Papers
2
Total Citations
15
H-Index
2
About
Bo Zeng is a researcher advancing the frontier of visual SLAM (Simultaneous Localization and Mapping) for mobile robots, with a specific focus on robust performance in dynamic, real-world environments. His key research areas include semantic SLAM, dynamic scene understanding, and stereo vision-based localization. Zeng’s major contribution lies in developing methods to overcome the traditional static-scene assumption that limits conventional SLAM algorithms. In his highly cited 2022 work on “Data association and loop closure in semantic dynamic SLAM,” he introduced a table retrieval method that integrates semantic information to accurately distinguish between static and dynamic objects, achieving 12 citations. Building on this, his 2023 paper on DFPC-SLAM proposed a dynamic feature point constraints approach using stereo vision, which explicitly classifies feature points as dynamic or static from semantic cues, significantly improving accuracy in cluttered environments. Though early in his career, Zeng’s work is already shaping how robots perceive and navigate in changing spaces, with his papers serving as foundational references for researchers tackling the challenge of robust SLAM in dynamic settings. His achievements highlight a promising trajectory in autonomous robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2