Approaches to Self-Driving Cars

What are the approaches used to make self-driving cars? Why does the path to full autonomous car always seems to always be 5 years away? In this video we’ll answer these questions and talk about the major approaches taken by the major players in the field like Tesla, , Waymo, and MobilEye. Spoiler alert: you need to take a data driven development using primarily a deep learning approach to address this massive task. Moreover, I’ll review the paper “Autonomy 2.0: Why is self-driving always 5 years away?“ in which they propose a fully end-to-end differentiable path to autonomy, using only deep neural networks. ## Autonomy 2.0: Why is self-driving always 5 years away? ## Abstract: “Despite the numerous successes of machine learning over the past decade (image recognition, decision-making, NLP, image synthesis), self-driving technology has not yet followed the same trend. In this paper, we study the history, composition, and development bottlenecks of t