SCDP: Learning Humanoid Locomotion from Partial Observations via Mixed-Observation Distillation
This enables robust humanoid locomotion for robotics applications without external sensing, though it is incremental as it builds on existing diffusion and distillation methods.
The paper tackled the challenge of deploying humanoid locomotion policies without relying on full-body state estimation by introducing Sensor-Conditioned Diffusion Policies (SCDP), which achieved near-perfect success (99-100%) in simulation for velocity control and 93% tracking success using only onboard sensors, and was successfully deployed on a real robot.
Distilling humanoid locomotion control from offline datasets into deployable policies remains a challenge, as existing methods rely on privileged full-body states that require complex and often unreliable state estimation. We present Sensor-Conditioned Diffusion Policies (SCDP) that enables humanoid locomotion using only onboard sensors, eliminating the need for explicit state estimation. SCDP decouples sensing from supervision through mixed-observation training: diffusion model conditions on sensor histories while being supervised to predict privileged future state-action trajectories, enforcing the model to infer the motion dynamics under partial observability. We further develop restricted denoising, context distribution alignment, and context-aware attention masking to encourage implicit state estimation within the model and to prevent train-deploy mismatch. We validate SCDP on velocity-commanded locomotion and motion reference tracking tasks. In simulation, SCDP achieves near-perfect success on velocity control (99-100%) and 93% tracking success in AMASS test set, performing comparable to privileged baselines while using only onboard sensors. Finally, we deploy the trained policy on a real G1 humanoid at 50 Hz, demonstrating robust real robot locomotion without external sensing or state estimation.