Xiangyan Tang

Tianjin University, Nanjing University of Science and Technology

Papers

Total Citations

H-Index

About

Xiangyan Tang is a researcher specializing in lightweight deep learning architectures for autonomous systems, with a focus on semantic segmentation and sensor fusion for small mobile robots. Their most cited work, "MIFNet: A lightweight multiscale information fusion network" (2021, 29 citations), introduces an efficient neural network that balances accuracy and computational efficiency for semantic segmentation in Internet of Things applications, including industrial robotics and self-driving vehicles. This contribution addresses the critical challenge of deploying deep learning on resource-constrained platforms. Tang’s earlier research tackled real-world perception problems for small ground robots with limited load capacity and computing resources. In "Road detection in image by fusion laser points based on fuzzy SVM" (2015, 4 citations), they proposed an online-updating fuzzy support vector machine method for robust road detection in complex outdoor environments. Similarly, "Obstacle detection based on image and laser points fusion for a small ground robot" (2015, 4 citations) introduced a fuzzy clustering-based approach for fusing laser and image data to detect obstacles. Tang’s work demonstrates a consistent focus on enabling practical, efficient perception for autonomous systems operating under severe computational constraints.