X-Morph: Human Motion Priors for Scalable Robot Learning Across Morphologies
2026-06-29 • Robotics
Robotics
AI summaryⓘ
The authors developed X-Morph, a method that transforms human movements into actions that non-human robots with legs—like four-legged or six-legged robots—can perform. They first adapt human motions to fit the robot's body shape, then teach the robot to follow these motions using reinforcement learning. Their approach works well on different robot types and helps robots perform tasks like walking and manipulating objects, even when given new or unseen human motions. This shows that human movement data can help teach many types of legged robots, not just humanoid ones.
humanoid behavior modelsnon-humanoid legged robotsmotion retargetingreinforcement learninglocomotionmanipulationkinematic plausibilityrobot dynamicspolicy distillationteleoperation
Authors
Ritwik Sharma, Shivam Sood, Arhaan Jain, Shyam Charan Kesavamoorthi, Chengyang He, Guillaume Sartoretti
Abstract
Recent progress in humanoid behavior models has been driven in large part by abundant human motion data, but comparable motion data is scarce for non-humanoid legged robots such as quadrupeds, hexapods, and quadruped manipulators. A promising alternative is to repurpose human motion across embodiments; however, direct retargeting often produces motions that are visually plausible yet physically inconsistent or difficult to track under robot dynamics. We present X-Morph, a human-motion-to-robot-behavior pipeline that converts human motion into deployable locomotion and loco-manipulation policies for diverse non-humanoid legged morphologies. A cross-morphology retargeting stage converts human motions into kinematically plausible, intent-preserving robot references, which are then tracked by a privileged RL policy and distilled into a causal student policy. We evaluate X-Morph on three morphologically distinct platforms: a quadruped, a hexapod, and a quadruped equipped with a manipulator. The resulting policies track diverse retargeted motions, generalize to unseen human motions, and support downstream use cases including video-based teleoperation, behavior-prior control, and text-conditioned motion generation. These results suggest that large-scale human motion can serve as a substrate for learning broad, reusable behavior priors beyond humanoid robots. Project page: https://maker-rat.github.io/morph/