Metraipolis › archive › dc_441cb4c87cbe

SABER: Learning Attention-based Semantic Affordance for Legged Locomotion — arXiv:2609.21572

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21572
License (as archived)
CC0-1.0
Archived
2026-10-10T02:30:12.262Z
SHA-256 of the archived text
f45d656a4d4eeb554103cb5bb408790ee0e8a92ade43452ee2da8586cf374536
Stable URL of this page
https://metraipolis.com/documento/dc_441cb4c87cbe

How to cite

SABER: Learning Attention-based Semantic Affordance for Legged Locomotion — arXiv:2609.21572 — arXiv (en), https://arxiv.org/abs/2609.21572 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_441cb4c87cbe (Metraipolis archive dc_441cb4c87cbe, sha256 f45d656a4d4eeb554103cb5bb408790ee0e8a92ade43452ee2da8586cf374536)
BibTeX
@misc{dc441cb4c87cbe,
  title = {SABER: Learning Attention-based Semantic Affordance for Legged Locomotion — arXiv:2609.21572},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21572},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_441cb4c87cbe; sha256 f45d656a4d4eeb554103cb5bb408790ee0e8a92ade43452ee2da8586cf374536},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21572. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Perceptive legged locomotion has advanced rapidly by integrating terrain geometry into learned policies, yet the integration of terrain meaning remains sparse: a pipe, a patch of grass, or a fragile box may be geometrically traversable while being inappropriate for contact. In industrial environments, where legged robots increasingly operate, a single misplaced step can damage fragile equipment, destabilize the robot, or endanger the site. To address this, we introduce SABER, a planner-free reinforcement-learning policy that jointly reasons about terrain geometry and semantic contact permission. The policy consumes a unified terrain-affordance map, where each cell encodes local 3D geometry and a semantic contact cost. We augment cross-attention with a learned, signed semantic bias: an additive term on the attention logits, gated by the contact cost, that reweights flagged cells by their distance from the nearest foot. A hazard therefore reshapes attention where it can still affect the next foothold, and its influence fades where it cannot. The resulting policy selects footholds on permitted support and keeps the leg clear of forbidden regions throughout the swing phase. We perform a systematic ablation that isolates the contribution of each architectural component; removing the semantic bias alone increases forbidden contacts by 55% while velocity tracking is unchanged. We validate the policy on a Unitree B2, demonstrating sim-to-real semantic contact selection across indoor and outdoor environments and four semantic obstacle classes.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.21572 — 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 2026-10-10T02:09:55.356Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).