{"ID":2892018,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.17085","arxiv_id":"2507.17085","title":"Deformable Cluster Manipulation via Whole-Arm Policy Learning","abstract":"Manipulating clusters of deformable objects presents a substantial challenge with widespread applicability, but requires contact-rich whole-arm interactions. A potential solution must address the limited capacity for realistic model synthesis, high uncertainty in perception, and the lack of efficient spatial abstractions, among others. We propose a novel framework for learning model-free policies integrating two modalities: 3D point clouds and proprioceptive touch indicators, emphasising manipulation with full body contact awareness, going beyond traditional end-effector modes. Our reinforcement learning framework leverages a distributional state representation, aided by kernel mean embeddings, to achieve improved training efficiency and real-time inference. Furthermore, we propose a novel context-agnostic occlusion heuristic to clear deformables from a target region for exposure tasks. We deploy the framework in a power line clearance scenario and observe that the agent generates creative strategies leveraging multiple arm links for de-occlusion. Finally, we perform zero-shot sim-to-real policy transfer, allowing the arm to clear real branches with unknown occlusion patterns, unseen topology, and uncertain dynamics. Website: https://sites.google.com/view/dcmwap/","short_abstract":"Manipulating clusters of deformable objects presents a substantial challenge with widespread applicability, but requires contact-rich whole-arm interactions. A potential solution must address the limited capacity for realistic model synthesis, high uncertainty in perception, and the lack of efficient spatial abstractio...","url_abs":"https://arxiv.org/abs/2507.17085","url_pdf":"https://arxiv.org/pdf/2507.17085v2","authors":"[\"Jayadeep Jacob\",\"Wenzheng Zhang\",\"Houston Warren\",\"Paulo Borges\",\"Tirthankar Bandyopadhyay\",\"Fabio Ramos\"]","published":"2025-07-22T23:58:30Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\"]","project_urls":"[\"https://sites.google.com/view/dcmwap/\"]","has_code":false,"code_links":[{"ID":611942,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2892018,"paper_url":"https://arxiv.org/abs/2507.17085","paper_title":"Deformable Cluster Manipulation via Whole-Arm Policy Learning","repo_url":"https://github.com/google/safevalues","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":611943,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2892018,"paper_url":"https://arxiv.org/abs/2507.17085","paper_title":"Deformable Cluster Manipulation via Whole-Arm Policy Learning","repo_url":"https://github.com/jayadeepj/dcmwap","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}