Clever AI Turns a World of Lasers Into Maps for Self-Driving Cars

432

The greatest advantage self-driving cars hold over outdated humans is the ability to tune out distractions. No buzzing phone, yelling kids, or lovely daydream will divert attention from their primary task. That doesn’t mean they can’t get overwhelmed with information in much the same way you do.

The fully autonomous vehicles that companies like Google, Ford, and Baidu are furiously developing all rely on light detection and ranging (LIDAR) to see and map the world. Those maps are key, because they provide crucial context for the vehicles and let them focus their sensors and computing power on temporary obstacles like cars, pedestrians, and cyclists.

The problem is that LIDAR, like your eyeballs, doesn’t just notice the relevant stuff. It sees lane lines and stop signs, sure. But it also records windows on buildings, leaves on trees, garbage cans in driveways. That makes for a cluttered map. “It’s not very useable,” says Civil Maps CEO Sravan Puttagunta.

Read the source article at wired.com