Implementation and Improvement of Autonomous Robot Car using SoC FPGA with DPU

摘要

Autonomous driving cars currently under development use many sensors, among which CCD/CMOS cameras are the most important. To improve real-time image processing technology and FPGA utilization for autonomous driving, FPGA design contests have been held on the theme of creating an automated small robotic car using FPGA. This paper describes our FPGA robot car under development for participation in the FPGA design contest to be held at FPT2022. Our design incorporates a Xilinx SoC FPGA and uses both hardware and software for control. We use Xilinx DPU IP for object detection with Yolo v3 tiny. Furthermore, we are working on improving the stability and reliability of the FPGA robot car by modifying our previous FPGA robot car.