An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning Applications
Recently, motion generation by machine learning has been actively researched to automate various tasks. Imitation learning is one such method that learns motions from data collected in advance. However, executing long-term tasks remains challenging. Therefore, a novel framework for imitation learnin...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9722836/ |
| _version_ | 1818744913456529408 |
|---|---|
| author | Kazuki Hayashi Sho Sakaino Toshiaki Tsuji |
| author_facet | Kazuki Hayashi Sho Sakaino Toshiaki Tsuji |
| author_sort | Kazuki Hayashi |
| collection | DOAJ |
| description | Recently, motion generation by machine learning has been actively researched to automate various tasks. Imitation learning is one such method that learns motions from data collected in advance. However, executing long-term tasks remains challenging. Therefore, a novel framework for imitation learning is proposed to solve this problem. The proposed framework comprises upper and lower layers, where the upper layer model, whose timescale is long, and lower layer model, whose timescale is short, can be independently trained. In this model, the upper layer learns long-term task planning, and the lower layer learns motion primitives. The proposed method was experimentally compared to hierarchical RNN-based methods to validate its effectiveness. Consequently, the proposed method showed a success rate equal to or greater than that of conventional methods. In addition, the proposed method required less than 1/20 of the training time compared to conventional methods. Moreover, it succeeded in executing unlearned tasks by reusing the trained lower layer. |
| first_indexed | 2024-12-18T02:51:52Z |
| format | Article |
| id | doaj.art-477b69af12714acc8b3e1896a22f7016 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T02:51:52Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-477b69af12714acc8b3e1896a22f70162022-12-21T21:23:26ZengIEEEIEEE Access2169-35362022-01-0110327663278110.1109/ACCESS.2022.31552559722836An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning ApplicationsKazuki Hayashi0https://orcid.org/0000-0002-8367-8962Sho Sakaino1https://orcid.org/0000-0002-5182-5649Toshiaki Tsuji2https://orcid.org/0000-0002-4532-4514Faculty of Engineering, Information and Systems, University of Tsukuba, Tsukuba, JapanDepartment of Intelligent Interaction Technologies, University of Tsukuba, Tsukuba, JapanDepartment of Electrical and Electronic Systems, Saitama University, Saitama, JapanRecently, motion generation by machine learning has been actively researched to automate various tasks. Imitation learning is one such method that learns motions from data collected in advance. However, executing long-term tasks remains challenging. Therefore, a novel framework for imitation learning is proposed to solve this problem. The proposed framework comprises upper and lower layers, where the upper layer model, whose timescale is long, and lower layer model, whose timescale is short, can be independently trained. In this model, the upper layer learns long-term task planning, and the lower layer learns motion primitives. The proposed method was experimentally compared to hierarchical RNN-based methods to validate its effectiveness. Consequently, the proposed method showed a success rate equal to or greater than that of conventional methods. In addition, the proposed method required less than 1/20 of the training time compared to conventional methods. Moreover, it succeeded in executing unlearned tasks by reusing the trained lower layer.https://ieeexplore.ieee.org/document/9722836/Bilateral controlimitation learningmotion planningrobot learning |
| spellingShingle | Kazuki Hayashi Sho Sakaino Toshiaki Tsuji An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning Applications IEEE Access Bilateral control imitation learning motion planning robot learning |
| title | An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning Applications |
| title_full | An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning Applications |
| title_fullStr | An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning Applications |
| title_full_unstemmed | An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning Applications |
| title_short | An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning Applications |
| title_sort | independently learnable hierarchical model for bilateral control based imitation learning applications |
| topic | Bilateral control imitation learning motion planning robot learning |
| url | https://ieeexplore.ieee.org/document/9722836/ |
| work_keys_str_mv | AT kazukihayashi anindependentlylearnablehierarchicalmodelforbilateralcontrolbasedimitationlearningapplications AT shosakaino anindependentlylearnablehierarchicalmodelforbilateralcontrolbasedimitationlearningapplications AT toshiakitsuji anindependentlylearnablehierarchicalmodelforbilateralcontrolbasedimitationlearningapplications AT kazukihayashi independentlylearnablehierarchicalmodelforbilateralcontrolbasedimitationlearningapplications AT shosakaino independentlylearnablehierarchicalmodelforbilateralcontrolbasedimitationlearningapplications AT toshiakitsuji independentlylearnablehierarchicalmodelforbilateralcontrolbasedimitationlearningapplications |