Earlier quoted context omitted.
In Lex fridmans interview with George Hotz, hots talks about why he thinks radar AI is a non starter and predicted that even though Tesla was still adamant about using their radar, they would eventually realize they only needed cameras. Hotz is the founder of comma.ai which is doing open source (I think?) Company.
What were his reasons? Searching the web reveals lots of machismo and assorted hero worship, but no actual solid technical arguments. Nobody in the field seems to think a vision-only solution is practical, other than Tesla, who are also not providing solid technical arguments that I can find. This IEEE item seems to summarize the situation well. https://spectrum.ieee.org/tesla-places-big-bet-vision-only-s...
If you have radar and lidar and vision, then you have at least three different specialist machine learning models running, and then another model running that takes their outputs and decides what the car is going to do. You may have even more than that, some doing specific tasks like localization.
Neural nets and vision only is a more difficult but in the long run straightforward solution. The example he brought up was alphazero vs some other chess engine that has a rook engine, and a knight engine, etc.
Basically he's backing the end to end neural network back approach over some kind of multi-sensor fusion.