SOURCE-LINKED INTELLIGENCE

SABER: Learning Attention-based Semantic Affordance for Legged Locomotion

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

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 permissio

Read original source ↗ Open in workspace

recordType

paper

region

Global