| 采用核增强学习方法的多机器人编队控制 |
| |
| 引用本文： | 吴军,徐昕,连传强,黄岩.采用核增强学习方法的多机器人编队控制[J].机器人,2011,33(3):379-384. |
| |
| 作者姓名： | 吴军 徐昕 连传强 黄岩 |
| |
| 作者单位： | 国防科技大学机电工程与自动化学院自动化研究所,湖南,长沙,410073 |
| |
| 基金项目： | 国家自然科学基金资助项目(60774076,60703072,90820302) |
| |
| 摘 要： | 提出一种分布式的核增强学习方法来优化多机器人编队控制性能.首先,通过添加虚拟领队机器人,结合分布式的跟随控制策略,实现基本的多机器人编队控制:其次,提出结合最小二乘策略迭代和策略评测的核增强学习方法,即利用基于核的最小二乘策略迭代算法离线获取初始的编队优化控制策略,再利用基于核的最小二乘策略计测算法实现编队控制策略的在...
|
| 关 键 词： | 多机器人 编队控制 增强学习 策略评测 策略迭代 核方法 |
Multi-robot Formation Control with Kernel-based Reinforcement Learning |
| |
| Wu Jun,XU Xin,LIAN Chuanqiang,HUANG Yan.Multi-robot Formation Control with Kernel-based Reinforcement Learning[J].Robot,2011,33(3):379-384. |
| |
| Authors: | Wu Jun XU Xin LIAN Chuanqiang HUANG Yan |
| |
| Affiliation: | WU Jun,XU Xin,LIAN Chuanqiang,HUANG Yan (Institute of Automation,College of Mechtronics and Automation,National University of Defense Technology,Changsha 410073,China) |
| |
| Abstract: | A distributed kernel-based reinforcement learning method is proposed to optimize the multi-robot formation control.Firstly,the basic formation control is realized based on a distributed leader-follower strategy by adding a virtualleader -robot.Secondly,a kernel-based reinforcement learning method,which combines the least squares policy iteration with the least squares policy evaluation,is proposed.The kernel-based least squares policy iteration method is used to obtain an initial formation optimal control p... |
| |
| Keywords: | multi-robot formation control reinforcement learning policy evaluation policy iteration kernel method |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
