Explicit Stair Geometry Conditioning for Robust Humanoid Locomotion
2026-05-11 • Robotics
Robotics
AI summaryⓘ
The authors address the difficulty humanoid robots face when climbing stairs that have different sizes and shapes. They developed a method that uses clear measurements of the stairs, like step height and depth, to help the robot adjust its steps better. By including these stair details directly in the robot's learning process, the robot climbs more reliably even on stairs it hasn't seen before. Tests both in simulation and real life showed the robot could climb many steps successfully, proving their approach works well.
humanoid robotstair climbingProximal Policy Optimization (PPO)locomotion policyterrain representationrobot perceptionstep heightstep depthrobot gaitrobot simulation
Authors
Jianguo Zhang, Wentai Xu, Shusheng Ye, Yuxiang He, Weimin Qi, Qinbo Sun, Ning Ding, Liguang Zhou
Abstract
Robust humanoid stair climbing remains challenging due to geometric discontinuities, sensitivity to step height variations, and perception uncertainty in real-world environments. Existing learning-based locomotion policies often rely on implicit terrain representations or blind proprioceptive feedback, limiting their ability to generalize across varying stair geometries and to anticipate required gait adjustments. This paper proposes an explicit stair geometry conditioning framework for robust humanoid stair climbing. Instead of encoding terrain as high-dimensional latent features, we extract a compact set of interpretable geometric parameters, including step height, step depth, and current yaw angle relative to the robot heading. These explicit stair parameters directly condition a Proximal Policy Optimization (PPO)-based locomotion policy, enabling proactive modulation of swing-foot clearance and stride characteristics according to stair structure. Simulation experiments demonstrate improved generalization across unseen stair heights beyond the training distribution. Real-world experiments on the Unitree G1 humanoid validate reliable indoor and outdoor stair traversal. In challenging outdoor scenarios, the robot successfully ascends 33 consecutive steps without failure, demonstrating robustness and practical deployability.