FastStair: Learning to Run Up Stairs with Humanoid Robots

2026-01-15

AI Summary

This work addresses the challenge of achieving both agility and stability in humanoid robots during high-speed stair climbing, where existing reinforcement learning approaches often yield unsafe behaviors while model-based planners tend to be overly conservative. The authors propose FastStair, a framework that integrates a dynamic foothold planner into the reinforcement learning pipeline. It employs multi-stage pretraining to establish a safe base policy and leverages LoRA to fuse speed-specialized expert policies, enabling adaptive control across the full velocity range. Evaluated on the Oli humanoid robot, the method achieves stable stair ascent at 1.65 m/s, successfully ascending a 33-step spiral staircase (17 cm per step) in under 12 seconds, and secured first place in the Canton Tower Robot Climbing Challenge, thereby breaking the speed barrier for humanoid stair running.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Manipulation
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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 hard constraints often induces conservative motion that limits speed. We present FastStair, a planner-guided, multi-stage learning framework that reconciles these complementary strengths to achieve fast and stable stair ascent. FastStair integrates a parallel model-based foothold planner into the RL training loop to bias exploration toward dynamically feasible contacts and to pretrain a safety-focused base policy. To mitigate planner-induced conservatism and the discrepancy between low- and high-speed action distributions, the base policy was fine-tuned into speed-specialized experts and then integrated via Low-Rank Adaptation (LoRA) to enable smooth operation across the full commanded-speed range. We deploy the resulting controller on the Oli humanoid robot, achieving stable stair ascent at commanded speeds up to 1.65 m/s and traversing a 33-step spiral staircase (17 cm rise per step) in 12 s, demonstrating robust high-speed performance on long staircases. Notably, the proposed approach served as the champion solution in the Canton Tower Robot Run Up Competition.

Problem

• humanoid robots
• stair running
• dynamic locomotion
• stability
• agility

Innovation

• planner-guided reinforcement learning
• multi-stage policy learning
• Low-Rank Adaptation (LoRA)
• dynamic stair climbing
• humanoid locomotion