Xiaoliang Ju
Papers
2
Total Citations
14
H-Index
2
About
Xiaoliang Ju is a leading researcher in mobile robotics localization, with a focus on developing robust, scene-adaptive error models for sensor fusion. Their work addresses a critical challenge in autonomous navigation: how to reliably combine data from LiDAR, visual odometry, and other exteroceptive sensors, particularly in GPS-denied environments. Ju’s key contribution is the creation of sophisticated error models that dynamically adapt to different operational scenes, dramatically improving the accuracy and reliability of vehicle localization. Their 2021 paper, "Scene-Aware Error Modeling of LiDAR/Visual Odometry for Fusion-Based Vehicle Localization," has garnered 9 citations, while their foundational 2019 work, "Learning Scene Adaptive Covariance Error Model of LiDAR Scan Matching for Fusion Based Localization," has been cited 5 times. By moving beyond static error assumptions, Ju’s research provides a practical framework for fusing disparate sensor streams—such as scan matching and visual odometry—into a cohesive, high-precision localization solution. This work is essential for advancing autonomous vehicles, field robotics, and any application requiring dependable navigation in complex, unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2