The design of a group of robots that should work together has to consider in an integrated way all the aspects of the "robot being": sensors and actuators, control, world modeling, strategy, coordination, adaptation and learning. At the speaker's lab this problem has been approached by defining a set of powerful tools to design with many degrees of freedom all the mentioned aspects. Their main features will be presented and discussed following a running example about the Robocup middle-size soccer robots.
behavior-based robotics, multi-agent systems, fuzzy modeling, omnidirectional vision, reinforcement learning
Bonarini A., Invernizzi G., Labella T. H., Matteucci M.. (2003)
An architecture to coordinate fuzzy behaviors to control an autonomous robot,
Fuzzy sets and systems, 134(1):101-115.
Restelli M., Sorrenti D. G., Marchese Fabio M.. (2004)
A Probabilistic Framework for Weighting Different Sensor Data in MUREA.
In Polani, D.; Browning, B.; Bonarini, A.; Yoshida, K. (ed.)
RoboCup 2003: Robot Soccer World Cup VII. Springer Verlag, Berlin. pp. 678 - 685.
Bonarini, A., Restelli M.. (2002)
An architecture to implement adaptive cooperative strategies for heterogeneous agents.
Proceedings of IROS 2002 Workshop on Cooperative Robotics. IEEE Press, Piscataway, NJ.