Smart Autonomous Vehicle Using End to End Learning

Autonomous Driving has passed the point of being called the next big step, as the smart car revolution is already taking shape around the world. Self-driving cars are relevant if not prevalent and the main obstacles to reach mass adoption are customer acceptance, cost, infrastructure and the reliance on several onerous algorithms that include perception, lane detection, path planning and variation in pathways. The objective of this research paper is to tackle the mentioned problems with a straightforward, reproducible and cost-effective solution, using end to end learning and replacing the numerous sensors with a camera. These were optimized directly by the proposed system with limited background processing. In this research paper authors achieved this by mapping pixels from only a single front-facing camera to direct driving instructions. The results obtained were better than state of the art and achieved the aim of the study proficiently.