Ding Li

University of British Columbia, National University of Defense Technology

Papers

Total Citations

H-Index

About

Ding Li is a researcher advancing the frontiers of autonomous systems, with a primary focus on LiDAR perception, multi-robot coordination, and self-supervised learning for 3D mapping. His most impactful contribution is **LiCaS3**, a novel self-supervised method for synchronizing LiDAR and camera data—a critical challenge in sensor fusion for autonomous driving and robotics. This work, which has garnered 10 citations since its 2022 publication, demonstrates how deep learning can eliminate the need for manual temporal calibration, enabling more robust and scalable perception systems. Li also developed **DeepMapping2**, a self-supervised framework for large-scale LiDAR map optimization that addresses the limitations of prior work by improving convergence on complex, real-world datasets. In the domain of multi-robot systems, his research on distributed intelligence for cooperative communication explores how data aggregation and multi-hop routing can enhance coordination among robot teams. By tackling both sensor-level calibration and system-level communication, Ding Li’s work bridges critical gaps in building reliable, autonomous agents that operate in dynamic environments. His contributions are particularly relevant for students and researchers working on sensor fusion, SLAM, and multi-agent systems.