Metraipolis › archive › dc_770f50e8a699

Robots That Take Initiative: A Framework for Building and Evaluating Proactive Robots — arXiv:2609.28910

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28910
License (as archived)
CC0-1.0
Archived
2026-10-08T04:27:11.108Z
SHA-256 of the archived text
c32b27c8fee6487510792609aafbd5ade6f2c8449ff11165a909260b9456efbf
Stable URL of this page
https://metraipolis.com/documento/dc_770f50e8a699

How to cite

Robots That Take Initiative: A Framework for Building and Evaluating Proactive Robots — arXiv:2609.28910 — arXiv (en), https://arxiv.org/abs/2609.28910 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_770f50e8a699 (Metraipolis archive dc_770f50e8a699, sha256 c32b27c8fee6487510792609aafbd5ade6f2c8449ff11165a909260b9456efbf)
BibTeX
@misc{dc770f50e8a699,
  title = {Robots That Take Initiative: A Framework for Building and Evaluating Proactive Robots — arXiv:2609.28910},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28910},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_770f50e8a699; sha256 c32b27c8fee6487510792609aafbd5ade6f2c8449ff11165a909260b9456efbf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28910. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Effective robot assistance beyond narrow roles and repetitive tasks requires robots to be proactive - to decide what needs to be done rather than waiting to be told. While proactivity is increasingly explored, it lacks a unified formulation, and work in the domain is typically evaluated offline against static human models that cannot capture the effect of a robot's actions on the environment and the user's own behavior. We introduce a unified formalism for proactive robot assistance, organize it into three levels, and provide a framework to address the highest level of unprompted proactive assistance. We then show that offline evaluation overstates performance in this setting, and contribute a closed-loop evaluation with a human model that adapts to the robot. Finally, we present a method, GAP, that instantiates our framework, learning from passive observation to anticipate user goals and act. Under closed-loop evaluation, prior state-of-the-art methods collapse, in some cases adding more work than they save, while GAP remains robust and substantially outperforms them.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.28910 — 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 2026-10-08T03:50:57.973Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).