Australian researchers have developed disruptive technology that allows autonomous vehicles to track pedestrians hidden behind buildings, and cyclists hidden by larger cars, trucks and buses.
The autonomous vehicle uses game-changing technology that allows it to “see” the world around it, including using X-rays that penetrate to blind-angled pedestrians and to detect cyclists hidden by fast-moving vehicles.
The iMOVE Cooperative Research Center-funded project, which is collaborating with the University of Sydney’s Australian Center for Field Robotics and the Australian affiliated vehicle solution company Cohda Wireless, has just published its new findings in a final report after three years of research and development.
The technology applications, which are being commercialized by Cohda, involve a new and promising technology for intelligent transport systems (ITS) called cooperative or collective perception (CP).
By using roadside ITS information sharing devices equipped with additional sensors such as cameras and lidar (“ITS stations”), vehicles can share what they “see” with others using vehicle-to-X (V2X) communication.
This allows autonomous vehicles to take advantage of different views. Being connected to one system significantly increases the range of perception, enabling connected vehicles to see things they normally would not.
The engineers and scientists who developed the technology said it could benefit all vehicles, not just those connected to the system.
“This is a game changer for both man-made and autonomous vehicles, which we hope will significantly improve the efficiency and safety of road transport,” said Professor Eduardo Nebot of the Australian Center for Field Robotics.
“The connected vehicle was able to track a pedestrian visually blocked 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, giving extra time to the driver or navigation. stuck to respond to this security risk, “he said.
Another experiment demonstrated the ability of CP technology to safely interact with pedestrians, responding to the perception information provided by the ITS station by the road.
The three-year project also demonstrated the expected behavior of a connected vehicle when interacting with a pedestrian speeding toward a designated intersection area.
“Using the ITS system, the connected autonomous vehicle managed to take preventive actions: to brake and stop before the pedestrian crossing based on the predicted movement of the pedestrian,” said Professor Nebot.
“Pedestrian tracking, prediction, route planning and decision making were based on the perception information received from ITS roadside stations.
“CP enables smart vehicles to break the physical and practical limitations of built-in perception sensors,” he said.
The leading project researcher Dr. Mao Shan said the research confirmed by using CP could improve awareness of vulnerable road users and the safety of many traffic scenarios.
“Our research has shown that a connected vehicle can ‘see’ a pedestrian around corners. More importantly, we demonstrate how connected autonomous vehicles can interact autonomously and safely with pedestrians and pedestrians, relying only on information. from the ITS roadside station, “he said.
Cohda Wireless Chief Technical Officer Professor Paul Alexander said the new technology “has the potential to increase safety in scenarios with both man-made and autonomous vehicles.”
“CP enables smart vehicles to break the physical and practical limitations of built-in perception sensors and embrace improved perception quality and robustness,” said Professor Alexander.
“This can lower the cost per vehicle to facilitate the massive implementation of CAV technology.”
Professor Alexander said that the use of CP for manually operated connected vehicles “also brings an attractive advantage by enabling perception capacity without retrofitting the vehicle with perception sensors and the associated processing unit.”
iMOVE’s CEO, Ian Christensen, said the project was a great example of the industry collaborating with scientists to unlock new innovations and commercial and public goods not only for the benefit of Australians but for road users around the world, including pedestrians and cyclists. .
“When we bring industry and scientists together, we can achieve many great things as a nation. IMOVE CRC is proud to have launched this exciting project and many others like it – which is about getting our best and most talented brains to work together about developing new technologies and innovations for problems and needs in the real world, “Christensen said.
Making self-driving cars human-friendly
Report: Development and demonstrations of collaborative perception for connected and automated vehicles: pdfhost.io/v/h1Xd1YCBM_Coopera… ption_Final_Report66
Provided by the University of Sydney
Citation: New technology gives smart cars ‘X-ray vision’, registers hidden pedestrians, cyclists (2021, 1 November) retrieved 2 November 2021 from https://techxplore.com/news/2021-11-technology-smart-cars-x – ray-vision.html
This document is subject to copyright. Except for any reasonable trade for the purpose of private investigation or research, no part may be reproduced without written permission. The content is provided for informational purposes only.