AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910929791221760 |
|---|---|
| author | Li, Jialong Cheng, Xuxin Huang, Tianshu Yang, Shiqi Qiu, Ri-Zhao Wang, Xiaolong |
| author_facet | Li, Jialong Cheng, Xuxin Huang, Tianshu Yang, Shiqi Qiu, Ri-Zhao Wang, Xiaolong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03738 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control Li, Jialong Cheng, Xuxin Huang, Tianshu Yang, Shiqi Qiu, Ri-Zhao Wang, Xiaolong Robotics Artificial Intelligence Machine Learning 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. |
| title | AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2505.03738 |