Robot Motion Planning by Rules and Strategies Based on Reinforcement Learning Scheme
Editor(s)
Dagli, C. H. and Akay, M. and Chen, C. L. P.|Fernandez, B. R. and Ghosh, J.
Abstract
A planning system for robot arm motion planning is proposed in this paper. The system decides its torque output according to a situation. It learns the mapping from the situation to the output by two kinds of control knowledge: the rule as a basic fragmentary motion and the strategy as a combination of the rules to achieve a given task. Computational simulations are carried out to investigate the behavior of the proposed system.
Recommended Citation
K. Naruse et al., "Robot Motion Planning by Rules and Strategies Based on Reinforcement Learning Scheme," Intelligent Engineering Systems Through Artificial Neural Networks, American Society of Mechanical Engineers (ASME), Jan 1995.
Meeting Name
1995 Artificial Neural Networks in Engineering
Department(s)
Mechanical and Aerospace Engineering
Keywords and Phrases
Computer Simulation; Intelligent Robots; Motion Control; Robot Learning; Robotic Arms; Torque Control
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 1995 American Society of Mechanical Engineers (ASME), All rights reserved.
Publication Date
01 Jan 1995
