CentralSystem - Central system for supporting automated vehicle testing and operation

The Central System project is focusing on realizing a transport system using the highest level state of the art technology to develop and demonstrate a holistic solution to support and operate autonomous vehicles in cooperation with infrastructure elements. The project targets to implement the system for testing purposes in the beginning, but should evolve for transport operation and control. In today’s mainstream for operation of highly automated vehicles the main environmental model for vehicle guidance is generated based on the ego vehicle’s perception system and eventually extended with infrastructure’s and other vehicle’s information. Our proposed solution builds up the global environment model externally in a cloud and supports the individual vehicles with a comprehensive world model or even can control them. The system will collect all information from both vehicle and infrastructure side and fuse them together in a cloud based, real time digital twin. Cloud based map content: • Static map (3D representation, vectorised data, material properties) • Semi static and semi dynamic content (like weather or lighting conditions, road conditions...) • Full dynamic data (vehicles, pedestrians and all relevant dynamic information) System properties: • Real time fusion of data using vehicle and infrastructure sensor data • Ability of recording data • Using of applicable international standards • Ability to support vehicles with real time environment model • System prepared for controlling infrastructure elements (e.g. traffic lights) or even vehicles • Support of future testing procedures for connected and automated vehicles • Scalable, reusable and future proof architecture The project is based on an exploratory phase in 2020 where the previous consortium has done a feasibility study, with a detailed literature overview of scientific papers, standards, regulations and progress and related activities. We have also organized an extensive measurement campaign on the M86 motorway, closed for public traffic, for four days. A functional sample was developed where a digital twin system was realized including infrastructure and vehicle data fusion (focusing only on pedestrian detections) through DSRC communication. In this particular project the consortium members plan to realize the system in bigger scale, extend the functionality to a certain level by implementation of particular services. The first infrastructure set would be installed on the M1-M7 highway’s common section in Hungary and also use existing Austrian road section based on the Alp.Lab test region. Further methodologies are planned to be developed related to HD mapping, testing, simulation, cloud control and traffic control.