In early 2018, it seemed like autonomous cars were ready to hit public roads. Then a self-driving Uber struck and killed a woman one night in Tempe, Arizona. The incident got folks worried and also highlighted this tech’s big flaw: It cannot reliably recognize hazards in all conditions. Even an untimely glare can mess with a car’s perception.
Autonomy - Relies - Suite - Tech - GPS
All-the-time autonomy relies on a suite of tech. GPS tells the car the best route, while sensors—radar, lidar, and cameras—spy obstacles. An artificially intelligent computer processes those inputs to make rapid decisions: slam the brakes for a person, or go through a leaf.
Vehicles must train for hundreds of thousands of hours to learn every hazard in every condition. Automakers can log that...