What the hell have we been working on if not that? What good is an autonomous driving system that is not able to consider what happens next?!?!?!?!????
Not crashing into fences. It's still an ongoing area of research in computer vision on how to detect repetitive objects made out of thin parts. Radar cannot reliably detect them due to being thin and optical methods are not yet advanced enough.
Presumably that? I think the author is just saying that it's going to get better.
He is not privy to what his competitors have been working on, in any case, except whatever has been announced publicly. (Unless he is doing industrial espionage.) Maybe it's just that Voyage's cars weren't predicting up until now?
I don't think there's any implication that the technology is perfect in my comment. But the idea that e.g. Waymo's software is not making some attempt at predicting future states, even implicitly, is absurd. This video[1] was released two years ago and references prediction at the provided timestamp.
We've been working on the prediction problem for some time. We should have a blog post coming out about our approach (it's pretty neat and in-line with this post) soon.
That's great to hear! I think upon fully reading the blog post it's clear that you meant the next leap forward it solving prediction, to the degree that perception has supposedly been solved. It will be interesting to see how y'all do. I for one want my self driving car yesterday.