DESIGN AND DEVELOP A SYSTEM FOR A DRIVERLESS CAR TO IDENTIFY HURDLES BY USING A CONVOLUTIONAL NEURAL NETWORK









Abstract

The evolution of Artificial Intelligence has catalyzed the field of technology. We can now develop things that were once just imagination. One such creation is the birth of the self-driving car. Days have come where one can do their work or even sleep in the car and without even touching the steering wheel, or accelerator you will still be able to reach your target destination safely. This paper proposes a working model of an autonomous car that's capable of driving from one location to another location or staying on different kinds of tracks such as straight tracks, curved tracks, and straight followed by curved tracks. A camera module is mounted over the top of the car with Raspberry Pi and sends the pictures from the real world to the CNN which then predicts one of the following directions. i.e. left, right, forward, and stop which is then followed by sending a signal from the Arduino to the controller of the car and as a result of it, the car moves in the desired direction without any human interaction.


Modules


Algorithms


Software And Hardware