Time Management and Real-Time Capabilities of Parallel and Distributed Simulation for the Virtual Development and Validation of Automated Driving Functions

Third party funded individual grant


Project Details

Project leader:
Prof. Dr. Reinhard German

Project members:
Wojciech Baron

Contributing FAU Organisations:
Computer Science 7 (Computer Networks and Communication Systems)

Funding source: andere Förderorganisation (INI.FAU)
Start date: 01/10/2018
End date: 30/09/2021


Research Fields

Quality of Service
Computer Science 7 (Computer Networks and Communication Systems)
Connected Mobility
Computer Science 7 (Computer Networks and Communication Systems)


Abstract (technical / expert description):

Distributed simulations are often used to improve performance or to couple different simulators. This coupling is very important for the simulation of autonomous driving functions, because reusable simulation components can be created for the closer and wider environment of the vehicle, for the ego and other vehicles, for sensor technology, for procedures in the control units, for vehicle dynamics and for similar aspects and can be executed together in a simulation. Furthermore, such a distributed simulation provides a starting point for coupling with real software or hardware components (SIL or HIL). Time management in the distributed simulation must ensure causality: if there are deviations in the assignment of simulation time to real-time in the components, causality violations can occur. One example is cooperative safety functions, where actions take place in a very fast sequence. Reasons for causality violations can be, for example, non-synchronized clocks or delays in message delivery. Another task of the time management is to ensure the reproducibility of the simulation results. Jitter in the execution time of individual components or during message transmission results in a non-determinism in the execution sequence, which can lead to a different simulation result.

Last updated on 2019-01-04 at 16:29