X-Loco: Towards Generalist Humanoid Locomotion Control via Synergetic Policy Distillation

2026-03-04

AI Summary

Humanoid robots struggle to achieve diverse and often conflicting motor skills—such as upright walking, fall recovery, and whole-body coordination—using a single control policy. To address this challenge, this work proposes a multi-expert collaborative training framework that integrates a context-aware expert selection mechanism with collaborative policy distillation. This approach enables a student policy, relying solely on visual inputs and velocity commands, to learn general-purpose locomotion control in an end-to-end manner. Notably, the method achieves the first vision-driven, unified controller that operates without reference motion priors, demonstrating strong performance in tasks like fall recovery and traversal of complex terrains. Ablation studies further confirm its significant advantages in knowledge transfer efficiency and multi-skill integration.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

While recent advances have demonstrated strong performance in individual humanoid skills such as upright locomotion, fall recovery and whole-body coordination, learning a single policy that masters all these skills remains challenging due to the diverse dynamics and conflicting control objectives involved. To address this, we introduce X-Loco, a framework for training a vision-based generalist humanoid locomotion policy. X-Loco trains multiple oracle specialist policies and adopts a synergetic policy distillation with a case-adaptive specialist selection mechanism, which dynamically leverages multiple specialist policies to guide a vision-based student policy. This design enables the student to acquire a broad spectrum of locomotion skills, ranging from fall recovery to terrain traversal and whole-body coordination skills. To the best of our knowledge, X-Loco is the first framework to demonstrate vision-based humanoid locomotion that jointly integrates upright locomotion, whole-body coordination and fall recovery, while operating solely under velocity commands without relying on reference motions. Experimental results show that X-Loco achieves superior performance, demonstrated by tasks such as fall recovery and terrain traversal. Ablation studies further highlight that our framework effectively leverages specialist expertise and enhances learning efficiency.

Problem

• humanoid locomotion
• generalist policy
• fall recovery
• whole-body coordination
• policy distillation

Innovation

• synergetic policy distillation
• generalist humanoid locomotion
• vision-based control
• specialist policy selection
• fall recovery