Guanqun Ding

National Institute of Advanced Industrial Science and Technology

Papers

Total Citations

H-Index

About

Guanqun Ding is a rising researcher in robotics and autonomous systems, with a primary focus on multimodal sensor fusion for odometry estimation. His most-cited work, "TransFusionOdom: Transformer-Based LiDAR-Inertial Fusion Odometry Estimation" (2023, 19 citations), introduces a novel learning-based framework that integrates LiDAR and inertial data using transformer architectures. This contribution addresses a critical challenge in mobile robotics—enhancing odometry accuracy and robustness without relying on handcrafted designs. By leveraging attention mechanisms, Ding's approach effectively fuses heterogeneous sensor streams, improving performance in complex environments where traditional methods falter. His work is part of a broader effort to advance deep learning for state estimation, and it has quickly gained recognition for its innovative fusion strategy. Ding’s research holds significant implications for autonomous navigation, particularly in applications requiring reliable localization under dynamic or degraded conditions. As a young scholar, his early citation impact signals a promising trajectory, with TransFusionOdom serving as a foundational piece for future developments in transformer-based sensor fusion.