Shangxing Wang

Beijing University of Civil Engineering and Architecture

Papers

Total Citations

H-Index

About

Shangxing Wang is a researcher whose work lies at the intersection of robotics, computer vision, and semantic intelligence, with a primary focus on improving autonomous navigation in complex, real-world settings. His most-cited contribution, "A Semantic Information-Based Optimized vSLAM in Indoor Dynamic Environments" (2023, 10 citations), addresses a critical limitation in traditional visual Simultaneous Localization and Mapping (vSLAM) systems, which typically assume static scenes. Wang’s key innovation involves integrating semantic information to enable mobile robots to robustly perform positioning and mapping tasks even in dynamic indoor environments—where moving objects like people or furniture would otherwise degrade performance. By optimizing vSLAM to handle such unpredictability, his work bridges the gap between theoretical algorithms and practical deployment, enhancing both sparse feature maps and dense map construction. This contribution is particularly valuable for service robotics and autonomous systems operating in human-centric spaces. Wang’s research underscores a growing trend toward context-aware robotics, and his findings offer a foundation for future advancements in robust, real-time navigation. With his focus on semantic optimization, he is helping to make autonomous robots more reliable and adaptable in the messy, ever-changing environments they are increasingly expected to serve.