USER: A Unified and Extensible System for Online Real-World Policy Learning in Embodied AI
Hongzhi Zang, Shu'ang Yu, Hao Lin, Tianxing Zhou, Zefang Huang, Zhen Guo, Xin Xu, Yuze Sheng 等 17 位作者
原文摘要
Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world systems cannot be arbitrarily accelerated, cheaply reset, or massively replicated, suggesting that real-world policy learning is not merely an algorithmic problem, but inherently a systems problem. We present \user, a \underline{U}nified and extensible \underline{S}yst\underline{E}m for online real-world policy lea\underline{R}ning. On the systems side, \user introduces a hardware abstraction layer for unified robot management and an adaptive communication plane that enables efficient cloud-edge training. On the learning side, \user adopts a fully asynchronous training framework, designs a persistent and cache-aware replay buffer, and provides extensible abstractions for rewards, algorithms, and policies. Experiments in both simulation and the real world demonstrate that \user supports multi-robot coordination, heterogeneous manipulators, cloud-edge training with large models, and long-running asynchronous training. Together, these capabilities establish \user as a unified and extensible systems foundation for online real-world policy learning.
cs.RO