Metraipolis › archive › dc_178f987dc875

Collective Learning for Unified Robotic Manipulation via Predictive Dynamics Adaptation — arXiv:2610.19141

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19141
License (as archived)
CC0-1.0
Archived
2026-10-15T21:57:43.057Z
SHA-256 of the archived text
be0bf5213e78342916a6e7cd659542c05a180af05cba7b68bf3103907ef4813e
Stable URL of this page
https://metraipolis.com/documento/dc_178f987dc875

How to cite

Collective Learning for Unified Robotic Manipulation via Predictive Dynamics Adaptation — arXiv:2610.19141 — arXiv (en), https://arxiv.org/abs/2610.19141 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_178f987dc875 (Metraipolis archive dc_178f987dc875, sha256 be0bf5213e78342916a6e7cd659542c05a180af05cba7b68bf3103907ef4813e)
BibTeX
@misc{dc178f987dc875,
  title = {Collective Learning for Unified Robotic Manipulation via Predictive Dynamics Adaptation — arXiv:2610.19141},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19141},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_178f987dc875; sha256 be0bf5213e78342916a6e7cd659542c05a180af05cba7b68bf3103907ef4813e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19141. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning a collective policy for state-based Cartesian manipulation across diverse robotic embodiments presents a fundamental challenge due to embodiment-dependent transition dynamics. Collective learning aggregates multi-robot experience to discover shared task structure, yet naive aggregation can average incompatible action modes when different embodiments realize the same Cartesian command through different transition behavior. This leads to strategy ambiguity and performance collapse on dynamically outlying embodiments. To address this, we propose PACE, a two-stage collective learning framework that separates shared task-space intent from embodiment-dependent transition dynamics. The first stage employs a representation layer pre-trained on offline trajectories to extract task-level context from collective data. The second stage introduces a decision layer equipped with a predictive dynamics adapter. By forcing the latent state to predict future transitions, this adapter acts as a latent regularizer that grounds the policy in the transition behavior of the executing robot while preserving real-time inference without online planning. Evaluations across simulated embodiments demonstrate that our method prevents performance collapse on distinct robots. It achieves over 93\% overall success and 89\% on dynamically out-of-distribution zero-shot simulated robots, outperforming the Transformer behavior cloning (82\%) and diffusion policy baselines (66\%). Physical KUKA deployment further validates the feasibility of the full state-based pipeline under zero-shot sim-to-real transfer.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.19141 — 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 2026-10-15T21:38:44.427Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).