As well as using LiDAR for its autonomous vehicles to navigate in the snow, Ford is using the technology to do so in the dark. The carmaker has tested one of its Fusion Hybrid autonomous research vehicles at its Arizona Proving Ground in conditions too dark for a human driver to see where they were going.
Ford explains that, typically, the virtual driver software in its autonomous vehicles employs LiDAR along with radar and cameras in order to navigate. Despite this, the test shows that LiDAR alone is enough for a vehicle to navigate autonomously in the dark.
UPGRADE TO NEW ATLAS PLUS
More than 1,500 New Atlas Plus subscribers directly support our journalism, and get access to our premium ad-free site and email newsletter. Join them for just US$19 a year.UPGRADE
"Thanks to LiDAR, the test cars aren't reliant on the sun shining, nor cameras detecting painted white lines on the asphalt," says Ford's technical leader for autonomous vehicles Jim McBride. "In fact, LiDAR allows autonomous cars to drive just as well in the dark as they do in the light of day."
To achieve this, Ford uses high-resolution 3D maps, with LiDAR pulses used to locate a car on the map in real time. During the test, the Fusion was operated in what Ford describes as "pitch black," with its headlights switched off. The car was monitored by engineers with night-vision goggles and there was an operator in the driver's seat to take control of the vehicle if necessary.
"As I rode in the back seat, I was following the car's progression in real time using computer monitoring," explains research scientist and engineer Wayne Williams. "Sure enough, it stayed precisely on track along those winding roads."
The video below shows the Fusion driving autonomously in the dark, with some of the LiDAR's 2.8 million infrared pulses a second able to be seen.