Metraipolis › archive › dc_7a5dc6bdc85d
Correct Robots Before They Make Mistakes: Proactive Human-in-the-Loop Intervention via Preference Learning — arXiv:2611.05667
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05667
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:30:33.159Z
- SHA-256 of the archived text
2c96017fab6b642178f45f2d1d27179e603c00563bdb6e658d2f4f7a541f6048- Stable URL of this page
https://metraipolis.com/documento/dc_7a5dc6bdc85d
How to cite
Correct Robots Before They Make Mistakes: Proactive Human-in-the-Loop Intervention via Preference Learning — arXiv:2611.05667 — arXiv (en), https://arxiv.org/abs/2611.05667 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a5dc6bdc85d (Metraipolis archive dc_7a5dc6bdc85d, sha256 2c96017fab6b642178f45f2d1d27179e603c00563bdb6e658d2f4f7a541f6048)
BibTeX
@misc{dc7a5dc6bdc85d,
title = {Correct Robots Before They Make Mistakes: Proactive Human-in-the-Loop Intervention via Preference Learning — arXiv:2611.05667},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05667},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a5dc6bdc85d; sha256 2c96017fab6b642178f45f2d1d27179e603c00563bdb6e658d2f4f7a541f6048},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05667. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper presents Proactive Human-in-the-Loop (PHIL), a framework for proactive policy correction and preference-based post-training. PHIL enables operators to preview policy-predicted future motion and intervene before anticipated undesirable actions. During takeover, PHIL continues querying the policy and displaying its predicted trajectories in the physical workspace through an extended reality (XR) interface. PHIL pairs rejected policy predictions with corrective action chunks subsequently executed from the same physical state over the same horizon, and preference-based post-training encourages the policy to favor these corrections. This paper evaluates PHIL on four real-world manipulation tasks using a diffusion policy and a pretrained vision-language-action policy. With five correction episodes per condition, PHIL increases mean success rates across the evaluated tasks and demonstration budgets from 44.0% to 70.3% for the diffusion policy and from 57.8% to 76.9% for X-VLA, compared with HG-DAgger. Separately, policies trained with proactive corrections show fewer unnecessary recovery behaviors in successful episodes. Project page: this https URL . 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/2611.05667 — 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 2026-11-05T18:20:03.981Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).