Le Sun
Papers
2
Total Citations
9
H-Index
2
About
Le Sun’s research focuses on advancing spatial data modeling and robotic perception, with key contributions in probabilistic mapping and dynamic obstacle detection. In his most cited work, “Kernel-specific Gaussian process for predicting pipe wall thickness maps” (2015, 6 citations), Sun tackled the challenge of modeling 2.5D spatial data—such as elevation and thickness maps—by developing a kernel-specific Gaussian process that captures spatial dependencies with high accuracy. This work has implications for robotics and geostatistics, enabling more reliable predictions in environments where data is organized in grids. Sun also addressed industrial safety in “Dynamic Obstacle Detection Based on Background Compensation in Robot’s Movement Space” (2017, 3 citations), proposing a method to quickly detect moving obstacles in a robot’s predefined path by compensating for background motion. This contribution enhances real-time perception for collaborative robots in dynamic workspaces. While his citation counts reflect a developing impact, Sun’s work bridges probabilistic modeling and practical robotics, offering foundational techniques for spatial inference and safe human-robot interaction. His research is particularly relevant for students and engineers working on autonomous navigation, industrial automation, and environmental monitoring.
Research Focus
Key Achievements
Top Papers
- 1Kernel-specific Gaussian process for predicting pipe wall thickness maps6 citations · 2015
- 2