USER: A Unified and Extensible System for Real-World Online Policy Learning
Overview
USER is a system for real-world online policy learning in embodied AI, integrating hardware abstraction, adaptive communication, and asynchronous training. It supports multi-robot coordination and cloud-edge training with large models, establishing a foundation for real-world policy learning in 2026.
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsUSER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
USER is a system designed for real-world online policy learning in embodied AI, addressing the challenges of real-world environments by integrating hardware abstraction, adaptive communication, and asynchronous training. It supports multi-robot coordination, heterogeneous manipulators, and cloud-edge training with large models, establishing a foundation for real-world policy learning.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).