A NEW NAVIGATION METHOD BASED ON REINFORCEMENT LEARNING AND ROUGH SETS
The ability of autonomous navigation and adaptability to environment are key issues for the application of mobile robots in complex and unknown environments. A new method based on reinforcement learning and rough sets is proposed to accomplish robot navigation tasks in unknown environment With reinforcement learning, robot can achieve autonomous navigation in an unknown environment. Because of the navigation knowledge of robot has the characteristic of incompleteness and inaccuracy, rough sets is an effective mathematical tools to deal with incompleteness. Rough sets can deal with robot initial navigation knowledge and simplify the complexity of navigation, therefore it can speedup the learning process of autonomous mobile robot and improve the obstacle avoidance ability of navigation system. This is the reason why we lead rough sets into reinforcement learning process. Finally, the effectiveness of the presented method is verified in simulation environment. The simulation results show that our method not only provides an effective way for the self-learning of mobile robot but also has good obstacle avoidance ability.
Reinforcement learning Q learning Rough sets Autonomous navigation
HONG-YAN WU SHU-HUA LIU JIE LIU
School of Computer Science, Northeast Normal University, Changchun, 130024, China
国际会议
2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)
昆明
英文
1093-1098
2008-07-12（万方平台首次上网日期，不代表论文的发表时间）