General Humanoid Whole-Body Control via Pretraining and Fast Adaptation

2026-02-12

AI Summary

This work addresses the limitations of humanoid robots in high-dynamic scenarios—specifically, insufficient motion diversity, difficulty in rapid adaptation, and poor balance robustness—by introducing the FAST framework. FAST integrates a Parseval-guided residual policy adaptation mechanism with centroid-aware control, leveraging a lightweight delta policy regularized by orthogonality and KL divergence constraints. This enables efficient fine-tuning and stable tracking of out-of-distribution actions on top of a pretrained base policy. Experimental results demonstrate that FAST significantly outperforms state-of-the-art methods in both simulation and real-world deployment, achieving notable advances in adaptation efficiency, dynamic balance robustness, and generalization capability.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Learning a general whole-body controller for humanoid robots remains challenging due to the diversity of motion distributions, the difficulty of fast adaptation, and the need for robust balance in high-dynamic scenarios. Existing approaches often require task-specific training or suffer from performance degradation when adapting to new motions. In this paper, we present FAST, a general humanoid whole-body control framework that enables Fast Adaptation and Stable Motion Tracking. FAST introduces Parseval-Guided Residual Policy Adaptation, which learns a lightweight delta action policy under orthogonality and KL constraints, enabling efficient adaptation to out-of-distribution motions while mitigating catastrophic forgetting. To further improve physical robustness, we propose Center-of-Mass-Aware Control, which incorporates CoM-related observations and objectives to enhance balance when tracking challenging reference motions. Extensive experiments in simulation and real-world deployment demonstrate that FAST consistently outperforms state-of-the-art baselines in robustness, adaptation efficiency, and generalization.

Problem

• humanoid whole-body control
• fast adaptation
• motion generalization
• robust balance
• out-of-distribution motion

Innovation

• Fast Adaptation
• Whole-Body Control
• Residual Policy Adaptation
• Center-of-Mass-Aware Control
• Humanoid Robotics