Skip to main content

Research Repository

Advanced Search

Learning a flexible neural energy function with a unique minimum for globally stable and accurate demonstration learning

Jin, Zhehao; Si, Weiyong; Liu, Andong; Zhang, Wen An; Yu, Li; Yang, Chenguang

Learning a flexible neural energy function with a unique minimum for globally stable and accurate demonstration learning Thumbnail


Authors

Zhehao Jin

Weiyong Si

Andong Liu

Wen An Zhang

Li Yu



Abstract

Learning a stable autonomous dynamic system (ADS) encoding human motion rules has been shown as an effective way for demonstration learning. However, the stability guarantee may sacrifice the demonstration learning accuracy. This article solves the issue by learning a stability certificate, represented by a neural energy function, on the demonstration set. We propose a polarlike space analysis approach to derive parameter constraints to guarantee the unique-minimum property of the neural energy function, which is essential for it to be a cogent stability certificate. Then, the neural energy function is learned to capture the demonstration preferences via constrained optimization algorithms. With the learned neural energy function, a globally asymptotically stable ADS with predefined position constraint is further formulated. We also quantitatively analyze the generalization ability of the learned ADS by utilizing the substantial flexibility of the neural energy function. The effectiveness of the proposed approach is validated on the LASA dataset and two representative robotic experiments.

Citation

Jin, Z., Si, W., Liu, A., Zhang, W. A., Yu, L., & Yang, C. (in press). Learning a flexible neural energy function with a unique minimum for globally stable and accurate demonstration learning. IEEE Transactions on Robotics, https://doi.org/10.1109/tro.2023.3303011

Journal Article Type Article
Acceptance Date Aug 3, 2023
Online Publication Date Aug 22, 2023
Deposit Date Sep 9, 2023
Publicly Available Date Aug 23, 2025
Journal IEEE Transactions on Robotics
Print ISSN 1552-3098
Electronic ISSN 1941-0468
Publisher Institute of Electrical and Electronics Engineers
Peer Reviewed Peer Reviewed
DOI https://doi.org/10.1109/tro.2023.3303011
Keywords Electrical and Electronic Engineering, Computer Science Applications, Control and Systems Engineering
Public URL https://uwe-repository.worktribe.com/output/11086298

Files

Learning a flexible neural energy function with a unique minimum for globally stable and accurate demonstration learning (9.5 Mb)
PDF

Licence
http://www.rioxx.net/licenses/all-rights-reserved

Publisher Licence URL
http://www.rioxx.net/licenses/all-rights-reserved

Copyright Statement
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

This is the author's accepted manuscript. The final published version is available here: https://doi.org/10.1109/tro.2023.3303011




You might also like



Downloadable Citations