Exactly, dude came on here saying “single modality sensors”. As if humans that are deaf can’t drive with just their eyes. Humans have been doing it with 2 cameras for a century (2 eyes).

He probably works at a startup as an intern or junior ai engineer.

Tesla sticthes like 5 cameras. The problem isn’t object detection, or localization it’s decision making (path finding and planning) to get from A to B that is the hard part.

He has no clue