Papers
2
Total Citations
74
H-Index
2
About
Shibo He is a leading researcher at the intersection of robotics, autonomous systems, and 3D computer vision. His work primarily focuses on enabling intelligent agents to perceive and reconstruct complex environments, with key contributions in neural implicit representations for spatial AI. He is best known for pioneering "NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction With Implicit Neural Representations" (2023, 71 citations), a landmark paper that bridges implicit neural rendering with active robotic exploration. This work introduces a novel uncertainty-driven framework that allows robots to autonomously plan view paths, dramatically improving the efficiency and completeness of 3D scene reconstruction without human intervention. Earlier in his career, He explored the foundations of mobile sensor networks in "Energy-constrained mobile sensor with motion plans for monitoring stochastic events" (2009), addressing the critical challenge of optimizing sensor movement for event capture under energy constraints. His research has profound implications for autonomous inspection, search-and-rescue robotics, and digital twin creation. With a growing citation impact, He is recognized for advancing the frontier where neural scene representations meet practical robotic autonomy.
Research Focus
Key Achievements
Top Papers
- 1
- 2