Metraipolis › archive › dc_fae9504c43e7
RoboPrompt: Intuitive Robot Policy Steering with Sparse Human Input — arXiv:2610.10534
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10534
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:49:31.631Z
- SHA-256 of the archived text
cd434e479b2f560bae6a05145f49a7a7b12b6777f09fd37273dd8faca711e2ef- Stable URL of this page
https://metraipolis.com/documento/dc_fae9504c43e7
How to cite
RoboPrompt: Intuitive Robot Policy Steering with Sparse Human Input — arXiv:2610.10534 — arXiv (en), https://arxiv.org/abs/2610.10534 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fae9504c43e7 (Metraipolis archive dc_fae9504c43e7, sha256 cd434e479b2f560bae6a05145f49a7a7b12b6777f09fd37273dd8faca711e2ef)
BibTeX
@misc{dcfae9504c43e7,
title = {RoboPrompt: Intuitive Robot Policy Steering with Sparse Human Input — arXiv:2610.10534},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10534},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fae9504c43e7; sha256 cd434e479b2f560bae6a05145f49a7a7b12b6777f09fd37273dd8faca711e2ef},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10534. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
End-to-end robot policies trained through imitation learning remain constrained by limited data diversity, making reliable zero-shot deployment in real-world settings challenging. Shared-autonomy methods enable human correction through teleoperation, but specialized hardware and operator training hinder deployment at scale. Other approaches incorporate human guidance as additional policy inputs, often requiring architectural changes and dedicated training for steerability, which limits their applicability across policies. We present RoboPrompt, a general-purpose, lightweight robot policy steering system that enables users to guide policy behavior through intuitive, sparse inputs, including drawn traces, target points, and coarse directional instructions. RoboPrompt decouples human-intention translation from the underlying policy: a reusable module converts human guidance into action drafts, which are refined through the diffusion or flow-matching dynamics of the base policy. By controlling action generation in noise space, RoboPrompt balances human intent with the policy prior without modifying the base policy architecture or fine-tuning it for steerability. Experiments demonstrate effective steering across Diffusion Policy, $\pi_{0.5}$, and FastWAM. We further use steered rollouts for online policy improvement through DAgger. After 2-3 rounds of iteration, average success rates increase by 15.5\% for $\pi_{0.5}$ across three tasks and by 21.3\% across three policies(Diffusion Policy, $\pi_{0.5}$, FastWAM) on the Insert Bread task, while average human intervention counts decrease by 44.0\% (2.86 to 1.60) and 81.9\% (2.60 to 0.47), respectively.
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/2610.10534 — 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 2026-10-08T12:18:30.599Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).