Yijin Xiong

China University of Mining and Technology

Papers

Total Citations

H-Index

About

Yijin Xiong is a rising researcher in robotics and autonomous systems, whose work focuses on advancing localization, mapping, and 3D perception for dynamic environments. Xiong’s key contributions lie in developing hybrid algorithms that fuse global and local features to improve robustness in challenging conditions. Their most cited work, “GF-SLAM: A Novel Hybrid Localization Method Incorporating Global and Arc Features” (2024, 8 citations), introduces a simultaneous localization and mapping system that adaptively operates when external signals are unstable, effectively mitigating cumulative errors common in local methods—a critical advancement for agricultural and field robotics. Xiong also explores scene flow estimation for LiDAR point clouds, as seen in “Multiscale Neighborhood Cluster Scene Flow Prior for LiDAR Point Clouds” (2024, 1 citation), addressing the difficult task of predicting point-wise 3D displacement from sparse sequential data. This work has direct applications in autonomous driving and robotics, where accurate motion perception is essential. Though early in their career, Xiong’s innovative integration of multiscale priors and hybrid SLAM architectures demonstrates a clear trajectory toward solving real-world navigation challenges. Their research is particularly valuable for students and engineers working on robust perception systems for GPS-denied or unstructured environments.