Metraipolis › archive › dc_58bdeef0bd0a
Policy-Induced Hand Priors in Humanoid Dual-Arm Manipulation: Diagnosing and Mitigating Initial-Pose Dependence — arXiv:2608.11769
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11769
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:52:21.555Z
- SHA-256 of the archived text
f47a7ec7f6ef7a125c0ed4124486699f21def9cc7c508ecc0bd2c8aea5b8e30d- Stable URL of this page
https://metraipolis.com/documento/dc_58bdeef0bd0a
How to cite
Policy-Induced Hand Priors in Humanoid Dual-Arm Manipulation: Diagnosing and Mitigating Initial-Pose Dependence — arXiv:2608.11769 — arXiv (en), https://arxiv.org/abs/2608.11769 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_58bdeef0bd0a (Metraipolis archive dc_58bdeef0bd0a, sha256 f47a7ec7f6ef7a125c0ed4124486699f21def9cc7c508ecc0bd2c8aea5b8e30d)
BibTeX
@misc{dc58bdeef0bd0a,
title = {Policy-Induced Hand Priors in Humanoid Dual-Arm Manipulation: Diagnosing and Mitigating Initial-Pose Dependence — arXiv:2608.11769},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11769},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_58bdeef0bd0a; sha256 f47a7ec7f6ef7a125c0ed4124486699f21def9cc7c508ecc0bd2c8aea5b8e30d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11769. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-language-action (VLA) policies are expected to operate robustly across variations in the robot's initial configuration, yet aggregate task success can conceal pose-specific failures and inappropriate hand selection. This work investigates initial-pose dependence in VLA-based humanoid dual-arm manipulation. We characterize the initial-condition-dependent early hand preference as a policy-induced hand prior and quantify it using HandPriorScore, residual hand bias, and target responsiveness. Evaluations across multiple policies and 17 initial configurations reveal strong initial-pose--policy interactions: the same pose produces substantially different success rates across policies, while a single policy exhibits large performance variation across poses. Specific initial arm configurations can suppress or induce an asymmetric hand preference, with the resulting effect varying in direction and strength across policies. Wrist-camera observations also influence hand selection and task performance. Expanding initial-pose coverage in the training dataset substantially improves robustness, while targeted augmentation around a low-performing configuration increases its success rate. Comparisons across training configurations show that sufficient exposure to the target simulation task is beneficial, whereas the effect of real or auxiliary data depends on pose coverage, simulation ratio, and observation availability. These findings characterize a pose-conditioned hand prior, identify a localized initial arm configuration as a causal handle on hand-selection behavior, and demonstrate how data coverage and training composition affect initial-pose robustness. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-13 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.11769 — 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 2026-10-19T05:47:37.806Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).