Metraipolis › archive › dc_eb2d5576ae98

TACOS: Terrain-Aware COntact Supervision for Visual Footstep Planning — arXiv:2610.37806

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.37806
License (as archived)
CC0-1.0
Archived
2026-11-01T02:43:44.931Z
SHA-256 of the archived text
609e90b4ed8088373e6090ce542ffd278cc24d9445a54f988a91a0de67a7661a
Stable URL of this page
https://metraipolis.com/documento/dc_eb2d5576ae98

How to cite

TACOS: Terrain-Aware COntact Supervision for Visual Footstep Planning — arXiv:2610.37806 — arXiv (en), https://arxiv.org/abs/2610.37806 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb2d5576ae98 (Metraipolis archive dc_eb2d5576ae98, sha256 609e90b4ed8088373e6090ce542ffd278cc24d9445a54f988a91a0de67a7661a)
BibTeX
@misc{dceb2d5576ae98,
  title = {TACOS: Terrain-Aware COntact Supervision for Visual Footstep Planning — arXiv:2610.37806},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.37806},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb2d5576ae98; sha256 609e90b4ed8088373e6090ce542ffd278cc24d9445a54f988a91a0de67a7661a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37806. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Humans navigate their environment based on their vision system, anticipating how the ground will respond before committing to a step. Self-supervised learning could provide legged robots the same ability, but the supervisory signal is typically chosen on intuition, and its effect on what the model learns is rarely examined. We present Terrain-Aware COntact Supervision (TACOS), which proposes a meaningful and consistent footstep instability score, based on the residual of a factor graph in legged state estimation. It projects the continuous score into preceding images to supervise a dense visual predictor. We propose two variants, a hard score that exploits hindsight and a causal soft score available immediately. Both metrics are compared against state-of-the-art alternatives in two independent evaluations that share no data or labels. On 1716 manually annotated contacts, both variants outperform every evaluated alternative at detecting instability and ranking its severity, improving pooled severity ranking by 28 % over the strongest baseline. On three outdoor test runs, our metric also trains the most accurate visual predictor, improving rank correlation by 58 % over the strongest alternative, and by a further 25 % when supplemented with onboard context. In a real-world experiment over a 50 m forest trajectory, the trained predictor handles non-geometric terrain properties such as mud and vegetation, while stepping around geometric obstacles like fallen branches. Code is available for reproducibility at this https URL .

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/2610.37806 — 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 2026-11-01T02:16:44.003Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).