For automated driving, the secure perception of the environment is a crucial prerequisite. The sensors and processing chains employed must meet the highest standards of reliability, precision, and realism. Currently, there are no approaches for effective and efficient validation of sensors and processing chains. To create the missing data foundation for sensor validation for automated driving, a reference system consisting of radar, camera, lidar, GNSS, and inertial sensors is to be established and integrated into a test vehicle. This reference sensor system surpasses today's production sensor technology by several years and forms the basis for accurate sensor data acquisition.
The Institute for High-Frequency Technology and Electronics (IHE) at the Karlsruhe Institute of Technology (KIT), the Hochschule Offenburg (HSO), and the Freudenberg FST GmbH are jointly developing a highly accurate radar system, which is a crucial component in the reference system for environmental perception and is periodically described by the Institute for Control and Systems Engineering (IRS) at KIT. The consortium leader, ANavS GmbH, enables the creation of an accurate representation of reality, a so-called "Ground Truth," for use in validation processes through the development of precise environmental perception and highly accurate sensor data fusion.
Within the project, the steps from simulated validation to the approval of sensors and functions will be defined and implemented by the consortium partners AKKA, FZI, IAVF, IPG, and GTÜ. The individual innovations in the validation and testing process for production sensor technology encompass AI methods for analyzing recorded scenarios, a "Sensor-in-the-Loop" test bench, integration into existing simulation tools, and a modular verification and validation process. The partners HQS and RAC are building a high-performance data platform for managing, processing, and providing reference data.
With the help of the mobile demonstrator from Dr. Ing. h.c. F. Porsche AG, initial data is recorded and utilized for the approval process of an exemplary perception system. The project has a duration from July 1, 2023, to June 30, 2026, with planned costs of approximately 10 million euros, and is supported by the Federal Ministry for Economic Affairs and Climate Action (BMWK) with approximately 5 million euros from the federal budget.
#RepliCar #AutomatedDriving #EnvironmentalPerception #SensorValidation #DataPlatform #BMWK #HQS