Title :
Motion simulation of robot arm using reinforcement learning
Author :
Oshiro, Takahito ; Watanabe, Kajiro
Author_Institution :
Hosei Univ., Tokyo
Abstract :
This paper describes the learning of robot arm action by reinforcement learning. We used Q-learning, which is a typical method of reinforcement learning, and which was programmed via MATLAB software. Simulations demonstrated the shortest path of robot arm motion to reach the target location.
Keywords :
control engineering computing; learning (artificial intelligence); manipulators; MATLAB software; Q-learning; motion simulation; reinforcement learning; robot arm; Application software; Computer errors; Error correction; Learning; MATLAB; Manufacturing industries; Medical robotics; Medical simulation; Robot kinematics; Service robots; Q-learning; reinforcement learning; robot arm; simulation;
Conference_Titel :
SICE, 2007 Annual Conference
Conference_Location :
Takamatsu
Print_ISBN :
978-4-907764-27-2
Electronic_ISBN :
978-4-907764-27-2
DOI :
10.1109/SICE.2007.4421144
