Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomy
It enables humanoid robots to autonomously navigate complex outdoor environments using standard navigation planners, addressing the problem of terrain-adaptive locomotion for real-world deployment.
This work trains a reference-guided RL locomotion policy for humanoid robots that modulates reference trajectories to match terrain geometry, achieving long-horizon autonomous navigation over rough terrain and stairs with onboard sensing and computation.
We present a method for training reference-guided, perceptive reinforcement learning locomotion policies for humanoid robots in which reference trajectories are modulated in training to be consistent with terrain geometry. Aiming to deploy our method with standard navigation autonomy infrastructure, we synthesize SE(2)-controllable reference trajectories inside the RL training loop, projecting desired footsteps onto valid footholds and adjusting swing-foot and center-of-mass trajectories to match the terrain. The resulting policy exposes a clean SE(2) velocity interface compatible with standard navigation planners. In simulation, environmentally-conditioned references significantly improve reference tracking performance compared to environment agnostic references. On hardware, we integrate the policy with an MPC + control barrier function planner and demonstrate long-horizon (>70m) closed-loop autonomous navigation on the Unitree G1 through outdoor environments containing rough terrain and consecutive flights of stairs, with all sensing and computation onboard.