Shupei Fan
Papers
1
Total Citations
4
H-Index
1
About
Shupei Fan is a leading researcher in energy-efficient AI hardware, specializing in multi-sensor fusion processors for autonomous systems. His work bridges the critical gap between advanced deep learning algorithms and practical hardware implementation, particularly for Bird's Eye View (BEV) fusion applications in autonomous driving and robot navigation. Fan's landmark contribution is the development of a 28nm 1.2GHz scalable vision and point cloud deep fusion processor, which achieves an impressive 5.27 TOPS/W energy efficiency. This processor features a novel CAM-based universal mapping unit that enables real-time fusion of camera and LiDAR data—a task traditionally constrained by high computational demands and memory bandwidth limitations. His 2024 paper on this architecture has already garnered significant attention, demonstrating the pressing industry need for such innovations. By tackling the substantial hardware challenges of multi-modal perception, Fan is enabling more reliable and efficient autonomous systems that can process complex environmental data in real time. His work represents a crucial step toward practical, low-power deployment of cutting-edge BEV fusion algorithms in next-generation autonomous vehicles and robotics platforms.
Research Focus
Key Achievements
Top Papers
- 1