Metraipolis › archive › dc_be8020022519

Learning Social Navigation from Internet Videos in the Policy State Space — arXiv:2609.37476

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.37476
License (as archived): CC0-1.0
Archived: 2026-10-07T17:32:55.892Z
SHA-256 of the archived text: 39aaf082286543cfee135beb17744e727119551c749a04d925d1cafdab529354
Stable URL of this page: https://metraipolis.com/documento/dc_be8020022519

How to cite

Learning Social Navigation from Internet Videos in the Policy State Space — arXiv:2609.37476 — arXiv (en), https://arxiv.org/abs/2609.37476 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be8020022519 (Metraipolis archive dc_be8020022519, sha256 39aaf082286543cfee135beb17744e727119551c749a04d925d1cafdab529354)

BibTeX

@misc{dcbe8020022519,
  title = {Learning Social Navigation from Internet Videos in the Policy State Space — arXiv:2609.37476},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37476},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be8020022519; sha256 39aaf082286543cfee135beb17744e727119551c749a04d925d1cafdab529354},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37476. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Training robust social-navigation policies requires simulators with diverse scene layouts, terrain, and human motion, but constructing such environments and specifying pedestrian behavior is costly. We propose an efficient pipeline that converts ordinary monocular walking videos directly into closed-loop social-navigation training environments in the policy's state space. Our key observation is that local social navigation primarily depends on two types of information: where the robot can traverse and how nearby pedestrians move. We therefore represent the static scene as a metric traversability map, which can be rigidly transformed under counterfactual robot motion, while directly replaying the pedestrian trajectories recovered from the video over time. This abstraction allows us to define the forward dynamics directly in the policy's state space and efficiently simulate counterfactual robot states without reconstructing or rendering photorealistic observations. The resulting policy achieves 81.2% success in the independent Arena benchmark, compared with 75.0% for the strongest baseline, and succeeds in 19/20 real-robot trials without policy fine-tuning. Project page: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.37476 — 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 2026-10-07T16:59:48.551Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).