Papers
4
Total Citations
60
H-Index
3
About
Lang Wu is a leading researcher in mobile robotics, with key contributions spanning LiDAR-based global localization, 3D object recognition, and visual-inertial SLAM. His most influential work, "Efficient and Reliable LiDAR-Based Global Localization Using Multiscale/Resolution Maps" (2021, 45 citations), tackles the challenge of large-scale structured environments by introducing an optimized branch and bound (BnB) algorithm that dramatically reduces search space for robust global localization. Wu further advanced 3D perception with "HCCG: Efficient High Compatibility Correspondence Grouping" (2022, 10 citations), enabling accurate object recognition and 6D pose estimation in cluttered scenes. In dynamic environments, his visual-inertial SLAM framework (2024) leverages spatiotemporal consistency optimization to overcome the limitations of static-environment assumptions. Most recently, Wu developed a real-time framework for generating multi-directional traversability maps (2024), addressing terrain anisotropy in unstructured settings—a critical step for autonomous ground robot navigation. With a growing citation footprint and a focus on practical, real-world deployment, Wu’s work bridges theoretical rigor and applied robotics, making him a rising figure in autonomous navigation and perception systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4