DocumentCode :
3180086
Title :
Creation and Compression of Global Control Policy for Swinging up Control of the Acrobot
Author :
Ueda, Ryuichi ; Arai, Tamio ; Matsushita, Kojiro
Author_Institution :
Dept. of Precision Eng., Tokyo Univ.
fYear :
2006
fDate :
9-15 Oct. 2006
Firstpage :
2557
Lastpage :
2562
Abstract :
The Acrobot is an underactuated robot and provides challenging control problems due to its nonlinearity. We try creating global control policies depending on the limitation of memory that is available for recording them. A swinging up task of the Acrobot is solved by dynamic programming (DP) without heuristics. The result of DP is compressed to an arbitrary size of control policy by our vector quantization (VQ) method. A chaotic but performable control policy can be obtained in the global state space of the Acrobot by DP. Moreover, we can verify that our VQ algorithm can reduce the dimension of the control policy from four to two in the process of compression
Keywords :
control nonlinearities; dynamic programming; motion control; robot dynamics; vector quantisation; Acrobot swinging up control; dynamic programming; global control policy; underactuated robot; vector quantization method; Actuators; Control systems; Dynamic programming; Helium; Intelligent robots; Nonlinear control systems; Optimal control; Precision engineering; Size control; Vector quantization; dynamic programming; optimal control; state-action map; the Acrobot; vector quantization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Robots and Systems, 2006 IEEE/RSJ International Conference on
Conference_Location :
Beijing
Print_ISBN :
1-4244-0258-1
Electronic_ISBN :
1-4244-0259-X
Type :
conf
DOI :
10.1109/IROS.2006.281706
Filename :
4058774
Link To Document :
بازگشت