Metraipolis › archive › dc_87bd45b76298
TactileStep: Sole Tactile Learning for Regulating Foot-Terrain Interaction in Humanoid Locomotion — arXiv:2609.28959
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28959
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T07:16:33.843Z
- SHA-256 of the archived text
1b2c66c3fc896c7a5306269f85c6e49481526b073ffdb69c51fe3dd3859984b4- Stable URL of this page
https://metraipolis.com/documento/dc_87bd45b76298
How to cite
TactileStep: Sole Tactile Learning for Regulating Foot-Terrain Interaction in Humanoid Locomotion — arXiv:2609.28959 — arXiv (en), https://arxiv.org/abs/2609.28959 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_87bd45b76298 (Metraipolis archive dc_87bd45b76298, sha256 1b2c66c3fc896c7a5306269f85c6e49481526b073ffdb69c51fe3dd3859984b4)
BibTeX
@misc{dc87bd45b76298,
title = {TactileStep: Sole Tactile Learning for Regulating Foot-Terrain Interaction in Humanoid Locomotion — arXiv:2609.28959},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28959},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_87bd45b76298; sha256 1b2c66c3fc896c7a5306269f85c6e49481526b073ffdb69c51fe3dd3859984b4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28959. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Humanoid parkour policies can traverse various terrains, but task completion may mask challenges of harsh landings, edge contacts, and unstable stance contacts. Humans naturally regulate foot-terrain interaction through tactile feedback, modulating contact compliance according to terrain stiffness. This highlights a key domain gap between humans and humanoid robots: the absence of rich tactile sensing in most humanoid systems. We address this problem with TactileStep, a deployable tactile learning framework that brings sole pressure sensing into humanoid locomotion control for softer touchdowns and more stable support. TactileStep aligns tactile simulation with the real pressure insole, allowing the policy to learn from the same contact features available on hardware. During training, we use tactile and motion cues to recognize different foot-contact phases and apply phase-aware rewards that encourage safer landing and more stable stance. Evaluated in simulation and on a Unitree G1 humanoid across diverse terrains, TactileStep reduces peak touchdown force by up to 48.8% and peak A-weighted impact noise by up to 30.1 dB over a strong perceptive baseline, while increasing stance contact area by up to 23.8%. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.28959 — 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 2026-10-08T06:38:53.757Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).