| アイテムタイプ |
共通アイテムタイプ(1) |
| 公開日 |
2025-02-06 |
| タイトル |
|
|
タイトル |
Diff-Control: A Stateful Diffusion-based Policy for Imitation Learning |
|
言語 |
en |
| 著者 |
Liu, Xiao
Zhou, Yifan
Weigend, Fabian Clemens
Sonawani, Shubham
池本, 周平
Amor, Heni Ben
|
| 著作権関連情報 |
|
|
権利情報 |
Copyright (c) 2024 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. |
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
While imitation learning provides a simple and effective framework for policy learning, acquiring consistent action during robot execution remains a challenging task. Existing approaches primarily focus on either modifying the action representation at data curation stage or altering the model itself, both of which do not fully address the scalability of consistent action generation. To overcome this limitation, we introduce the Diff-Control policy, which utilizes a diffusion-based model to learn action representation from a state-space modeling viewpoint. We demonstrate that diffusion-based policies can acquire statefulness through a Bayesian formulation facilitated by ControlNet, leading to improved robustness and success rates. Our experimental results demonstrate the significance of incorporating action statefulness in policy learning, where Diff-Control shows improved performance across various tasks. Specifically, Diff-Control achieves an average success rate of 72% and 84% on stateful and dynamic tasks, respectively. Notably, Diff-Control also shows consistent performance in the presence of perturbations, outperforming other state-of-the-art methods that falter under similar conditions. Project page: https://diff-control.github.io/ |
|
言語 |
en |
| 備考 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2024, 14 - 18 October 2024, Abu Dhabi ,UAE |
|
言語 |
en |
| 書誌情報 |
en : 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
発行日 2024-12-25
|
| 出版社 |
|
|
出版者 |
IEEE |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Training |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Torque |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Imitation learning |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Scalability |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Perturbation methods |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Process control |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Sensor systems and applications |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Robustness |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Intelligent sensors |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Intelligent robots |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_6501 |
|
資源タイプ |
journal article |
| 出版タイプ |
|
|
出版タイプ |
AM |
|
出版タイプResource |
http://purl.org/coar/version/c_ab4af688f83e57aa |
| DOI |
|
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.1109/IROS58592.2024.10801557 |
| ISBN |
|
|
|
識別子タイプ |
ISBN |
|
|
関連識別子 |
979-8-3503-7770-5 |
| ISSN |
|
|
収録物識別子タイプ |
EISSN |
|
収録物識別子 |
2153-0866 |
| 会議記述 |
|
|
|
会議名 |
IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2024 |
|
|
言語 |
en |
|
|
開始年 |
2024 |
|
|
開始月 |
10 |
|
|
開始日 |
14 |
|
|
終了年 |
2024 |
|
|
終了月 |
10 |
|
|
終了日 |
18 |
|
開催国 |
ARE |
| 研究者情報 |
|
|
URL |
https://hyokadb02.jimu.kyutech.ac.jp/html/100001226_ja.html |
| 論文ID（連携） |
|
|
値 |
10445310 |
| 連携ID |
|
|
値 |
12865 |
10445310.pdf (7.7 MB)
