Automatic Creation of an Autonomous Agent: Genetic Evolution of a Neural Network Driven Robot

The paper describes the results of the evolutionary development of a real, neural-network driven mobile robot. The evolutionary approach to the development of neural controllers for autonomous agents has been successfully used by many researchers, but most - if not all - studies have been carried out with computer simulations. Instead, in this research the whole evolutionary process takes places entirely on a real robot without human intervention. Although the experiments described here tackle a simple task of navigation and obstacle avoidance, we show a number of emergent phenomena that are characteristic of autonomous agents. The neural controllers of the evolved best individuals display a full exploitation of non-linear and recurrent connections that make them more efficient than analogous man-designed agents. In order to fully understand and describe the robot behavior, we have also employed quantitative ethological tools [13], and showed that the adaptation dynamics conform to predictions made for animals.


Editor(s):
Cliff, D.
Husbands, P.
Meyer, J.-A.
Wilson, S.
Published in:
Proceedings of the third international conference on Simulation of adaptive behavior: From Animals to Animats 3, 421-430
Presented at:
3rd International Conference on Simulation of Adaptive Behavior (SAB'1994), Brighton, England, August 8-12
Year:
1994
Publisher:
Cambridge, MA, USA, MIT Press
ISBN:
0-262-53122-4
Keywords:
Note:
D. Cliff, P. Husbands, J.-A. Meyer, and S. Wilson (eds.)
Laboratories:




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

n/a:
Download fulltextPS.Z
External link:
Download fulltextURL
Rate this document:

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