Technology

Development and use of cooperative perception for CAVs

Cooperative perception

Cooperative perception, or collective perception (CP) is an emerging and promising technology for intelligent transportation systems (ITS), and its development and demonstration has been the focus of a recently completed iMOVE project.

That project was DSRC and cooperative perception, about which in December last year we published a progress report, available at Road safety lift: CAVs can now see around corners. iMOVE’s participants on the project were Cohda Wireless, and the University of Sydney’s Australian Centre for Field Robotics.

Project objectives

The DSRC and cooperative perception project’s objectives were:

1. Development of fundamental multi-vehicle cooperative framework that can enable a number of commercial applications of DSRC technology.
2. Development of consistent and efficient data fusion algorithms that can operate across four vehicle scenarios:

  • Single road user tracking from a stationary platform
  • Multiple road users tracking from a stationary platform
  • Multiple road users tracking from a moving platform
  • Cross-platform data fusion (fusing posed estimates of multiple targets associated with uncertainty from multiple inhomogeneous platforms)

These scenarios cover most typical V2X interactions.

3. Demonstration of safety/automation benefit in low DSRC penetration environments.

Demonstrations

The final report, Development and Demonstrations of Cooperative Perception for Connected and Automated Vehicles, outlines the experiments used to demonstrate the use of CP to:

  •  improve awareness of vulnerable road users and thus safety for CAVs in various traffic scenarios
  •  show that CAVs can autonomously and safely interact with walking and running pedestrians, relying only on the CP information received from other ITS-stations through V2X communication
  •  report the handling of collective perception messages (CPMs) received from multiple ITS-stations, and through data fusion and multiple road user tracking, enabling path-planning/decision-making within the CAV

These demonstrations were performed in simulated and real-world traffic environments using a manually-driven CV, a fully autonomous CAV, and intelligent roadside units (IRSU) platforms retrofitted with vision and laser sensors and a road user tracking system.

This project is one of the first demonstrations of urban vehicle automation using only CP information.

Report findings

The experiment and demonstration undertaken in this project were to bring a focus to the question of the safety and robustness of cooperative perception in the operation of CAVs on public roads. That’s the CP framework, in concert with intelligent roadside units and CAV platforms developed by the ACFR and Cohda Wireless.

CP also reduces the load on individual vehicles’ local perception capabilities and can improve the robustness and safety of AVs. Its use could also result in a lowering of tech requirements and cost of vehicles’ onboard sensing systems.

Additionally, the report considered what work might follow on from this project. That will be a:

    …focus on developing more advanced and ready-to-deploy ITS-S platforms that can better suit the future road transportation and building an open standard high definition (HD) map for CP enabled autonomous driving purpose. A comprehensive set of algorithms will also be developed towards safer, lower cost, and more efficient operation of CAVs, exploiting the HD map, V2X, and CP technologies. Lastly, we will aim to test the developed CP and CAV technologies in more sophisticated traffic environments.

Download the report, watch the webinar

For your copy of the final report please click the button below.

You might also want to hear Professor Paul Alexander of Cohda Wireless and Professor Eduardo Nebot and Dr Mao Shan of the Australian Centre for Field Robotics speak about this project in our October 2021 webinar, VIDEO: C-ITS projects leading the way in Australia.

DOWNLOAD THE FINAL REPORT

More from iMOVE

Most Popular

To Top