Search papers, labs, and topics across Lattice.
The paper introduces ReST-RL, a hierarchical reinforcement learning framework for humanoid robots to transport objects on a tray by decoupling locomotion from payload stabilization. ReST-RL integrates a base locomotion policy with a residual module that cancels gait-induced perturbations at the end-effector. The approach achieves high success rates in simulation and demonstrates zero-shot sim-to-real transfer on a Unitree G1 humanoid, outperforming end-to-end baselines in gait smoothness and orientation accuracy.
Humanoid robots can now reliably transport objects on a tray in the real world, thanks to a hierarchical RL approach that isolates and cancels gait-induced disturbances.
Stabilizing unsecured payloads against the inherent oscillations of dynamic bipedal locomotion remains a critical engineering bottleneck for humanoids in unstructured environments. To solve this, we introduce ReST-RL, a hierarchical reinforcement learning architecture that explicitly decouples locomotion from payload stabilization, evaluated via the SteadyTray benchmark. Rather than relying on monolithic end-to-end learning, our framework integrates a robust base locomotion policy with a dynamic residual module engineered to actively cancel gait-induced perturbations at the end-effector. This architectural separation ensures steady tray transport without degrading the underlying bipedal stability. In simulation, the residual design significantly outperforms end-to-end baselines in gait smoothness and orientation accuracy, achieving a 96.9% success rate in variable velocity tracking and 74.5% robustness against external force disturbances. Successfully deployed on the Unitree G1 humanoid hardware, this modular approach demonstrates highly reliable zero-shot sim-to-real generalization across various objects and external force disturbances.
