Scania and six partners recently collaborated in the PRoPART (Precise and Robust Positioning for Automated Road Transports) project that demonstrated it’s possible to pinpoint the position of a self-driving truck to within 10-centimetre accuracy. Perhaps more importantly, the Scania self-driving truck performed driving manoeuvers, including a safe lane change, with two unconnected manned cars in proximity. The ability to safely drive in proximity with other vehicles is a critical component of incorporating autonomous trucks into traffic on roadways.
To achieve the centimetre-level positioning, the PRoPART project fused data from multiple driver assistance systems, including the Galileo global navigation system, radar systems mounted along the AstraZero test area in Sweden, and the Scania truck’s own camera and front and side radars. The collaboration of perception sensor data is said to provide the Scania self-driving truck with an accurate representation of the surrounding environment, while the precise positioning helps the truck safely perform the lane change.
Infrastructure Shares Data, Too
A lot has been written about different methods for autonomous vehicles to communicate with each other and use data from their own sensors to interpret the surrounding environment. The PRoPART project goes a step further by utilizing the infrastructure itself. “In addition to positioning, we’ve also added infrastructure-to-vehicle communications,” says Project Coordinator Stefan Nord, RISE at the Swedish Research Institute. “If vehicles share information, you can extend their horizon and benefit from data from another vehicle to also look around the corner and thereby gather more data as a basis for manoeuvring decisions.”
You will find hundreds of new and used Scania trucks for sale every day on TruckLocator.