A California start-up working on artificial intelligence-powered mapping software for self-driving cars today received $6.6 million from a group of investors that includes the Ford Motor Company.
Like other automakers, Ford is testing its autonomous car technology in Michigan and on public roads in California, where its engineers are evaluating the sensors that detect and track objects in the vehicle’s view. But the company’s investment in the AI mapping start-up, called Civil Maps, reflects the important role that AI and machine learning play in interpreting information from those sensors.
Civil Maps has developed software that can process raw 3D data from LiDAR (high-resolution laser imaging), cameras, and other sensors on autonomous vehicles into a machine-readable format.
“Autonomous vehicles require a totally new kind of map,” the company’s CEO Sravan Puttagunta said in a statement. “Civil Maps’ scalable map generation process enables fully autonomous vehicles to drive like humans do—identifying on-road and off-road features even when they might be missing, deteriorated or hidden from view and letting a car know what it can expect along its route.”
A video offers a real world example of how the technology works. On a street in downtown San Francisco, a car’s computer processes the view from a forward facing-camera into several components. At the bottom are the lanes: the computer recognizes the white dashed markers and separates the street into three different color-coded lanes.