Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control

TL;DR

This paper introduces EAGLE, a distillation framework that creates a unified humanoid control policy capable of managing diverse robots and complex behaviors without extensive tuning, advancing scalable humanoid control.

Contribution

EAGLE is the first iterative distillation method that produces a single policy controlling multiple heterogeneous humanoids with rich behaviors, without per-robot reward tuning.

Findings

Achieves high tracking accuracy across multiple robots

Demonstrates robustness in real-world experiments

Outperforms existing methods in simulation and real settings

Abstract

Humanoid Whole-Body Controllers trained with reinforcement learning (RL) have recently achieved remarkable performance, yet many target a single robot embodiment. Variations in dynamics, degrees of freedom (DoFs), and kinematic topology still hinder a single policy from commanding diverse humanoids. Moreover, obtaining a generalist policy that not only transfers across embodiments but also supports richer behaviors-beyond simple walking to squatting, leaning-remains especially challenging. In this work, we tackle these obstacles by introducing EAGLE, an iterative generalist-specialist distillation framework that produces a single unified policy that controls multiple heterogeneous humanoids without per-robot reward tuning. During each cycle, embodiment-specific specialists are forked from the current generalist, refined on their respective robots, and new skills are distilled back into the generalist by training on the pooled embodiment set. Repeating this loop until performance convergence produces a robust Whole-Body Controller validated on robots such as Unitree H1, G1, and Fourier N1. We conducted experiments on five different robots in simulation and four in real-world settings. Through quantitative evaluations, EAGLE achieves high tracking accuracy and robustness compared to other methods, marking a step toward scalable, fleet-level humanoid control. See more details at https://eagle-wbc.github.io/