At this point, I'm fully convinced vision-only FSD will work and is the best approach to achieve generalized FSD first. In the future, we may have improved and cheap sensors, but for now, Tesla will win this race to a consumer-deployable generalized (90%+ of USA) robotaxi service.
I'm convinced because what Tesla is able to do with their approach and diverse data advantage. Here's one example:
Tesla is able to implement state-of-the-art approaches on the fly, test them out in their diverse fleet in all weather conditions and locales, and then re-deploy / fine-tune / unit-test on the fly. Tesla has the best iterative approach to a problem that no one has solved. Their iterations are 100x (my hyperbole) faster and more data-based than any competitor.
This is a complete myth borne by actual ignorance of what others are doing. The facts are pretty clear when you compare the content of AI DAY versus what others have presented. Tesla literally doesn’t use RL. While for others like Cruise and mobileye, RL is a huge part of their driving policy.
Tesla clearly doesn’t deal with uncertainty or reasoning which explains some of the dumb things it does while Cruise has that built into their NN architecture.
The difference in NN complexity and advancement is literally light years.
I could go on and on.
Tesla is actually behind others in their stack moving to software 2.0. They literally tell you that. It’s amazing how ignorance is bliss and people chose spreading balant lies.