Metraipolis › archive › dc_f37eb3ee453d

Is Online Interaction Necessary for Recovery? A Minimalist Approach to Robust Planning via Perturbation — arXiv:2609.33049

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33049
License (as archived)
CC0-1.0
Archived
2026-10-08T00:17:02.167Z
SHA-256 of the archived text
12cdb97ddb41b947915598840337a3e50a5b89c8786c669afd262f3407eb03f3
Stable URL of this page
https://metraipolis.com/documento/dc_f37eb3ee453d

How to cite

Is Online Interaction Necessary for Recovery? A Minimalist Approach to Robust Planning via Perturbation — arXiv:2609.33049 — arXiv (en), https://arxiv.org/abs/2609.33049 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f37eb3ee453d (Metraipolis archive dc_f37eb3ee453d, sha256 12cdb97ddb41b947915598840337a3e50a5b89c8786c669afd262f3407eb03f3)
BibTeX
@misc{dcf37eb3ee453d,
  title = {Is Online Interaction Necessary for Recovery? A Minimalist Approach to Robust Planning via Perturbation — arXiv:2609.33049},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33049},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f37eb3ee453d; sha256 12cdb97ddb41b947915598840337a3e50a5b89c8786c669afd262f3407eb03f3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33049. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Behavior cloning (BC) is vulnerable to covariate shift during closed-loop execution, where small prediction or execution errors can drive the robot toward states poorly covered by the demonstration data. We focus on action-sequence planning, where a policy predicts a finite-horizon sequence of actions as a reference trajectory for robot execution. Existing approaches to covariate shift often rely on collecting additional corrective demonstrations, requiring further environment interaction and access to an expert or reference policy. We propose Perturbation-Augmented Recovery Supervision (PARS), a simple training approach for improving recovery using only existing demonstrations. PARS perturbs the robot's proprioceptive state and anchors only the later portion of the predicted trajectory to the original demonstration, leaving the earlier portion free to generate corrective motion and recover toward the demonstrated behavior within the planning horizon. Unlike conventional input-noise augmentation, which preserves the original supervision target over the entire prediction horizon, PARS explicitly provides trajectory-level supervision for recovery from perturbed states. PARS requires neither additional environment interaction nor expert queries and can be instantiated across different action-sequence policy classes with only minor modifications to their BC objectives. Experiments on 51 RLBench manipulation tasks with flow-based, transformer-based, and diffusion-based policies demonstrate that PARS improves robustness to covariate shift during closed-loop execution.

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/2609.33049 — 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 2026-10-07T23:52:16.443Z 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).