Home >Unlabelled > Australian researchers develop X-ray vision for cars
Australian researchers develop X-ray vision for cars
By Ai4civilengineering • November 22, 2021 • • Comments : 0
Australian researchers develop X-ray vision for carsAustralian researchers have developed a promising new technology that could help autonomous vehicles track pedestrians hidden and cyclists obscured by buildings, cars, trucks and buses.
The University of Sydney’s Australian Centre for Field Robotics and Australian connected vehicle solutions company Cohda Wireless developed the technology that uses X-ray style vision to penetrate through to blind spots.
The technique, known as cooperative or collective perception, uses roadside ITS information sharing units equipped with cameras and lidar to allow vehicles to ‘see’ what other vehicles are ‘seeing’ using vehicle-to-everything (V2X) communications.
The project received funding from the iMOVE Cooperative Research Centre. Codha is commercialising the technology for intelligent transport system applications.
During a successful demonstration, the system was able to take pre-emptive action by braking and stopping before a pedestrian rushed onto the road, based on the pedestrian’s predicted movement.
Professor Eduardo Nebot from the Australian Centre for Field Robotics said the technology could benefit all vehicles, not just those connected to the system.
“This is a game changer for both human-operated and autonomous vehicles which we hope will substantially improve the efficiency and safety of road transportation,” he said.
“The connected vehicle was able to track a pedestrian visually obstructed by a building with CP information. This was achieved seconds before its local perception sensors or the driver could possibly see the same pedestrian around the corner, providing extra time for the driver or the navigation stack to react to this safety hazard.”
https://www.civilengineering.ai/australian-researchers-develop-x-ray-vision-for-cars/
Subscribe to:
Post Comments
(
Atom
)
Post a Comment