ULC: A Unified and Fine-Grained Controller for Humanoid Loco-Manipulation

TL;DR

The Unified Loco-Manipulation Controller (ULC), a single-policy framework that simultaneously tracks root velocity, root height, torso rotation, and dual-arm joint positions in an end-to-end manner, proving the feasibility of unified control without sacrificing performance is proposed.

Abstract

Loco-Manipulation for humanoid robots aims to enable robots to integrate mobility with upper-body tracking capabilities. Most existing approaches adopt hierarchical architectures that decompose control into isolated upper-body (manipulation) and lower-body (locomotion) policies. While this decomposition reduces training complexity, it inherently limits coordination between subsystems and contradicts the unified whole-body control exhibited by humans. We demonstrate that a single unified policy can achieve a combination of tracking accuracy, large workspace, and robustness for humanoid loco-manipulation. We propose the Unified Loco-Manipulation Controller (ULC), a single-policy framework that simultaneously tracks root velocity, root height, torso rotation, and dual-arm joint positions in an end-to-end manner, proving the feasibility of unified control without sacrificing performance. We achieve this unified control through key technologies: sequence skill acquisition for progressive learning complexity, residual action modeling for fine-grained control adjustments, command polynomial interpolation for smooth motion transitions, random delay release for robustness to deploy variations, load randomization for generalization to external disturbances, and center-of-gravity tracking for providing explicit policy gradients to maintain stability. We validate our method on the Unitree G1 humanoid robot with 3-DOF (degrees-of-freedom) waist. Compared with strong baselines, ULC shows better tracking performance to disentangled methods and demonstrating larger workspace coverage. The unified dual-arm tracking enables precise manipulation under external loads while maintaining coordinated whole-body control for complex loco-manipulation tasks.

Figures (6)

• Figure 1: Diverse loco-manipulation capabilities enabled by ULC. The humanoid robot demonstrates various coordinated whole-body actions, including picking up bread from a table and placing it in a refrigerator, pushing a cart with coordinated locomotion, squatting to shovel sand from the ground, lifting boxes from the floor to table height with dual-arm coordination, picking up dolls from the ground with hand switching and placing them on a sofa, sitting and playing ukulele with fine motor control, placing items in a microwave with precise manipulation, cleaning kitchen surfaces with wiping motions, erasing blackboards with arm coordination, and performing torso rotation in outdoor environments.
• Figure 2: Method overview of the Unified Loco-Manipulation Controller (ULC). Our approach employs massively parallel reinforcement learning to train a single unified policy that tracks procedurally sampled commands including root velocity, root height, torso orientation, and arm joint positions. The framework addresses multi-task learning challenges through sequential skill acquisition with adaptive curriculum, deployment-realistic command generation with interpolation and random delay, and loaded balance optimization with center of mass tracking.
• Figure 3: Time-series visualization of the doll pick-and-place task, covering all key stages: squatting to pick up the doll, hand switching, and placing the doll at the target location.
• Figure 4: Time-series visualization of the refrigerator task, covering all five stages: picking up the bread, walking to the refrigerator, opening the door, placing the bread inside, and closing the door.
• Figure 5: Comparison of joint angle tracking errors for ULC and traditional PD control (gains: $K_p=80$, $K_d=3$) under different external loads (0.5 kg, 1.0 kg, 1.5 kg) in real-world experiments. ULC consistently achieves lower errors than PD control at all load levels, demonstrating superior force adaptation and robustness to external disturbances.