DocumentCode :
2608698
Title :
Direct adaptive control of a flexible robot using reinforcement learning
Author :
Subudhi, Bidyadhar ; Pradhan, Santanu Kumar
fYear :
2010
fDate :
27-29 Dec. 2010
Firstpage :
129
Lastpage :
136
Abstract :
This paper proposes a new adaptive control using the concept of reinforcement learning to address adaptivity for varied payload conditions for a two-link flexible manipulator (TLFM). The application of reinforcement learning has been implemented using a method called adaptive dynamic programming. Decentralized controllers for the decoupled system have been also designed using LQR technique. Then the reinforcement learning is used to tune the gains of the optimal control to adapt in terms of different payload to the manipulator end effecter. Simulation results show that proposed controller provides better end point tracking then LQR fixed gain controller.
Keywords :
adaptive control; decentralised control; dynamic programming; end effectors; flexible manipulators; learning (artificial intelligence); linear quadratic control; LQR technique; adaptive dynamic programming; decentralized controller; fixed gain controller; manipulator end effecter; optimal control; reinforcement learning; two link flexible manipulator; Adaptive control; Industrial electronics; Learning; Service robots; Actor Critic based Reinforcement Learning; Adaptive dynamic programming Variable Tip Mass; Flexible-Link Manipulator;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Industrial Electronics, Control & Robotics (IECR), 2010 International Conference on
Conference_Location :
Orissa
Print_ISBN :
978-1-4244-8544-4
Type :
conf
DOI :
10.1109/IECR.2010.5720144
Filename :
5720144
Link To Document :
بازگشت