Evolution of Adaptive-Synapse Controllers

This paper is concerned with artificial evolution of neuro-controllers with adaptive synapses for autonomous mobile robots. The method consists of encoding on the genotype a set of local modification rules that synapses obey while the robot freely moves in the environment [2]. The synaptic weights are not encoded on the genotype. In the experiments presented here, a "behavior-based fitness" function gives reproductive advantage to robots that can solve a sequential task. The results show that evolutionary adaptive controllers solve the task much faster and better than evolutionary standard (non-adaptive) controllers, that the method scales up well to large architectures whereas standard controllers do not, and that evolved adaptive controllers are not trivial and cannot be reduced to a fixed-weight network.


Published in:
Advances in Artificial Life
Presented at:
5th European Conference on Artificial Life (ECAL'1999), EPFL, Lausanne, Switzerland, 13-17 September
Year:
1999
Keywords:
Note:
D. Floreano et al. (eds.)
Laboratories:




 Record created 2006-01-12, last modified 2018-03-17

n/a:
Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)