SIA OpenIR  > 空间自动化技术研究室
Long Time Sequential Task Learning From Unstructured Demonstration
Zhang HW(张会文)1,2,3; Liu YW(刘玉旺)1,2; Zhou WJ(周维佳)1,2
Department空间自动化技术研究室
Source PublicationIEEE ACCESS
ISSN2169-3536
2019
Volume7Pages:96240-96252
Indexed BySCI ; EI
EI Accession number20193207296817
WOS IDWOS:000478961900067
Contribution Rank1
Funding OrganizationNational Natural Science Foundation of China
KeywordBayesian segmentation imitation learning KL divergence movement primitives mixture model
AbstractLearning from demonstration (LfD), which provides a natural way to transfer skills to robots, has been extensively researched for decades, and an army of methods and applications have been developed and investigated for learning an individual or low-level task. Nevertheless, learning long time sequential tasks is still very difficult as it involves task segmentation and sub-task clustering under an extremely large demonstration variance. Besides, the representation problem should be considered when doing segmentation. This paper presents a new unified framework to solve the problems of segmentation, clustering, and representation in a sequential task. The segmentation algorithm segments unstructured demonstrations into movement primitives (MPs). Then, the MPs are automatically clustered and labeled so that they can be reused in other tasks. Finally, the representation model is leveraged to encode and generalize the learned MPs in new contexts. To achieve the first goal, a change-point detection algorithm based on Bayesian inference is leveraged. It can segment unstructured demonstrations online with minimum prior knowledge requirements. By following the Gaussian distributed assumption in the segmentation model, MPs are encoded by Gaussians or Gaussian mixture models. Thus, the clustering of MPs is formulated as a clustering over cluster (CoC) problem. The Kullback-Leibler divergence is used to measure similarities between MPs, through which the MPs with smaller distance are clustered into the same group. To replay and generalize the task in novel contexts, we use task-parameterized regression models such as the Gaussian mixture regression. We implemented our framework on a sequential open-and-place task. The experiments demonstrate that the segmentation accuracy of our framework can reach 94.3% and the recognition accuracy can reach 97.1%. Comparisons with the state-of-the-art algorithm also indicate that our framework is superior or comparable to their results.
Language英语
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS KeywordONLINE SEGMENTATION ; MOVEMENT ; PRIMITIVES ; IMITATION ; MOTION ; SKILLS
WOS Research AreaComputer Science ; Engineering ; Telecommunications
Funding ProjectNational Natural Science Foundation of China[61821005] ; National Natural Science Foundation of China[51605474]
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/25461
Collection空间自动化技术研究室
Corresponding AuthorZhang HW(张会文)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
3.Shenyang Institute of Automation, University of Chinese Academy of Sciences, Beijing 100049, China
Recommended Citation
GB/T 7714
Zhang HW,Liu YW,Zhou WJ. Long Time Sequential Task Learning From Unstructured Demonstration[J]. IEEE ACCESS,2019,7:96240-96252.
APA Zhang HW,Liu YW,&Zhou WJ.(2019).Long Time Sequential Task Learning From Unstructured Demonstration.IEEE ACCESS,7,96240-96252.
MLA Zhang HW,et al."Long Time Sequential Task Learning From Unstructured Demonstration".IEEE ACCESS 7(2019):96240-96252.
Files in This Item: Download All
File Name/Size DocType Version Access License
Long Time Sequential(24866KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang HW(张会文)]'s Articles
[Liu YW(刘玉旺)]'s Articles
[Zhou WJ(周维佳)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang HW(张会文)]'s Articles
[Liu YW(刘玉旺)]'s Articles
[Zhou WJ(周维佳)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang HW(张会文)]'s Articles
[Liu YW(刘玉旺)]'s Articles
[Zhou WJ(周维佳)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Long Time Sequential Task Learning From Unstructured Demonstration.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.