And that’s a very big step in the right direction if you want to see self-driving cars everywhere. Currently, so many self-driving cars are tested in cities because there is an abundance of detailed 3D mapping data that not only lets the cars know where all the roads go, but how high things like curbs are. But in order for self-serving cars to ever truly be able to take the place of driven ones, they’ll need to go everywhere our current vehicles can–including out into the countryside where detailed maps are sometimes lacking.
That’s where MIT’s new MapLite project comes in, reports Engadget. MapLite is a framework that allows self-driving cars to navigate without the help of 3D maps. The framework works by sensing the car’s GPS location and then uses the car’s sensors to select a local endpoint to drive to that its sensors can “see.” MapLite still has objectives to overcome (it doesn’t work well on mountainous roads), but it’s excellent proof of concept that shows detailed 3D maps aren’t needed for everywhere a self-driving car may find itself.