The car came to rest more than 70 metres away, on the opposite side of the road, leaving a trail of wreckage. According to witnesses, the Model S burst into flames while still airborne. Several passersby tried to open the doors and rescue the driver, but they couldn’t unlock the car. When they heard explosions and saw flames through the windows, they retreated. Even the firefighters, who arrived 20 minutes later, could do nothing but watch the Tesla burn.
At that moment, Rita Meier was unaware of the crash. She tried calling her husband, but he didn’t pick up. When he still hadn’t returned her call hours later – highly unusual for this devoted father – she attempted to track his car using Tesla’s app. It no longer worked. By the time police officers rang her doorbell late that night, Meier was already bracing for the worst.
Bad code. Guinea pig owners. Cars not communicating with each other. Relying on just the car’s vision and location is stupid.
If they would use lidar you would get speed and distance from surrounding objects, which seems like valuable data for a moving object. With cameras you get a 2d picture that can only guestimate distance using multiple cameras and software.
Also, not only do they rely on “just vision”, crucially they rely on real-time processing without any memory or persistent mapping.
This, more than anything else is what bewilders me most.
They could map an area, and when observing a construction hazard save that data and share it with other vehicles so they know when route setting or anticipate the object. Not they don’t. If it drives past a hazard and goes around the block it has to figure out how to navigate the hazard again with no familiarity. That’s so foolish.
and what’s even more ridiculous than that (imo) is that if every tesla mapped the area, you’d get it from loads of different angles: no more “oops 1 off computer vision edge case”
indeed. new experiences should be remembered…like a human.