Evolving connection weights between sensors and actuators in robots

J.M. Molina, A. Berlanga, A. Sanchis, P. Isasi
ISIE '97 Proceeding of the IEEE International Symposium on Industrial Electronics  
In this paper an evolution strategy (ES) is introduced, to learn reactive behaviour in autonomous robots. An ES is used to learn high-performance reactive behaviour for navigation and collisions avoidance. The learned behaviour is able to solve the problem in a dynamic environment; so, the learning process has proven the ability to obtain generalised behaviours. The robot starts without information about the right associations between sensors and actuators, and, from this situation, the robot
more » ... uation, the robot is able to learn, through experience, to reach the highest adaptability grade to the sensors information. No subjective information about "how to accomplish the task" is included in the fitness function. A mini-robot Khepera has been used to test the learned behaviour. IEEE Catalog Number: 97THS280 -686 -ISIE'97 -Guimades, Portugal Authorized licensed use limited to: Univ Carlos III. Downloaded on March 26, 2009 at 11:44 from IEEE Xplore. Restrictions apply.
doi:10.1109/isie.1997.649054 fatcat:yywb7kavwzcmdmmcj7x4l4smty