← Back to Benchmarks
simmediumhumanoidmetric · varies

FastStair: Learning to Run Up Stairs with Humanoid Robots

Description

Running up stairs is effortless for humans but remains extremely challenging for humanoid robots due to the simultaneous requirements of high agility and strict stability. Model-free reinforcement learning (RL) can generate dynamic locomotion, yet implicit stability rewards and heavy reliance on task-specific reward shaping tend to result in unsafe behaviors, especially on stairs; conversely, model-based foothold planners encode contact feasibility and stability structure, but enforcing their ha

Source

http://arxiv.org/abs/2601.10365v1