PTDL:Multi-Terrain Fall Recovery via Phase-Terrain Decoupled Learning
2026-06-08 • Robotics
Robotics
AI summaryⓘ
The authors developed a method to help humanoid robots stand up and walk again after falling on different types of ground like flat surfaces, gravel, and slopes. Their approach trains the robot to handle the falling and walking parts separately and for each terrain type, but only uses one unified control policy. This helps the robot recover balance and start walking smoothly without needing to know exactly what kind of surface it is on during use. They tested this method in simulations and real robots, showing stable and adaptable recovery and walking across various terrains.
humanoid robotsfall recoverylocomotionproprioceptionphase decouplingterrain adaptationmotion priorreinforcement learningUnitree G1robot control policy
Authors
Xiaoyu Xu, Zhiming Chen, Yuenan Zhao, Ran Song, Wei Zhang
Abstract
Humanoid robots can fall on slopes, gravel, and uneven ground in unstructured environments. We target integrated fall recovery and locomotion: rebuilding balance from a fallen state using proprioception alone and resuming velocity-commanded walking at the fall site. Prior methods often stop at quasi-static rise, neglect the post-fall ground-contact phase, or, when trained on mixed terrains without separating recovery and locomotion phases or per-surface constraints, collapse to a single compromise get-up across surfaces. We propose Phase--Terrain Decoupled Learning (PTDL), which decouples training supervision along phase and terrain axes while deploying one proprioceptive policy. On the phase axis, projected-gravity-gated dual motion-prior discriminators and a probe-to-walk transition link post-fall recovery to commanded walking. On the terrain axis, terrain-stratified recovery shaping assigns surface-specific training supervision on flat ground, gravel, and slopes; terrain labels are training-only and withheld from policy observations, enabling implicit post-fall strategy selection at deployment. We validate PTDL on a 29-DoF Unitree G1 across flat ground, gravel, and slopes up to 20 degrees in simulation and on hardware, achieving stable cross-terrain recovery, smooth recovery-to-locomotion transitions, and differentiated post-fall rise behaviors under one deployed policy.