ZytleBot: FPGA Integrated Development Platform for ROS Based Autonomous Mobile Robot

Abstract

The FPT2019 FPGA Design Competition is a competition aimed at recommending innovations in utilizing FPGAs to realize level 5 autonomous driving vehicles. We have developed "ZytleBot", an ROS based robot utilizing FPGA for the contest. ZytleBot calculates all processing necessary for autonomous driving in realtime within a programmable SoC. Therefore, it is possible to go around the course imitating an actual road, detect signals and obstacles and take appropriate behavior without any external operation. Robot development requires a wide range of knowledge and technology, but we have proceeded robot development efficiently by using ROS, a robot development middleware, and TurtleBot3, a robot development platform. As an application of FPGA, road surface image preprocessing and traffic signal detector using machine learning is implemented in the FPGA. The traffic signal detector uses HOG features and SVM classifiers, which runs over 270 times faster than running on the processor. We also provide ZytleBot as a platform for efficient development of FPGA integrated ROS robots.