Papers
1
Total Citations
31
H-Index
1
About
Zhengkun Wu is a leading researcher in robotics and computer vision, with a primary focus on advancing Simultaneous Localization and Mapping (SLAM) technologies for dynamic environments. His most cited work, "Visual SLAM Based on Semantic Segmentation and Geometric Constraints for Dynamic Indoor Environments" (2022, 31 citations), addresses a critical limitation in traditional visual SLAM algorithms: their vulnerability to moving objects that degrade localization accuracy. By integrating semantic segmentation with geometric constraints, Wu developed a robust framework that effectively filters out dynamic elements—such as people or moving furniture—while preserving static scene features for precise robot navigation. This contribution has significant implications for autonomous systems operating in real-world, unpredictable settings, from service robots to autonomous vehicles. Wu’s research bridges the gap between deep learning and classical robotics, demonstrating how semantic understanding can enhance geometric mapping. With his work gaining traction in the SLAM community, he is recognized for pushing the boundaries of reliable perception in cluttered, dynamic indoor spaces—a key step toward truly autonomous mobile robots.
Research Focus
Key Achievements
Top Papers
- 1