Metraipolis › archive › dc_45f697dfe89c

MimicX: Policy-in-the-Loop Supervision Refinement for Video-Driven Humanoid Motion Tracking — arXiv:2610.09055

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.09055
License (as archived): CC0-1.0
Archived: 2026-10-08T11:10:33.863Z
SHA-256 of the archived text: 3b67a2d7b642bee0398aa90be5a51e00599f26805ac4f1fbd165357c5b5c8f5e
Stable URL of this page: https://metraipolis.com/documento/dc_45f697dfe89c

How to cite

MimicX: Policy-in-the-Loop Supervision Refinement for Video-Driven Humanoid Motion Tracking — arXiv:2610.09055 — arXiv (en), https://arxiv.org/abs/2610.09055 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45f697dfe89c (Metraipolis archive dc_45f697dfe89c, sha256 3b67a2d7b642bee0398aa90be5a51e00599f26805ac4f1fbd165357c5b5c8f5e)

BibTeX

@misc{dc45f697dfe89c,
  title = {MimicX: Policy-in-the-Loop Supervision Refinement for Video-Driven Humanoid Motion Tracking — arXiv:2610.09055},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09055},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45f697dfe89c; sha256 3b67a2d7b642bee0398aa90be5a51e00599f26805ac4f1fbd165357c5b5c8f5e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09055. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Human videos provide rich motion targets for humanoid learning, yet visually plausible references can still produce persistent failures under physics-based execution. These failures reveal where training supervision should change. We present MimicX, a policy-in-the-loop framework that uses execution feedback to refine video-driven humanoid motion tracking. Starting from reconstructed and retargeted motion, MimicX localizes difficult transitions and affected body regions, then jointly adapts tracking objectives and the reset curriculum for policy continuation. Repeated rollout verification selects execution-priority improvements subject to tracking guards. Across four core video tasks, MimicX consistently improves tracking accuracy and Robust Execution Horizon relative to the Fixed Reference baseline. Task-averaged results show a 25.7% reduction in body-tracking error and a 255.6% increase in execution horizon. Additional video, motion-reference, and collision-scene studies evaluate the method beyond the core tasks, while MimicX-HLoop accelerates feedback through heterogeneous execution. Overall, MimicX turns policy failure into actionable supervision for deciding what to refine and which refinement to retain.

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/2610.09055 — 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 2026-10-08T10:14:06.044Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).