How Self-Driving Cars Sense the Road and Why Sensor Choices Divide the Industry
Autonomous vehicles now operate commercially in places like Austin, Texas, though they remain imperfect, as shown by a recent San Francisco incident involving a pedestrian. Self-driving systems run a continuous loop of sensing, predicting, deciding and acting, which must complete in tens of milliseconds. Because automated systems detect hazards almost instantly, they can begin braking far sooner than human drivers, who need roughly a second and a half to react. Companies disagree on hardware: Waymo combines lidar, radar and cameras for redundancy, while Tesla dropped radar and relies mainly on cameras and neural networks. Each sensor type has weaknesses in conditions like rain and fog, which is why critics question camera-only designs.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.


Discussion (0)
Log in to join the discussion and vote.
Log in