ABSTRACT
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 biggest obstacles to reach the mass adoption are customer acceptance, cost, infrastructure, and the reliance on several onerous algorithms that include perception, lane marking detection, path planning, and variation in pathways. This study tackled the mentioned problems with a straightforward and cost-effective solution, using end-to-end learning, replacing the numerous sensors with a camera, and commandeering just the forward, backward, left, and right controls. These were optimized directly by our system with limited background processing. The project achieved this by mapping pixels from a single front-facing camera to direct steering instructions. The results obtained were better than state-of-the art and achieved the aim of the study.
