Metraipolis › archive › dc_62ef8bb82a24

DexTaG: Tactile-as-Guidance in Reinforcement Learning for Dexterous Manipulation — arXiv:2609.33882

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33882
License (as archived)
CC0-1.0
Archived
2026-10-08T00:17:14.126Z
SHA-256 of the archived text
3b380719bcc2ea8355929539f5068e01e7938b0d66abeface3d4ead811caee84
Stable URL of this page
https://metraipolis.com/documento/dc_62ef8bb82a24

How to cite

DexTaG: Tactile-as-Guidance in Reinforcement Learning for Dexterous Manipulation — arXiv:2609.33882 — arXiv (en), https://arxiv.org/abs/2609.33882 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62ef8bb82a24 (Metraipolis archive dc_62ef8bb82a24, sha256 3b380719bcc2ea8355929539f5068e01e7938b0d66abeface3d4ead811caee84)
BibTeX
@misc{dc62ef8bb82a24,
  title = {DexTaG: Tactile-as-Guidance in Reinforcement Learning for Dexterous Manipulation — arXiv:2609.33882},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33882},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62ef8bb82a24; sha256 3b380719bcc2ea8355929539f5068e01e7938b0d66abeface3d4ead811caee84},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33882. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Glove-based motion capture is emerging as a scalable approach to collecting dexterous-hand demonstration data. However, due to the kinematic gap between the human and robot hand, the recorded human motions cannot be executed directly on the robot, especially for contact-rich tool-use tasks involving in-hand reorientation. Prior work bridges this gap in simulation through reinforcement learning (RL) or trajectory optimization, but the human contact pattern is hard to preserve under such formulations, often producing unnatural manipulation and unstable functional grasps. These methods also train a separate policy or solve a separate optimization for each reference trajectory, which is inefficient. To solve these problems, we propose DexTaG, a tactile-guided RL framework for dexterous manipulation. During training, tactile signals captured by the glove guide policy search toward the measured human contact pattern, reducing reliance on precise reference geometry for contact supervision. To improve efficiency, we train a single generalizable retargeter jointly on all training trajectories of the same object. The retargeter is further distilled into a tactile-free student controller conditioned on the target object trajectory for real-world deployment. On marker-pen and hammer manipulation tasks, DexTaG learns natural, contact-rich behaviors that baselines with distance-based contact heuristics fail to learn, generalizes to held-out trajectories of the same object and task, and outperforms single-trajectory baselines on OakInk2.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.33882 — 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 2026-10-07T23:52:16.500Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).