Intensification Phase Cluster 1 - Safe automated mobility
The topics and projects of Cluster 1, Cluster 2 and Cluster 3 from the start-up phase will be brought together and worked on in SAFIR Cluster (SC) 1 "Safe Automated Mobility" under the leadership of Prof. Dr. Andreas Riener. SC 1 is dedicated to increasing road safety in increasingly automated mobility. The focus of the MIRASOFT project (IP 6) is on mixed real-virtual testing, especially with regard to the safeguarding of AVF when interacting with vulnerable road users (VRUs). The mixed reality environment, implemented on the basis of OpenX standards, should make it possible in the future to test the safety of series-produced vehicles in a reproducible manner with little effort and intervention. The COSINUS project (IP 7) is concerned with the reliability of automotive sensor systems and their transmission components from the perspective of a global safety system. Here, too, the focus is on VRUs and, through exemplary validation of C2X applications on motorcycles, statements are made about the reliability of control units (e.g., through "predictive health monitoring") and communication itself in load situations. The impulse project HyMne (IP 8) is dedicated to validation using artificial intelligence (AI) methods. Based on real-life tests, for example, AI methods are to be used to generate scenarios for testing the AVF and an evaluation methodology for the quality of training data is to be developed. Furthermore, a method for validating the robustness of applied AI methods will be implemented.
Impulse project 6: MIRASOFT - Mixed Reality-supported safeguarding of safety-critical automated driving functions
Building on the results of the set-up phase, the further development of the MR environment on the basis of open, standardised interfaces is being driven forward in three sub-projects (TPs) in impulse project IP1. The results of MIRASOFT, synchronised with the exploratory project EP1 Autobit as well as the architecture project IIP2, which will run from 2023, are to lead to an extended NCAP-based test scenario. In addition to the individual research contributions in the key topics, IIP1 MIRASOFT shows how auto-mated vehicles could be safeguarded in the future based on simulation.
Impulse Project 7: "Reliability Enhancement of the Global Security System Including VRUs" (COSINUS)
Impulse Project 7 "Increasing the Reliability of the Global Security System with the Inclusion of VRUs" makes a contribution to the global security system based on sensor technology, communication technology and test systems using digitalisation. For this purpose, the focus is on innovative subsystems as well as communication per se.
Impulse Project 8: Hybrid Models and AI Methods for Safe Mobility (HyMne) - Data Generation and Data Quality
In addition to simulations, real driving tests are indispensable for testing systems that cause autonomous intervention in the longitudinal or lateral dynamics of a vehicle. Due to the high costs of real-life tests, it is necessary to identify few but "relevant" function-specific test scenarios, to realise them reproducibly in the vehicle and to evaluate them afterwards. Simulations can be used to identify and analyse the "relevant" test scenarios, but also data from traffic scenarios recorded during journeys on public roads. In the intensification phase, bridges between the simulation and the real world are to be created in the safeguarding process with the help of AI methods. The advantages of AI methods are to be used in a targeted manner.
Impuls Project 10: Localization and control in combined indoor and outdoor scenarios (KASINO)
The level of automation in modern vehicles is constantly increasing. Vehicles must take over more and more tasks from the driver and master them reliably. To make this possible, the vehicle must be able to determine its own position precisely in every situation, e.g. on highways, in inner cities, in tunnels and parking garages. Satellite-based systems are used for this purpose outdoors. In indoor areas, however, these are not available, therefore different positioning systems must be used. These systems often differ greatly from each other both in their interface and in their precision.
Impulse Project 11 (IP11): SINUS Safety Functions in Future Complex Communication Situations
The SINUS (Safety Functions in Future Complex Communication Situations) project aims to improve the road safety of connected and automated vehicles. Connected vehicles are vehicles equipped with V2X communication, which enables them to communicate with each other. In addition, V2X communication can enable cooperative driving in automated vehicles. Connected and automated vehicles will improve road safety, efficiency, and comfort through increased sensor information.
Impulsprojekt 12: AURORA - Functionalsafety for Automotive Objekt Recognition of Optical sensors by state monitoring of CameRAs (Kopie 1)
Vehicle sensors, crucial for safety-relevant environment detection, degrade over time. The AURORA project, led by Prof. Elger, is cantered on Predictive Health Monitoring to anticipate this degradation, ensuring enhanced safety. Car2X communication, a pivotal feature, provides comprehensive data, both internal and external. The project's ambition is not only to refine the SelfX diagnostic function but also to use advanced machine learning algorithms. These algorithms are designed to identify potential sensor malfunctions early, further safeguarding vehicular operations.
Impulse Project 13: Hybrid Models and AI Methods for Safe Mobility (HyMne 2) - Data Generation and Data Quality
With the transition to a higher degree of automated driving, new risks arise, e. g. in connection with mixed traffic, where vehicles with different degrees of automation as well as unprotected road users such as motorcyclists, cyclists and pedestrians use the same road infrastructure. This also increases the complexity and importance of ensuring the safety of vehicle functions. This is where the SAFIR Impulse Project 13 (IP13) comes in and contributes to the safeguarding of automated vehicles.
Exploratives Project 4 (EP): Cloud-based software architecture for high-automated vehicles (DRAFT)
Highly automated vehicle functions, increased entertainment, strong connectivity within the vehicle infrastructure, shorter development cycles, and many other factors will present enormous challenges for vehicle manufacturers in the future. Therefore, DRAFT aims to standardize and simplify the underlying vehicle architecture.