Metraipolis › archive › dc_f137ca9ff8df

Language-Conditioned Behavioral Cloning for Autonomous Endoscope Guidance — arXiv:2610.41978

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41978
License (as archived)
CC0-1.0
Archived
2026-11-02T05:05:50.378Z
SHA-256 of the archived text
178867bed4e4f460d7ae96399b4f1b2b2656a07e945e2e44f6bb9dd0d9703252
Stable URL of this page
https://metraipolis.com/documento/dc_f137ca9ff8df

How to cite

Language-Conditioned Behavioral Cloning for Autonomous Endoscope Guidance — arXiv:2610.41978 — arXiv (en), https://arxiv.org/abs/2610.41978 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f137ca9ff8df (Metraipolis archive dc_f137ca9ff8df, sha256 178867bed4e4f460d7ae96399b4f1b2b2656a07e945e2e44f6bb9dd0d9703252)
BibTeX
@misc{dcf137ca9ff8df,
  title = {Language-Conditioned Behavioral Cloning for Autonomous Endoscope Guidance — arXiv:2610.41978},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41978},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f137ca9ff8df; sha256 178867bed4e4f460d7ae96399b4f1b2b2656a07e945e2e44f6bb9dd0d9703252},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41978. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automated endoscope guidance reduces the need for continuous manual camera control during minimally invasive surgery. However, the desired camera motion depends on the surgeon's immediate intentions and cannot always be inferred from the visual operative scene alone. We propose to automate the task using language-conditioned behavioral cloning; we define 6 clinically relevant guidance behaviors and collect 235 subtask demonstrations. In preliminary phantom experiments, our policy achieves 100% success on focus, overview, and stop, 80% on search-tip and follow-tip behaviors, and 50% on horizon leveling. These results demonstrate the feasibility of learning heterogeneous surgeon-requested camera behaviors with a single visuomotor policy, while the observed failure modes motivate future work on adding temporal context for more demanding guidance tasks.

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/2610.41978 — 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 2026-11-02T04:49:28.234Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).