Papers
12
Total Citations
188
H-Index
7
About
Luping Wang is a computer vision and robotics researcher whose work centers on enabling mobile robots to perceive, understand, and navigate complex real-world environments using monocular vision. His most significant contributions revolve around leveraging the geometric properties of spatial right-angles and corner projections to help robots interpret both indoor and outdoor scenes — a deceptively elegant approach that sidesteps the computational burden of many conventional methods. Wang's foundational 2018 papers on visual navigation and indoor scene understanding through spatial right-angle projections (44 and 28 citations respectively) established a distinctive research thread he has developed systematically across Manhattan and non-Manhattan structures, curved corridors, and cluttered obstacle environments. His 2022 work on semantic SLAM-based dense mapping for large-scale dynamic outdoor environments (34 citations) demonstrates a broadening scope, integrating semantic understanding with simultaneous localization and mapping. More recently, Wang has extended these principles to unstructured field environments, tackling winding and bending pathways where irregular features and varying illumination pose acute challenges. Across his portfolio, Wang's cumulative citation impact exceeds 180, reflecting meaningful influence within the robotics and computer vision communities. His research offers practical value for autonomous home robots, medical supply delivery systems, and field robotics — making his geometric projection framework both theoretically interesting and immediately applicable.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Understanding of indoor scenes based on projection of spatial rectangles28 citations · 2018
- 4
- 5
- 6Reconstruction for Indoor Scenes Based on an Interpretable Inference17 citations · 2021
- 7
- 8
- 9
- 10