|
JAIST Repository >
b. 情報科学研究科・情報科学系 >
b11. 会議発表論文・発表資料等 >
b11-1. 会議発表論文・発表資料 >
このアイテムの引用には次の識別子を使用してください:
https://hdl.handle.net/10119/20305
|
| タイトル: | Collaborative Manipulation in Clutter Scenes via Dual-Branch Grasping and Stackelberg Pushing |
| 著者: | Ye, Jianze
Li, Chenghao
Zhang, Haolan
Zhou, Peiwen
Chong, Nak Young |
| キーワード: | Robotic manipulation
Deep reinforcement learning
Grasp planning
Stackelberg game
Multi-agent coordination
Pushing and grasping
Cluttered environment |
| 発行日: | 2025-12-29 |
| 出版者: | Institute of Electrical and Electronics Engineers (IEEE) |
| 誌名: | 2025 25th International Conference on Control, Automation and Systems (ICCAS) |
| 開始ページ: | 739 |
| 終了ページ: | 745 |
| DOI: | 10.23919/ICCAS66577.2025.11301175 |
| 抄録: | In cluttered scenes, effective object manipulation often requires both precise grasping and proactive scene rearrangement. We propose a dual-branch reinforcement learning framework that separately predicts grasp position and orientation, trained via supervised pretraining and shaped rewards to ensure stable and sample-efficient learning. To minimize unnecessary pushing, we model the coordination between grasp and push agents as a Stackelberg game, where the push agent acts only when grasp success is unlikely, to enhance downstream grasp success. Experimental results in simulation show that our method improves grasp success and action efficiency, outperforming existing baselines in both success rate and policy economy. |
| Rights: | This is the author's version of the work. Copyright (C) ICROS. 2025 25th International Conference on Control, Automation and Systems (ICCAS 2025), 2025, pp. 739-745. DOI: https://doi.org/10.23919/ICCAS66577.2025.11301175. Personal use of this material is permitted. This material is posted here with permission of Institute of Control, Robotics and Systems (ICROS). |
| URI: | https://hdl.handle.net/10119/20305 |
| 資料タイプ: | author |
| 出現コレクション: | b11-1. 会議発表論文・発表資料 (Conference Papers)
|
このアイテムのファイル:
| ファイル |
記述 |
サイズ | 形式 |
|---|
| I-CHONG-N-0107.pdf | | 1833Kb | Adobe PDF | 見る/開く |
|
当システムに保管されているアイテムはすべて著作権により保護されています。
|
