Load-Aware Locomotion Control for Humanoid Robots in Industrial Transportation Tasks

TL;DR

This paper introduces a load-aware locomotion control framework for humanoid robots in industrial tasks, combining reinforcement learning and state estimation to improve stability and robustness under varying loads, trained in simulation and deployed in real-world scenarios.

Contribution

It proposes a novel decoupled loco-manipulation architecture with a reinforcement learning policy and a history-based state estimator, enabling load-aware control without fine-tuning on real robots.

Findings

Faster training convergence in simulation.

Accurate height and velocity tracking.

Stable loco-manipulation in real-world tests.

Abstract

Humanoid robots deployed in industrial environments are required to perform load-carrying transportation tasks that tightly couple locomotion and manipulation. However, achieving stable and robust locomotion under varying payloads and upper-body motions is challenging due to dynamic coupling and partial observability. This paper presents a load-aware locomotion framework for industrial humanoids based on a decoupled yet coordinated loco-manipulation architecture. Lower-body locomotion is controlled via a reinforcement learning policy producing residual joint actions on kinematically derived nominal configurations. A kinematics-based locomotion reference with a height-conditioned joint-space offset guides learning, while a history-based state estimator infers base linear velocity and height and encodes residual load- and manipulation-induced disturbances in a compact latent representation. The framework is trained entirely in simulation and deployed on a full-size humanoid robot without fine-tuning. Simulation and real-world experiments demonstrate faster training, accurate height tracking, and stable loco-manipulation. Project page: https://lequn-f.github.io/LALO/