Shaoting Zhu
Papers
3
Total Citations
9
H-Index
2
About
Shaoting Zhu is a rising force in robotics, specializing in bridging the critical gap between simulation and real-world deployment for legged robots. His research centers on integrating reinforcement learning, vision-language models (VLMs), and physical simulators to create robust, agile robotic systems. Zhu’s major contributions include the development of the **VR-Robo framework** (2025, 4 citations), which tackles the persistent sim-to-real gap by enhancing visual realism in training environments, enabling more reliable robot navigation and locomotion in complex settings. He also introduced **SARO** (2025, 3 citations), a space-aware system that leverages VLMs for terrain crossing in 3D environments, pushing the boundaries of how foundation models can guide quadruped robots through challenging landscapes. Additionally, his work on **Robust Robot Walker** (2025, 2 citations) addresses the practical challenge of navigating over small, undetectable obstacles—or “tiny traps”—without relying on unreliable exteroceptive sensors. Though early in his career, Zhu’s innovative approaches are already shaping the future of agile, visually-aware robotic locomotion.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Robust Robot Walker: Learning Agile Locomotion over Tiny Traps2 citations · 2025