Metraipolis › archive › dc_f8c19289e44d

Assisting for Open-Ended Tasks: Goal-Oriented Shared Autonomy as a Particle Filter — arXiv:2609.32576

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.32576
License (as archived): CC0-1.0
Archived: 2026-10-08T00:16:57.111Z
SHA-256 of the archived text: 24aae6da10a2d4fcb88897363ea395a3fc68776f79de1430d80ecb40ca571f21
Stable URL of this page: https://metraipolis.com/documento/dc_f8c19289e44d

How to cite

Assisting for Open-Ended Tasks: Goal-Oriented Shared Autonomy as a Particle Filter — arXiv:2609.32576 — arXiv (en), https://arxiv.org/abs/2609.32576 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f8c19289e44d (Metraipolis archive dc_f8c19289e44d, sha256 24aae6da10a2d4fcb88897363ea395a3fc68776f79de1430d80ecb40ca571f21)

BibTeX

@misc{dcf8c19289e44d,
  title = {Assisting for Open-Ended Tasks: Goal-Oriented Shared Autonomy as a Particle Filter — arXiv:2609.32576},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32576},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f8c19289e44d; sha256 24aae6da10a2d4fcb88897363ea395a3fc68776f79de1430d80ecb40ca571f21},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32576. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A common approach for shared autonomy blends human inputs with autonomous assistance based on the human's likely goal. However, most existing approaches assume that a static set of possible goals is known a priori, which limits the use of such methods in unstructured assistive settings. We instead investigate how to enable shared autonomy with open-ended and dynamically changing goals. We formulate goal-oriented shared autonomy as a particle filter in which particles represent candidate human goals. Unlike conventional approaches with a fixed goal set, our transition model dynamically proposes new candidate goals as the interaction evolves, and human actions update the belief over these goals in real time. We instantiate this framework with foundation models (e.g., vision grounding and large language models) that propose context-relevant semantic goals, generate goal-conditioned assistance from low-level skill primitives, and refine those skills from human corrections. We assess our approach through a user study where 12 participants perform a variety of tabletop manipulation tasks with our method and state-of-the-art shared autonomy baselines. The results show that our particle filter-based approach reduces the amount of time users spend teleoperating the system and improves user satisfaction. User study videos: this https URL

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/2609.32576 — 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 2026-10-07T23:52:16.421Z 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).