They can partner with software companies—but may end up following their leadby Hod Lipson, Melba Kurman / May 19, 2017 / Leave a comment
When human drivers let intelligent software take the wheel, driverless cars will offer billions of people all over the world a safer and more convenient mode of transport. In an ideal future, our roads will glisten with swarms of tightly packed driverless cars. Moving in schools like fish, these cars will demonstrate extraordinary anti-collision abilities, effortlessly navigating through streets full of pedestrians and falling gracefully into fuel-efficient formations on long, empty stretches of motorway. Some cars will carry a passenger or two. Others will be empty, on their way to drop off a pizza or to pick up a child from school.
The exact configurations vary, but most driverless cars today use several digital cameras, a radar sensor, and a laser-radar (lidar) device to “see” where they’re going. These cars pair a global positioning system (GPS) device with another location device called an inertial measurement unit (IMU) that compensates for GPS inaccuracies. An onboard computer takes the information streaming in from the sensors and GPS, folds that data onto a high-definition map that contains stored information on crossroads and traffic lights, and processes it into a 3D model called an “occupancy grid.” Software knits all this data together and provides driverless cars with artificial vision that is increasingly accurate and responsive.