Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization

Embodied AI and Robotics LLO SRT Robot Morphologies
2025年09月02日
我们提出了一种统一的通用运动策略，该策略在50种不同的足式机器人上进行了训练。通过结合改进的、感知本体结构的网络架构（URMAv2）与基于性能的课程学习方法，以应对极端的本体随机化，我们的策略学会了控制数百万种形态各异的机器人。该策略能够实现零样本迁移，成功应用于未见过的真实世界人形和四足机器人。
We present a single, general locomotion policy trained on a diverse collection of 50 legged robots. By combining an improved embodiment-aware architecture (URMAv2) with a performance-based curriculum for extreme Embodiment Randomization, our policy learns to control millions of morphological variations. Our policy achieves zero-shot transfer to unseen real-world humanoid and quadruped robots.
许愿