Development of a vehicle for driving with Convolutional Neural Network

Abstract

The aim of this paper is the design, simulation, construction and programming of the autonomous vehicle, capable of obstacle avoidance, object tracking also image and video processing. The vehicle will use a built-in camera for evaluating and navigating the terrain, a six-axis accelerometer and gyro for calculating angular velocities and accelerations, Arduino for interfacing with motors as well as with Raspberry Pi which is the main on-board computer. The design of the vehicle is performed in Autodesk Fusion 360. Most of the mechanical parts have been 3D printed. In order to control the chassis of the vehicle through the microcontrollers, the development of the PCB was required. On top of this, a camera has been added to the vehicle, in order to achieve obstacle avoidance and perform object tracking. The video processing required to achieve these goals is done by using OpenCV and Convolutional Neural Network. Among other objectives of this paper is the detection of traffic signs. The application of the Convolutional Neural Network algorithm after some of the examinations made has shown greater precision in recognizing STOP traffic sign of different positions and occlusion ratios, and finding the path for the fastest time.