Metraipolis › archive › dc_8dfe3486fd45
Contact-Guided Exploration for Non-Prehensile Locomanipulation with Multi-Critic RL — arXiv:2608.28140
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28140
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T11:51:33.355Z
- SHA-256 of the archived text
5f704ab53975720adcc4af2fd32f0c3280f9711071fbe8f083346f242a7e5786- Stable URL of this page
https://metraipolis.com/documento/dc_8dfe3486fd45
How to cite
Contact-Guided Exploration for Non-Prehensile Locomanipulation with Multi-Critic RL — arXiv:2608.28140 — arXiv (en), https://arxiv.org/abs/2608.28140 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8dfe3486fd45 (Metraipolis archive dc_8dfe3486fd45, sha256 5f704ab53975720adcc4af2fd32f0c3280f9711071fbe8f083346f242a7e5786)
BibTeX
@misc{dc8dfe3486fd45,
title = {Contact-Guided Exploration for Non-Prehensile Locomanipulation with Multi-Critic RL — arXiv:2608.28140},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28140},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8dfe3486fd45; sha256 5f704ab53975720adcc4af2fd32f0c3280f9711071fbe8f083346f242a7e5786},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28140. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Non-prehensile manipulation offers versatile skills for moving and rearranging heavy or bulky objects, particularly when combined with a mobile manipulation platform. However, both model-based and model-free approaches struggle with the complex hybrid dynamics and the sparsity of the contact in these tasks. To address these challenges, we propose a contact-guided exploration strategy implemented within a Multi-Critic Reinforcement Learning (RL) framework. A dedicated exploration critic is trained with a dense contact-seeking reward that guides the end-effector toward meaningful contact points; its influence is progressively decayed to recover a task-optimal policy. We obtain candidate interaction points from a general-purpose grasping algorithm, enabling the exploration mechanism to generalise across various object geometries. We evaluate the approach on multiple tasks, including box pushing, chair transportation, and a dishwasher opening task. Finally, we validate the chair transportation policy through extensive experiments on a quadrupedal mobile manipulator, demonstrating deployable non-prehensile manipulation in the real world. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.28140 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T11:18:08.711Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).