DocumentCode
393787
Title
Control of hyper-redundant robot using QDSEGA
Author
Ito, Kazuyuki ; Matsuno, Fumitoshi
Author_Institution
Okayama Univ., Japan
Volume
3
fYear
2002
fDate
5-7 Aug. 2002
Firstpage
1499
Abstract
We consider a flexible autonomous system. To realize the system, we employ a hyper-redundant system (a flexible hardware system) and reinforcement learning controller "QDSEGA" (Q-learning with structuring exploration space based on genetic algorithm) which is a flexible software system. In this paper we apply QDSEGA for controlling of the hyper-redundant robot. To demonstrate the effectiveness, a task of acquisition of locomotion patterns is applied to a multi-legged formation and a snake-like formation, from which an effective locomotion is obtained.
Keywords
adaptive systems; flexible manipulators; genetic algorithms; learning (artificial intelligence); legged locomotion; redundant manipulators; Q-learning; adaptive system; genetic algorithm; hyper-redundant robot; multiple-legged locomotion; reinforcement learning; snake-like locomotion; Automatic control; Control systems; Genetic algorithms; Hardware; Learning; Orbital robotics; Robot control; Robotics and automation; Software systems; Space exploration;
fLanguage
English
Publisher
ieee
Conference_Titel
SICE 2002. Proceedings of the 41st SICE Annual Conference
Print_ISBN
0-7803-7631-5
Type
conf
DOI
10.1109/SICE.2002.1196529
Filename
1196529
Link To Document