Driving in the dark seems like something autonomous vehicles should be able to do. After all, the technology relies on algorithms, cameras, and sensors, not light-sensitive eyes. Yet, autonomous car companies haven’t been promoting their product’s after-hours capabilities, partly because the technology just hasn’t been advanced enough.
Autonomous vehicles’ reliance on cameras is obviously out of the question in the night. Ford — the company who claims they will have autonomous technology ready by 2020 — announced today that their camera-less, self-driving darkness tests have been successful, and they released a YouTube video to prove it.
The video shows a prototype Ford Fusion navigating the company’s Arizona test track. The green tint of night vision goggles, the radioed in call of “sunset in T-5 minutes” at the top of the video, and the “Project Nightonomy” title gives the video a feeling of watching something top secret. The entire video feels like insight into a black ops mission, complete with epic background music and camouflage army helmets.
The view from the driver’s seat “is an odd feeling looking at the viewer and seeing exactly what I expected, but as soon as I look out the window all I saw was blackness,” the safety driver in the front seat states over the radio.
Despite the military theme and dramatics, the video itself is somewhat anti-climatic, which is exactly what the engineers at Ford are going for.
Testing the car in a lightless environment took out the camera element of self-driving entirely, Ford’s director of autonomous vehicle development Randy Visintainer told Re/code.
“The LIDAR, being the active laser source, was able to illuminate the space in close [proximity],” Visintainer said. “And you can see we could do the localization, object detection and tracking [with just the LIDAR]. That was the purpose of the test, to show the capability to continue to operate in the absence of the camera.”
Project Nightonomy showed that a car could rely only on LIDAR (Light Detection And Ranging) and an internal map to guide the car over a winding road in complete darkness. It’s one type of condition at which sight-reliant humans will never best autonomous vehicles.