AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control

TL;DR

This paper introduces AMO, a hybrid framework combining reinforcement learning and trajectory optimization for real-time, adaptive whole-body control of humanoid robots, enhancing stability and operational workspace.

Contribution

AMO is a novel hybrid approach integrating sim-to-real RL with trajectory optimization, enabling adaptive and robust control of high-DoF humanoid robots.

Findings

AMO outperforms baselines in stability and workspace in simulation.

AMO demonstrates effective real-world deployment on a 29-DoF humanoid.

AMO enables autonomous task execution through imitation learning.

Abstract

Humanoid robots derive much of their dexterity from hyper-dexterous whole-body movements, enabling tasks that require a large operational workspace: such as picking objects off the ground. However, achieving these capabilities on real humanoids remains challenging due to their high degrees of freedom (DoF) and nonlinear dynamics. We propose Adaptive Motion Optimization (AMO), a framework that integrates sim-to-real reinforcement learning (RL) with trajectory optimization for real-time, adaptive whole-body control. To mitigate distribution bias in motion imitation RL, we construct a hybrid AMO dataset and train a network capable of robust, on-demand adaptation to potentially O.O.D. commands. We validate AMO in simulation and on a 29-DoF Unitree G1 humanoid robot, demonstrating superior stability and an expanded workspace compared to strong baselines. Finally, we show that AMO's consistent performance supports autonomous task execution via imitation learning, underscoring the system's versatility and robustness.