Most of the existing and under development autonomous vehicles rely on local sensors, such as cameras and LiDARs, to perceive the environment and interact with other road users. Despite significant advances in sensor technology in recent years, such setups typically still can’t detect hazards that aren’t in direct line of sight.
Now, researchers have developed a new technology that uses other vehicles and roadside cameras to do that job. New disruptive technology allows autonomous vehicles to track running pedestrians hidden behind buildings and cyclists obscured by larger cars, trucks, and buses. The project is developed via a collaboration between the University of Sydney and Australian tech company Cohda Wireless and is funded by Australia’s iMOVE Cooperative Research Centre.
The experimental “collective perception” (CP) system incorporates both vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. Using roadside ITS (intelligent transportation systems) stations equipped with additional sensors such as cameras and LiDAR, the car utilizing the technology receives data transmitted from vehicles ahead of it. The approaching car’s driver is alerted via an X-ray-style display that shows the location of the hidden danger obscured by fast-moving vehicles.
This allows autonomous vehicles to tap into various viewpoints. Being hooked up to the one system significantly increases the range of perception, allowing connected vehicles to see things they wouldn’t normally do. Using the ITS system, the connected autonomous vehicle also manages to take pre-emptive action: braking and stopping.
During the field tests, the CP technology successfully demonstrated its ability to safely interact with walking pedestrians, responding based on the perception information provided by the roadside ITS station. It also demonstrated the expected behavior of a connected vehicle when interacting with a pedestrian rushing towards a designated crossing area. The pedestrian tracking, prediction, path planning, and decision-making were based on the perception information received from the ITS roadside stations.
The engineers and scientists developing the technology said it 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,” said Professor Eduardo Nebot from the Australian Centre for Field Robotics.