I am currently pursuing a Ph.D. at The University of Hong Kong (HKU). I completed both my bachelor’s and master’s degrees with honors at Sun Yat-sen University.
My research focuses on autonomy in intelligent mobile systems, with a particular interest in perception in dynamic environments for robotic interaction. This involves robust localization in complex and degenerate scenarios, constructing detailed geometric and semantic models, scene abstraction and understanding, and lifelong learning for autonomous mapping in unfamiliar settings.
A comprehensive multi-LiDAR, multi-scenario dataset that extensively incorporates segments of real-world geometric degeneracy.
A LiDAR-centric localization and mapping approach that enhances the accuracy and resilience of SLAM methods across diverse environments, particularly in scenarios with LiDAR degradation.
A centralized system to facilitate collaborative LiDAR-ranging-inertial state estimation, enabling robotic swarms to operate without the need for anchor deployment, and demonstrating significant enhancements in the accuracy of collaborative SLAM estimates.
DCL-SLAM is presented, a front-end agnostic fully distributed collaborative Light Detection And Ranging SLAM framework to co-localize in an unknown environment with low information exchange and achieves higher accuracy and lower bandwidth than other state-of-the-art multirobot LiDAR SLAM systems.