Papers
57
Total Citations
1,520
H-Index
21
About
Xieyuanli Chen is a leading researcher in autonomous robotics and intelligent perception, with expertise spanning LiDAR-based localization, 3D scene understanding, simultaneous localization and mapping (SLAM), and mobile robot navigation. His work has made significant contributions to how autonomous systems perceive and interact with dynamic environments. Chen's most influential contributions include pioneering learning-based approaches for moving object segmentation in 3D LiDAR data (237 citations), enabling robots to build consistent maps and avoid collisions in real-world settings. His OverlapTransformer network (196 citations) advanced place recognition by introducing an efficient, yaw-angle-invariant architecture critical for loop closure in SLAM systems. His comprehensive survey on global LiDAR localization (108 citations) has become an important reference for the broader robotics community. Beyond localization, Chen has tackled practical challenges such as compressing dense 3D point cloud maps for storage efficiency (99 citations), real-time LiDAR segmentation on embedded platforms (95 citations), and long-term indoor localization using semantic floor plan maps. His earlier work on monocular vision-LiDAR SLAM for urban search and rescue demonstrates a longstanding commitment to real-world robotic applications. With over 900 cumulative citations, Chen's research meaningfully advances the state of autonomous robot perception and navigation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3A Survey on Global LiDAR Localization: Challenges, Advances and Open Problems108 citations · 2024
- 4Deep Compression for Dense Point Cloud Maps99 citations · 2021
- 5
- 6LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloud59 citations · 2024
- 7
- 8
- 9
- 10Long-Term Localization Using Semantic Cues in Floor Plan Maps39 citations · 2022