Metraipolis › archive › dc_82be707d983e

Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution — arXiv:2508.05941

Source
arXiv (en)
Original
https://arxiv.org/abs/2508.05941
License (as archived)
CC0-1.0
Archived
2026-11-04T18:55:41.575Z
SHA-256 of the archived text
2b5846199fa54583d270cae5a1190527cb99d8d58edff5847e7a17deb9be01b6
Stable URL of this page
https://metraipolis.com/documento/dc_82be707d983e

How to cite

Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution — arXiv:2508.05941 — arXiv (en), https://arxiv.org/abs/2508.05941 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_82be707d983e (Metraipolis archive dc_82be707d983e, sha256 2b5846199fa54583d270cae5a1190527cb99d8d58edff5847e7a17deb9be01b6)
BibTeX
@misc{dc82be707d983e,
  title = {Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution — arXiv:2508.05941},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2508.05941},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_82be707d983e; sha256 2b5846199fa54583d270cae5a1190527cb99d8d58edff5847e7a17deb9be01b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2508.05941. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visuomotor policies trained via behavior cloning are vulnerable to covariate shift, where small deviations from expert trajectories can compound into failure. Common strategies to mitigate this issue involve expanding the training distribution through human-in-the-loop corrections or synthetic data augmentation. However, these approaches are often labor-intensive, rely on strong task assumptions, or compromise the quality of imitation. We introduce Latent Policy Barrier, a framework for robust visuomotor policy learning. Inspired by Control Barrier Functions, LPB treats the latent embeddings of expert demonstrations as an implicit barrier separating safe, in-distribution states from unsafe, out-of-distribution (OOD) ones. Our approach decouples the role of precise expert imitation and OOD recovery into two separate modules: a base diffusion policy solely on expert data, and a dynamics model trained on both expert and suboptimal policy rollout data. At inference time, the dynamics model predicts future latent states and optimizes them to stay within the expert distribution. Both simulated and real-world experiments show that LPB improves both policy robustness and data efficiency, enabling reliable manipulation from limited expert data and without additional human correction or annotation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2508.05941 — 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 2026-11-04T18:35:37.500Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).