Ziquan Wang
Papers
1
Total Citations
11
H-Index
1
About
Ziquan Wang is a researcher in robotics and computer vision, with a primary focus on simultaneous localization and mapping (SLAM) in dynamic environments. His most notable contribution is the development of SIIS-SLAM (2022), a visual SLAM system that leverages sequential image instance segmentation to robustly filter out dynamic objects—such as moving pedestrians or vehicles—that typically degrade mapping accuracy. By building upon the ORB-SLAM3 framework, Wang’s approach significantly enhances the reliability of autonomous robot navigation in real-world, unpredictable settings. This work has garnered 11 citations, reflecting its relevance to the growing field of dynamic SLAM. Wang’s research addresses a critical bottleneck in robotics: enabling machines to perceive and map environments that are constantly changing, which is essential for applications like autonomous driving, service robotics, and augmented reality. His work stands out for its practical integration of deep learning-based segmentation with classical SLAM pipelines, offering a scalable solution for robust spatial intelligence.
Research Focus
Key Achievements
Top Papers
- 1SIIS-SLAM: A Vision SLAM Based on Sequential Image Instance Segmentation11 citations · 2022