Can Gong

Wuhan University of Science and Technology

Papers

Total Citations

H-Index

About

Can Gong is a researcher at the forefront of autonomous robotic navigation, with a primary focus on visual SLAM (Simultaneous Localization and Mapping) systems designed for dynamic, real-world environments. His most-cited work, "Real-time visual SLAM based YOLO-Fastest for dynamic scenes" (2024, 14 citations), addresses a critical limitation of traditional SLAM—its reliance on static scenes—by integrating lightweight object detection to filter out moving objects in real time. This contribution enhances the robustness and accuracy of autonomous robots operating in unpredictable settings, such as crowded urban spaces or industrial floors. Gong’s research bridges computer vision and robotics, demonstrating how efficient deep learning models like YOLO-Fastest can be leveraged for practical, high-speed perception. His work is particularly notable for its emphasis on real-time performance, a key requirement for deployment in autonomous vehicles and drones. With growing citations, Gong is establishing himself as a rising voice in the field, pushing SLAM technology beyond controlled labs into the messy, dynamic world where robots must truly navigate.