Self-Driving Cars for Unmapped Country Roads: System Navigates Using Only GPS and Sensors
Companies like Google only test their self-driving car fleets in cities where they've also spent hours labeling the exact 3-D positions of lanes, off-ramps, and stop signs. Streets that are unpaved, unlit, or unreliably marked are more complicated to map, and get a lot less traffic, so companies have less incentive to develop 3-D maps for them. One way around this is to create systems advanced enough to navigate without these maps. MIT researchers have developed MapLite, a framework that allows self-driving cars to drive on roads they've never been on before, without 3-D map. MapLite combines simple GPS data that you'd find on Google Maps with a series of perception sensors, including LIDAR, that observe the road conditions.