Metraipolis › archive › dc_79fa2e23a56c

Manifold Generative Annealing for Contact Constraint-aware Impedance Control with Reinforcement Learning Prior — arXiv:2610.21140

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21140
License (as archived)
CC0-1.0
Archived
2026-10-16T10:39:48.981Z
SHA-256 of the archived text
4353b8e09664cec274084c9c65c41b1563d60ce970ecdc21c808588dda359542
Stable URL of this page
https://metraipolis.com/documento/dc_79fa2e23a56c

How to cite

Manifold Generative Annealing for Contact Constraint-aware Impedance Control with Reinforcement Learning Prior — arXiv:2610.21140 — arXiv (en), https://arxiv.org/abs/2610.21140 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_79fa2e23a56c (Metraipolis archive dc_79fa2e23a56c, sha256 4353b8e09664cec274084c9c65c41b1563d60ce970ecdc21c808588dda359542)
BibTeX
@misc{dc79fa2e23a56c,
  title = {Manifold Generative Annealing for Contact Constraint-aware Impedance Control with Reinforcement Learning Prior — arXiv:2610.21140},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21140},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_79fa2e23a56c; sha256 4353b8e09664cec274084c9c65c41b1563d60ce970ecdc21c808588dda359542},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21140. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Contact-rich robotic tasks require coordinated motion and impedance under uncertain interaction dynamics and physical constraints. While recent methods on learned policies provide useful interaction strategies, they may fail when contact conditions differ from those encountered during training. Model-based generative methods show promising receding-horizon trajectories optimization results, but often lack structured behavioral guidance and refinement that jointly accounts for constraint geometry and actual contact responses. To this end, we propose Manifold Generative Annealing (MGA), a joint model-free and model-based generative framework for motion--impedance optimization. MGA first organizes pretrained reinforcement learning policies into structured sequence proposals, retaining task-specific interaction strategies without committing to their execution. It then evaluates these proposals alongside exploratory samples through model-based rollouts for refinement or separate execution selection. Crucially, realization-aware manifold refinement aligns updates from the refinement bank with both task constraints and locally achievable physical responses, allowing learned experience to guide online adaptation under changing contact conditions. Experiments cover surface scanning, peg insertion, and humanoid pushing, with improved safety success rate of impedance control under nominal and sensing-shift conditions.

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/2610.21140 — 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 2026-10-16T08:52:17.612Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).