Humanoid Rickshaw Pulling: Whole-Body Locomotion under Coupled Wheeled Loads

2026-10-03

AI Summary

This study addresses the whole-body control challenge faced by humanoid robots when pulling passive wheeled vehicles, specifically maintaining upper-body contact while adapting to unknown coupling forces. To this end, we propose a whole-body control framework based on privileged teacher distillation and reinforcement learning fine-tuning. By employing a history-conditioned policy, the robot implicitly infers coupled dynamics using only proprioceptive feedback, achieving stable grasping, balance maintenance, and precise trajectory tracking without load-specific retuning. The proposed approach is successfully validated on Unitree G1 hardware, executing starting, turning, and stopping maneuvers while towing 115 kg payloads, including rigid loads and human passengers. Notably, the system significantly reduces oscillations and energy consumption, yielding a cost of transport lower than that of unloaded walking, thereby demonstrating robust heavy-load transportation capabilities.

Abstract

Humanoid robots could transport payloads substantially heavier than themselves by pulling passive wheeled vehicles instead of carrying the load. This capability, however, creates a coupled locomotion problem: the robot must maintain persistent upper-body contact while adapting to unknown, configuration-dependent forces arising from the payload, vehicle, and terrain. We present a whole-body control framework for humanoid rickshaw pulling that tracks commanded vehicle motion while preserving balance and stable grasps under uncertain load dynamics. During training, a privileged teacher exploits vehicle states, interaction forces, and load properties. Its actions and latent are distilled into a history-conditioned student that implicitly infers coupled dynamics from proprioceptive responses, followed by reinforcement-learning fine-tuning. Comparisons with \emph{No History} and \emph{Only History} baselines show that the resulting policy achieves accurate vehicle tracking while reducing vehicle oscillation, torso tilt, and actuation cost. Behavioral analysis shows that Unitree G1 propels the rickshaw and generates gait-synchronized whole-body reactions that stabilize its lateral and roll motions. Moreover, pulling redistributes joint effort and yields a lower robot-normalized cost-of-transport proxy than unloaded walking over most tested load--speed conditions. On hardware, a single policy performs starting, sustained pulling, turning, and stopping with both rigid payloads and human passengers, handling a loaded rickshaw mass of up to 115~kg without load-specific retuning. These results demonstrate robust heavy-load transportation through coordinated and persistent humanoid--vehicle interaction.

Problem

• humanoid robot
• coupled locomotion
• wheeled load transportation
• whole-body control
• load dynamics

Innovation

• whole-body control
• knowledge distillation
• reinforcement learning
• humanoid locomotion
• coupled dynamics