Metraipolis › archive › dc_a7bf6bcff875

Cross-Embodiment Causal Transfer from Human Videos to Robot Manipulation — arXiv:2610.21798

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.21798
License (as archived): CC0-1.0
Archived: 2026-10-16T09:28:49.327Z
SHA-256 of the archived text: 2bb2abde5f6e99152f0a86f263b55b021c395d8dce605222312e9e5fd1070b0b
Stable URL of this page: https://metraipolis.com/documento/dc_a7bf6bcff875

How to cite

Cross-Embodiment Causal Transfer from Human Videos to Robot Manipulation — arXiv:2610.21798 — arXiv (en), https://arxiv.org/abs/2610.21798 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a7bf6bcff875 (Metraipolis archive dc_a7bf6bcff875, sha256 2bb2abde5f6e99152f0a86f263b55b021c395d8dce605222312e9e5fd1070b0b)

BibTeX

@misc{dca7bf6bcff875,
  title = {Cross-Embodiment Causal Transfer from Human Videos to Robot Manipulation — arXiv:2610.21798},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21798},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a7bf6bcff875; sha256 2bb2abde5f6e99152f0a86f263b55b021c395d8dce605222312e9e5fd1070b0b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21798. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scaling robot manipulation models requires large amounts of interaction data, yet collecting diverse real-robot experience remains costly. Human manipulation videos, in contrast, provide abundant and diverse task experience that could potentially benefit robot learning. However, differences in morphology, action spaces, and control mechanisms make human motions unsuitable as direct supervision for robot actions, raising a scientific question: what knowledge in human videos should be transferred across embodiments to robot manipulation? To address this question, we analyze subtask transfer through the lens of causal beams, focusing on which contextual conditions and interaction dependencies should be retained to support local task effects. Based on this perspective, we propose Causal-Beam-Guided Subtask Transfer (CBST). CBST learns manipulation-related representations from human videos and grounds them in task-level semantic variables using robot demonstrations. Within a predefined manipulation model, causal-beam constraints guide contextual information selection by requiring retained assignments to sustain local mechanism outputs while preserving nontrivial responsiveness to retained inputs. The selected semantic information conditions a world-action model, allowing the robot to generate actions from its own observations without requiring human-robot motion correspondence. Experiments on robot manipulation benchmarks show improvements in task success over the corresponding world-action model baselines.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.21798 — 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 2026-10-16T08:44:18.002Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).