Self-driving cars… What could POSSIBLY go wrong? How terrible software design decisions led to Uber’s deadly 2018 crash.
NTSB says the system “did not include consideration for jaywalking pedestrians.”
Because that never happens.
As I have said numerous times before, no one does proper systems design. How could you design a “driving system” and not consider all of the things it might encounter. Like jaywalking? Bets on whether or not they considered the canonical issue of “child chasing soccer ball into street?
Like most self-driving software, Uber’s software tries to classify each object it detects into one of several categories—like car, bicycle, or “other.” Then, based on this classification, the software computes a speed and likely trajectory for the object. This system failed catastrophically in Tempe.
Self-driving cars are a good idea, in the long-run. In the short-term, I don’t believe they are quite ready for prime time. Click thru to the referenced article to see all the ways Uber went wrong.