Papers
2
Total Citations
18
H-Index
2
About
Kunyuan Xu is a robotics researcher whose work focuses on two critical challenges in autonomous systems: robust localization for mobile robots and precise manipulation for industrial automation. In his highly cited 2020 paper, Xu introduced a novel loop closure detection approach using simplified structures for low-cost LiDAR, directly addressing the fundamental problem of cumulative error in simultaneous localization and mapping (SLAM). His method enables fast and accurate loop detection, significantly improving global localization stability—a breakthrough that has earned 13 citations and influences cost-effective robot navigation solutions. Xu’s 2019 work tackles the equally demanding task of rapid grasping of small industrial parts from cluttered charging trays. By developing a practical RGB-D sensor-based method, he achieved rapid detection and fine pose estimation of textureless, dark objects in chaotic production line environments. This contribution, cited 5 times, demonstrates his ability to solve real-world industrial challenges where traditional vision systems fail. Xu’s research bridges the gap between theoretical SLAM advances and practical automation needs, making him a notable figure in both robotic perception and manufacturing efficiency.
Research Focus
Key Achievements
Top Papers
- 1
- 2