Dongming Fang

Papers

Total Citations

H-Index

About

Dongming Fang is a robotics researcher specializing in autonomous navigation, particularly for indoor mobile robots. His work focuses on solving the critical challenge of reliable self-localization and mapping in environments where traditional SLAM (Simultaneous Localization and Mapping) methods can fail. Fang’s key contribution is a robust algorithm for global map establishment using content-based image matching, which enables robots to recover from "kidnapped robot" scenarios—situations where collisions or visual ambiguities cause localization failure. This approach is especially tailored for floor-cleaning robots, which must operate reliably in cluttered, repetitive indoor spaces. His most-cited paper, "Keyframes Global Map Establishing Method for Robot Localization through Content-Based Image Matching" (2017), has garnered 3 citations, reflecting its niche but practical impact on applied robotics. Fang’s work addresses a persistent industry problem, offering a computationally efficient alternative to more fragile localization techniques. By improving map robustness against similar-looking objects and sensor disturbances, his research helps bridge the gap between academic SLAM theory and real-world deployment in service robotics.