Press Space to continue
Finding signal on Twitter is more difficult than it used to be. We curate the best tweets on topics like AI, startups, and product development every weekday so you can focus on what matters.
Press Space to continue
Press Space to continue
Avoiding a pothole is a harder computer vision problem than avoiding a pedestrian. NASA's JPL robotics lab has called negative obstacles, holes instead of objects, one of the most difficult problems in autonomous driving. The reason is pure geometry. An object sticking up from the road stays visible as you approach. The angle it takes up in a camera's view shrinks in proportion to distance. A hole shrinks in proportion to distance squared. Double your distance from a pedestrian and they look…