Learning Task-Oriented Dexterous Grasping from Human Knowledge
文献类型：会议论文
| 作者 | Li, Hui4; Zhang YL(张吟龙)1 ; Li, Yanan3; He, Hongsheng4
|
| 出版日期 | 2021 |
| 会议日期 | May 30 - June 5, 2021 |
| 会议地点 | Xi'an, China |
| 关键词 | Dexterous Grasping Task-Oriented Grasping Grasp Topology Reinforcement Learning |
| 页码 | 6192-6198 |
| 英文摘要 | Industrial automation requires robot dexterity to automate many processes such as product assembling, packaging, and material handling. The existing robotic systems lack the capability to determining proper grasp strategies in the context of object affordances and task designations. In this paper, a framework of task-oriented dexterous grasping is proposed to learn grasp knowledge from human experience and to deploy the grasp strategies while adapting to grasp context. Grasp topology is defined and grasp strategies are learned from an established dataset for task-oriented dexterous manipulation. To adapt to various grasp context, a reinforcement-learning based grasping policy was implemented to deploy different task-oriented strategies. The performance of the system was evaluated in a simulated grasping environment by using an AR10 anthropomorphic hand installed in a Sawyer robotic arm. The proposed framework achieved a hit rate of 100% for grasp strategies and an overall top-3 match rate of 95.6%. The success rate of grasping was 85.6% during 2700 grasping experiments for manipulation tasks given in natural-language instructions. |
| 源文献作者 | Baidu ; Biomimetic Intelligence and Robotics ; dji ; et al. ; Mech Mind Robotics Technologies ; Toyota Research Institute |
| 产权排序 | 2 |
| 会议录 | 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
 |
| 会议录出版者 | IEEE |
| 会议录出版地 | New York |
| 语种 | 英语 |
| ISSN号 | 1050-4729 |
| ISBN号 | 978-1-7281-9077-8 |
| WOS记录号 | WOS:000765738804090 |
| 源URL | [http://ir.sia.cn/handle/173321/30559]  |
| 专题 | 沈阳自动化研究所_工业控制网络与系统研究室 |
| 通讯作者 | He, Hongsheng |
| 作者单位 | 1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 2.The Department of Engineering and Design, University of Sussex, United Kingdom 3.110016, China 4.The Department of Electrical Engineering and Computer Science, Wichita State University, United States |
| 推荐引用方式 GB/T 7714 | Li, Hui,Zhang YL,Li, Yanan,et al. Learning Task-Oriented Dexterous Grasping from Human Knowledge[C]. 见:. Xi'an, China. May 30 - June 5, 2021. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
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。