Cone Detection System with Camera and LiDAR in Formula Student Driverless Car

Formula Student is a European engineering competition whose primary goal is building a full racing car. In 2017, Formula Student Germany introduced a new class - Driverless. This category challenges teams to integrate autonomous driving technologies into their vehicles. This paper explores the development of a high-precision cone detection system for a Formula Student Driverless car by AGH Racing, which is crucial for navigating the cone-defined track limits. The entire system was implemented using the Robot Operating System (ROS) framework with Python and C++ programming languages. The developed system is based on the ZED 2i camera and the LiDAR Ouster OS1 128. This approach harnesses the strengths of both technologies: the camera's rapid and accurate image-based detection and the LiDAR's superior precision in generating a 3D point cloud of the environment.