- Robot Hardware Page 1
- Robot Hardware Page 2
- Robot Hardware Page 3
- Robot Hardware Page 4
- Robot Hardware Page 5
- Image Gallery
The purpose of this project is to explore some research done by Rodney Brooks and Pattie Maes at MIT in the early 1990's. Their work involved a six-legged robot that could learn to walk. The most remarkable aspect of their design is that each leg was controlled by a separate brain, and each brain had no communication with the other five brains. The success of the learning process was achieved when each leg gradually coordinated its behaviors with those of the others, resulting in a variety of smooth and efficient gaits.
At first glance, this might seem absurd. How can coordinated behavior emerge from six different brains that have no idea what the others are thinking? How can each brain possibly figure out when to do what, how or where, with nothing to go on? Trial and error? The truth is (1), yes there is lots of trial and error involved, and (2) no, each brain does have a little knowledge to go on (sensory input).
Back in the mid 1980's, Brooks introduced his ideas on adaptive robot control systems that were not based on top-down architectures with a single executive control unit. He approached the subject of artificial intelligence from a seemingly bottom-up, behavior-based perspective, out of which sprang the concept of subsumption architecture.
Brooks, R. A., "A Robust Layered Control System for a Mobile Robot", IEEE Journal of Robotics and Automation, Vol. 2, No. 1, March 1986, pp. 1423; also MIT AI Memo 864, September 1985.
Brooks, R. A., "How To Build Complete Creatures Rather Than Isolated Cognitive Simulators", Architectures for Intelligence, K. VanLehn (ed), Erlbaum, Hillsdale, NJ, Fall 1989, pp. 225239.
Brooks, R. A., "Challenges for Complete Creature Architectures", First International Conference on Simulation of Adaptive Behavior, Paris, France, September 1990, pp. 434443.
Brooks, R. A., "Intelligence Without Representation", Artificial Intelligence Journal (47), 1991, pp. 139159.
Brooks, R. A., "Intelligence Without Reason", Proceedings of 12th Int. Joint Conf. on Artificial Intelligence, Sydney, Australia, August 1991, pp. 569595.
Maes, P. and R. A. Brooks, "Learning to Coordinate Behaviors", AAAI, Boston, MA, August 1990, pp. 796802.