Volvo XC60 in snow

Scottish weather data could help improve self-driving cars

Self-driving cars could navigate better in poor weather and on dark nights thanks to data collected by two researchers driving a car around the Scottish Highlands.

Professor Andrew Wallace and Dr Sen Wang, from Heriot-Watt University, chased rain, snow, and fog around the rural northern roads and the urban sprawl of Edinburgh to gather the data.

As part of the road trip, the two researchers kitted out a van with light detection and ranging (lidar) radar, stereo cameras, and geo-positioning devices. The technology produced a new dataset of three hours’ worth of radar images and 200,000 tagged road objects, including other vehicles and pedestrians.

Undated handout photo issued by Heriot-Watt University of a van with light detection and ranging (LiDAR) radar, stereo cameras and geo-positioning devices

Image credit: Heriot-Watt University

According to the researchers, the information will be valuable to manufacturers and researchers of driverless vehicles as most public data currently available is based on sunny, clear days. It has also relied mainly on data collected from optical sensors, which do not work as well during bad weather.

“When a car pulls out in front of you, you try to predict what it will do – will it swerve, will it take off? That’s what autonomous vehicles will have to do, and now we have a database that can put them on that path, even in poor weather,” Dr Wang explained.

Meanwhile, Professor Wallace said that data sets are essential in developing and benchmarking perception systems for autonomous vehicles. “We’re many years from driverless cars being on the streets, but autonomous vehicles are already being used in controlled circumstances or piloting areas.”

Wallace said that the duo has shown that radar can help autonomous vehicles to navigate, map, and interpret their environment in poor weather when vision and lidar can fail.

“We need to improve the resolution of the radar, which is naturally fuzzy,” he added. “If we can combine hi-res optical images with the weather-penetrating capability of enhanced radar that takes us closer to autonomous vehicles being able to see and map better, and ultimately navigate more safely.”

Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.

Recent articles