MIT is challenging companies running self-driving cars using HD Maps
3-D maps limit the places where self-driving cars can operate, this is a reality that self-driving cars. While millions of miles in the U.S. alone still remains unmapped, companies creating HD Maps are not going to be ready with HD Maps of all the country anytime soon, as there is no incentive to do that. Then, how can self-driving cars relying on HD Maps be ready to navigate across the country?
MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) is challenging this thought prevailing in the autonomous car industry that HD Maps are the only way to run these cars in the future. They are suggesting a new approach to create systems advanced enough to navigate without these very high detailed maps.
CSAIL’s Director Daniela Rus and his colleagues have named this concept called MapLite [Access the PDF], a framework that allows self-driving cars to drive on roads they’ve never been on before without 3-D maps.
As part of a collaboration with the Toyota Research Institute, researchers used a Toyota Prius that they outfitted with a range of LIDAR and IMU sensors. MapLite combines simple GPS data that you’d find on Google Maps with a series of sensors that observe the road conditions. In tandem, these two elements allowed the team to autonomously drive on multiple unpaved country roads in Devens, Massachusetts, and reliably detect the road more than 100 feet in advance.
Another challenge with HD Maps is the sheer size and volume of data. “Maps for even a small city tend to be gigabytes; to scale to the whole country, you’d need incredibly high-speed connections and massive servers,” says Teddy Ort, a graduate student in robotics at the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory. “But for our approach, a global map could fit on a flash drive.”