Knowledge Commons of Institute of Automation,CAS
Robotic Skill Learning for Precision Assembly With Microscopic Vision and Force Feedback | |
Qin, Fangbo1,2![]() ![]() ![]() ![]() | |
发表期刊 | IEEE-ASME TRANSACTIONS ON MECHATRONICS
![]() |
ISSN | 1083-4435 |
2019-06-01 | |
卷号 | 24期号:3页码:1117-1128 |
通讯作者 | Zhang, Dapeng(dapeng.zhang@ia.ac.cn) |
摘要 | This paper proposes a skill learning approach for precision assembly robot, aiming to realize efficient skill transfer from teacher to robot through several demonstrations. The framework is designed considering that a skill has multiple controllers and procedures. A complex skill is segmented to an action sequence according to the changes of the teacher's selective attention settings on the multiple system variables. The learning of each action is to select a predefined action class and learn its key parameters from the demonstration data. The action sequence forms a finite-state machine. To execute an action, first the action instance is generated from the action class and the learned parameters. Then at each time step, the action state is updated by the Gaussian mixture model based dynamical system and is sent to the lower level controller as the reference signal, so that the action state evolves toward the target with a specified motion pattern. In this paper, the action classes of image feature guided motion and the force constrained motion are proposed based on the multicamera microscopic vision and three-dimensional force feedback, respectively, which can be reused in different skills. The proposed approach was validated by the two experiments of the sleeve-cavity assembly and the coil-cylinder assembly. |
关键词 | Force control learning from demonstration microscopic vision precision assembly robotic skill learning |
DOI | 10.1109/TMECH.2019.2909081 |
关键词[WOS] | TASKS ; MODEL |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program of China[2018YFD0400902] ; Science Challenge Project[TZ2018006-0204-02] ; National Natural Science Foundation of China[61673383] ; National Natural Science Foundation of China[61733004] ; National Natural Science Foundation of China[61873266] ; National Natural Science Foundation of China[61873266] ; National Natural Science Foundation of China[61733004] ; National Natural Science Foundation of China[61673383] ; Science Challenge Project[TZ2018006-0204-02] ; National Key Research and Development Program of China[2018YFD0400902] |
项目资助者 | National Natural Science Foundation of China ; Science Challenge Project ; National Key Research and Development Program of China |
WOS研究方向 | Automation & Control Systems ; Engineering |
WOS类目 | Automation & Control Systems ; Engineering, Manufacturing ; Engineering, Electrical & Electronic ; Engineering, Mechanical |
WOS记录号 | WOS:000472193600022 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 人工智能+制造 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23621 |
专题 | 中国科学院工业视觉智能装备工程实验室_精密感知与控制 |
通讯作者 | Zhang, Dapeng |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China |
第一作者单位 | 精密感知与控制研究中心 |
通讯作者单位 | 精密感知与控制研究中心 |
推荐引用方式 GB/T 7714 | Qin, Fangbo,Xu, De,Zhang, Dapeng,et al. Robotic Skill Learning for Precision Assembly With Microscopic Vision and Force Feedback[J]. IEEE-ASME TRANSACTIONS ON MECHATRONICS,2019,24(3):1117-1128. |
APA | Qin, Fangbo,Xu, De,Zhang, Dapeng,&Li, Ying.(2019).Robotic Skill Learning for Precision Assembly With Microscopic Vision and Force Feedback.IEEE-ASME TRANSACTIONS ON MECHATRONICS,24(3),1117-1128. |
MLA | Qin, Fangbo,et al."Robotic Skill Learning for Precision Assembly With Microscopic Vision and Force Feedback".IEEE-ASME TRANSACTIONS ON MECHATRONICS 24.3(2019):1117-1128. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
robotics skill learn(2296KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 | |
micro-skill-learning(21744KB) | 影音 | 开放获取 | ODC BY | 浏览 下载 |
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。
修改评论