HWC-Loco: A Hierarchical Whole-Body Control Approach to Robust Humanoid Locomotion

2025-03-02

AI Summary

Robust bipedal locomotion for humanoid robots in dynamic environments faces challenges including high modeling complexity, significant sim-to-real discrepancy, and inherent trade-offs between safety and task performance. This paper proposes a hierarchical whole-body control framework that formulates policy learning as a robust optimization problem, uniquely integrating human behavioral priors with rigid-body dynamics constraints to establish an adaptive trade-off mechanism. It explicitly models autonomous recovery capabilities under safety-critical scenarios, thereby breaking the conventional conservatism–task-success trade-off. The method unifies a hierarchical policy architecture, physics-based simulation-enhanced reinforcement learning, embedded kinematic and dynamic constraints, and cross-domain generalization training. Evaluated in both simulation and real-world deployments, the approach achieves a 42% improvement in fault recovery rate and a 31% increase in task completion rate over state-of-the-art methods, demonstrating superior performance across complex terrains, multi-configuration robots, and diverse gaits.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Safety and Robustness

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
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Humanoid robots, capable of assuming human roles in various workplaces, have become essential to the advancement of embodied intelligence. However, as robots with complex physical structures, learning a control model that can operate robustly across diverse environments remains inherently challenging, particularly under the discrepancies between training and deployment environments. In this study, we propose HWC-Loco, a robust whole-body control algorithm tailored for humanoid locomotion tasks. By reformulating policy learning as a robust optimization problem, HWC-Loco explicitly learns to recover from safety-critical scenarios. While prioritizing safety guarantees, overly conservative behavior can compromise the robot's ability to complete the given tasks. To tackle this challenge, HWC-Loco leverages a hierarchical policy for robust control. This policy can dynamically resolve the trade-off between goal-tracking and safety recovery, guided by human behavior norms and dynamic constraints. To evaluate the performance of HWC-Loco, we conduct extensive comparisons against state-of-the-art humanoid control models, demonstrating HWC-Loco's superior performance across diverse terrains, robot structures, and locomotion tasks under both simulated and real-world environments.

Problem

• Develops robust control for humanoid robots in diverse environments.
• Balances goal-tracking and safety recovery in locomotion tasks.
• Evaluates performance across terrains, structures, and real-world conditions.

Innovation

• Hierarchical policy for robust control
• Reformulates policy learning as optimization
• Dynamically balances goal-tracking and safety