USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
USER is a unified system designed to enable online policy learning in real-world physical environments. It solves challenges by integrating a hardware abstraction layer for diverse robots, an adaptive communication plane for cloud-edge training, and a fully asynchronous learning framework with persistent data management. This creates an extensible foundation capable of handling multi-robot coordination and large models in the real world.