Metraipolis › archive › dc_c5f798b83052

Kinematic Hypothesis Context: Embodiment-Conditioned Learned Video Coding for Bandwidth-Limited Robot Policy Uplinks — arXiv:2611.07411

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07411
License (as archived)
CC0-1.0
Archived
2026-11-06T14:53:51.079Z
SHA-256 of the archived text
20c33300e5cd0ec677cfdabf81409a13fa0eac92223ab9a60de69c4aa16583da
Stable URL of this page
https://metraipolis.com/documento/dc_c5f798b83052

How to cite

Kinematic Hypothesis Context: Embodiment-Conditioned Learned Video Coding for Bandwidth-Limited Robot Policy Uplinks — arXiv:2611.07411 — arXiv (en), https://arxiv.org/abs/2611.07411 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c5f798b83052 (Metraipolis archive dc_c5f798b83052, sha256 20c33300e5cd0ec677cfdabf81409a13fa0eac92223ab9a60de69c4aa16583da)
BibTeX
@misc{dcc5f798b83052,
  title = {Kinematic Hypothesis Context: Embodiment-Conditioned Learned Video Coding for Bandwidth-Limited Robot Policy Uplinks — arXiv:2611.07411},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07411},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c5f798b83052; sha256 20c33300e5cd0ec677cfdabf81409a13fa0eac92223ab9a60de69c4aa16583da},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07411. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robots increasingly run large vision-language-action policies on remote servers, making the camera uplink the bottleneck. Existing video codecs spend bits on content the receiver could predict: the robot's own motion. We introduce the kinematic hypothesis context, a zero-rate conditioning signal that both ends build from joint states, the robot model and the camera calibration. Ego-motion homographies, per-link robot reprojections, an end-effector plane and a background memory warp the previous reconstruction into hypotheses that condition a learned video codec. We prove that history-only and global-pose conditioning with a limited receptive field cannot access this information under large motion, and that coding gains become task gains at the policy's success cliff. On LIBERO, the context saves 23.9% bit rate over a capacity-matched history-conditioned codec and 40-56% over x264, x265 and SVT-AV1, and needs 23.2% fewer bits than DCVC-RT at equal policy action deviation; trained to lower rates, it matches DCVC-RT in PSNR. In closed loop at equal rate, OpenVLA-OFT success nearly doubles from 22.8% to 43.1% at 6 kbps (72.6% with lower-rate training, 23.6 points above DCVC-RT), pi_0.5 success rises from 55.5% to 77.4%, and the gain grows under packet loss. The context transfers across three codec hosts and to real robot data.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.07411 — 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 2026-11-06T14:25:42.632Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).