Fuzzy Q-learning obstacle avoidance algorithm of humanoid robot in unknown environment

This paper proposes a fuzzy Q-learning (FQL) algorithm to solve the problem of the robot obstacle avoidance in unknown environment. FastSLAM algorithm is used to localize the position of the robot. Traditional Q-learning algorithm, optimized Q-learning algorithm, FQL algorithm are compared. The simu...

Full description

Saved in:
Bibliographic Details
Published in2018 37th Chinese Control Conference (CCC) pp. 5186 - 5190
Main Authors Wen, Shuhuan, Chen, Jianhua, Li, Zhen, Rad, Ahmad B., Mohammed Othman, Kamal
Format Conference Proceeding
LanguageEnglish
Published Technical Committee on Control Theory, Chinese Association of Automation 01.07.2018
Subjects
Collision avoidance
Convergence
FASTSLAM
fuzzy logic control
Fuzzy sets
Humanoid robots
Mobile robots
obstacle avoidance
Path planning
Q-learning
Online AccessGet full text

Cover

More Information
Summary:This paper proposes a fuzzy Q-learning (FQL) algorithm to solve the problem of the robot obstacle avoidance in unknown environment. FastSLAM algorithm is used to localize the position of the robot. Traditional Q-learning algorithm, optimized Q-learning algorithm, FQL algorithm are compared. The simulation results show that FQL algorithm has a faster learning speed than other two algorithms and the results demonstrate that the fuzzy Q-learning obstacle avoidance algorithm is effective.
ISSN:2161-2927
DOI:10.23919/ChiCC.2018.8483654