Papers
1
Total Citations
3
H-Index
1
About
Xujun Han is a rising researcher in robotics and computer vision, with a core focus on advancing visual-based pose estimation for robotic manipulation. His most cited work, "PoseFusion: Multi-Scale Keypoint Correspondence for Monocular Camera-to-Robot Pose Estimation in Robotic Manipulation" (2024), tackles a fundamental challenge in robotics: accurately determining a camera’s pose relative to a robot without relying on traditional fiducial markers. This innovation addresses the limitations of conventional calibration methods, which often fail in dynamic or unstructured environments. By introducing a multi-scale keypoint correspondence framework, Han’s approach enhances robustness and precision, enabling more flexible and reliable robot perception. Though early in his career, with this paper already garnering 3 citations, his work signals a significant step toward markerless, vision-driven robotic systems. Han’s contributions are particularly valuable for applications in autonomous manufacturing, warehouse logistics, and human-robot collaboration, where accurate pose estimation is critical. His research bridges the gap between computer vision and practical robotics, offering a scalable solution that reduces dependency on physical markers. As the field moves toward more adaptive and intelligent robots, Han’s work stands out for its potential to simplify calibration pipelines and improve real-world deployment.
Research Focus
Key Achievements
Top Papers
- 1