Tesla’s Head of AI Says The Firm Uses a Harder Approach to Self-Driving for Scalability Reasons

Earlier this week, Tesla’s head of Artificial Intelligence (AI) Andrej Karpathy took part in a CVPR’20 workshop on Scalability in Autonomous Driving during which he discussed the firm’s approach to self-driving. In the talk, he confessed that Tesla is using a harder approach to autonomous driving but one that is more likely to scale properly.

The executive gave a presentation where he shared two videos: one of Tesla’s self-driving car doing a turn and one of Waymo’s doing the same. He explained that while both turns looked identical, the decision making behind them was very different…

Kaparthy went on to say that Tesla is working on a scalable self-driving system deployable in millions of cars which is why the firm is using a vision-based approach. Because it is easier to scale.