A Unified and General Humanoid Whole-Body Controller for Fine-Grained Locomotion

2025-02-05

AI Summary

Existing approaches model humanoid robot locomotion as a single, static, and passive process, severely limiting agility and naturalness. This paper proposes HUGWBC, a unified whole-body controller for human-like locomotion, which—through a single policy—achieves fine-grained, multimodal (walking, running, jumping, hopping), parameter-tunable (step frequency, leg swing height, torso pitch/yaw, height), and highly robust motion control. It further enables real-time external upper-body interventions and teleoperated arm manipulation, bridging the longstanding locomotion-manipulation decoupling bottleneck. Methodologically, HUGWBC integrates a general task instruction space, symmetry-aware loss functions, intervention-based reinforcement learning, and sim-to-real transfer. Evaluated on a physical humanoid platform, it demonstrates high-fidelity trajectory tracking, strong disturbance rejection, and stable execution across all instruction combinations. A systematic analysis reveals intrinsic couplings among locomotion parameters.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Locomotion is a fundamental skill for humanoid robots. However, most existing works made locomotion a single, tedious, unextendable, and passive movement. This limits the kinematic capabilities of humanoid robots. In contrast, humans possess versatile athletic abilities-running, jumping, hopping, and finely adjusting walking parameters such as frequency, and foot height. In this paper, we investigate solutions to bring such versatility into humanoid locomotion and thereby propose HUGWBC: a unified and general humanoid whole-body controller for fine-grained locomotion. By designing a general command space in the aspect of tasks and behaviors, along with advanced techniques like symmetrical loss and intervention training for learning a whole-body humanoid controlling policy in simulation, HugWBC enables real-world humanoid robots to produce various natural gaits, including walking (running), jumping, standing, and hopping, with customizable parameters such as frequency, foot swing height, further combined with different body height, waist rotation, and body pitch, all in one single policy. Beyond locomotion, HUGWBC also supports real-time interventions from external upper-body controllers like teleoperation, enabling loco-manipulation while maintaining precise control under any locomotive behavior. Our experiments validate the high tracking accuracy and robustness of HUGWBC with/without upper-body intervention for all commands, and we further provide an in-depth analysis of how the various commands affect humanoid movement and offer insights into the relationships between these commands. To our knowledge, HugWBC is the first humanoid whole-body controller that supports such fine-grained locomotion behaviors with high robustness and flexibility.

Problem

• Enhance humanoid robot locomotion versatility
• Develop unified whole-body controller for diverse gaits
• Enable customizable parameters and real-time interventions

Innovation

• Unified whole-body control for versatile locomotion
• Simulation-based learning with symmetrical loss
• Real-time intervention for loco-manipulation