Continual Learning for Anthropomorphic Hand Grasping
文献类型：期刊论文
| 作者 | Li, Wanyi1 ; Wei, Wei1,2; Wang, Peng1,3,4
|
| 刊名 | IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
 |
| 出版日期 | 2024-04-01 |
| 卷号 | 16期号:2页码:559-569 |
| 关键词 | Anthropomorphic hands continual learning (CL) grasping |
| ISSN号 | 2379-8920 |
| DOI | 10.1109/TCDS.2023.3284070 |
| 通讯作者 | Wang, Peng(pengwang@ia.ac.cn) |
| 英文摘要 | It is important and challenging to learn to grasp different objects with anthropomorphic robotic hands continually and incrementally. However, most current works do not have this property. They learn grasp planners using large preprepared datasets, do not generalize well to new objects and are difficult to improve continually. Besides, existing continual leaning works rarely target at anthropomorphic hand grasping, and usually deal with short streams of experiences. Because of the intrinsic long stream nature of anthropomorphic hand grasping, it is hard to utilize off-the-shelf continual learning (CL) methods for it. In this article, we propose to introduce continual machine learning into anthropomorphic hand grasping and design the CL framework of anthropomorphic grasping (CLFAG framework). It includes three modules: 1) Data Producer; 2) Grasp Experiences; and 3) CL Algorithm A(CL), thus, makes the CL of anthropomorphic grasping possible. To overcome the catastrophic forgetting problem in long streams of grasping experiences, we propose a CL algorithm based on importance-based regularization and diversity-aware replay within the CLFAG framework. Furthermore, we construct a dataset for CL of anthropomorphic grasping. Experiments on constructed dataset and in simulation demonstrate the effectiveness and superiority of the proposed approach. |
| 资助项目 | National Key Research and Development Program of China |
| WOS研究方向 | Computer Science ; Robotics ; Neurosciences & Neurology |
| 语种 | 英语 |
| WOS记录号 | WOS:001197861000020 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key Research and Development Program of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/58294]  |
| 专题 | 智能机器人系统研究 |
| 通讯作者 | Wang, Peng |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techno, Shanghai 200031, Peoples R China 4.Chinese Acad Sci, Hong Kong Inst Sci & Innovat, Ctr Artificial Intelligence & Robot, Hong Kong, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Wanyi,Wei, Wei,Wang, Peng. Continual Learning for Anthropomorphic Hand Grasping[J]. IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,2024,16(2):559-569. |
| APA | Li, Wanyi,Wei, Wei,&Wang, Peng.(2024).Continual Learning for Anthropomorphic Hand Grasping.IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,16(2),559-569. |
| MLA | Li, Wanyi,et al."Continual Learning for Anthropomorphic Hand Grasping".IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 16.2(2024):559-569. |
入库方式： OAI收割
来源：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。