摘要
结合最小二乘策略迭代(Least-squares policy iteration,LSPI)的算法特性和基于滚动窗口的实时重规划,提出一种新的基于LSPI和滚动窗口的反应式导航学习控制方法。仿真和实验结果表明:该方法对移动机器人在未知环境中的运动控制有效,并且对未知环境具有自适应性。
Combining the advantages of least-squares policy iteration(LSPI)and path planning based on rolling windows, a novel reactive navigation method based on LSPI,and rolling windows was presented.The results show that the proposed method is effective for reactive navigation of mobile robots in unknown environment and the adaptation for unknown environments of the proposed method is verified.
出处
《中南大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
2013年第3期970-977,共8页
Journal of Central South University:Science and Technology
基金
国家自然科学基金资助项目(61075072
90820302)
教育部新世纪优秀人才支持计划(NCET-10-0901)