the ethical issues related to the unrestricted collection of student data.

[128] Katarina Sperling, Cormac McGrath, Linnéa Stenliden, Anna Åkerfeldt and Fredrik Heintz. 2023.
Mapping AI Literacy in Teacher Education.
In 2nd International Symposium on Digital Transformation: August 21-23, 2023, Linnaeus University, Växjö.
Link: https://open.lnu.se/index.php/isdt/artic...

Artificial intelligence (AI) is often highlighted as a transformative technology that can“address some of the biggest challenges in education today”(UNESCO, 2019). Introducing data-driven AI in classrooms also raises pedagogical and ethical concerns related to students’, teachers’ and teacher educators’ understanding of how AI works in theory and practice (Holmes, 2022; Sperling et al., 2022). This extended abstract presents initial findings from the first study conducted within the WASP-HS1-funded research project: \"AI Literacy for Swedish Teacher Education - A Participatory Design Approach\". The project aims to establish a scientific foundation for teaching AI literacy in teacher education (TE) programs.

[127] Mattias Tiger, David Bergström, Simon Wijk Stranius, Evelina Holmgren, Daniel de Leng and Fredrik Heintz. 2023.
On-Demand Multi-Agent Basket Picking for Shopping Stores.
In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 5793–5799. IEEE. ISBN: 9798350323658, 9798350323665.
DOI: 10.1109/ICRA48891.2023.10160398.
Note: Funding: Wallenberg AI, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation; National Graduate School in Computer Science (CUGS), Sweden; Excellence Center at Linkoping-Lund for Information Technology (ELLIIT); Knut and Alice Wallenberg Foundation [KAW 2019.0350]; TAILOR Project - EU Horizon 2020 research and innovation programme [952215]
fulltext:postprint: https://liu.diva-portal.org/smash/get/di...

Imagine placing an online order on your way to the grocery store, then being able to pick the collected basket upon arrival or shortly after. Likewise, imagine placing any online retail order, made ready for pickup in minutes instead of days. In order to realize such a low-latency automatic warehouse logistics system, solvers must be made to be basketaware. That is, it is more important that the full order (the basket) is picked timely and fast, than that any single item in the order is picked quickly. Current state-of-the-art methods are not basket-aware. Nor are they optimized for a positive customer experience, that is; to prioritize customers based on queue place and the difficulty associated with picking their order. An example of the latter is that it is preferable to prioritize a customer ordering a pack of diapers over a customer shopping a larger order, but only as long as the second customer has not already been waiting for too long. In this work we formalize the problem outlined, propose a new method that significantly outperforms the state-of-the-art, and present a new realistic simulated benchmark. The proposed method is demonstrated to work in an on-line and real-time setting, and to solve the on-demand multi-agent basket picking problem for automated shopping stores under realistic conditions.

[126] Johan Källström and Fredrik Heintz. 2023.
Model-Based Multi-Objective Reinforcement Learning with Dynamic Utility Functions.
In Proceedings of the Adaptive and Learning Agents Workshop (ALA) at AAMAS 2023, pages 1–9.
Workshop Website: https://alaworkshop2023.github.io/
Paper Link: https://alaworkshop2023.github.io/papers...

Many real-world problems require a trade-off between multiple conflicting objectives. Decision-makers’ preferences over solutions to such problems are determined by their utility functions, which convert multi-objective values to scalars. In some settings, utility functions change over time, and the goal is to find methods that can efficiently adapt an agent’s policy to changes in utility. Previous work on learning with dynamic utility functions has focused on model-free methods, which often suffer from poor sample efficiency. In this work, we instead propose a model-based actor-critic, which explores with diverse utility functions through imagined rollouts within a learned world model between interactions with the real environment. An experimental evaluation shows that by learning a model of the environment the performance of the agent can be improved compared to model-free algorithms.

[125] Conor F. Hayes, Roxana Rădulescu, Eugenio Bargiacchi, Johan Källström, Matthew Macfarlane, Mathieu Reymond, Timothy Verstraeten, Luisa M. Zintgraf, Richard Dazeley, Fredrik Heintz, Enda Howley, Athirai A. Irissappane, Patrick Mannion, Ann Nowé, Gabriel Ramos, Marcello Restelli, Peter Vamplew and Diederik M. Roijers. 2023.
A Brief Guide to Multi-Objective Reinforcement Learning and Planning.
In A. Ricci, W. Yeoh, N. Agmon, B. An, editors, Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 1988–1990. ISBN: 978-1-4503-9432-1.
Proceedings: https://www.ifaamas.org/Proceedings/aama...

Real-world sequential decision-making tasks are usually complex, and require trade-offs between multiple–often conflicting–objectives. However, the majority of research in reinforcement learning (RL) and decision-theoretic planning assumes a single objective, or that multiple objectives can be handled via a predefined weighted sum over the objectives. Such approaches may oversimplify the underlying problem, and produce suboptimal results. This extended abstract outlines the limitations of using a semi-blind iterative process to solve multi-objective decision making problems. Our extended paper [4], serves as a guide for the application of explicitly multi-objective methods to difficult problems.

[124] Peter Vamplew, Benjamin J. Smith, Johan Källström, Gabriel Ramos, Roxana Rădulescu, Diederik M. Roijers, Conor F. Hayes, Fredrik Heintz, Patrick Mannion, Pieter J.K. Libin, Richard Dazeley and Cameron Foale. 2023.
Scalar Reward is Not Enough.
In Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 839–841. ISBN: 978-1-4503-9432-1.
Proceedings: https://www.ifaamas.org/Proceedings/aama...

Silver et al.[14] posit that scalar reward maximisation is sufficient to underpin all intelligence and provides a suitable basis for artificial general intelligence (AGI). This extended abstract summarises the counter-argument from our JAAMAS paper [19].

[123] Johan Källström and Fredrik Heintz. 2023.
Model-Based Actor-Critic for Multi-Objective Reinforcement Learning with Dynamic Utility Functions.
In Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 2818–2820. ISBN: 978-1-4503-9432-1.
Proceedings: https://www.ifaamas.org/Proceedings/aama...

Many real-world problems require a trade-off between multiple conflicting objectives. Decision-makers’ preferences over solutions to such problems are determined by their utility functions, which convert multi-objective values to scalars. In some settings, utility functions change over time, and the goal is to find methods that can efficiently adapt an agent’s policy to changes in utility. Previous work on learning with dynamic utility functions has focused on model-free methods, which often suffer from poor sample efficiency. In this work, we instead propose a model-based actor-critic, which explores with diverse utility functions through imagined rollouts within a learned world model between interactions with the real environment. An experimental evaluation on Minecart, a well-known benchmark for multi-objective reinforcement learning, shows that by learning a model of the environment the quality of the agent’s policy is improved compared to model-free algorithms.

[122] Kashyap Haresamudram, Stefan Larsson and Fredrik Heintz. 2023.
Three Levels of AI Transparency.
Computer, 56(2):93–100. IEEE COMPUTER SOC.
DOI: 10.1109/MC.2022.3213181.
Note: Funding Agencies|AI Transparency and Consumer Trust; Wallenberg AI; Autonomous Systems and Software Program-Humanities and Society (WASP-HS)

The concept of transparency is fragmented in artificial intelligence (AI) research, often limited to transparency of the algorithm alone. We propose that AI transparency operates on three levels-algorithmic, interaction, and social-all of which need to be considered to build trust in AI. We expand upon these levels using current research directions, and identify research gaps resulting from the conceptual fragmentation of AI transparency highlighted within the context of the three levels.

[121] Finn Rietz, Sven Magg, Fredrik Heintz, Todor Stoyanov, Stefan Wermter and Johannes A. Stork. 2023.
Hierarchical goals contextualize local reward decomposition explanations.
Neural Computing & Applications, 35(??):16693–16704. Springer London Ltd.
DOI: 10.1007/s00521-022-07280-8.
Note: Funding Agencies|Orebro University; Wallenberg AI, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation; Federal Ministry for Economic Affairs and Climate [FKZ 20X1905A-D]
fulltext:print: https://liu.diva-portal.org/smash/get/di...

One-step reinforcement learning explanation methods account for individual actions but fail to consider the agents future behavior, which can make their interpretation ambiguous. We propose to address this limitation by providing hierarchical goals as context for one-step explanations. By considering the current hierarchical goal as a context, one-step explanations can be interpreted with higher certainty, as the agents future behavior is more predictable. We combine reward decomposition with hierarchical reinforcement learning into a novel explainable reinforcement learning framework, which yields more interpretable, goal-contextualized one-step explanations. With a qualitative analysis of one-step reward decomposition explanations, we first show that their interpretability is indeed limited in scenarios with multiple, different optimal policies-a characteristic shared by other one-step explanation methods. Then, we show that our framework retains high interpretability in such cases, as the hierarchical goal can be considered as context for the explanation. To the best of our knowledge, our work is the first to investigate hierarchical goals not as an explanation directly but as additional context for one-step reinforcement learning explanations.

2022
[120] Susanne Kjällander, Anna Åkerfeldt, Linda Mannila and Fredrik Heintz. 2022.
Signs of learning in middle school computing education.
In . In series: 2022 IEEE Frontiers in Education Conference (FIE) #??. Institute of Electrical and Electronics Engineers (IEEE). ISBN: 9781665462440, 9781665462457.
DOI: 10.1109/FIE56618.2022.9962658.

Programming has been part of Swedish elementary school curriculum for six years and the aim of this full paper is to find out how teachers can design programming activities so that students engage and learn. A mix-methods research project with a social semiotic, multimodal theoretical framework – Designs for learning – is used to investigate teaching and learning in a class during three years. The results in this small-scale study indicate that collaboration is a successful didactic design for programming lessons in school. Computational thinking is prevalent and both digital skills (such as coding) and digital competencies (such as understanding the impact of technology in society) are practiced and met in programming lessons merging Science, Technology, Engineering, Arts, and Mathematics.

[119] Anna Åkerfeldt, Susanne Kjällander, Linda Mannila and Fredrik Heintz. 2022.
Exploring programming didactics in primary school - a gender perspective.
In 2022 IEEE Frontiers in Education Conference (FIE). In series: Frontiers in Education (FIE) Conference #??. Institute of Electrical and Electronics Engineers (IEEE). ISBN: 9781665462440, 9781665462457.
DOI: 10.1109/FIE56618.2022.9962386.

This Research Full Paper explore inclusion in programming in primary school. Education plays a crucial role in engaging a diverse group of students with different social backgrounds and interests. Therefore, this study aims to shed light upon inclusion in programming in primary school, focusing on gender to increase the knowledge regarding inclusion in programming didactics. The following research questions have guided the study: How are programming activities designed in primary school? How do pupils approach the programming tasks given? Can any gender differences be observed, and what are the consequences for the teaching practice? The theoretical framework used to analyse the empirical material is at the intersection between multimodal social semiotics [1] and a design-oriented perspective [2]. The empirical material consists of classroom video observations. Programming lessons in grades 4-8 have been observed and videos was recorded during 2019-2020. The pupils have worked on eight different programming tasks during the lessons. Analysis of these programming activities (tasks, instructions and resources used) focusing on gender has been made. Findings show two aspects 1) interest and position and 2) representations of knowledge. Regarding interest and position, the study of programming activities shows both similarities and differences between girls’ and boys’ approach to the task. Similarities are shown regarding the learning activities. No differences in coding strategies or creativity are observed if the task has an open design. The differences are shown in the guided tasks, where boys tend to engage in the tasks from their interests rather than following instructions and girls tend to follow the instructions given by the teacher. From a gender perspective, the boys might find programming more creative and fun, and the girls might feel less engaged as their interest falls into the background. Secondly, knowledge representations might affect who is seen as an expert within the CS field. For example, in grades 4 and 5, a male voice was represented in the video clips and a guest teacher used when presenting programming activities. The resources used in the lessons can be seen as representations of knowledge. In this case, they are always connected to a social and cultural domain [3], an environment foremost represented by males in this case.

[118] Linda Mannila, Anna Åkerfeldt, Susanne Kjällander and Fredrik Heintz. 2022.
Exploring Gender Differences in Primary School Programming.
In 2022 IEEE Frontiers in Education Conference (FIE). In series: Frontiers in Education (FIE) Conference #??. Institute of Electrical and Electronics Engineers (IEEE). ISBN: 9781665462440, 9781665462457.
DOI: 10.1109/FIE56618.2022.9962482.

As a result of the increased digitalisation, many countries have introduced programming in their primary education curricula. One main objective is to give all children equal opportunities to develop the skills needed to be an active participant and producer in a digitalized society. This also addresses another important objective, that of increased diversity and broadened participation. Despite technology being a natural part in our everyday lives, stereotypical views of programming as a primarily male activity still exist. In this paper, we explore girls’ and boys’ experiences of programming at school and in their spare time. The study is situated in primary school classrooms in Sweden, where programming was introduced in a cross-curricular manner as part of digital competence in 2018. While most students reported having some programming experience, it was quite limited. The results show that, compared to the girls, boys in grades 4-9 are somewhat more positive towards programming and get more programming experience both at school and in their spare time. Similarly, boys rated their self-perceived programming skills higher than the girls. In grades 1-3, no gender disparity was found in students’ attitudes, experiences or skills. However, the gender differences in grades 4-9 were not reflected to an equally high extent in the students’ programming skills, as girls and boys did equally well on many skills related tasks. The analysis highlights the importance of well planned, motivating and relevant tasks in order to provide positive experiences of programming in the classroom.

[117] Katarina Sperling, Linnéa Stenliden, Jörgen Nissen and Fredrik Heintz. 2022.
Still w(AI)ting for the automation of teaching: An exploration of machine learning in Swedish primary education using Actor-Network Theory.
European Journal of Education, 57(4):584–600. Wiley-Blackwell Publishing Inc..
DOI: 10.1111/ejed.12526.
Fulltext: https://doi.org/10.1111/ejed.12526
fulltext:print: https://liu.diva-portal.org/smash/get/di...

Machine learning and other artificial intelligence (AI) technologies are predicted to play a transformative role in primary education, where these technologies for automation and personalization are now being introduced to classroom instruction. This article explores the rationales and practices by which machine learning and AI are emerging in schools. We report on ethnographic fieldwork in Sweden, where a machine learning teaching aid in mathematics, the AI Engine, was tried out by 22 teachers and more than 250 primary education students. By adopting an Actor-Network Theory approach, the analysis focuses on the interactions within the network of heterogeneous actors bound by the AI Engine as an obligatory passage point. The findings show how the actions and accounts emerging within the complex ecosystem of human actors compensate for the unexpected and undesirable algorithmic decisions of the AI Engine. We discuss expectations about AI in education, contradictions in how the AI Engine worked and uncertainties about how machine learning algorithms ‘learn’ and predict. These factors contribute to our understanding of the potential of automation and personalisation—a process that requires continued re-negotiations. The findings are presented in the form of a fictional play in two acts, an ethnodrama. The ethnodrama highlights controversies in the use of AI in education, such as the lack of transparency in algorithmic decision-making—and how this can play out in real-life learning contexts. The findings of this study contribute to a better understanding of AI in primary education.

[116] Daniel Engelsons, Mattias Tiger and Fredrik Heintz. 2022.
Coverage Path Planning in Large-scale Multi-floor Urban Environments with Applications to Autonomous Road Sweeping.
In 2022 International Conference on Robotics and Automation (ICRA), pages 3328–3334. Institute of Electrical and Electronics Engineers (IEEE). ISBN: 9781728196817, 9781728196824.
DOI: 10.1109/ICRA46639.2022.9811941.
Note: Funding: 10.13039/501100004063-Knut and Alice Wallenberg Foundation (Grant Number: KAW 2019.0350)
fulltext:postprint: https://liu.diva-portal.org/smash/get/di...

Coverage Path Planning is the work horse of contemporary service task automation, powering autonomous floor cleaning robots and lawn mowers in households and office sites. While steady progress has been made on indoor cleaning and outdoor mowing, these environments are small and with simple geometry compared to general urban environments such as city parking garages, highway bridges or city crossings. To pave the way for autonomous road sweeping robots to operate in such difficult and complex environments, a benchmark suite with three large-scale 3D environments representative of this task is presented. On this benchmark we evaluate a new Coverage Path Planning method in comparison with previous well performing algorithms, and demonstrate state-of-the-art performance of the proposed method. Part of the success, for all evaluated algorithms, is the usage of automated domain adaptation by in-the-loop parameter optimization using Bayesian Optimization. Apart from improving the performance, tedious and bias-prone manual tuning is made obsolete, which makes the evaluation more robust and the results even stronger.

[115] Peter Vamplew, Benjamin J. Smith, Johan Källström, Gabriel Ramos, Roxana Rădulescu, Diederik M. Roijers, Conor F. Hayes, Fredrik Heintz, Patrick Mannion, Pieter J. K. Libin, Richard Dazeley and Cameron Foale. 2022.
Scalar reward is not enough: a response to Silver, Singh, Precup and Sutton (2021).
Autonomous Agents and Multi-Agent Systems, 36(2):????. Springer.
DOI: 10.1007/s10458-022-09575-5.
Note: Funding: Flemish Government; National Cancer Institute of the U.S. National Institutes of Health [1R01CA240452-01A1]; Research Foundation Flanders (FWO) [1242021N]; Swedish Governmental Agency for Innovation Systems [NFFP7/2017-04885]; Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation; National University of Ireland Galway Hardiman Scholarship; FAPERGS [19/2551-0001277-2]; FAPESP [2020/05165-1]
fulltext:print: http://liu.diva-portal.org/smash/get/div...

The recent paper “Reward is Enough” by Silver, Singh, Precup and Sutton posits that the concept of reward maximisation is sufficient to underpin all intelligence, both natural and artificial, and provides a suitable basis for the creation of artificial general intelligence. We contest the underlying assumption of Silver et al. that such reward can be scalar-valued. In this paper we explain why scalar rewards are insufficient to account for some aspects of both biological and computational intelligence, and argue in favour of explicitly multi-objective models of reward maximisation. Furthermore, we contend that even if scalar reward functions can trigger intelligent behaviour in specific cases, this type of reward is insufficient for the development of human-aligned artificial general intelligence due to unacceptable risks of unsafe or unethical behaviour.

[114] Conor F. Hayes, Roxana Rădulescu, Eugenio Bargiacchi, Johan Källström, Matthew Macfarlane, Mathieu Reymond, Timothy Verstraeten, Luisa M. Zintgraf, Richard Dazeley, Fredrik Heintz, Enda Howley, Athirai A. Irissappane, Patrick Mannion, Ann Nowé, Gabriel Ramos, Marcello Restelli, Peter Vamplew and Diederik M. Roijers. 2022.
A practical guide to multi-objective reinforcement learning and planning.
Autonomous Agents and Multi-Agent Systems, 36(1):????. Springer.
DOI: 10.1007/s10458-022-09552-y.
Note: Funding: Fonds voor Wetenschappelijk Onderzoek (FWO)FWO [1SA2820N]; Flemish GovernmentEuropean Commission; FWOFWO [iBOF/21/027]; National University of Ireland Galway Hardiman Scholarship; FAPERGSFundacao de Amparo a Ciencia e Tecnologia do Estado do Rio Grande do Sul (FAPERGS) [19/2551-0001277-2]; FAPESPFundacao de Amparo a Pesquisa do Estado de Sao Paulo (FAPESP) [2020/05165-1]; Swedish Governmental Agency for Innovation SystemsVinnova [NFFP7/2017-04885]; Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation; LIFT - Dutch Research Council (NWO) [019.011]; 2017 Microsoft Research PhD Scholarship Program; 2020 Microsoft Research EMEA PhD Award
fulltext:print: http://liu.diva-portal.org/smash/get/div...

Real-world sequential decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcement learning and decision-theoretic planning either assumes only a single objective, or that multiple objectives can be adequately handled via a simple linear combination. Such approaches may oversimplify the underlying problem and hence produce suboptimal results. This paper serves as a guide to the application of multi-objective methods to difficult problems, and is aimed at researchers who are already familiar with single-objective reinforcement learning and planning methods who wish to adopt a multi-objective perspective on their research, as well as practitioners who encounter multi-objective decision problems in practice. It identifies the factors that may influence the nature of the desired solution, and illustrates by example how these influence the design of multi-objective decision-making systems for complex problems.

[113] Edward Curry, Fredrik Heintz, Morten Irgens, Arnold W. M. Smeulders and Stefano Stramigioli. 2022.
Partnership on AI, Data, and Robotics.
Communications of the ACM, 65(4):54–55. ASSOC COMPUTING MACHINERY.
DOI: 10.1145/3513000.

n/a

[112] Johan Källström, R. Granlund and Fredrik Heintz. 2022.
Design of simulation-based pilot training systems using machine learning agents.
Aeronautical Journal, 126(1300):907–931. Cambridge University Press.
DOI: 10.1017/aer.2022.8.
Note: Funding Agencies|Swedish Governmental Agency for Innovation SystemsVinnova [NFFP7/2017-04885]; Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation; Swedish Research CouncilSwedish Research CouncilEuropean Commission [2020/5-230]
fulltext:print: http://liu.diva-portal.org/smash/get/div...

The high operational cost of aircraft, limited availability of air space, and strict safety regulations make training of fighter pilots increasingly challenging. By integrating Live, Virtual, and Constructive simulation resources, efficiency and effectiveness can be improved. In particular, if constructive simulations, which provide synthetic agents operating synthetic vehicles, were used to a higher degree, complex training scenarios could be realised at low cost, the need for support personnel could be reduced, and training availability could be improved. In this work, inspired by the recent improvements of techniques for artificial intelligence, we take a user perspective and investigate how intelligent, learning agents could help build future training systems. Through a domain analysis, a user study, and practical experiments, we identify important agent capabilities and characteristics, and then discuss design approaches and solution concepts for training systems to utilise learning agents for improved training value.

2021
[111] Erik Nikko, Zoran Sjanic and Fredrik Heintz. 2021.
Towards Verification and Validation of Reinforcement Learning in Safety-Critical Systems: A Position Paper from the Aerospace Industry.
In Robust and Reliable Autonomy in the Wild, International Joint Conferences on Artificial Intelligence.
Link to paper: http://rbr.cs.umass.edu/r2aw/papers/R2AW...

Reinforcement learning techniques have successfully been applied to solve challenging problems. Among the more famous examples are playing games such as Go and real-time computer games such as StarCraft II. In addition, reinforcement learning has successfully been deployed in cyber-physical systems such as robots playing a curling-based game. These are all important and significant achievements indicating that the techniques can be of value for the aerospace industry. However, to use these techniques in the aerospace industry, very high requirements on verification and validation must be met. In this position paper, we outline four key problems for verification and validation of reinforcement learning techniques. Solving these are an important step towards enabling reinforcement learning techniques to be used in safety critical domains such as the aerospace industry.

[110] Johan Källström, Rego Granlund and Fredrik Heintz. 2021.
Design of Simulation-Based Pilot Training Systems using Machine Learning Agents.
In Proceedings of the 32nd Congress of the International Council of Aeronautical Sciences (ICAS). The International Council of the Aeronautical Sciences. ISBN: 9783932182914.
ICAS 2020/21 - CD-ROM PROCEEDINGS: https://www.icas.org/ICAS_ARCHIVE/ICAS20...

The high operational cost of aircraft, limited availability of air space, and strict safety regulations make training of fighter pilots increasingly challenging. By integrating Live, Virtual, and Constructive simulation resources, efficiency and effectiveness can be improved. In particular, if constructive simulations, which provide synthetic agents operating synthetic vehicles, were used to a higher degree, complex training scenarios could be realized at low cost, the need for support personnel could be reduced, and training availability could be improved. In this work, inspired by the recent improvements of techniques for artificial intelligence, we take a user perspective and investigate how intelligent, learning agents could help build future training systems. Through a domain analysis, a user study, and practical experiments, we identify important agent capabilities and characteristics, and then discuss design approaches and solution concepts for training systems to utilize learning agents for improved training value.

[109] Gerald Steinbauer, Martin Kandlhofer, Tara Chklovski, Fredrik Heintz and Sven Koenig. 2021.
Education in Artificial Intelligence K-12.
Künstliche Intelligenz, 35(2):127–129. Springer.
DOI: 10.1007/s13218-021-00734-6.
Note: Funding Agencies: Graz University of Technology
fulltext:print: http://liu.diva-portal.org/smash/get/div...

[108] Fredrik Präntare, Herman Appelgren and Fredrik Heintz. 2021.
Anytime Heuristic and Monte Carlo Methods for Large-Scale Simultaneous Coalition Structure Generation and Assignment.
In THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, pages 11317–11324. In series: AAAI Conference on Artificial Intelligence #??. ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. ISBN: 9781577358664.
DOI: 10.1609/aaai.v35i13.17349.
Note: Funding Agencies|Wallenberg AI, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation; TAILOR project - EU Horizon 2020 research and innovation programme [952215]; Knut and Alice Wallenberg FoundationKnut & Alice Wallenberg Foundation [KAW 2019.0350]
Fulltext: https://doi.org/10.1609/aaai.v35i13.1734...

Optimal simultaneous coalition structure generation and assignment is computationally hard. The state-of-the-art can only compute solutions to problems with severely limited input sizes, and no effective approximation algorithms that are guaranteed to yield high-quality solutions are expected to exist. Real-world optimization problems, however, are often characterized by large-scale inputs and the need for generating feasible solutions of high quality in limited time. In light of this, and to make it possible to generate better feasible solutions for difficult large-scale problems efficiently, we present and benchmark several different anytime algorithms that use general-purpose heuristics and Monte Carlo techniques to guide search. We evaluate our methods using synthetic problem sets of varying distribution and complexity. Our results show that the presented algorithms are superior to previous methods at quickly generating near-optimal solutions for small-scale problems, and greatly superior for efficiently finding high-quality solutions for large-scale problems. For example, for problems with a thousand agents and values generated with a uniform distribution, our best approach generates solutions 99.5% of the expected optimal within seconds. For these problems, the state-of-the-art solvers fail to find any feasible solutions at all.

[107] Fredrik Heintz. 2021.
Three Interviews About K-12 AI Education in America, Europe, and Singapore.
Künstliche Intelligenz, 35(??):233–237. SPRINGER HEIDELBERG.
DOI: 10.1007/s13218-021-00730-w.

As the impact and importance of artificial intelligence (AI) grows, there is a growing trend to teach AI in primary and secondary education (K-12). To provide an international perspective, we have conducted three interviews with practitioners and policy makers from AI4K12 in the US (D. Touretzky, C. Gardner-McCune, and D. Seehorn), from Singapore (L. Liew) and from the European Commission (F. Benini).

[106] Gerald Steinbauer, Martin Kandlhofer, Tara Chklovski, Fredrik Heintz and Sven Koenig. 2021.
A Differentiated Discussion About AI Education K-12.
Künstliche Intelligenz, 35(2):131–137. Springer Nature.
DOI: 10.1007/s13218-021-00724-8.
Note: Funding Agencies|Graz University of Technology
fulltext:print: http://liu.diva-portal.org/smash/get/div...

AI Education for K-12 and in particular AI literacy gained huge interest recently due to the significantly influence in daily life, society, and economy. In this paper we discuss this topic of early AI education along four dimensions: (1) formal versus informal education, (2) cooperation of researchers in AI and education, (3) the level of education, and (4) concepts and tools.

[105] Full text  Mattias Tiger, David Bergström, Andreas Norrstig and Fredrik Heintz. 2021.
Enhancing Lattice-Based Motion Planning With Introspective Learning and Reasoning.
IEEE Robotics and Automation Letters, 6(3):4385–4392. Institute of Electrical and Electronics Engineers (IEEE).
DOI: 10.1109/LRA.2021.3068550.
Note: Funding: Wallenberg AI, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation; National Graduate School in Computer Science (CUGS), Sweden; Excellence Center at Linkoping-Lund for Information Technology (ELLIIT); TAILOR Project - EU Horizon 2020 research and innovation programme [952215]; Knut and Alice Wallenberg FoundationKnut & Alice Wallenberg Foundation [KAW 2019.0350]
Fulltext: https://doi.org/10.1109/LRA.2021.3068550
fulltext:print: https://liu.diva-portal.org/smash/get/di...

Lattice-based motion planning is a hybrid planning method where a plan is made up of discrete actions, while simultaneously also being a physically feasible trajectory. The planning takes both discrete and continuous aspects into account, for example action pre-conditions and collision-free action-duration in the configuration space. Safe motion planning rely on well-calibrated safety-margins for collision checking. The trajectory tracking controller must further be able to reliably execute the motions within this safety margin for the execution to be safe. In this work we are concerned with introspective learning and reasoning about controller performance over time. Normal controller execution of the different actions is learned using machine learning techniques with explicit uncertainty quantification, for safe usage in safety-critical applications. By increasing the model accuracy the safety margins can be reduced while maintaining the same safety as before. Reasoning takes place to both verify that the learned models stays safe and to improve collision checking effectiveness in the motion planner using more accurate execution predictions with a smaller safety margin. The presented approach allows for explicit awareness of controller performance under normal circumstances, and detection of incorrect performance in abnormal circumstances. Evaluation is made on the nonlinear dynamics of a quadcopter in 3D using simulation.

[104] Full text  Susanne Kjallander, Linda Mannila, Anna Akerfeldt and Fredrik Heintz. 2021.
Elementary Students First Approach to Computational Thinking and Programming.
Education Sciences, 11(2):????. MDPI.
DOI: 10.3390/educsci11020080.
Note: Funding Agencies|Marcus and Amalia Wallenberg Foundation [MAW 2017.0096]
fulltext:print: https://liu.diva-portal.org/smash/get/di...

Digital competence and programming are actively highlighted areas in education worldwide. They are becoming part of curricula all over the world, including the Swedish elementary school curriculum, Children are expected to develop computational thinking through programming activities, mainly in mathematics-which are supposed to be based on both proven experience and scientific grounds. Both are lacking in the lower grades of elementary school. This article gives unique insight into pupils learning during the first programming lessons based on a group of Swedish pupils experiences when entering school. The goal of the article is to inform education policy and practice. The large interdisciplinary, longitudinal research project studies approximately 1500 students aged 6-16 and their teachers over three years, using video documentation, questionnaires, and focus group interviews. This article reports on empirical data collected during the first year in one class with 30 pupils aged 6-7 years. The social semiotic, multimodal theoretical framework \"Design for Learning\" is used to investigate potential signs of learning in pupils multimodal representations when they, for example, use block programming in the primary and secondary transformation unit. We show that young pupils have positive attitudes to programming and high self-efficacy, and that pupils signs of learning in programming are multimodal and often visible in social interactions.

[103] Full text  Fredrik Präntare and Fredrik Heintz. 2021.
Hybrid Dynamic Programming for Simultaneous Coalition Structure Generation and Assignment.
In Uchiya, Takahiro, Bai, Quan, Marsa-Maestre, Ivan, editors, PRIMA 2020: Principles and Practice of Multi-Agent Systems: 23rd International Conference, Nagoya, Japan, November 18–20, 2020, Proceedings, pages 19–33. In series: Lecture notes in artificial intelligence #12568. Springer. ISBN: 978-3-030-69322-0, 978-3-030-69321-3.
DOI: 10.1007/978-3-030-69322-0_2.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

We present, analyze and benchmark two algorithms for simultaneous coalition structure generation and assignment: one based entirely on dynamic programming, and one anytime hybrid approach that uses branch-and-bound together with dynamic programming. To evaluate the algorithms’ performance, we benchmark them against both CPLEX (an industry-grade solver) and the state-of-the-art using difficult randomized data sets of varying distribution and complexity. Our results show that our hybrid algorithm greatly outperforms CPLEX, pure dynamic programming and the current state-of-the-art in all of our benchmarks. For example, when solving one of the most difficult problem sets, our hybrid approach finds optimum in roughly 0.1% of the time that the current best method needs, and it generates 98% efficient interim solutions in milliseconds in all of our anytime benchmarks; a considerable improvement over what previous methods can achieve.

2020
[102] Linda Mannila, Fredrik Heintz, Susanne Kjällander and Anna+ Åkerfeldt. 2020.
Programming in primary education: Towards a research based assessment framework.
In WiPSCE '20: Proceedings of the 15th Workshop on Primary and Secondary Computing Education. ACM Digital Library. ISBN: 9781450387590.
DOI: 10.1145/3421590.3421598.

In March 2017, the Swedish government decided to introduce digital competence - including programming - in primary school. As a consequence, every math and technology teacher in grades 1-9 in Sweden is expected to integrate programming in their teaching. Furthermore, the Swedish school law requires that teaching is based on scientific evidence and proven experience. In addition to professional development for teachers, it is hence crucial to also conduct research on different aspects of programming in the classroom. In this paper, we describe the process of developing a scientifically grounded instrument for assessing students' programming skills, as part of a longitudinal research project investigating how students in primary school learn programming. We also present the main findings related to the suitability of the instrument based on a pilot study conducted in spring 2019, collecting data from 310 students.

[101] Fredrik Präntare, Mattias Tiger, David Bergström, Herman Appelgren and Fredrik Heintz. 2020.
Towards Utilitarian Combinatorial Assignment with Deep Neural Networks and Heuristic Algorithms.
In .

This paper presents preliminary work on using deep neural networksto guide general-purpose heuristic algorithms for performing utilitarian combinatorial assignment. In more detail, we use deep learning in an attempt to produce heuristics that can be used together with e.g., search algorithms to generatefeasible solutions of higher quality more quickly. Our results indicate that ourapproach could be a promising future method for constructing such heuristics.

[100] Full text  Johan Källström and Fredrik Heintz. 2020.
Agent Coordination in Air Combat Simulation using Multi-Agent Deep Reinforcement Learning.
In 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pages 2157–2164. IEEE conference proceedings. ISBN: 9781728185279, 9781728185262.
DOI: 10.1109/SMC42975.2020.9283492.
Note: Funding: Swedish Governmental Agency for Innovation SystemsVinnova [NFFP7/2017-04885]; Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation
Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC): https://ieeexplore.ieee.org/xpl/conhome/...
fulltext:postprint: https://liu.diva-portal.org/smash/get/di...

Simulation-based training has the potential to significantly improve training value in the air combat domain. However, synthetic opponents must be controlled by high-quality behavior models, in order to exhibit human-like behavior. Building such models by hand is recognized as a very challenging task. In this work, we study how multi-agent deep reinforcement learning can be used to construct behavior models for synthetic pilots in air combat simulation. We empirically evaluate a number of approaches in two air combat scenarios, and demonstrate that curriculum learning is a promising approach for handling the high-dimensional state space of the air combat domain, and that multi-objective learning can produce synthetic agents with diverse characteristics, which can stimulate human pilots in training.

[99] Full text  Mattias Tiger and Fredrik Heintz. 2020.
Spatio-Temporal Learning, Reasoning and Decision-Making with Robot Safety Applications: PhD Research Project Extended Abstract.
In Fredrik Johansson, editor, Proceedings of the 32nd annual workshop of the Swedish Artificial Intelligence Society (SAIS 2020).

Cyber-physical systems such as robots and intelligent transportation systems are heavy producers and consumers of trajectory data. Making sense of this data and putting it to good use is essential for such systems. When industrial robots, intelligent vehicles and aerial drones are intended to co-exist, side-by-side, with people in human-tailored environments safety is paramount. Safe operations require uncertainty-aware motion pattern recognition, incremental reasoning and rapid decision-making to manage collision avoidance, monitor movement execution and detect abnormal motion. We investigate models and techniques that can support and leverage the interplay between these various trajectory-based capabilities to improve the state-of-the-art for intelligent autonomous systems.

[98] Full text  Johan Källström and Fredrik Heintz. 2020.
Learning Agents for Improved Efficiency and Effectiveness in Simulation-Based Training.
In Poceedings of the 32nd annual workshop of the Swedish Artificial Intelligence Society (SAIS), pages 1–2.
Konferensens fulltext: https://www.chalmers.se/SiteCollectionDo...

Team training in complex domains often requires a substantial amount of resources, e.g., instructors, role-players and vehicles. For this reason, it may be difficult to realize efficient and effective training scenarios in a real-world setting. Instead, intelligent agents can be used to construct synthetic, simulationbased training environments. However, building behavior models for such agents is challenging, especially for the end-users of the training systems, who typically do not have expertise in artificial intelligence. In this PhD project, we study how machine learning can be used to simplify the process of constructing agents for simulation-based training. As a case study we use a simulation-based air combat training system. By constructing smarter synthetic agents the dependency on human training providers can be reduced, and the availability as well as the quality of training can be improved.

[97] Full text  Fredrik Präntare and Fredrik Heintz. 2020.
An anytime algorithm for optimal simultaneous coalition structure generation and assignment.
Autonomous Agents and Multi-Agent Systems, 34(1):????. SPRINGER.
DOI: 10.1007/s10458-020-09450-1.
Note: Funding Agencies|Linkoping University; Wallenberg AI, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation
fulltext:print: http://liu.diva-portal.org/smash/get/div...

An important research problem in artificial intelligence is how to organize multiple agents, and coordinate them, so that they can work together to solve problems. Coordinating agents in a multi-agent system can significantly affect the systems performance-the agents can, in many instances, be organized so that they can solve tasks more efficiently, and consequently benefit collectively and individually. Central to this endeavor is coalition formation-the process by which heterogeneous agents organize and form disjoint groups (coalitions). Coalition formation often involves finding a coalition structure (an exhaustive set of disjoint coalitions) that maximizes the systems potential performance (e.g., social welfare) through coalition structure generation. However, coalition structure generation typically has no notion of goals. In cooperative settings, where coordination of multiple coalitions is important, this may generate suboptimal teams for achieving and accomplishing the tasks and goals at hand. With this in mind, we consider simultaneously generating coalitions of agents and assigning the coalitions to independent alternatives (e.g., tasks/goals), and present an anytime algorithm for the simultaneous coalition structure generation and assignment problem. This combinatorial optimization problem hasmany real-world applications, including forming goal-oriented teams. To evaluate the presented algorithms performance, we present five methods for synthetic problem set generation, and benchmark the algorithm against the industry-grade solver CPLEXusing randomized data sets of varying distribution and complexity. To test its anytime-performance, we compare the quality of its interim solutions against those generated by a greedy algorithm and pure random search. Finally, we also apply the algorithm to solve the problem of assigning agents to regions in a major commercial strategy game, and show that it can be used in game-playing to coordinate smaller sets of agents in real-time.

[96] Full text  Mattias Tiger and Fredrik Heintz. 2020.
Incremental Reasoning in Probabilistic Signal Temporal Logic.
International Journal of Approximate Reasoning, 119(??):325–352. Elsevier.
DOI: 10.1016/j.ijar.2020.01.009.
Note: Funding agencies: National Graduate School in Computer Science, Sweden (CUGS); Swedish Research Council (VR) Linnaeus Center CADICSSwedish Research Council; ELLIIT Excellence Center at Linkoping-Lund for Information Technology; Wallenberg AI, Autonomous Systems and Softwar
Fulltext: https://doi.org/10.1016/j.ijar.2020.01.0...
fulltext:print: http://liu.diva-portal.org/smash/get/div...

Robot safety is of growing concern given recent developments in intelligent autonomous systems. For complex agents operating in uncertain, complex and rapidly-changing environments it is difficult to guarantee safety without imposing unrealistic assumptions and restrictions. It is therefore necessary to complement traditional formal verification with monitoring of the running system after deployment. Runtime verification can be used to monitor that an agent behaves according to a formal specification. The specification can contain safety-related requirements and assumptions about the environment, environment-agent interactions and agent-agent interactions. A key problem is the uncertain and changing nature of the environment. This necessitates requirements on how probable a certain outcome is and on predictions of future states. We propose Probabilistic Signal Temporal Logic (ProbSTL) by extending Signal Temporal Logic with a sub-language to allow statements over probabilities, observations and predictions. We further introduce and prove the correctness of the incremental stream reasoning technique progression over well-formed formulas in ProbSTL. Experimental evaluations demonstrate the applicability and benefits of ProbSTL for robot safety.

2019
[95] Full text  David Bergström, Mattias Tiger and Fredrik Heintz. 2019.
Bayesian optimization for selecting training and validation data for supervised machine learning.
In 31st annual workshop of the Swedish Artificial Intelligence Society (SAIS 2019), Umeå, Sweden, June 18-19, 2019..

Validation and verification of supervised machine learning models is becoming increasingly important as their complexity and range of applications grows. This paper describes an extension to Bayesian optimization which allows for selecting both training and validation data, in cases where data can be generated or calculated as a function of a spatial location.

[94] Full text  Johan Källström and Fredrik Heintz. 2019.
Reinforcement Learning for Computer Generated Forces using Open-Source Software.
In Proceedings of the 2019 Interservice/Industry Training, Simulation, and Education Conference (IITSEC), pages 1–11.
Conference Agenda: https://www.xcdsystem.com/iitsec/program...
Paper: https://s3.amazonaws.com/amz.xcdsystem.c...
I/ITSEC Knowledge Repository: http://www.iitsecdocs.com/volumes

The creation of behavior models for computer generated forces (CGF) is a challenging and time-consuming task, which often requires expertise in programming of complex artificial intelligence algorithms. This makes it difficult for a subject matter expert with knowledge about the application domain and the training goals to build relevant scenarios and keep the training system in pace with training needs. In recent years, machine learning has shown promise as a method for building advanced decision-making models for synthetic agents. Such agents have been able to beat human champions in complex games such as poker, Go and StarCraft. There is reason to believe that similar achievements are possible in the domain of military simulation. However, in order to efficiently apply these techniques, it is important to have access to the right tools, as well as knowledge about the capabilities and limitations of algorithms. This paper discusses efficient applications of deep reinforcement learning, a machine learning technique that allows synthetic agents to learn how to achieve their goals by interacting with their environment. We begin by giving an overview of available open-source frameworks for deep reinforcement learning, as well as libraries with reference implementations of state-of-the art algorithms. We then present an example of how these resources were used to build a reinforcement learning environment for a CGF software intended to support training of fighter pilots. Finally, based on our exploratory experiments in the presented environment, we discuss opportunities and challenges related to the application of reinforcement learning techniques in the domain of air combat training systems, with the aim to efficiently construct high quality behavior models for computer generated forces.

[93] Full text  Johan Källström and Fredrik Heintz. 2019.
Multi-Agent Multi-Objective Deep Reinforcement Learning for Efficient and Effective Pilot Training.
In Ingo Staack and Petter Krus, editors, Proceedings of the 10th Aerospace Technology Congress (FT), pages 101–111. In series: Linköping Electronic Conference Proceedings #162. ISBN: 978-91-7519-006-8.
DOI: 10.3384/ecp19162011.
fulltext:print: http://liu.diva-portal.org/smash/get/div...

The tactical systems and operational environment of modern fighter aircraft are becoming increasingly complex. Creating a realistic and relevant environment for pilot training using only live aircraft is difficult, impractical and highly expensive. The Live, Virtual and Constructive (LVC) simulation paradigm aims to address this challenge. LVC simulation means linking real aircraft, ground-based systems and soldiers (Live), manned simulators (Virtual) and computer controlled synthetic entities (Constructive). Constructive simulation enables realization of complex scenarios with a large number of autonomous friendly, hostile and neutral entities, which interact with each other as well as manned simulators and real systems. This reduces the need for personnel to act as role-players through operation of e.g. live or virtual aircraft, thus lowering the cost of training. Constructive simulation also makes it possible to improve the availability of training by embedding simulation capabilities in live aircraft, making it possible to train anywhere, anytime. In this paper we discuss how machine learning techniques can be used to automate the process of constructing advanced, adaptive behavior models for constructive simulations, to improve the autonomy of future training systems. We conduct a number of initial experiments, and show that reinforcement learning, in particular multi-agent and multi-objective deep reinforcement learning, allows synthetic pilots to learn to cooperate and prioritize among conflicting objectives in air combat scenarios. Though the results are promising, we conclude that further algorithm development is necessary to fully master the complex domain of air combat simulation.

[92] Full text  Johan Källström and Fredrik Heintz. 2019.
Tunable Dynamics in Agent-Based Simulation using Multi-Objective Reinforcement Learning.
In Proceedings of the 2019 Adaptive and Learning Agents Workshop (ALA), 2019, pages 1–7.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

Agent-based simulation is a powerful tool for studying complex systems of interacting agents. To achieve good results, the behavior models used for the agents must be of high quality. Traditionally these models have been handcrafted by domain experts. This is a difficult, expensive and time consuming process. In contrast, reinforcement learning allows agents to learn how to achieve their goals by interacting with the environment. However, after training the behavior of such agents is often static, i.e. it can no longer be affected by a human. This makes it difficult to adapt agent behavior to specific user needs, which may vary among different runs of the simulation. In this paper we address this problem by studying how multi-objective reinforcement learning can be used as a framework for building tunable agents, whose characteristics can be adjusted at runtime to promote adaptiveness and diversity in agent-based simulation. We propose an agent architecture that allows us to adapt popular deep reinforcement learning algorithms to multi-objective environments. We empirically show that our method allows us to train tunable agents that can approximate the policies of multiple species of agents.

[91] Daniele DellAglio, Thomas Eiter, Fredrik Heintz and Danh Le-Phuoc. 2019.
Special issue on stream reasoning.
Semantic Web, 10(3):453–455. IOS PRESS.
DOI: 10.3233/SW-190351.

n/a

[90] Full text  Magnus Selin, Mattias Tiger, Daniel Duberg, Fredrik Heintz and Patric Jensfelt. 2019.
Efficient Autonomous Exploration Planning of Large Scale 3D-Environments.
IEEE Robotics and Automation Letters, 4(2):1699–1706. Institute of Electrical and Electronics Engineers (IEEE).
DOI: 10.1109/LRA.2019.2897343.
fulltext:postprint: https://liu.diva-portal.org/smash/get/di...

Exploration is an important aspect of robotics, whether it is for mapping, rescue missions or path planning in an unknown environment. Frontier Exploration planning (FEP) and Receding Horizon Next-Best-View planning (RH-NBVP) are two different approaches with different strengths and weaknesses. FEP explores a large environment consisting of separate regions with ease, but is slow at reaching full exploration due to moving back and forth between regions. RH-NBVP shows great potential and efficiently explores individual regions, but has the disadvantage that it can get stuck in large environments not exploring all regions. In this work we present a method that combines both approaches, with FEP as a global exploration planner and RH-NBVP for local exploration. We also present techniques to estimate potential information gain faster, to cache previously estimated gains and to exploit these to efficiently estimate new queries.

[89] Full text  Daniel de Leng and Fredrik Heintz. 2019.
Approximate Stream Reasoning with Metric Temporal Logic under Uncertainty.
In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), pages 2760–2767. AAAI Press.
DOI: 10.1609/aaai.v33i01.33012760.
AAAI Digital Library Conferences: https://aaai.org/Library/conferences-lib...

Stream reasoning can be defined as incremental reasoning over incrementally-available information. The formula progression procedure for Metric Temporal Logic (MTL) makes use of syntactic formula rewritings to incrementally evaluate formulas against incrementally-available states. Progression however assumes complete state information, which can be problematic when not all state information is available or can be observed, such as in qualitative spatial reasoning tasks or in robotics applications. In those cases, there may be uncertainty as to which state out of a set of possible states represents the ‘true’ state. The main contribution of this paper is therefore an extension of the progression procedure that efficiently keeps track of all consistent hypotheses. The resulting procedure is flexible, allowing a trade-off between faster but approximate and slower but precise progression under uncertainty. The proposed approach is empirically evaluated by considering the time and space requirements, as well as the impact of permitting varying degrees of uncertainty.

2018
[88] Linda Mannila, Fredrik Heintz, Susanne Kjällander and Anna Åkerfeldt. 2018.
Programming in Primary School: Towards a Research-Based Assessment Instrument.
In WiPSCE '20: Proceedings of the 15th Workshop on Primary and Secondary Computing Education. In series: ACM International Conference Proceeding Series #10. ACM Digital Library. ISBN: 9781450387590.
DOI: 10.1145/3421590.3421598.

In March 2017, the Swedish government decided to introduce digital competence - including programming - in primary school. As a consequence, every math and technology teacher in grades 1-9 in Sweden is expected to integrate programming in their teaching. Furthermore, the Swedish school law requires that teaching is based on scientific evidence and proven experience. In addition to professional development for teachers, it is hence crucial to also conduct research on different aspects of programming in the classroom. In this paper, we describe the process of developing a scientifically grounded instrument for assessing students' programming skills, as part of a longitudinal research project investigating how students in primary school learn programming. We also present the main findings related to the suitability of the instrument based on a pilot study conducted in spring 2019, collecting data from 310 students.

[87] Full text  Daniel de Leng and Fredrik Heintz. 2018.
Partial-State Progression for Stream Reasoning with Metric Temporal Logic.
In SIXTEENTH INTERNATIONAL CONFERENCE ON PRINCIPLES OF KNOWLEDGE REPRESENTATION AND REASONING, pages 633–634. ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE.
Note: Funding Agencies|National Graduate School in Computer Science, Sweden (CUGS)

The formula progression procedure for Metric Temporal Logic (MTL), originally proposed by Bacchus and Kabanza, makes use of syntactic formula rewritings to incrementally evaluate MTL formulas against incrementally-available states. Progression however assumes complete state information, which can be problematic when not all state information is available or can be observed, such as in qualitative spatial reasoning tasks or in robot applications. Our main contribution is an extension of the progression procedure to handle partial state information. For each missing truth value, we efficiently consider all consistent hypotheses by branching progression for each such hypothesis. The resulting procedure is flexible, allowing a trade-off between faster but approximate and slower but precise partial-state progression.

[86] Full text  Fredrik Präntare and Fredrik Heintz. 2018.
An Anytime Algorithm for Simultaneous Coalition Structure Generation and Assignment.
In Tim Miller, Nir Oren, Yuko Sakurai, Itsuki Noda, Bastin Tony Roy Savarimuthu and Tran Cao Son, editors, PRIMA 2018: Principles and Practice of Multi-Agent Systems: 21st International Conference, Tokyo, Japan, October 29-November 2, 2018, Proceedings, pages 158–174. In series: Lecture Notes in Computer Science #11224. ISBN: 9783030030971, 9783030030988.
DOI: 10.1007/978-3-030-03098-8_10.

A fundamental problem in artificial intelligence is how to organize and coordinate agents to improve their performance and skills. In this paper, we consider simultaneously generating coalitions of agents and assigning the coalitions to independent tasks, and present an anytime algorithm for the simultaneous coalition structure generation and assignment problem. This optimization problem has many real-world applications, including forming goal-oriented teams of agents. To evaluate the algorithm’s performance, we extend established methods for synthetic problem set generation, and benchmark the algorithm against CPLEX using randomized data sets of varying distribution and complexity. We also apply the algorithm to solve the problem of assigning agents to regions in a major commercial strategy game, and show that the algorithm can be utilized in game-playing to coordinate smaller sets of agents in real-time.

[85] Full text  Olov Andersson, Oskar Ljungqvist, Mattias Tiger, Daniel Axehill and Fredrik Heintz. 2018.
Receding-Horizon Lattice-based Motion Planning with Dynamic Obstacle Avoidance.
In 2018 IEEE Conference on Decision and Control (CDC), pages 4467–4474. In series: Conference on Decision and Control (CDC) #2018. Institute of Electrical and Electronics Engineers (IEEE). ISBN: 9781538613955, 9781538613948, 9781538613962.
DOI: 10.1109/CDC.2018.8618964.
Note: This work was partially supported by FFI/VINNOVA, the Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP) funded by Knut and Alice Wallenberg Foundation, the Swedish Foundation for Strategic Research (SSF) project Symbicloud, the ELLIIT Excellence Center at Linköping-Lund for Information Technology, Swedish Research Council (VR) Linnaeus Center CADICS, and the National Graduate School in Computer Science, Sweden (CUGS).
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

A key requirement of autonomous vehicles is the capability to safely navigate in their environment. However, outside of controlled environments, safe navigation is a very difficult problem. In particular, the real-world often contains both complex 3D structure, and dynamic obstacles such as people or other vehicles. Dynamic obstacles are particularly challenging, as a principled solution requires planning trajectories with regard to both vehicle dynamics, and the motion of the obstacles. Additionally, the real-time requirements imposed by obstacle motion, coupled with real-world computational limitations, make classical optimality and completeness guarantees difficult to satisfy. We present a unified optimization-based motion planning and control solution, that can navigate in the presence of both static and dynamic obstacles. By combining optimal and receding-horizon control, with temporal multi-resolution lattices, we can precompute optimal motion primitives, and allow real-time planning of physically-feasible trajectories in complex environments with dynamic obstacles. We demonstrate the framework by solving difficult indoor 3D quadcopter navigation scenarios, where it is necessary to plan in time. Including waiting on, and taking detours around, the motions of other people and quadcopters.

[84] Full text  Mattias Tiger and Fredrik Heintz. 2018.
Gaussian Process Based Motion Pattern Recognition with Sequential Local Models.
In 2018 IEEE Intelligent Vehicles Symposium (IV), pages 1143–1149. In series: IEEE Intelligent Vehicles Symposium #2018. Institute of Electrical and Electronics Engineers (IEEE). ISBN: 9781538644522, 9781538644515, 9781538644539.
DOI: 10.1109/IVS.2018.8500676.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

Conventional trajectory-based vehicular traffic analysis approaches work well in simple environments such as a single crossing but they do not scale to more structurally complex environments such as networks of interconnected crossings (e.g. urban road networks). Local trajectory models are necessary to cope with the multi-modality of such structures, which in turn introduces new challenges. These larger and more complex environments increase the occurrences of non-consistent lack of motion and self-overlaps in observed trajectories which impose further challenges. In this paper we consider the problem of motion pattern recognition in the setting of sequential local motion pattern models. That is, classifying sub-trajectories from observed trajectories in accordance with which motion pattern that best explains it. We introduce a Gaussian process (GP) based modeling approach which outperforms the state-of-the-art GP based motion pattern approaches at this task. We investigate the impact of varying local model overlap and the length of the observed trajectory trace on the classification quality. We further show that introducing a pre-processing step filtering out stops from the training data significantly improves the classification performance. The approach is evaluated using real GPS position data from city buses driving in urban areas for extended periods of time.

[83] Full text  Fredrik Heintz and Linda Mannila. 2018.
Computational Thinking for All - An Experience Report on Scaling up Teaching Computational Thinking to All Students in a Major City in Sweden.
In SIGCSE '18: Proceedings of the 49th ACM Technical Symposium on Computer Science Education (SIGCSE), pages 137–142. Association for Computing Machinery (ACM). ISBN: 978-1-4503-5103-4.
DOI: 10.1145/3159450.3159586.

The Swedish government has recently introduced digital competence including programming in the Swedish K-9 curriculum starting no later than fall 2018. This means that 100 000 teachers need to learn programming and digital competence in less than a year. In this paper we report on our experience working with professional teacher training in Sweden's fifth largest city. The city has about 150 000 inhabitants and about 50 schools with about 14 000 students in primary education. The project has been carried out in close cooperation with the municipality.The work started in the fall of 2014 with a pilot study with 10 teachers in different subjects that was carried out during spring 2015. The pilot study was successful as the teachers were able to introduce activities related to programming and computational thinking in their subjects after only two half day workshops. The next step was to scale this up to include all the schools in the city. As expected, this turned out to be a larger challenge. More than 70 teachers were involved in the second part of the project. Some of the lessons learned are that it is quite easy to provide teacher training, but harder to get teachers to actually change their teaching and even more challenging to get teachers to help their colleagues introduce programming or computational thinking in their teaching.Based on our experience we draw some general conclusions and make suggestions for how to scale up the teaching of programming and computational thinking to all.

2017
[82] Full text  Daniel de Leng and Fredrik Heintz. 2017.
Towards Adaptive Semantic Subscriptions for Stream Reasoning in the Robot Operating System.
In 2017 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), pages 5445–5452. In series: IEEE International Conference on Intelligent Robots and Systems #??. IEEE. ISBN: 978-1-5386-2682-5.
DOI: 10.1109/IROS.2017.8206440.
Note: Funding Agencies|National Graduate School in Computer Science, Sweden (CUGS); Swedish Aeronautics Research Council [NFFP6]; Swedish Foundation for Strategic Research (SSF) project CUAS; Swedish Research Council (VR) Linnaeus Center CADICS; ELLIIT Excellence Center at Linkoping-Lund for Information Technology

Modern robotic systems often consist of a growing set of information-producing components that need to be appropriately connected for the system to function properly. This is commonly done manually or through relatively simple scripts by specifying explicitly which components to connect. However, this process is cumbersome and error-prone, does not scale well as more components are introduced, and lacks flexibility and robustness at run-time. This paper presents an algorithm for setting up and maintaining implicit subscriptions to information through its semantics rather than its source, which we call semantic subscriptions. The proposed algorithm automatically reconfigures the system when necessary in response to changes at run-time, making the semantic subscriptions adaptive to changing circumstances. To illustrate the effectiveness of adaptive semantic subscriptions, we present a case study with two SoftBank Robotics NAO robots for handling the cases when a component stops working and when new components, in this case a second robot, become available. The solution has been implemented as part of a stream reasoning framework integrated with the Robot Operating System (ROS).

[81] Full text  Fredrik Präntare, Ingemar Ragnemalm and Fredrik Heintz. 2017.
An Algorithm for Simultaneous Coalition Structure Generation and Task Assignment.
In Bo An, Ana Bazzan, João Leite, Serena Villata and Leendert van der Torre, editors, PRIMA 2017: Principles and Practice of Multi-Agent Systems 20th International Conference, Nice, France, October 30 – November 3, 2017, Proceedings, pages 514–522. In series: Lecture Notes in Computer Science #10621. Springer. ISBN: 9783319691305, 9783319691312.
DOI: 10.1007/978-3-319-69131-2_34.

Groups of agents in multi-agent systems may have to cooperate to solve tasks efficiently, and coordinating such groups is an important problem in the field of artificial intelligence. In this paper, we consider the problem of forming disjoint coalitions and assigning them to independent tasks simultaneously, and present an anytime algorithm that efficiently solves the <em>simultaneous coalition structure generation and task assignment</em> problem. This NP-complete combinatorial optimization problem has many real-world applications, including forming cross-functional teams aimed at solving tasks. To evaluate the algorithm's performance, we extend established methods for synthetic problem set generation, and benchmark the algorithm using randomized data sets of varying distribution and complexity. Our results show that the presented algorithm efficiently finds optimal solutions, and generates high quality solutions when interrupted prior to finishing an exhaustive search. Additionally, we apply the algorithm to solve the problem of assigning agents to regions in a commercial computer-based strategy game, and empirically show that our algorithm can significantly improve the coordination and computational efficiency of agents in a real-time multi-agent system.

[80] Full text  Fredrik Heintz, Linda Mannila, Lars-Åke Nordén, Peter Parnes and Regnell Björn. 2017.
Introducing Programming and Digital Competence in Swedish K–9 Education.
In Valentina Dagienė and Arto Hellas, editors, Informatics in Schools: Focus on Learning Programming: 10th International Conference on Informatics in Schools: Situation, Evolution, and Perspective (ISSEP), Helsinki, Finland, November 13-15, 2017, pages 117–128. In series: Lecture Notes in Computer Science #10696. Springer. ISBN: 9783319714820, 9783319714837.
DOI: 10.1007/978-3-319-71483-7_10.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

The role of computer science and IT in Swedish schools hasvaried throughout the years. In fall 2014, the Swedish government gavethe National Agency for Education (Skolverket) the task of preparing aproposal for K-9 education on how to better address the competencesrequired in a digitalized society. In June 2016, Skolverket handed overa proposal introducing digital competence and programming as interdisciplinarytraits, also providing explicit formulations in subjects such asmathematics (programming, algorithms and problem-solving), technology(controlling physical artifacts) and social sciences (fostering awareand critical citizens in a digital society). In March 2017, the governmentapproved the new curriculum, which needs to be implemented by fall 2018 at the latest. We present the new K-9 curriculum and put it ina historical context. We also describe and analyze the process of developingthe revised curriculum, and discuss some initiatives for how toimplement the changes.

[79] Fredrik Heintz and Fredrik Löfgren. 2017.
Linköping Humanoids: Application RoboCup 2017 Standard Platform League.

This is the application for the RoboCup 2017 Standard Platform League from the Link¨oping Humanoids teamLinköping Humanoids participated in both RoboCup 2015 and 2016 with the intention of incrementally developing a good team by learning as much as possible. We significantly improved from 2015 to 2016, even though we still didn’t perform very well. Our main challenge is that we are building our software from the ground up using the Robot Operating System (ROS) as the integration and development infrastructure. When the system became overloaded, the ROS infrastructure became very unpredictable. This made it very hard to debug during the contest, so we basically had to remove things until the load was constantly low. Our top priority has since been to make the system stable and more resource efficient. This will take us to the next level.From the start we have been clear that our goal is to have a competitive team by 2017 since we are developing our own software from scratch we are very well aware that we needed time to build up the competence and the software infrastructure. We believe we are making good progress towards this goal. The team of about 10 students has been very actively working during the fall with weekly workshops and bi-weekly one day hackathons.

2016
[78] Fredrik Heintz and Fredrik Löfgren. 2016.
Linköping Humanoids: Application RoboCup 2016 Standard Platform League.
In , pages 1–2.
Qualification Video for RoboCup Standard Platform League 2016: https://www.youtube.com/watch?v=Og8Azj2Y...
fulltext:preprint: http://liu.diva-portal.org/smash/get/div...

This is the application for the RoboCup 2016 Standard Platform League from the Linköping Humanoids team.Linköping Humanoids participated in RoboCup 2015. We didn’t do very well, but we learned a lot. When we arrived nothing worked. However, we fixed more and more of the open issues and managed to play a draw in our final game. We also participated in some of the technical challenges and scored some points. At the end of the competition we had a working team. This was both frustrating and rewarding. Analyzing the competition we have identified both what we did well and the main issues that we need to fix. One important lesson is that it takes time to develop a competitive RoboCup SPL team. Weare dedicated to improving our performance over time in order to be competitive in 2017.

[77] Full text  Fredrik Heintz, Linda Mannila and Tommy Färnqvist. 2016.
A Review of Models for Introducing Computational Thinking, Computer Science and Computing in K-12 Education.
In Proceedings of the 46th Frontiers in Education (FIE). In series: Frontiers in Education Conference #??. IEEE. ISBN: 978-1-5090-1790-4, 978-1-5090-1791-1.
DOI: 10.1109/FIE.2016.7757410.

Computing is becoming ever increasingly importantto our society. However, computing in primary and secondaryeducation has not been well developed. Computing has traditionallybeen primarily a university level discipline and there areno widely accepted general standards for what computing at K–12 level entails. Also, as the interest in this area is rather new,the amount of research conducted in the field is still limited. Inthis paper we review how 10 different countries have approachedintroducing computing into their K–12 education. The countriesare Australia, England, Estonia, Finland, New Zealand, Norway,Sweden, South Korea, Poland and USA.The studied countries either emphasize digital competenciestogether with programming or the broader subject of computingor computer science. Computational thinking is rarely mentionedexplicitly, but the ideas are often included in some form. Themost common model is to make it compulsory in primary schooland elective in secondary school. A few countries have made itcompulsory in both. While some countries have only introducedit in secondary school.

[76] Full text  Mattias Tiger and Fredrik Heintz. 2016.
Stream Reasoning using Temporal Logic and Predictive Probabilistic State Models.
In 23nd International Symposium on Temporal Representation and Reasoning (TIME), 2016. IEEE Computer Society.
Note: Presented at the 23nd International Symposium on Temporal Representation and Reasoning (TIME) at the Technical University of Denmark (DTU), Denmark, the 19th October 2016.

Integrating logical and probabilistic reasoning and integrating reasoning over observations and predictions are two important challenges in AI. In this paper we propose P-MTL as an extension to Metric Temporal Logic supporting temporal logical reasoning over probabilistic and predicted states. The contributions are (1) reasoning over uncertain states at single time points, (2) reasoning over uncertain states between time points, (3) reasoning over uncertain predictions of future and past states and (4) a computational environment formalism that ground the uncertainty in observations of the physical world. Concrete robot soccer examples are given.

[75] Full text  Mattias Tiger and Fredrik Heintz. 2016.
Stream Reasoning using Temporal Logic and Predictive Probabilistic State Models.
In 23nd International Symposium on Temporal Representation and Reasoning (TIME), 2016, pages 196–205. IEEE Computer Society. ISBN: 978-1-5090-3825-1.
DOI: 10.1109/TIME.2016.28.
Note: Presented at the 23nd International Symposium on Temporal Representation and Reasoning (TIME) at the Technical University of Denmark (DTU), Denmark, the 19th October 2016.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

Integrating logical and probabilistic reasoning and integrating reasoning over observations and predictions are two important challenges in AI. In this paper we propose P-MTL as an extension to Metric Temporal Logic supporting temporal logical reasoning over probabilistic and predicted states. The contributions are (1) reasoning over uncertain states at single time points, (2) reasoning over uncertain states between time points, (3) reasoning over uncertain predictions of future and past states and (4) a computational environment formalism that ground the uncertainty in observations of the physical world. Concrete robot soccer examples are given.

[74] Full text  Daniel de Leng and Fredrik Heintz. 2016.
DyKnow: A Dynamically Reconfigurable Stream Reasoning Framework as an Extension to the Robot Operating System.
In Proceedings of the Fifth IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR), pages 55–60. IEEE conference proceedings. ISBN: 978-1-5090-4616-4, 978-1-5090-4617-1.
DOI: 10.1109/SIMPAR.2016.7862375.
Note: Funding agencies: National Graduate School in Computer Science, Sweden (CUGS); Swedish Foundation for Strategic Research (SSF) project CUAS; Swedish Research Council (VR) Linnaeus Center CADICS; ELLIIT Excellence Center at Linkoping- Lund for Information Technology; Swedis

DyKnow is a framework for stream reasoning aimed at robot applications that need to reason over a wide and varying array of sensor data for e.g. situation awareness. The framework extends the Robot Operating System (ROS). This paper presents the architecture and services behind DyKnow's run-time reconfiguration capabilities and offers an analysis of the quantitative and qualitative overhead. Run-time reconfiguration offers interesting advantages, such as fault recovery and the handling of changes to the set of computational and information resources that are available to a robot system. Reconfiguration capabilities are becoming increasingly important with the advances in areas such as the Internet of Things (IoT). We show the effectiveness of the suggested reconfiguration support by considering practical case studies alongside an empirical evaluation of the minimal overhead introduced when compared to standard ROS.

[73] Full text  Mehul Bhatt, Esra Erdem, Fredrik Heintz and Michael Spranger. 2016.
Cognitive robotics in JOURNAL OF EXPERIMENTAL and THEORETICAL ARTIFICIAL INTELLIGENCE, vol 28, issue 5, pp 779-780.
Journal of experimental and theoretical artificial intelligence (Print), 28(5):779–780. TAYLOR & FRANCIS LTD.
DOI: 10.1080/0952813X.2016.1218649.

n/a

[72] Alexander Kleiner, Fredrik Heintz and Satoshi Tadokoro. 2016.
Editorial: Special Issue on Safety, Security, and Rescue Robotics (SSRR), Part 2.
Journal of Field Robotics, 33(4):409–410. WILEY-BLACKWELL.
DOI: 10.1002/rob.21661.

n/a

[71] Alexander Kleiner, Fredrik Heintz and Satoshi Tadokoro. 2016.
Editorial: Special Issue on Safety, Security, and Rescue Robotics (SSRR), Part 1.
Journal of Field Robotics, 33(3):263–264. WILEY-BLACKWELL.
DOI: 10.1002/rob.21653.

n/a

[70] Full text  Daniel de Leng and Fredrik Heintz. 2016.
Qualitative Spatio-Temporal Stream Reasoning With Unobservable Intertemporal Spatial Relations Using Landmarks.
In Dale Schuurmans, Dale Wellman, editors, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI), pages 957–963. In series: Proceedings of the AAAI Conference on Artificial Intelligence #??. AAAI Press. ISBN: 978-1-57735-762-9.
Link to full text: http://www.aaai.org/ocs/index.php/AAAI/A...

Qualitative spatio-temporal reasoning is an active research area in Artificial Intelligence. In many situations there is a need to reason about intertemporal qualitative spatial relations, i.e. qualitative relations between spatial regions at different time-points. However, these relations can never be explicitly observed since they are between regions at different time-points. In applications where the qualitative spatial relations are partly acquired by for example a robotic system it is therefore necessary to infer these relations. This problem has, to the best of our knowledge, not been explicitly studied before. The contribution presented in this paper is two-fold. First, we present a spatio-temporal logic MSTL, which allows for spatio-temporal stream reasoning. Second, we define the concept of a landmark as a region that does not change between time-points and use these landmarks to infer qualitative spatio-temporal relations between non-landmark regions at different time-points. The qualitative spatial reasoning is done in RCC-8, but the approach is general and can be applied to any similar qualitative spatial formalism.

[69] Full text  Tommy Färnqvist, Fredrik Heintz, Patrick Lambrix, Linda Mannila and Chunyan Wang. 2016.
Supporting Active Learning by Introducing an Interactive Teaching Tool in a Data Structures and Algorithms Course.
In Proceedings of the 47th ACM Technical Symposium on Computer Science Education (SIGCSE 2016), pages 663–668. ACM Publications. ISBN: 978-1-4503-3685-7.
DOI: 10.1145/2839509.2844653.

Traditionally, theoretical foundations in data structures and algorithms (DSA) courses have been covered through lectures followed by tutorials, where students practise their understanding on pen-and-paper tasks. In this paper, we present findings from a pilot study on using the interactive e-book OpenDSA as the main material in a DSA course. The goal was to redesign an already existing course by building on active learning and continuous examination through the use of OpenDSA. In addition to presenting the study setting, we describe findings from four data sources: final exam, OpenDSA log data, pre and post questionnaires as well as an observation study. The results indicate that students performed better on the exam than during previous years. Students preferred OpenDSA over traditional textbooks and worked actively with the material, although a large proportion of them put off the work until the due date approaches.

2015
[68] Fredrik Löfgren, Jon Dybeck and Fredrik Heintz. 2015.
Qualification document: RoboCup 2015 Standard Platform League.
In , pages 1–2.
Qualification Video for RoboCup Standard Platform League 2015: https://www.youtube.com/watch?v=YNVzj6VL...
fulltext:preprint: http://liu.diva-portal.org/smash/get/div...
fulltext:preprint: http://liu.diva-portal.org/smash/get/div...

This is the application for the RoboCup 2015 StandardPlatform League from the ”LiU Robotics” team. In thisdocument we present ourselves and what we want to achieve byour participation in the conference and competition

[67] Full text  Tommy Färnqvist, Fredrik Heintz, Patrick Lambrix, Linda Mannila and Chunyan Wang. 2015.
Supporting Active Learning Using an Interactive Teaching Tool in a Data Structures and Algorithms Course.
In Proceedings of 5:e Utvecklingskonferensen för Sveriges ingenjörsutbildningar (UtvSvIng), pages 76–79. In series: Technical report / Department of Information Technology, Uppsala University #2016-002.
Fulltext: http://utvecklingskonferens.it.uu.se/fil...

Traditionally, theoretical foundations in data structuresand algorithms (DSA) courses have been covered throughlectures followed by tutorials, where students practise theirunderstanding on pen-and-paper tasks. In this paper, we presentfindings from a pilot study on using the interactive e-bookOpenDSA as the main material in a DSA course. The goal was toredesign an already existing course by building on active learningand continuous examination through the use of OpenDSA. Inaddition to presenting the study setting, we describe findings fromfour data sources: final exam, OpenDSA log data, pre- and postcourse questionnaires as well as an observation study. The resultsindicate that students performed better on the exam than duringprevious years. Students preferred OpenDSA over traditionaltextbooks and worked actively with the material, although alarge proportion of them put off the work until the due dateapproaches.

[66] Full text  Michaël Grimsberg, Fredrik Heintz, Viggo Kann, Inger Erlander Klein and Lars Öhrström. 2015.
Vem styr egentligen grundutbildningen?.
In Proceedings of 5:e Utvecklingskonferensen för Sveriges ingenjörsutbildningar (UtvSvIng). In series: Technical report / Department of Information Technology, Uppsala University #2016-002.

Vi belyser olikheter och likheter i hur grundutbildningen styrs på fyra svenska tekniska högskolor. Vi jämför hur lärare och examinatorer väljs ut, hur medel fördelas och vilken roll programansvariga (eller motsvarande) har. De strukturella skillnaderna är relativt stora med störst autonomi för programansvariga på Chalmers tekniska högskola vilket delvis har att göra med att detta lärosäte lyder under aktiebolagslagen.

[65] Full text  Fredrik Heintz, Aseel Berglund, Björn Hedin and Viggo Kann. 2015.
En jämförelse mellan programsamanhållande kurser vid KTH och LiU.
In Proceedings of 5:e Utvecklingskonferensen för Sveriges ingenjörsutbildningar (UtvSvIng). In series: Technical report / Department of Information Technology, Uppsala University #2016-002.

Programsammanhållande kurser där studenter från årskurs 1-3 gemensamt reflekterar över teman med koppling till deras studier och framtida yrkesliv finns på både KTH och Linköpings universitet (LiU). Syftet med kurserna är främst att skapa en helhet i utbildningen och ge förståelse för vad den leder till, genom att få studenterna att reflektera över sina studier och sin kommande yrkesroll. Detta leder förhoppningsvis till ökad genomströmning och minskade avhopp. Kurserna har gemensamt ursprung men har utvecklats i olika riktningar. Artikeln jämför tre programsammanhållande kurser för Datateknik KTH, Medieteknik KTH samt Data- och mjukvaruteknik Linköpings universitet.

[64] Full text  Fredrik Heintz, Tommy Färnqvist and Jesper Thorén. 2015.
Programutvecklingsstrategier för att öka kopplingen mellan programmering och matematik.
In Proceedings of 5:e Utvecklingskonferensen för Sveriges ingenjörsutbildningar (UtvSvIng). In series: Technical report / Department of Information Technology, Uppsala University #2016-002.

Matematik och programmering är två viktiga inslag i civilingenjörsprogram inom data- och mjukvaruteknik. De studenter som klarar dessa kurser klarar sannolikt resten av utbildningen. Idag har fler studenter programmering än matematik som huvudsakligt intresse. Därför har Linköpings universitet aktivt jobbat med olika strategier för att öka kopplingen mellan programmering och matematik, främst i de inledande kurserna. För att undersöka studenternas attityder till matematik och programmering har vi genomfört flera enkätstudier som bl.a. visar att intresset för matematik är stort men intresset för programmering ännu större och att studenterna tror de kommer ha betydligt mer nytta av programmering än matematik under sin karriär. Texten är tänkt som grund för en diskussion kring hur kopplingarna mellan matematik och programmering kan göras tydligare och starkare.

[63] Full text  Mattias Tiger and Fredrik Heintz. 2015.
Towards Unsupervised Learning, Classification and Prediction of Activities in a Stream-Based Framework.
In Proceedings of the Thirteenth Scandinavian Conference on Artificial Intelligence (SCAI), pages 147–156. In series: Frontiers in Artificial Intelligence and Applications #278. IOS Press. ISBN: 978-1-61499-588-3.
DOI: 10.3233/978-1-61499-589-0-147.
länk till artikeln: https://www.ida.liu.se/divisions/aiics/p...

Learning to recognize common activities such as traffic activities and robot behavior is an important and challenging problem related both to AI and robotics. We propose an unsupervised approach that takes streams of observations of objects as input and learns a probabilistic representation of the observed spatio-temporal activities and their causal relations. The dynamics of the activities are modeled using sparse Gaussian processes and their causal relations using a probabilistic graph. The learned model supports in limited form both estimating the most likely current activity and predicting the most likely future activities. The framework is evaluated by learning activities in a simulated traffic monitoring application and by learning the flight patterns of an autonomous quadcopter.

[62] Full text  Daniel de Leng and Fredrik Heintz. 2015.
Ontology-Based Introspection in Support of Stream Reasoning.
In S. Nowaczyk, editor, Thirteenth scandinavian conference on artificial intelligence (SCAI), pages 78–87. IOS Press. ISBN: 9781614995883, 9781614995890.
Link to publication: https://www.ida.liu.se/divisions/aiics/p...

Building complex systems such as autonomous robots usually require the integration of a wide variety of components including high-level reasoning functionalities. One important challenge is integrating the information in a system by setting up the data flow between the components. This paper extends our earlier work on semantic matching with support for adaptive on-demand semantic information integration based on ontology-based introspection. We take two important standpoints. First, we consider streams of information, to handle the fact that information often becomes continually and incrementally available. Second, we explicitly represent the semantics of the components and the information that can be provided by them in an ontology. Based on the ontology our custom-made stream configuration planner automatically sets up the stream processing needed to generate the streams of information requested. Furthermore, subscribers are notified when properties of a stream changes, which allows them to adapt accordingly. Since the ontology represents both the systems information about the world and its internal stream processing many other powerful forms of introspection are also made possible. The proposed semantic matching functionality is part of the DyKnow stream reasoning framework and has been integrated in the Robot Operating System (ROS).

[61] Full text  Daniel de Leng and Fredrik Heintz. 2015.
Ontology-Based Introspection in Support of Stream Reasoning.
In Odile Papini, Salem Benferhat, Laurent Garcia, Marie-Laure Mugnier, Eduardo Fermé, Thomas Meyer, Renata Wassermann, Torsten Hahmann, Ken Baclawski, Adila Krisnadhi, Pavel Klinov, Stefano Borgo and Oliver Kutz Daniele Porello15, editors, Proceedings of the Joint Ontology Workshops (JOWO 2015), Buenos Aires, Argentina, July 25-27, 2015: The Joint Ontology Workshops - Episode 1, pages 1–8. In series: CEUR Workshop Proceedings #??. Rheinisch-Westfaelische Technische Hochschule Aachen * Lehrstuhl Informatik V.
Note: Workshops held at the 24th International Joint Conference on Artificial Intelligence - IJCAI 2015, Buenos Aires, Argentina, July 25-27, 2015
Link to publication: http://ceur-ws.org/Vol-1517/JOWO-15_FOfA...
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

Building complex systems such as autonomous robots usually require the integration of a wide variety of components including high-level reasoning functionalities. One important challenge is integrating the information in a system by setting up the data flow between the components. This paper extends our earlier work on semantic matching with support for adaptive on-demand semantic information integration based on ontology-based introspection. We take two important stand-points. First, we consider streams of information, to handle the fact that information often becomes continually and incrementally available. Second, we explicitly represent the semantics of the components and the information that can be provided by them in an ontology. Based on the ontology our custom-made stream configuration planner automatically sets up the stream processing needed to generate the streams of information requested. Furthermore, subscribers are notified when properties of a stream changes, which allows them to adapt accordingly. Since the ontology represents both the system's information about the world and its internal stream processing many other powerful forms of introspection are also made possible. The proposed semantic matching functionality is part of the DyKnow stream reasoning framework and has been integrated in the Robot Operating System (ROS).

[60] Full text  Fredrik Heintz, Linda Mannila, Karin Nygårds, Peter Parnes and Björn Regnell. 2015.
Computing at School in Sweden – Experiences fromIntroducing Computer Science within Existing Subjects.
In Proceeding of the 8th International Conference on Informatics in Schools:Situation, Evolution, and Perspective (ISSEP). In series: Lecture Notes in Computer Science #9378. Springer. ISBN: 978-3-319-25395-4.

Computing is no longer considered a subject area only relevant for anarrow group of professionals, but rather as a vital part of general education thatshould be available to all children and youth. Since making changes to nationalcurricula takes time, people are trying to find other ways of introducing childrenand youth to computing. In Sweden, several current initiatives by researchers andteachers aim at finding ways of working with computing within the current curriculum.In this paper we present case studies based on a selection of these initiativesfrom four major regions in Sweden and based on these case studies wepresent our ideas for how to move forward on introducing computational thinkingon a larger scale in Swedish education.

[59] Full text  Mattias Tiger and Fredrik Heintz. 2015.
Online Sparse Gaussian Process Regression for Trajectory Modeling.
In 18th International Conference on Information Fusion (Fusion), 2015, pages 782–791. IEEE. ISBN: 9780982443866, 9780982443873.
Publisher's full text: https://ieeexplore.ieee.org/document/726...

Trajectories are used in many target tracking and other fusion-related applications. In this paper we consider the problem of modeling trajectories as Gaussian processes and learning such models from sets of observed trajectories. We demonstrate that the traditional approach to Gaussian process regression is not suitable when modeling a set of trajectories. Instead we introduce an approach to Gaussian process trajectory regression based on an alternative way of combing two Gaussian process (GP) trajectory models and inverse GP regression. The benefit of our approach is that it works well online and efficiently supports sophisticated trajectory model manipulations such as merging and splitting of trajectory models. Splitting and merging is very useful in spatio-temporal activity modeling and learning where trajectory models are considered discrete objects. The presented method and accompanying approximation algorithm have time and memory complexities comparable to state of the art of regular full and approximative GP regression, while havinga more flexible model suitable for modeling trajectories. The novelty of our approach is in the very flexible and accurate model, especially for trajectories, and the proposed approximative method based on solving the inverse problem of Gaussian process regression.

[58] Full text  Martin Danelljan, Fahad Shahbaz Khan, Michael Felsberg, Karl Granström, Fredrik Heintz, Piotr Rudol, Mariusz Wzorek, Jonas Kvarnström and Patrick Doherty. 2015.
A Low-Level Active Vision Framework for Collaborative Unmanned Aircraft Systems.
In Lourdes Agapito, Michael M. Bronstein and Carsten Rother, editors, COMPUTER VISION - ECCV 2014 WORKSHOPS, PT I, pages 223–237. In series: Lecture Notes in Computer Science #8925. Springer Publishing Company. ISBN: 978-3-319-16177-8, 978-3-319-16178-5.
DOI: 10.1007/978-3-319-16178-5_15.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

Micro unmanned aerial vehicles are becoming increasingly interesting for aiding and collaborating with human agents in myriads of applications, but in particular they are useful for monitoring inaccessible or dangerous areas. In order to interact with and monitor humans, these systems need robust and real-time computer vision subsystems that allow to detect and follow persons.In this work, we propose a low-level active vision framework to accomplish these challenging tasks. Based on the LinkQuad platform, we present a system study that implements the detection and tracking of people under fully autonomous flight conditions, keeping the vehicle within a certain distance of a person. The framework integrates state-of-the-art methods from visual detection and tracking, Bayesian filtering, and AI-based control. The results from our experiments clearly suggest that the proposed framework performs real-time detection and tracking of persons in complex scenarios

[57] Full text  Olov Andersson, Fredrik Heintz and Patrick Doherty. 2015.
Model-Based Reinforcement Learning in Continuous Environments Using Real-Time Constrained Optimization.
In Blai Bonet and Sven Koenig, editors, Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), pages 2497–2503. AAAI Press. ISBN: 978-1-57735-698-1.
fulltext:print: http://liu.diva-portal.org/smash/get/div...

Reinforcement learning for robot control tasks in continuous environments is a challenging problem due to the dimensionality of the state and action spaces, time and resource costs for learning with a real robot as well as constraints imposed for its safe operation. In this paper we propose a model-based reinforcement learning approach for continuous environments with constraints. The approach combines model-based reinforcement learning with recent advances in approximate optimal control. This results in a bounded-rationality agent that makes decisions in real-time by efficiently solving a sequence of constrained optimization problems on learned sparse Gaussian process models. Such a combination has several advantages. No high-dimensional policy needs to be computed or stored while the learning problem often reduces to a set of lower-dimensional models of the dynamics. In addition, hard constraints can easily be included and objectives can also be changed in real-time to allow for multiple or dynamic tasks. The efficacy of the approach is demonstrated on both an extended cart pole domain and a challenging quadcopter navigation task using real data.

2014
[56] Full text  Aseel Berglund and Fredrik Heintz. 2014.
Integrating Soft Skills into Engineering Education for Increased Student Throughput and more Professional Engineers.
In Proceedings of LTHs 8:e Pedagogiska Inspirationskonferens (PIK). Lunds university.
Link to publication: http://www.lth.se/fileadmin/lth/genombro...

Soft skills are recognized as crucial for engineers as technical work is becoming more and more collaborative and interdisciplinary. Today many engineering educations fail to give appropriate training in soft skills. Linköping University has therefore developed a completely new course “Professionalism for Engineers” for two of its 5-year engineering programs in the area of computer science. The course stretches over the first 3 years with students from the three years taking it together. The purpose of the course is to give engineering students training in soft skills that are of importance during the engineering education as well as during their professional career. The examination is based on the Dialogue Seminar Method developed for learning from experience and through reflection. The organization of the course is innovative in many ways.

[55] Full text  Patrick Doherty, Jonas Kvarnström, Mariusz Wzorek, Piotr Rudol, Fredrik Heintz and Gianpaolo Conte. 2014.
HDRC3 - A Distributed Hybrid Deliberative/Reactive Architecture for Unmanned Aircraft Systems.
In Kimon P. Valavanis, George J. Vachtsevanos, editors, Handbook of Unmanned Aerial Vehicles, pages 849–952. Springer Science+Business Media B.V.. ISBN: 978-90-481-9706-4, 978-90-481-9707-1.
DOI: 10.1007/978-90-481-9707-1_118.
Find book at a Swedish library/Hitta boken i ett svenskt bibliotek: http://libris.kb.se/bib/16541662
Find book in another country/Hitta boken i ett annat land: http://www.worldcat.org/search?qt=worldc...

This chapter presents a distributed architecture for unmanned aircraft systems that provides full integration of both low autonomy and high autonomy. The architecture has been instantiated and used in a rotorbased aerial vehicle, but is not limited to use in particular aircraft systems. Various generic functionalities essential to the integration of both low autonomy and high autonomy in a single system are isolated and described. The architecture has also been extended for use with multi-platform systems. The chapter covers the full spectrum of functionalities required for operation in missions requiring high autonomy. A control kernel is presented with diverse flight modes integrated with a navigation subsystem. Specific interfaces and languages are introduced which provide seamless transition between deliberative and reactive capability and reactive and control capability. Hierarchical Concurrent State Machines are introduced as a real-time mechanism for specifying and executing low-level reactive control. Task Specification Trees are introduced as both a declarative and procedural mechanism for specification of high-level tasks. Task planners and motion planners are described which are tightly integrated into the architecture. Generic middleware capability for specifying data and knowledge flow within the architecture based on a stream abstraction is also described. The use of temporal logic is prevalent and is used both as a specification language and as an integral part of an execution monitoring mechanism. Emphasis is placed on the robust integration and interaction between these diverse functionalities using a principled architectural framework. The architecture has been empirically tested in several complex missions, some of which are described in the chapter.

[54] Full text  Mattias Tiger and Fredrik Heintz. 2014.
Towards Learning and Classifying Spatio-Temporal Activities in a Stream Processing Framework.
In Ulle Endriss and João Leite, editors, STAIRS 2014: Proceedings of the 7th European Starting AI Researcher Symposium, pages 280–289. In series: Frontiers in Artificial Intelligence and Applications #264. IOS Press. ISBN: 978-1-61499-420-6, 978-1-61499-421-3.
DOI: 10.3233/978-1-61499-421-3-280.
Fulltext: https://doi.org/10.3233/978-1-61499-421-...
Ebook: STAIRS 2014: http://ebooks.iospress.nl/volume/stairs-...
fulltext:print: http://liu.diva-portal.org/smash/get/div...

We propose an unsupervised stream processing framework that learns a Bayesian representation of observed spatio-temporal activities and their causal relations. The dynamics of the activities are modeled using sparse Gaussian processes and their causal relations using a causal Bayesian graph. This allows the model to be efficient through compactness and sparsity in the causal graph, and to provide probabilities at any level of abstraction for activities or chains of activities. Methods and ideas from a wide range of previous work are combined and interact to provide a uniform way to tackle a variety of common problems related to learning, classifying and predicting activities. We discuss how to use this framework to perform prediction of future activities and to generate events.

[53] Full text  Fredrik Heintz and Daniel de Leng. 2014.
Spatio-Temporal Stream Reasoning with Incomplete Spatial Information.
In Torsten Schaub, Gerhard Friedrich and Barry O'Sullivan, editors, Proceedings of the Twenty-first European Conference on Artificial Intelligence (ECAI'14), August 18-22, 2014, Prague, Czech Republic, pages 429–434. In series: Frontiers in Artificial Intelligence and Applications #263. IOS Press. ISBN: 978-1-61499-418-3, 978-1-61499-419-0.
DOI: 10.3233/978-1-61499-419-0-429.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

Reasoning about time and space is essential for many applications, especially for robots and other autonomous systems that act in the real world and need to reason about it. In this paper we present a pragmatic approach to spatio-temporal stream reasoning integrated in the Robot Operating System through the DyKnow framework. The temporal reasoning is done in the Metric Temporal Logic and the spatial reasoning in the Region Connection Calculus RCC-8. Progression is used to evaluate spatio-temporal formulas over incrementally available streams of states. To handle incomplete information the underlying first-order logic is extended to a three-valued logic. When incomplete spatial information is received, the algebraic closure of the known information is computed. Since the algebraic closure might have to be re-computed every time step, we separate the spatial variables into static and dynamic variables and reuse the algebraic closure of the static variables, which reduces the time to compute the full algebraic closure. The end result is an efficient and useful approach to spatio-temporal reasoning over streaming information with incomplete information.

[52] Full text  Daniel de Leng and Fredrik Heintz. 2014.
Towards On-Demand Semantic Event Processing for Stream Reasoning.
In 17th International Conference on Information Fusion. ISBN: 9788490123553.

The ability to automatically, on-demand, apply pattern matching over streams of information to infer the occurrence of events is an important fusion functionality. Existing event detection approaches require explicit configuration of what events to detect and what streams to use as input. This paper discusses on-demand semantic event processing, and extends the semantic information integration approach used in the stream processing middleware framework DyKnow to incorporate this new feature. By supporting on-demand semantic event processing, systems can automatically configure what events to detect and what streams to use as input for the event detection. This can also include the detection of lower-level events as well as processing of streams. The semantic stream query language C-SPARQL is used to specify events, which can be seen as transformations over streams. Since semantic streams consist of RDF triples, we suggest a method to convert between RDF streams and DyKnow streams. DyKnow is integrated in the Robot Operating System (ROS) and used for example in collaborative unmanned aircraft systems missions.

[51] Full text  Fredrik Heintz and Inger Erlander Klein. 2014.
The Design of Sweden's First 5-year Computer Science and Software Engineering Program.
In Proceedings of the 45th ACM Technical Symposium on Computer Science Education (SIGCSE 2014), pages 199–204. ACM Press. ISBN: 978-1-4503-2605-6.
DOI: 10.1145/2538862.2538925.

2013
[50] Full text  Patrick Doherty, Fredrik Heintz and Jonas Kvarnström. 2013.
Robotics, Temporal Logic and Stream Reasoning.
In Proceedings of Logic for Programming Artificial Intelligence and Reasoning (LPAR), 2013.

[49] Full text  Fredrik Heintz and Inger Erlander Klein. 2013.
Civilingenjör i Mjukvaruteknik vid Linköpings universitet: mål, design och erfarenheter.
In S. Vikström, R. Andersson, F. Georgsson, S. Gunnarsson, J. Malmqvist, S. Pålsson och D. Raudberget, editors, Proceedings of 4:de Utvecklingskonferensen för Sveriges ingenjörsutbildningar (UtvSvIng). In series: UMINF #13:21.

Hösten 2013 startade Linköpings universitet den första civilingenjörsutbildningen i Mjukvaruteknik. Utbildningens mål är att bland annat att ge ett helhetsperspektiv på modern storskalig mjukvaruutveckling, ge en gedigen grund i datavetenskap och computational thinking samt främja entreprenörskap och innovation. Studenternas gensvar har varit över förväntan med över 600 sökande till de 30 platserna varav 134 förstahandssökande. Här presenterar vi programmets vision, mål, designprinciper samt det färdiga programmet. En viktig förebild är ACM/IEEE Computer Science Curricula som precis kommit i en ny uppdaterad version. Tre pedagogiska idéer vi har följt är (1) att använda projektkurser för att integrera teori och praktik samt ge erfarenhet i den vanligaste arbetsformen i näringslivet; (2) att undervisa i flera olika programspråk och flera olika programutvecklingsmetodiker för att ge en plattform att ta till sig det senaste på området; och (3) att införa en programsammanhållande kurs i ingenjörsprofessionalism i årskurs 1–3 som ger studenterna verktyg att reflektera över sitt eget lärande, att jobba i näringslivet samt sin professionella yrkesroll. Artikeln avslutas med en diskussion om viktiga aspekter som computational thinking och ACM/IEEE CS Curricula.

[48] Full text  Fredrik Heintz and Tommy Färnqvist. 2013.
Återkoppling genom automaträttning.
In Proceedings of 4:de Utvecklingskonferensen för Sveriges ingenjörsutbildningar (UtvSvIng).
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

Vi har undersökt olika former av återkoppling genom automaträttning i en kurs i datastrukturer och algoritmer. 2011 undersökte vi effekterna av tävlingsliknande moment som också använder automaträttning. 2012 införde vi automaträttning av laborationerna. Vi undersökte då hur återkoppling genom automaträttning påverkar studenternasarbetssätt, prestationsgrad och relation till den examinerande personalen. Genom automaträttning får studenterna omedelbar återkoppling om deras program är tillräckligt snabbt och ger rätt svar på testdata. När programmet är korrekt och resurseffektivt kontrollerar kursassistenterna att programmet även uppfyller andra krav som att vara välskrivet och välstrukturerat. Efter kursen undersökte vi studenternas inställning till och upplevelse av automaträttning genom en enkät. Resultaten är att studenterna är positiva till automaträttning (80% av alla som svarade) och att den påverkade studenternas sätt att arbeta huvudsakligen positivt. Till exempel svarade 50% att de ansträngde sig hårdare tack vare automaträttningen. Dessutom blir rättningen mer objektiv då den görs på exakt samma sätt för alla. Vår slutsats är att återkoppling genom automaträttning ger positiva effekter och upplevs som positiv av studenterna.

[47] Full text  Fredrik Heintz. 2013.
Semantically Grounded Stream Reasoning Integrated with ROS.
In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 5935–5942. In series: IEEE International Conference on Intelligent Robots and Systems. Proceedings #??. IEEE conference proceedings. ISBN: 978-146736358-7.
DOI: 10.1109/IROS.2013.6697217.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

High level reasoning is becoming essential to autonomous systems such as robots. Both the information available to and the reasoning required for such autonomous systems is fundamentally incremental in nature. A stream is a flow of incrementally available information and reasoning over streams is called stream reasoning. Incremental reasoning over streaming information is necessary to support a number of important robotics functionalities such as situation awareness, execution monitoring, and decision making.This paper presents a practical framework for semantically grounded temporal stream reasoning called DyKnow. Incremental reasoning over streams is achieved through efficient progression of temporal logical formulas. The reasoning is semantically grounded through a common ontology and a specification of the semantic content of streams relative to the ontology. This allows the finding of relevant streams through semantic matching. By using semantic mappings between ontologies it is also possible to do semantic matching over multiple ontologies. The complete stream reasoning framework is integrated in the Robot Operating System (ROS) thereby extending it with a stream reasoning capability.

[46] Full text  Fredrik Heintz and Daniel de Leng. 2013.
Semantic Information Integration with Transformations for Stream Reasoning.
In 16th International Conference on Information Fusion, pages 445–452. IEEE. ISBN: 978-605-86311-1-3.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

The automatic, on-demand, integration of information from multiple diverse sources outside the control of the application itself is central to many fusion applications. An important problem is to handle situations when the requested information is not directly available but has to be generated or adapted through transformations. This paper extends the semantic information integration approach used in the stream-based knowledge processing middleware DyKnow with support for finding and automatically applying transformations. Two types of transformations are considered. Automatic transformation between different units of measurements and between streams of different types. DyKnow achieves semantic integration by creating a common ontology, specifying the semantic content of streams relative to the ontology and using semantic matching to find relevant streams. By using semantic mappings between ontologies it is also possible to do semantic matching over multiple ontologies. The complete stream reasoning approach is integrated in the Robot Operating System (ROS) and used in collaborative unmanned aircraft systems missions.

[45] Full text  Patrick Doherty, Fredrik Heintz and Jonas Kvarnström. 2013.
High-level Mission Specification and Planning for Collaborative Unmanned Aircraft Systems using Delegation.
Unmanned Systems, 1(1):75–119. World Scientific.
DOI: 10.1142/S2301385013500052.

Automated specification, generation and execution of high level missions involving one or more heterogeneous unmanned aircraft systems is in its infancy. Much previous effort has been focused on the development of air vehicle platforms themselves together with the avionics and sensor subsystems that implement basic navigational skills. In order to increase the degree of autonomy in such systems so they can successfully participate in more complex mission scenarios such as those considered in emergency rescue that also include ongoing interactions with human operators, new architectural components and functionalities will be required to aid not only human operators in mission planning, but also the unmanned aircraft systems themselves in the automatic generation, execution and partial verification of mission plans to achieve mission goals. This article proposes a formal framework and architecture based on the unifying concept of delegation that can be used for the automated specification, generation and execution of high-level collaborative missions involving one or more air vehicles platforms and human operators. We describe an agent-based software architecture, a temporal logic based mission specification language, a distributed temporal planner and a task specification language that when integrated provide a basis for the generation, instantiation and execution of complex collaborative missions on heterogeneous air vehicle systems. A prototype of the framework is operational in a number of autonomous unmanned aircraft systems developed in our research lab.

[44] Full text  Fredrik Heintz, Jonas Kvarnström and Patrick Doherty. 2013.
Stream-Based Hierarchical Anchoring.
Künstliche Intelligenz, 27(2):119–128. Springer.
DOI: 10.1007/s13218-013-0239-2.

Autonomous systems situated in the real world often need to recognize, track, and reason about various types of physical objects. In order to allow reasoning at a symbolic level, one must create and continuously maintain a correlation between symbols denoting physical objects and sensor data being collected about them, a process called anchoring.In this paper we present a stream-based hierarchical anchoring framework. A classification hierarchy is associated with expressive conditions for hypothesizing the type and identity of an object given streams of temporally tagged sensor data. The anchoring process constructs and maintains a set of object linkage structures representing the best possible hypotheses at any time. Each hypothesis can be incrementally generalized or narrowed down as new sensor data arrives. Symbols can be associated with an object at any level of classification, permitting symbolic reasoning on different levels of abstraction. The approach is integrated in the DyKnow knowledge processing middleware and has been applied to an unmanned aerial vehicle traffic monitoring application.

2012
[43] Patrick Doherty, Fredrik Heintz and David Landén. 2012.
A Distributed Task Specification Language for Mixed-Initiative Delegation.
In Nirmit Desai, Alan Liu, Michael Winikoff, editors, Principles and Practice of Multi-Agent Systems: 13th International Conference, PRIMA 2010, Kolkata, India, November 12-15, 2010, Revised Selected Papers, pages 42–57. In series: Lecture Notes in Computer Science #7057. Springer Berlin/Heidelberg. ISBN: 978-3-642-25919-7, 978-3-642-25920-3.
DOI: 10.1007/978-3-642-25920-3_4.

In the next decades, practically viable robotic/agent systems are going to be mixed-initiative in nature. Humans will request help from such systems and such systems will request help from humans in achieving the complex mission tasks required. Pragmatically, one requires a distributed task specification language to define tasks and a suitable data structure which satisfies the specification and can be used flexibly by collaborative multi-agent/robotic systems. This paper defines such a task specification language and an abstract data structure called Task Specification Trees which has many of the requisite properties required for mixed-initiative problem solving and adjustable autonomy in a distributed context. A prototype system has been implemented for this delegation framework and has been used practically with collaborative unmanned aircraft systems.

[42] David Landén, Fredrik Heintz and Patrick Doherty. 2012.
Complex Task Allocation in Mixed-Initiative Delegation: A UAV Case Study.
In Nirmit Desai, Alan Liu, Michael Winikoff, editors, Principles and Practice of Multi-Agent Systems: 13th International Conference, PRIMA 2010, Kolkata, India, November 12-15, 2010, Revised Selected Papers, pages 288–303. In series: Lecture Notes in Computer Science #7057. Springer Berlin/Heidelberg. ISBN: 978-3-642-25919-7, 978-3-642-25920-3.
DOI: 10.1007/978-3-642-25920-3_20.

Unmanned aircraft systems (UASs) are now becoming technologically mature enough to be integrated into civil society. An essential issue is principled mixed-initiative interaction between UASs and human operators. Two central problems are to specify the structure and requirements of complex tasks and to assign platforms to these tasks. We have previously proposed Task Specification Trees (TSTs) as a highly expressive specification language for complex multi-agent tasks that supports mixed-initiative delegation and adjustable autonomy. The main contribution of this paper is a sound and complete distributed heuristic search algorithm for allocating the individual tasks in a TST to platforms. The allocation also instantiates the parameters of the tasks such that all the constraints of the TST are satisfied. Constraints are used to model dependencies between tasks, resource usage as well as temporal and spatial requirements on complex tasks. Finally, we discuss a concrete case study with a team of unmanned aerial vehicles assisting in a challenging emergency situation.

[41] Luc De Raedt, Christian Bessiere, Didier Dubois, Patrick Doherty, Paolo Frasconi, Fredrik Heintz and Peter Lucas. 2012.
Proceedings of the 20th European Conference on Artificial Intelligence (ECAI).
Conference Proceedings. In series: Frontiers in Artificial Intelligence and Applications #242. IOS Press. 1056 pages. ISBN: 978-1-61499-097-0.

[40] Full text  Fredrik Heintz and Tommy Färnqvist. 2012.
Pedagogical Experiences of Competitive Elements in an Algorithms Course.
In Proceedings of LTHs 7:e Pedagogiska Inspirationskonferens (PIK).
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

We claim that competitive elements can improve thequality of programming and algorithms courses. To test this, weused our experience from organising national and internationalprogramming competitions to design and evaluate two differentcontests in an introductory algorithms course. The first contestturned lab assignments into a competition, where two groups rancompetitions and two were control groups and did not compete.The second, voluntary, contest, consisting of 15 internationalprogramming competition style problems, was designed tosupport student skill acquisition by providing them withopportunities for deliberate practise. We found that competitiveelements do influence student behaviour and our mainconclusions from the experiment are that students really likecompetitions, that the competition design is very important forthe resulting behaviour of the students, and that active studentsperform better on exams.We also report on an extra-curricular activity in the form of asemester long programming competition as a way of supportingstudent's deliberate practise in computer programming.

[39] Full text  Patrick Doherty and Fredrik Heintz. 2012.
Delegation-Based Collaboration.
In Proceedings of the 5th International Conference on Cognitive Systems (CogSys).

[38] Full text  Fredrik Heintz and Zlatan Dragisic. 2012.
Semantic Information Integration for Stream Reasoning.
In Proceedings of the 15th International Conference on Information Fusion (FUSION). Linköping University Electronic Press.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

The main contribution of this paper is a practicalsemantic information integration approach for stream reasoningbased on semantic matching. This is an important functionality for situation awareness applications where temporal reasoning over streams from distributed sources is needed. The integration is achieved by creating a common ontology, specifying the semantic content of streams relative to the ontology and then use semantic matching to find relevant streams. By using semantic mappings between ontologies it is also possible to do semantic matching over multiple ontologies. The complete stream reasoning approach is integrated in the Robot Operating System(ROS) and used in collaborative unmanned aircraft systems missions.

2011
[37] Full text  Patrick Doherty, Fredrik Heintz and David Landén. 2011.
A Delegation-Based Collaborative Robotic Framework.
In Christian Guttmann, editor, Proceedings of the 3rd International Workshop on Collaborative Agents - Research and development.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

[36] Anders Kofod-Peteresen, Fredrik Heintz and Langseth Helge. 2011.
Elevent Scandinavian Conference on Artifical Intelligence SCAI 2011.
Conference Proceedings. In series: Frontiers in Artificial Intelligence and Applications #227. IOS Press. 197 pages. ISBN: 978-1-60750-753-6.

[35] Full text  Patrick Doherty, Fredrik Heintz and David Landén. 2011.
A Delegation-Based Architecture for Collaborative Robotics.
In Danny Weyns and Marie-Pierre Gleizes, editors, Agent-Oriented Software Engineering XI: 11th International Workshop, AOSE 2010, Toronto, Canada, May 10-11, 2010, Revised Selected Papers, pages 205–247. In series: Lecture Notes in Computer Science #6788. Springer Berlin/Heidelberg. ISBN: 978-3-642-22635-9.
DOI: 10.1007/978-3-642-22636-6_13.
Find book in another country/Hitta boken i ett annat land: http://www.worldcat.org/search?q=978-3-6...
find book at a swedish library/hitta boken i ett svenskt bibliotek: http://libris.kb.se/bib/12509689
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

Collaborative robotic systems have much to gain by leveraging results from the area of multi-agent systems and in particular agent-oriented software engineering. Agent-oriented software engineering has much to gain by using collaborative robotic systems as a testbed. In this article, we propose and specify a formally grounded generic collaborative system shell for robotic systems and human operated ground control systems. Collaboration is formalized in terms of the concept of delegation and delegation is instantiated as a speech act. Task Specification Trees are introduced as both a formal and pragmatic characterization of tasks and tasks are recursively delegated through a delegation process implemented in the collaborative system shell. The delegation speech act is formally grounded in the implementation using Task Specification Trees, task allocation via auctions and distributed constraint problem solving. The system is implemented as a prototype on Unmanned Aerial Vehicle systems and a case study targeting emergency service applications is presented.

[34] Full text  Patrick Doherty and Fredrik Heintz. 2011.
A Delegation-Based Cooperative Robotic Framework.
In Proceedings of the IEEE International Conference on Robotics and Biomimetic, pages 2955–2962. IEEE conference proceedings. ISBN: 978-1-4577-2136-6.
DOI: 10.1109/ROBIO.2011.6181755.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

Cooperative robotic systems, such as unmanned aircraft systems, are becoming technologically mature enough to be integrated into civil society. To gain practical use and acceptance, a verifiable, principled and well-defined foundation for interactions between human operators and autonomous systems is needed. In this paper, we propose and specify such a formally grounded collaboration framework. Collaboration is formalized in terms of the concept of delegation and delegation is instantiated as a speech act. Task Specification Trees are introduced as both a formal and pragmatic characterization of tasks and tasks are recursively delegated through a delegation process. The delegation speech act is formally grounded in the implementation using Task Specification Trees, task allocation via auctions and distributed constraint solving. The system is implemented as a prototype on unmanned aerial vehicle systems and a case study targeting emergency service applications is presented.

2010
[33] Full text  Patrick Doherty, Jonas Kvarnström, Fredrik Heintz, David Landén and Per-Magnus Olsson. 2010.
Research with Collaborative Unmanned Aircraft Systems.
In Gerhard Lakemeyer, Hector J. Levesque, Fiora Pirri, editors, Proceedings of the Dagstuhl Workshop on Cognitive Robotics. In series: Dagstuhl Seminar Proceedings #10081. Leibniz-Zentrum für Informatik.

We provide an overview of ongoing research which targets development of a principled framework for mixed-initiative interaction with unmanned aircraft systems (UAS). UASs are now becoming technologically mature enough to be integrated into civil society. Principled interaction between UASs and human resources is an essential component in their future uses in complex emergency services or bluelight scenarios. In our current research, we have targeted a triad of fundamental, interdependent conceptual issues: delegation, mixed- initiative interaction and adjustable autonomy, that is being used as a basis for developing a principled and well-defined framework for interaction. This can be used to clarify, validate and verify different types of interaction between human operators and UAS systems both theoretically and practically in UAS experimentation with our deployed platforms.

[32] Full text  Fredrik Heintz, Jonas Kvarnström and Patrick Doherty. 2010.
Stream-Based Reasoning in DyKnow.
In Gerhard Lakemeyer and Hector J. Levesque and Fiora Pirri, editors, Proceedings of the Dagstuhl Workshop on Cognitive Robotics. In series: Dagstuhl Seminar Proceedings #10081. Leibniz-Zentrum für Informatik.

The information available to modern autonomous systems is often in the form of streams. As the number of sensors and other stream sources increases there is a growing need for incremental reasoning about the incomplete content of sets of streams in order to draw relevant conclusions and react to new situations as quickly as possible. To act rationally, autonomous agents often depend on high level reasoning components that require crisp, symbolic knowledge about the environment. Extensive processing at many levels of abstraction is required to generate such knowledge from noisy, incomplete and quantitative sensor data. We define knowledge processing middleware as a systematic approach to integrating and organizing such processing, and argue that connecting processing components with streams provides essential support for steady and timely flows of information. DyKnow is a concrete and implemented instantiation of such middleware, providing support for stream reasoning at several levels. First, the formal kpl language allows the specification of streams connecting knowledge processes and the required properties of such streams. Second, chronicle recognition incrementally detects complex events from streams of more primitive events. Third, complex metric temporal formulas can be incrementally evaluated over streams of states. DyKnow and the stream reasoning techniques are described and motivated in the context of a UAV traffic monitoring application.

[31] Full text  Fredrik Heintz, Jonas Kvarnström and Patrick Doherty. 2010.
Stream-Based Middleware Support for Embedded Reasoning.
In Proceedings of the AAAI Spring Symposium on Embedded Reasoning: Intelligence in Embedded Systems (ER). AAAI Press. ISBN: 978-157735458-1.

For autonomous systems such as unmanned aerial vehicles to successfully perform complex missions, a great deal of embedded reasoning is required at varying levels of abstraction. In order to make use of diverse reasoning modules in such systems, issues of integration such as sensor data flow and information flow between such modules has to be taken into account. The DyKnow framework is a tool with a formal basis that pragmatically deals with many of the architectural issues which arise in such systems. This includes a systematic stream-based method for handling the sense-reasoning gap, caused by the wide difference in abstraction levels between the noisy data generally available from sensors and the symbolic, semantically meaningful information required by many high-level reasoning modules. DyKnow has proven to be quite robust and widely applicable to different aspects of hybrid software architectures for robotics.In this paper, we describe the DyKnow framework and show how it is integrated and used in unmanned aerial vehicle systems developed in our group. In particular, we focus on issues pertaining to the sense-reasoning gap and the symbol grounding problem and the use of DyKnow as a means of generating semantic structures representing situational awareness for such systems. We also discuss the use of DyKnow in the context of automated planning, in particular execution monitoring.

[30] Full text  Mattias Krysander, Fredrik Heintz, Jacob Roll and Erik Frisk. 2010.
FlexDx: A Reconfigurable Diagnosis Framework.
Engineering applications of artificial intelligence, 23(8):1303–1313. Elsevier.
DOI: 10.1016/j.engappai.2010.01.004.
fulltext:postprint: http://liu.diva-portal.org/smash/get/div...

Detecting and isolating multiple faults is a computationally expensive task. It typically consists of computing a set of tests and then computing the diagnoses based on the test results. This paper describes FlexDx, a reconfigurable diagnosis framework which reduces the computational burden while retaining the isolation performance by only running a subset of all tests that is sufficient to find new conflicts. Tests in FlexDx are thresholded residuals used to indicate conflicts in the monitored system. Special attention is given to the issues introduced by a reconfigurable diagnosis framework. For example, tests are added and removed dynamically, tests are partially performed on historic data, and synchronous and asynchronous processing are combined. To handle these issues FlexDx has been implemented using DyKnow, a stream-based knowledge processing middleware framework. Concrete methods for each component in the FlexDx framework are presented. The complete approach is exemplified on a dynamic system which clearly illustrates the complexity of the problem and the computational gain of the proposed approach.

[29] Full text  Fredrik Heintz, Jonas Kvarnström and Patrick Doherty. 2010.
Stream-Based Reasoning Support for Autonomous Systems.
In Proceedings of the 19th European Conference on Artificial Intelligence (ECAI). In series: Frontiers in Artificial Intelligence and Applications #215. IOS Press. ISBN: 978-1-60750-605-8.
DOI: 10.3233/978-1-60750-606-5-183.

For autonomous systems such as unmanned aerial vehicles to successfully perform complex missions, a great deal of embedded reasoning is required at varying levels of abstraction. To support the integration and use of diverse reasoning modules we have developed DyKnow, a stream-based knowledge processing middleware framework. By using streams, DyKnow captures the incremental nature of sensor data and supports the continuous reasoning necessary to react to rapid changes in the environment. DyKnow has a formal basis and pragmatically deals with many of the architectural issues which arise in autonomous systems. This includes a systematic stream-based method for handling the sense-reasoning gap, caused by the wide difference in abstraction levels between the noisy data generally available from sensors and the symbolic, semantically meaningful information required by many highlevel reasoning modules. As concrete examples, stream-based support for anchoring and planning are presented.

[28] Full text  Fredrik Heintz and Patrick Doherty. 2010.
Federated DyKnow, a Distributed Information Fusion System for Collaborative UAVs.
In Proceedings of the 11th International Conference on Control, Automation, Robotics and Vision (ICARCV), pages 1063–1069. IEEE conference proceedings. ISBN: 978-1-4244-7814-9.
DOI: 10.1109/ICARCV.2010.5707967.

As unmanned aerial vehicle (UAV) applications are becoming more complex and covering larger physical areas there is an increasing need for multiple UAVs to cooperatively solve problems. To produce more complete and accurate information about the environment we present the DyKnow Federation framework for distributed fusion among collaborative UAVs. A federation is created and maintained using a multi-agent delegation framework which allows high-level specification and reasoning about resource bounded cooperative problem solving. When the federation is set up, local information is transparently shared between the agents according to specification. The work is presented in the context of a multi-UAV traffic monitoring scenario.

[27] Full text  Fredrik Heintz, Jonas Kvarnström and Patrick Doherty. 2010.
Bridging the sense-reasoning gap: DyKnow - Stream-based middleware for knowledge processing.
Advanced Engineering Informatics, 24(1):14–26. Elsevier.
DOI: 10.1016/j.aei.2009.08.007.

Engineering autonomous agents that display rational and goal-directed behavior in dynamic physical environments requires a steady flow of information from sensors to high-level reasoning components. However, while sensors tend to generate noisy and incomplete quantitative data, reasoning often requires crisp symbolic knowledge. The gap between sensing and reasoning is quite wide, and cannot in general be bridged in a single step. Instead, this task requires a more general approach to integrating and organizing multiple forms of information and knowledge processing on different levels of abstraction in a structured and principled manner. We propose knowledge processing middleware as a systematic approach to organizing such processing. Desirable properties are presented and motivated. We argue that a declarative stream-based system is appropriate for the required functionality and present DyKnow, a concrete implemented instantiation of stream-based knowledge processing middleware with a formal semantics. Several types of knowledge processes are defined and motivated in the context of a UAV traffic monitoring application. In the implemented application, DyKnow is used to incrementally bridge the sense-reasoning gap and generate partial logical models of the environment over which metric temporal logical formulas are evaluated. Using such formulas, hypotheses are formed and validated about the type of vehicles being observed. DyKnow is also used to generate event streams representing for example changes in qualitative spatial relations, which are used to detect traffic violations expressed as declarative chronicles.

2009
[26] Full text  Patrick Doherty, Jonas Kvarnström and Fredrik Heintz. 2009.
A Temporal Logic-based Planning and Execution Monitoring Framework for Unmanned Aircraft Systems.
Autonomous Agents and Multi-Agent Systems, 19(3):332–377. Springer.
DOI: 10.1007/s10458-009-9079-8.

Research with autonomous unmanned aircraft systems is reaching a new degree of sophistication where targeted missions require complex types of deliberative capability integrated in a practical manner in such systems. Due to these pragmatic constraints, integration is just as important as theoretical and applied work in developing the actual deliberative functionalities. In this article, we present a temporal logic-based task planning and execution monitoring framework and its integration into a fully deployed rotor-based unmanned aircraft system developed in our laboratory. We use a very challenging emergency services application involving body identification and supply delivery as a vehicle for showing the potential use of such a framework in real-world applications. TALplanner, a temporal logic-based task planner, is used to generate mission plans. Building further on the use of TAL (Temporal Action Logic), we show how knowledge gathered from the appropriate sensors during plan execution can be used to create state structures, incrementally building a partial logical model representing the actual development of the system and its environment over time. We then show how formulas in the same logic can be used to specify the desired behavior of the system and its environment and how violations of such formulas can be detected in a timely manner in an execution monitor subsystem. The pervasive use of logic throughout the higher level deliberative layers of the system architecture provides a solid shared declarative semantics that facilitates the transfer of knowledge between different modules.

[25] Full text  Fredrik Heintz, Jonas Kvarnström and Patrick Doherty. 2009.
Stream Reasoning in DyKnow: A Knowledge Processing Middleware System.
In Proceedings of the Stream Reasoning Workshop. In series: CEUR Workshop Proceedings #466. M. Jeusfeld c/o Redaktion Sun SITE, Informatik V, RWTH Aachen.

The information available to modern autonomous systems is often in the form of streams. As the number of sensors and other stream sources increases there is a growing need for incremental reasoning about the incomplete content of sets of streams in order to draw relevant conclusions and react to new situations as quickly as possible. To act rationally, autonomous agents often depend on high level reasoning components that require crisp, symbolic knowledge about the environment. Extensive processing at many levels of abstraction is required to generate such knowledge from noisy, incomplete and quantitative sensor data. We define knowledge processing middleware as a systematic approach to integrating and organizing such processing, and argue that connecting processing components with streams provides essential support for steady and timely flows of information. DyKnow is a concrete and implemented instantiation of such middleware, providing support for stream reasoning at several levels. First, the formal KPL language allows the specification of streams connecting knowledge processes and the required properties of such streams. Second, chronicle recognition incrementally detects complex events from streams of more primitive events. Third, complex metric temporal formulas can be incrementally evaluated over streams of states. DyKnow and the stream reasoning techniques are described and motivated in the context of a UAV traffic monitoring application.

[24] Fredrik Heintz and Jonas Kvarnström. 2009.
Proceedings of the Swedish AI Society Workshop 2009.
Conference Proceedings. In series: Linköping Electronic Conference Proceedings #35. Linköping University Electronic Press, Linköpings universitet. 65 pages.
Link to Book: http://www.ep.liu.se/ecp/035/

[23] Full text  Fredrik Heintz, Jonas Kvarnström and Patrick Doherty. 2009.
A Stream-Based Hierarchical Anchoring Framework.
In Proceedings of the IEEE/RSJ International Conference on Intelligent RObots and Systems (IROS). IEEE conference proceedings. ISBN: 978-1-4244-3803-7.
DOI: 10.1109/IROS.2009.5354372.
IEEE Xplore: http://ieeexplore.ieee.org/stamp/stamp.j...

[22] Full text  Fredrik Heintz. 2009.
DyKnow: A Stream-Based Knowledge Processing Middleware Framework.
PhD Thesis. In series: Linköping Studies in Science and Technology. Dissertations #1240. Linköping University Electronic Press. 258 pages. ISBN: 9789173936965.
cover: http://liu.diva-portal.org/smash/get/div...

As robotic systems become more and more advanced the need to integrate existing deliberative functionalities such as chronicle recognition, motion planning, task planning, and execution monitoring increases. To integrate such functionalities into a coherent system it is necessary to reconcile the different formalisms used by the functionalities to represent information and knowledge about the world. To construct and integrate these representations and maintain a correlation between them and the environment it is necessary to extract information and knowledge from data collected by sensors. However, deliberative functionalities tend to assume symbolic and crisp knowledge about the current state of the world while the information extracted from sensors often is noisy and incomplete quantitative data on a much lower level of abstraction. There is a wide gap between the information about the world normally acquired through sensing and the information that is assumed to be available for reasoning about the world.As physical autonomous systems grow in scope and complexity, bridging the gap in an ad-hoc manner becomes impractical and inefficient. Instead a principled and systematic approach to closing the sensereasoning gap is needed. At the same time, a systematic solution has to be sufficiently flexible to accommodate a wide range of components with highly varying demands. We therefore introduce the concept of knowledge processing middleware for a principled and systematic software framework for bridging the gap between sensing and reasoning in a physical agent. A set of requirements that all such middleware should satisfy is also described.A stream-based knowledge processing middleware framework called DyKnow is then presented. Due to the need for incremental refinement of information at different levels of abstraction, computations and processes within the stream-based knowledge processing framework are modeled as active and sustained knowledge processes working on and producing streams. DyKnow supports the generation of partial and context dependent stream-based representations of past, current, and potential future states at many levels of abstraction in a timely manner.To show the versatility and utility of DyKnow two symbolic reasoning engines are integrated into Dy-Know. The first reasoning engine is a metric temporal logical progression engine. Its integration is made possible by extending DyKnow with a state generation mechanism to generate state sequences over which temporal logical formulas can be progressed. The second reasoning engine is a chronicle recognition engine for recognizing complex events such as traffic situations. The integration is facilitated by extending DyKnow with support for anchoring symbolic object identifiers to sensor data in order to collect information about physical objects using the available sensors. By integrating these reasoning engines into DyKnow, they can be used by any knowledge processing application. Each integration therefore extends the capability of DyKnow and increases its applicability.To show that DyKnow also has a potential for multi-agent knowledge processing, an extension is presented which allows agents to federate parts of their local DyKnow instances to share information and knowledge.Finally, it is shown how DyKnow provides support for the functionalities on the different levels in the JDL Data Fusion Model, which is the de facto standard functional model for fusion applications. The focus is not on individual fusion techniques, but rather on an infrastructure that permits the use of many different fusion techniques in a unified framework.The main conclusion of this thesis is that the DyKnow knowledge processing middleware framework provides appropriate support for bridging the sense-reasoning gap in a physical agent. This conclusion is drawn from the fact that DyKnow has successfully been used to integrate different reasoning engines into complex unmanned aerial vehicle (UAV) applications and that it satisfies all the stated requirements for knowledge processing middleware to a significant degree.

2008
[21] Full text  Fredrik Heintz and Patrick Doherty. 2008.
DyKnow Federations: Distributing and Merging Information Among UAVs.
In Proceedings of the 11th International Conference on Information Fusion (FUSION). IEEE conference proceedings. ISBN: 978-3-8007-3092-6.

As unmanned aerial vehicle (UAV) applications become more complex and versatile there is an increasing need to allow multiple UAVs to cooperate to solve problems which are beyond the capability of each individual UAV. To provide more complete and accurate information about the environment we present a DyKnow federation framework for information integration in multi-node networks of UAVs. A federation is created and maintained using a multiagent delegation framework and allows UAVs to share local information as well as process information from other UAVs as if it were local using the DyKnow knowledge processing middleware framework. The work is presented in the context of a multi UAV traffic monitoring scenario.

[20] Full text  Fredrik Heintz, Jonas Kvarnström and Patrick Doherty. 2008.
Bridging the Sense-Reasoning Gap: DyKnow - A Middleware Component for Knowledge Processing.
In Martin Hulse and Manfred Hild, editors, IROS Workshop on Current Software Frameworks in Cognitive Robotics Integrating Different Computational Paradigms.
Note: No proceedings, but CD

Developing autonomous agents displaying rational and goal-directed behavior in a dynamic physical environment requires the integration of both sensing and reasoning components. Due to the different characteristics of these components there is a gap between sensing and reasoning. We believe that this gap can not be bridged in a single step with a single technique. Instead, it requires a more general approach to integrating components on many different levels of abstraction and organizing them in a structured and principled manner. In this paper we propose knowledge processing middleware as a systematic approach for organizing such processing. Desirable properties of such middleware are presented and motivated. We then go on to argue that a declarative streambased system is appropriate to provide the desired functionality. Finally, DyKnow, a concrete example of stream-based knowledge processing middleware that can be used to bridge the sense-reasoning gap, is presented. Different types of knowledge processes and components of the middleware are described and motivated in the context of a UAV traffic monitoring application.

[19] Full text  Jonas Kvarnström, Fredrik Heintz and Patrick Doherty. 2008.
A Temporal Logic-Based Planning and Execution Monitoring System.
In Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS). AAAI Press. ISBN: 978-1-57735-386-7, 978-1-57735-387-4.

As no plan can cover all possible contingencies, the ability to detect failures during plan execution is crucial to the robustness of any autonomous system operating in a dynamic and uncertain environment. In this paper we present a general planning and execution monitoring system where formulas in an expressive temporal logic specify the desired behavior of a system and its environment. A unified domain description for planning and monitoring provides a solid shared declarative semantics permitting the monitoring of both global and operator-specific conditions. During plan execution, an execution monitor subsystem detects violations of monitor formulas in a timely manner using a progression algorithm on incrementally generated partial logical models. The system has been integrated on a fully deployed autonomous unmanned aircraft system. Extensive empirical testing has been performed using a combination of actual flight tests and hardware-in-the-loop simulations in a number of different mission scenarios.

[18] Full text  Mattias Krysander, Fredrik Heintz, Jacob Roll and Erik Frisk. 2008.
Dynamic Test Selection for Reconfigurable Diagnosis.
In Proceedings of the 47th IEEE Conference on Decision and Control, pages 1066–1072. In series: IEEE Conference on Decision and Control. Proceedings #??. IEEE. ISBN: 978-1-4244-3124-3, 978-1-4244-3123-6.
DOI: 10.1109/CDC.2008.4738793.

Detecting and isolating multiple faults is a computationally intense task which typically consists of computing a set of tests, and then computing the diagnoses based on the test results. This paper proposes a method to reduce the computational burden by only running the tests that are currently needed, and dynamically starting new tests when the need changes. A main contribution is a method to select tests such that the computational burden is reduced while maintaining the isolation performance of the diagnostic system. Key components in the approach are the test selection algorithm, the test initialization procedures, and a knowledge processing framework that supports the functionality needed. The approach is exemplified on a relatively small dynamical system, which still illustrates the complexity and possible computational gain with the proposed approach.

[17] Full text  Fredrik Heintz, Mattias Krysander, Jacob Roll and Erik Frisk. 2008.
FlexDx: A Reconfigurable Diagnosis Framework.
In Proceedings of the 19th International Workshop on Principles of Diagnosis (DX).

Detecting and isolating multiple faults is a computationally intense task which typically consists of computing a set of tests, and then computing the diagnoses based on the test results. This paper describes FlexDx, a reconfigurable diagnosis framework which reduces the computational burden by only running the tests that are currently needed. The method selects tests such that the isolation performance of the diagnostic system is maintained. Special attention is given to the practical issues introduced by a reconfigurable diagnosis framework such as FlexDx. For example, tests are added and removed dynamically, tests are partially performed on historic data, and synchronous and asynchronous processing are combined. To handle these issues FlexDx uses DyKnow, a stream-based knowledge processing middleware framework. The approach is exemplified on a relatively small dynamical system, which still illustrates the computational gain with the proposed approach.

[16] Full text  Fredrik Heintz, Jonas Kvarnström and Patrick Doherty. 2008.
Knowledge Processing Middleware.
In S. Carpin, I. Noda, E. Pagello, M. Reggiani and O. von Stryk, editors, Proceedings of the 1st International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR), pages 147–158. In series: Lecture Notes in Computer Science #5325. Springer. ISBN: 978-3-540-89075-1, 978-3-540-89076-8.
DOI: 10.1007/978-3-540-89076-8_17.
fulltext:preprint: http://liu.diva-portal.org/smash/get/div...

Developing autonomous agents displaying rational and goal-directed behavior in a dynamic physical environment requires the integration of a great number of separate deliberative and reactive functionalities. This integration must be built on top of a solid foundation of data, information and knowledge having numerous origins, including quantitative sensors and qualitative knowledge databases. Processing is generally required on many levels of abstraction and includes refinement and fusion of noisy sensor data and symbolic reasoning. We propose the use of knowledge processing middleware as a systematic approach for organizing such processing. Desirable properties of such middleware are presented and motivated. We then argue that a declarative stream-based system is appropriate to provide the desired functionality. Different types of knowledge processes and components of the middleware are described and motivated in the context of a UAV traffic monitoring application. Finally DyKnow, a concrete example of stream-based knowledge processing middleware, is briefly described.

2007
[15] Full text  Fredrik Heintz, Piotr Rudol and Patrick Doherty. 2007.
From Images to Traffic Behavior - A UAV Tracking and Monitoring Application.
In Proceedings of the 10th International Conference on Information Fusion (FUSION). IEEE conference proceedings. ISBN: 978-0-662-45804-3, 978-0-662-47830-0.
DOI: 10.1109/ICIF.2007.4408103.
Link: http://www.ida.liu.se/~frehe/publication...

An implemented system for achieving high level situation awareness about traffic situations in an urban area is described. It takes as input sequences of color and thermal images which are used to construct and maintain qualitative object structures and to recognize the traffic behavior of the tracked vehicles in real time. The system is tested both in simulation and on data collected during test flights. To facilitate the signal to symbol transformation and the easy integration of the streams of data from the sensors with the GIS and the chronicle recognition system, DyKnow, a stream-based knowledge processing middleware, is used. It handles the processing of streams, including the temporal aspects of merging and synchronizing streams, and provides suitable abstractions to allow high level reasoning and narrow the sense reasoning gap.

[14] Full text  Fredrik Heintz, Piotr Rudol and Patrick Doherty. 2007.
Bridging the Sense-Reasoning Gap Using DyKnow: A Knowledge Processing Middleware Framework.
In Joachim Hertzberg, Michael Beetz and Roman Englert, editors, Proceedings of the 30th Annual German Conference on Artificial Intelligence (KI), pages 460–463. In series: Lecture Notes in Computer Science #4667. Springer. ISBN: 978-3-540-74564-8.
DOI: 10.1007/978-3-540-74565-5_40.
Link: http://www.ida.liu.se/~frehe/publication...

To achieve complex missions an autonomous unmanned aerial vehicle (UAV) operating in dynamic environments must have and maintain situational awareness. This can be achieved by continually gathering information from many sources, selecting the relevant information for current tasks, and deriving models about the environment and the UAV itself. It is often the case models suitable for traditional control, are not sufficient for deliberation. The need for more abstract models creates a sense-reasoning gap. This paper presents DyKnow, a knowledge processing middleware framework, and shows how it supports bridging the gap in a concrete UAV traffic monitoring application. In the example, sequences of color and thermal images are used to construct and maintain qualitative object structures. They model the parts of the environment necessary to recognize traffic behavior of tracked vehicles in real-time. The system has been implemented and tested in simulation and on data collected during flight tests.

2006
[13] Full text  Fredrik Heintz and Patrick Doherty. 2006.
A knowledge processing middleware framework and its relation to the JDL data fusion model.
Journal of Intelligent & Fuzzy Systems, 17(4):335–351. IOS Press.

Any autonomous system embedded in a dynamic and changing environment must be able to create qualitative knowledge and object structures representing aspects of its environment on the fly from raw or preprocessed sensor data in order to reason qualitatively about the environment and to supply such state information to other nodes in the distributed network in which it is embedded. These structures must be managed and made accessible to deliberative and reactive functionalities whose successful operation is dependent on being situationally aware of the changes in both the robotic agent's embedding and internal environments. DyKnow is a knowledge processing middleware framework which provides a set of functionalities for contextually creating, storing, accessing and processing such structures. The framework is implemented and has been deployed as part of a deliberative/reactive architecture for an autonomous unmanned aerial vehicle. The architecture itself is distributed and uses real-time CORBA as a communications infrastructure. We describe the system and show how it can be used to create more abstract entity and state representations of the world which can then be used for situation awareness by an unmanned aerial vehicle in achieving mission goals. We also show that the framework is a working instantiation of many aspects of the JDL data fusion model.

2005
[12] Full text  Fredrik Heintz and Patrick Doherty. 2005.
A knowledge processing middleware framework and its relation to the JDL data fusion model.
In The 8th International Conference on Information Fusion,2005.

[11] Full text  Fredrik Heintz and Patrick Doherty. 2005.
A Knowledge processing Middleware Framework and its Relation to the JDL Data Fusion model.
In SWAR 05,2005, pages 50–51.

[10] Full text  Fredrik Heintz and Patrick Doherty. 2005.
A Knowledge processing Middleware Framework and its Relation to the JDL Data Fusion model.
In 3rd joint SAIS-SSL event on Artificial Intelligence an Learning Systems,2005. Mälardalens University.

2004
[9] Full text  Fredrik Heintz and Patrick Doherty. 2004.
DyKnow: A Framework for Processing Dynamic Knowledge and Object Structures in Autonomous Systems.
In Proceedings of the Second Joint SAIS/SSLS Workshop.

[8] Full text  Fredrik Heintz and Patrick Doherty. 2004.
DyKnow: An approach to middleware for knowledge processing.
Journal of Intelligent & Fuzzy Systems, 15(1):3–13. IOS Press.

Any autonomous system embedded in a dynamic and changing environment must be able to create qualitative knowledge and object structures representing aspects of its environment on the fly from raw or preprocessed sensor data in order to reason qualitatively about the environment. These structures must be managed and made accessible to deliberative and reactive functionalities which are dependent on being situationally aware of the changes in both the robotic agent's embedding and internal environment. DyKnow is a software framework which provides a set of functionalities for contextually accessing, storing, creating and processing such structures. The system is implemented and has been deployed in a deliberative/reactive architecture for an autonomous unmanned aerial vehicle. The architecture itself is distributed and uses real-time CORBA as a communications infrastructure. We describe the system and show how it can be used in execution monitoring and chronicle recognition scenarios for UAV applications.

[7] Full text  Patrick Doherty, Patrik Haslum, Fredrik Heintz, Torsten Merz, Per Nyblom, Tommy Persson and Björn Wingman. 2004.
A Distributed Architecture for Autonomous Unmanned Aerial Vehicle Experimentation.
In 7th International Symposium on Distributed Autonomous Robotic Systems,2004. LAAS.

[6] Full text  Fredrik Heintz and Patrick Doherty. 2004.
Managing Dynamic Object Structures using Hypothesis Generation and Validation.
In AAAI Workshop on Anchoring Symbols to Sensor Data,2004, pages 54–62. AAAI Press.

[5] Full text  Fredrik Heintz and Patrick Doherty. 2004.
DyKnow: A Framework for Processing Dynamic Knowledge and Object Structures in Autonomous Systems.
In Barbara Dunin-Keplicz, Andrzej Jankowski, Andrzej Skowron, Marcin Szczuka, editors, Proceedings of the International Workshop on Monitoring, Security, and Rescue Techniques in Multi-Agent Systems (MSRAS), pages 479–492. In series: Advances in Soft Computing #28. Springer. ISBN: 978-3540232452.
DOI: 10.1007/3-540-32370-8_37.

Any autonomous system embedded in a dynamic and changing environment must be able to create qualitative knowledge and object structures representing aspects of its environment on the fly from raw or preprocessed sensor data in order to reason qualitatively about the environment. These structures must be managed and made accessible to deliberative and reactive functionalities which are dependent on being situationally aware of the changes in both the robotic agent’s embedding and internal environment. DyKnow is a software framework which provides a set of functionalities for contextually accessing, storing, creating and processing such structures. The system is implemented and has been deployed in a deliberative/reactive architecture for an autonomous unmanned aerial vehicle. The architecture itself is distributed and uses real-time CORBA as a communications infrastructure. We describe the system and show how it can be used in execution monitoring and chronicle recognition scenarios for UAV applications.

2001
[4] Full text  Fredrik Heintz, Johan Kummeneje and Paul Scerri. 2001.
Using Simulated RoboCup to Teach AI in Undergraduate Education.
In Proceedings of the 7th Scandinavian Conference on Artificial Intelligence (SCAI), pages 13–21. In series: Frontiers in Artificial Intelligence and Applications #66. IOS Press. ISBN: 1-58603-161-9.

In this paper we argue that RoboCup is a useful tool for the teaching of AI in undergraduate education. We provide case studies, from two Swedish universities, of how RoboCup based AI courses can be implemented using a problem based approach. Although the courses were successful there are significant areas for improvement. Firstly, to help students cope with the complexity of the domain we developed RoboSoc, a general software framework for developing simulated RoboCup agents. Secondly, we propose creating close co-operation between the teachers and researchers at Scandinavian Universities with the aim of increasing the motivation of both students and teachers by providing accessible information and competence.

[3] Full text  Fredrik Heintz and Patrick Doherty. 2001.
Chronicle Recognition in the WITAS UAV Project: A Preliminary Report.
In Proceedings of the Swedish AI Society Workshop.

This paper describes the chronicle recognition problem and reports its status in the WITAS UAV project. We describe how we use the IxTeT chronicle recognition system to define chronicles (scenarios or situations), like a vehicle passing another vehicle, and how it is incorporated in the WITAS architecture. We also discuss known problems with the current system and possible directions of future research.

2000
[2] Fredrik Heintz, Johan Kummeneje and Paul Scerri. 2000.
Simulated RoboCup in University Undergraduate Education.
In Proceedings of the Fourth Internation Workshop on RoboCup, pages 309–314. In series: Lecture Notes in Computer Science #2019. Springer Berlin/Heidelberg. ISBN: 978-3-540-42185-6, 978-3-540-45324-6.
DOI: 10.1007/3-540-45324-5_31.

We argue that RoboCup can be used to improve the teaching of AI in undergraduate education. We give some examples of how AI courses using RoboCup can be implemented using a problem based approach at two different Universities. To reduce the negative aspects found we present a solution, with the aim of easing the burden of grasping the domain of RoboCup for the students, RoboSoc which is a general framework for developing simulated RoboCup agents.

[1] Fredrik Heintz. 2000.
FCFoo99.
In Proceedings of RoboCup-99: Robot Soccer World Cup III (RoboCup), pages 563–566. In series: Lecture Notes in Computer Science #1856. Springer London. ISBN: 3-540-41043-0.
Link: http://dl.acm.org/citation.cfm?id=698527

Introduction The emphasis of FCFoo was mainly on building a library for developers of RoboCup teams, designed especially for educational use. After the competition the library was more or less totally rewritten and nally published as part of the Master Thesis of Fredrik Heintz [4]. The agents are built on a layered reactive-deliberative architecture. The four layers describes the agent on dierent levels of abstraction and deliberation. The lowest level is mainly reactive while the others are more deliberate. The teamwork is based on nite automatas and roles. A role is a set of attributes describing some of the behaviour of a player. The decision-making uses decisiontrees to classify the situation and select the appropriate skill to perform. The other two layers are used to calculate the actual command to be sent to the server. The agent architecture and the basic design are inspired by the champions of RoboCup'98, CMUnited [6, 7]. The idea of using decision-trees and role