Paper Info
Title
Comparative study of two homeostatic mechanisms in evolved neural controllers for legged locomotion
Abstract
This paper presents a preliminary study on the advantages of IMO bio-inspired homeostatic mechanisms in neural controllers of legged robots. We consider a robot made up of one leg of 3 dof pushing a body that is sliding on a rail with a friction force. The synthesis of the controller is done by an evolutionary algorithm which choose to attach to each synapse a particular plastic law. Four models of network incorporating or not each homeostatic law are proposed. After evolution, effectiveness of each kind of adaptive controllers is compared in term of statistics on a task of controlling the speed of the robot. The robustness to a perturbation generated by the viscous friction is analyzed in terms of control. Results show that homeostatic mechanisms increase evolvability, stability and adaptivity of those controllers.
Year
DOI
Venue
2004
10.1109/IROS.2004.1389804
IROS 2004). Proceedings. 2004 IEEE/RSJ International Conference
Keywords
Field
DocType
adaptive control,control system synthesis,evolutionary computation,legged locomotion,neurocontrollers,stability,velocity control,IMO bio-inspired homeostatic mechanisms,adaptive controllers,evolutionary algorithm,evolved neural controllers,friction force,legged locomotion,legged robots,plastic law,viscous friction
Control theory,Evolutionary algorithm,Computer science,Friction force,Control theory,Evolvability,Evolutionary computation,Control engineering,Robustness (computer science),Adaptive control,Robot
Conference
Volume
ISBN
Citations 
3
0-7803-8463-6
8
PageRank 
References 
Authors
0.70
8
2
Name
Order
Citations
PageRank
Thierry Hoinville1746.50
Patrick Henaff27711.33