| 欠驱动机器人强化学习算法仿真及结果分析 |
| |
| 引用本文： | 臧希喆,王晓林,吴晓光,刘鑫宇.欠驱动机器人强化学习算法仿真及结果分析[J].江南大学学报(自然科学版),2012,11(2):132-136. |
| |
| 作者姓名： | 臧希喆 王晓林 吴晓光 刘鑫宇 |
| |
| 作者单位： | 哈尔滨工业大学机电工程学院,黑龙江哈尔滨,150001 |
| |
| 基金项目： | 国家自然科学基金，机器人技术与系统国家重点实验室(哈尔滨工业大学)自主课题项目 |
| |
| 摘 要： | 针对纯被动机器人对环境变化敏感,抗干扰能力差等问题,提出了一种基于Sarsa(λ)强化学习的底层PD控制器参数优化算法.在MatODE环境下建立双足有膝关节机器人模型并进行控制器设计.通过与传统控制器仿真结果的对比分析,得出该算法可使模型获得更加稳定的行走步态,同时提高了系统抵抗斜坡扰动的能力,增强机器人的行走鲁棒性.
|
| 关 键 词： | 被动行走 强化学习 双足 Sarsa(λ)学习 |
Simulation for Passive Dynamic Walking Robot Based on Reinforcement Learning Algorithm |
| |
| ZANG Xi-zhe
,
WANG Xiao-lin
,
WU Xiao-guang
,
LIU Xin-yu.Simulation for Passive Dynamic Walking Robot Based on Reinforcement Learning Algorithm[J].Journal of Southern Yangtze University:Natural Science Edition,2012,11(2):132-136. |
| |
| Authors: | ZANG Xi-zhe WANG Xiao-lin WU Xiao-guang LIU Xin-yu |
| |
| Institution: | (School of Mechanical and Electrical Engineering,Harbin Institute of Technology,Harbin 150001,China) |
| |
| Abstract: | For fully passive dynamic walking robot sensitive to the change of environment and poor in anti-interference,a parameters optimized algorithm for underlying PD controller based on the Sarsa(λ) reinforcement learning was proposed here.The robot model with knees and controller were built in the environment of MatODE.Compared with traditional controller we draw the conclusion that this algorithm can make robot get more stable gait,at the same time,improve the ability to overcome the slope disturbance and strengthen the walking robustness. |
| |
| Keywords: | passive dynamic walking reinforcement learning biped Sarsa(λ) learning |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
