A hybrid environment adaptation controller for a snake-like robot with online and autonomous learning ability
Yang GZ(杨贵志); Ma SG(马书根); Li B(李斌); Wang YC(王越超)
2010
会议名称2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010
会议日期December 14-18, 2010
会议地点Tianjin, China
关键词Biomimetics Friction Optimization Robotics Robots
页码1478-1483
中文摘要In this paper, we propose a two-modes autonomous controller for a snake-like robot to adapt to the environments with different friction coefficients. According to the cyclic 3-stages experiential learning theory, the controller integrates an open-form searching method and a closed-form searching method, which correspond to the two modes of the controller respectively. We introduce a mechanism to remember the already derived optimal relationship, thereby gradually approximating the optimal relationship for all environments. The controller can learn online so the approximation can be improved online and the controller will be also more and more accurate. The learning is also autonomous. After enough learning, the approximation will be very accurate so the optimum can be attained just by predicting rather than learning, thereby avoiding unnecessary leaning. Therefore, the controller is efficient. The accuracy and efficiency are validated in the simulations.
收录类别EI
产权排序1
会议主办者IEEE Robotics and Automation Society; Hebei University of Technology; Tianjin University of Technology; Tianjin Association for Science and Technology
会议录2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010
会议录出版者IEEE Computer Society
会议录出版地Piscataway, NJ
语种英语
ISBN号978-1-4244-9317-3
内容类型会议论文
源URL[http://ir.sia.cn/handle/173321/8482]  
专题沈阳自动化研究所_机器人学研究室
推荐引用方式
GB/T 7714
Yang GZ,Ma SG,Li B,et al. A hybrid environment adaptation controller for a snake-like robot with online and autonomous learning ability[C]. 见:2010 IEEE International Conference on Robotics and Biomimetics, ROBIO 2010. Tianjin, China. December 14-18, 2010.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace