← Search

Yuze Sheng

2 accepted papers

2026

SCOPE: Skeleton Graph-Based Computation-Efficient Framework for Autonomous UAV Exploration

RA-L 2026

Autonomous exploration in unknown environments is key for mobile robots, helping them perceive, map, and make decisions in complex areas. However, current methods often rely on frequent global optimization, suffering from high computational latency and trajectory oscillation, especially on resource-

Cited by 0SourceScholar
2026

USER: A Unified and Extensible System for Online Real-World Policy Learning in Embodied AI

RSS 2026poster

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, which makes scalable data collection, heterogeneous deployment, a…

Cited by 0SourceScholar