Locomotion Beyond Feet

TL;DR

This paper presents a comprehensive system enabling humanoid robots to perform stable, whole-body locomotion across complex terrains by combining physics-based keyframe animation with reinforcement learning and hierarchical planning.

Contribution

It introduces a novel approach that integrates human-like keyframe motion encoding with reinforcement learning for robust, terrain-generalized humanoid locomotion in challenging environments.

Findings

Robust locomotion achieved on complex terrains

System generalizes across obstacle types and sequences

Successful real-world robot experiments conducted

Abstract

Most locomotion methods for humanoid robots focus on leg-based gaits, yet natural bipeds frequently rely on hands, knees, and elbows to establish additional contacts for stability and support in complex environments. This paper introduces Locomotion Beyond Feet, a comprehensive system for whole-body humanoid locomotion across extremely challenging terrains, including low-clearance spaces under chairs, knee-high walls, knee-high platforms, and steep ascending and descending stairs. Our approach addresses two key challenges: contact-rich motion planning and generalization across diverse terrains. To this end, we combine physics-grounded keyframe animation with reinforcement learning. Keyframes encode human knowledge of motor skills, are embodiment-specific, and can be readily validated in simulation or on hardware, while reinforcement learning transforms these references into robust, physically accurate motions. We further employ a hierarchical framework consisting of terrain-specific motion-tracking policies, failure recovery mechanisms, and a vision-based skill planner. Real-world experiments demonstrate that Locomotion Beyond Feet achieves robust whole-body locomotion and generalizes across obstacle sizes, obstacle instances, and terrain sequences.