JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: https://hdl.handle.net/10119/20305

Title: Collaborative Manipulation in Clutter Scenes via Dual-Branch Grasping and Stackelberg Pushing
Authors: Ye, Jianze
Li, Chenghao
Zhang, Haolan
Zhou, Peiwen
Chong, Nak Young
Keywords: Robotic manipulation
Deep reinforcement learning
Grasp planning
Stackelberg game
Multi-agent coordination
Pushing and grasping
Cluttered environment
Issue Date: 2025-12-29
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Magazine name: 2025 25th International Conference on Control, Automation and Systems (ICCAS)
Start page: 739
End page: 745
DOI: 10.23919/ICCAS66577.2025.11301175
Abstract: 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
Material Type: author
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
I-CHONG-N-0107.pdf1833KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, JAIST (ir-sys[at]ml.jaist.ac.jp)