Toward Generalizable Robotic Dual-Arm Flipping Manipulation
文献类型:期刊论文
作者 | Huang, Haifeng1,2; Zeng, Chao3; Cheng, Long4,5; Yang, Chenguang1,2 |
刊名 | IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS |
出版日期 | 2024-05-01 |
卷号 | 71期号:5页码:4954-4962 |
ISSN号 | 0278-0046 |
关键词 | Dynamic movement primitive (DMP) flipping task learning from demonstration (LfD) skill generalization |
DOI | 10.1109/TIE.2023.3288189 |
通讯作者 | Yang, Chenguang(cyang@ieee.org) |
英文摘要 | Robotic dual-arm manipulation often requires close cooperation between the arms. Dual-arm manipulation tasks are always difficult to program in advance, and then, executed autonomously by the robots. Learning from demonstration is an efficient programming method for robots that can transfer human skills to robots. However, conventional skill learning methods, e.g., dynamic movement primitives (DMPs) can only characterize the motion information of each dimension independently, and cannot take into account the relationship between multidimensional information. Participially, flipping manipulation is quite common in industry production lines, but it has not been well addressed yet to provide a robotics solution to this task. In this article, we propose an improved DMP model, called the object-level constrained DMP, which effectively preserves the association between multidimensional information. Similarly, we also propose an orientation generalization method for the flipping task. In addition, we show how to demonstrate the flipping task via a teleoperation system. Finally, experiments are performed on a Baxter robot to verify the effectiveness of the methods. |
资助项目 | National Nature Science Foundation of China (NSFC)[U20A20200] ; National Nature Science Foundation of China (NSFC)[62025307] ; National Nature Science Foundation of China (NSFC)[62311530097] ; Guangdong Basic and Applied Basic Research Foundation[2020B1515120054] ; Industrial Key Technologies R&D Program of Foshan[2020001006308] ; Industrial Key Technologies R&D Program of Foshan[2020001006496] ; [92148204] |
WOS研究方向 | Automation & Control Systems ; Engineering ; Instruments & Instrumentation |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:001127180600009 |
资助机构 | National Nature Science Foundation of China (NSFC) ; Guangdong Basic and Applied Basic Research Foundation ; Industrial Key Technologies R&D Program of Foshan |
源URL | [http://ir.ia.ac.cn/handle/173211/54789] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Yang, Chenguang |
作者单位 | 1.South China Univ Technol, Coll Automat Sci & Engn, Minist Educ, Key Lab Autonomous Syst & Networked Control, Guangzhou 510640, Peoples R China 2.South China Univ Technol, Coll Automat Sci & Engn, GuangDong Engn Technol Res Ctr Control Intelligen, Guangzhou 510640, Peoples R China 3.Univ Hamburg, Dept Informat, Tech Aspects Multimodal Syst TAMS Grp, D-22527 Hamburg, Germany 4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Huang, Haifeng,Zeng, Chao,Cheng, Long,et al. Toward Generalizable Robotic Dual-Arm Flipping Manipulation[J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS,2024,71(5):4954-4962. |
APA | Huang, Haifeng,Zeng, Chao,Cheng, Long,&Yang, Chenguang.(2024).Toward Generalizable Robotic Dual-Arm Flipping Manipulation.IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS,71(5),4954-4962. |
MLA | Huang, Haifeng,et al."Toward Generalizable Robotic Dual-Arm Flipping Manipulation".IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 71.5(2024):4954-4962. |
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。