|
|
vaida-abstract
Abstract - lic thesis Robert Lundh, Örebro university
Plan-Based Configuration of a Group of Robots
----------
Imagine the following situation. You give your favorite robot, named
Pippi, the task to fetch a parcel that just arrived at your front door.
While pushing the parcel back to you, she must travel through a door
opening.
Unfortunately,the parcel she is pushing is blocking her camera, giving
her a hard time to see the door to cross. If she cannot see the door,
she cannot safely push the parcel through the door opening. What would
you as a human do in a similar situation?
Most probably you would ask someone for help, someone to guide you
through the door, as we ask for help when we need to park our car in a
tight parking spot. Why not let the robots do the same? Why not let
robots help each other? Luckily for Pippi, there is another robot,
named Emil, vacuum cleaning the floor in the same room. Since
Emil can view both Pippi and the door at the same time, he can guide
Pippi through the door, enabling her to deliver the parcel to you.
This work is about societies of autonomous robots in which robots can
help each other by offering information-producing functionalities. A
functional configuration is a way to allocate and connect
functionalities among robots. In general, different configurations can
be used to solve the same task, depending on the current
situation. For the work on configurations, we have three steps.
The first step is to formally define the idea of functional
configuration.
The second step is to investigate how configurations can be
automatically generated and executed. The third step is to address the
problem of when and how to change a configuration in response to
changing conditions. In this licentiate thesis we report initial work
that focus on the two first steps: the third step is a subject of
future work. We propose a formal definition of functional
configurations, and we propose an approach based on artificial
intelligence (AI) planning techniques to automatically generate a
preferred configuration for a given
task, environment, and set of resources. To illustrate these ideas, we
describe an experimental system where these are implemented, and show
two examples in which two robots mutually help each other to accomplish
tasks. In the first example they help each other to cross a door, and
in the second example they carry a bar together
|
|
 |
 |
|
