Metraipolis › archive › dc_2e5bfcef7fab

Closing the Dynamics Gap through Self-Directed Robotic Interaction — arXiv:2611.02691

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02691
License (as archived)
CC0-1.0
Archived
2026-11-03T10:58:35.621Z
SHA-256 of the archived text
d9568bf174115f67d3157a983450a4c15a20d26de9bec7b21442f3c826d499ee
Stable URL of this page
https://metraipolis.com/documento/dc_2e5bfcef7fab

How to cite

Closing the Dynamics Gap through Self-Directed Robotic Interaction — arXiv:2611.02691 — arXiv (en), https://arxiv.org/abs/2611.02691 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e5bfcef7fab (Metraipolis archive dc_2e5bfcef7fab, sha256 d9568bf174115f67d3157a983450a4c15a20d26de9bec7b21442f3c826d499ee)
BibTeX
@misc{dc2e5bfcef7fab,
  title = {Closing the Dynamics Gap through Self-Directed Robotic Interaction — arXiv:2611.02691},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02691},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e5bfcef7fab; sha256 d9568bf174115f67d3157a983450a4c15a20d26de9bec7b21442f3c826d499ee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02691. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic Real2Sim2Real systems can reconstruct a scene in simulation from camera observations, but contact-rich dynamics such as friction and restitution cannot be observed without interaction. We call this the dynamics gap and present CUE, an agentic system that closes it by interacting with the environment itself. Given only a high-level instruction and no resets, the agent builds its own perception, identifies physical parameters, and targets interactions where its simulation is least accurate. On billiards, CUE reduces held-out ball-position error by 72% relative to the strongest baseline across 25 hidden-physics conditions in simulation, and we further deploy it on a real pool table. More details can be found on the project website: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.02691 — 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 2026-11-03T10:49:38.670Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).