Development of Flexible Autonomous Car System Using Machine Learning and Blockchain

Abstract

Autonomous Driving car is an upcoming technology. In our project, we are taking a step towards this vision by developing a system using Raspberry Pi, image processing and machine learning and connect the system to any electric car. The proposed system provides an autonomous car feature to any existing electric car on the road that doesn’t have autonomous driving feature inbuilt within it. Most existing electric cars that are on roads don’t have this technology and this is mostly found in new and expensive cars. An alarming fact about autonomous cars is that many of them are being frequently hacked, indicating a problem related to security. The application of blockchain network, which seems to provide security and transparency in the usage of the network is employed to transfer data. Using the proposed system, such autonomous car feature can be installed separately at a cheaper expense in all existing electric cars. We aim to achieve the above by using image processing which is trained by using neural networks to create a model through which autonomous cars are achieved. With the usage of blockchain network, security and transparency of data transfer can be achieved. The hardware components used in this project are Raspberry PI 3 B microcomputer and camera module. This Raspberry Pi and camera unit forms a separate system which, when connected to the electronic control unit, helps the car to drive automatically.