Payload-Robust Control for Humanoid Loco-Manipulation in Industrial Transportation Tasks

Overview

Abstract

Humanoid robots performing industrial transportation must maintain stable locomotion while coordinating perception and manipulation under varying payloads. This paper presents a payload-robust locomotion framework for full-size humanoid robots. The commanded base height is analytically mapped to a nominal lower-body configuration. A kinematics-based locomotion reference is used only to guide policy training. Upper-body motions and end-effector payloads are randomized during training, while deployment motions are generated by a perception-driven kinematic controller. A temporal history encoder estimates base velocity and height and extracts a latent feature from recent whole-body proprioceptive observations. The lower-body policy is trained entirely in simulation and transferred to the physical robot without fine-tuning. Simulation results demonstrate faster convergence, accurate base-state estimation, and latent structure associated with payload variations. Real-robot experiments validate stable box transportation under varying payloads.

Method Overview

Paper page 1
Overview of the proposed payload-robust humanoid loco-manipulation framework. A perception-driven kinematic controller generates upper-body trajectories from 6D object pose estimates. The lower-body policy is conditioned on whole-body proprioceptive observations, explicit base-state estimates, and a latent feature extracted from the observation history, and outputs residual joint commands added to a height-conditioned joint-space offset.

Velocity-Commanded Lower-Body References

Upper-Body Disturbance Simulation in Isaac Gym

Box Segmentation & 6D Object Pose Estimation

Depalletizing Task