Name of Paper

Increasing Mobile Robot Learning Rates Through Sharing of Experiences


Authors

D.A. Keating and I.D. Kelly


Published

Proc UKACC International Conference on Control ‘98, Wales, 1-4 Sept. pp 1664-1669.


Abstract

This paper describes a learning algorithm for autonomous mobile robots based on sets of fuzzy automata. The task the robots have to learn is how to avoid obstacles reactively. The approach presented here is one in which two or four robots learn simultaneously, with the experiences of each robot being passed onto the others. It is shown that this sharing of experiences results in faster and more robust learning than is the case without sharing.


Electronic copy

ctrl98.ps.Z (200K)