Robot path planning by artificial potential field optimization based on reinforcement learning with fuzzy state

Author

Zhuang, Xiaodong ; Meng, Qingchun ; Yin, Bo ; Wang, Hanping

Author_Institution

Dept. of Electron. & Eng., Ocean Univ. of Qingdao, China

Volume

2

fYear

2002

fDate

2002

Firstpage

1166

Abstract

Temporal difference (TD) learning with fuzzy state is applied to robot navigation in a multi-obstacle environment. An interpretation of the state evaluation function is given by regarding the state evaluation as a discrete artificial potential field (APF). Global optimal path planning is implemented with the APF obtained by TD learning. The APF obtained is globally optimal and avoids the local minimum areas, which always appear in traditional APF methods. Fuzzy state is introduced to improve the learning efficiency. A computer evaluation experiment shows the method´s effectiveness and efficiency.

Keywords

Markov processes; decision theory; digital simulation; fuzzy set theory; learning (artificial intelligence); mobile robots; optimal control; path planning; probability; artificial potential field optimization; discrete artificial potential field; fuzzy state; global optimal path planning; learning efficiency; multi-obstacle environment; reinforcement learning; robot navigation; robot path planning; state evaluation function; temporal difference learning; Automatic control; Control systems; Fuzzy control; Intelligent control; Learning systems; Mobile robots; Navigation; Optimal control; Path planning; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2002. Proceedings of the 4th World Congress on

Print_ISBN

0-7803-7268-9

Type

conf

DOI

10.1109/WCICA.2002.1020763

Filename

1020763