Model Validation for Credible Simulation
Description
As simulation becomes a cornerstone of virtual testing and validation in automotive and other industries, ensuring the credibility of simulation models is paramount. Credible simulation requires validated models that accurately represent real-world behavior across domains such as vehicle dynamics, sensors, traffic, and environment. This training provides participants with knowledge about the methodology, the metrics, and the important aspects during data collection and re-simulation to validate simulation models on the example of perception sensor models. The goal is to support safety argumentation and regulatory compliance in virtual validation workflows.
Who should attend?
This training is intended for simulation engineers, model developers, validation specialists, software architects, test engineers, and project managers involved in virtual validation. It is also relevant for researchers, tool vendors, and anyone responsible for ensuring the credibility of simulation models used in safety-critical applications.
Course Objectives
By the end of this one-day course, participants will: Understand the principles and requirements for credible simulation / Learn ways to derive requirements and relevant effects for simulation models / Learn the importance of reference data accuracy and re-simulation of measurements / Learn methods and metrics for validating simulation models / Gain practical insight into sensor model verification, validation, and uncertainty quantification / Explore workflows and tools that support model credibility and traceability / Identify best practices for documentation and evidence generation in model validation.
Course Contents
- Introduction to Credible Simulation
- Definition and importance of Credible Simulation.
- Regulatory and safety requirements for model validation.
- Co-Simulation Concepts
- Definition and benefits of co-simulation for credible simulation.
- Benefits of standards in heterogeneous simulation environments.
- Model Validation Methodology
- Verification vs. validation: concepts and differences.
- Uncertainty quantification and sensitivity analysis.
- Metrics for model validation.
- Domain-Specific Validation
- Validation of vehicle dynamics models.
- Traffic behavior model validation.
- Environment and 3D asset quality.
- Sensor model validation.
- Case Studies and Best Practices
- Real-world example of sensor model validation.
- Requirements / analysis of relevant effects.
- Measurement conduction.
- Re-simulation of measurements.
- Validation with qualified metrics.
- Lessons learned and common pitfalls.
- Real-world example of sensor model validation.
- Discussion & Outlook
- Virtual proving grounds.
- Continuous validation.
- Opportunities for participants’ projects.
Philipp Rosenberger
Persival GmbH
Philipp Rosenberger is co-founder and CEO of Persival GmbH, which supports sensor manufacturers and OEMs in the specification, development and validation of perception sensor models. He recently finished his PhD thesis on "Metrics for Specification, Validation, and Uncertainty Prediction for Credibility in Simulation of Active Perception Sensor Systems".Until the end of 2022, he has been working for six years as a research assistant at the Institute of Automotive Engineering at the Technical University of Darmstadt under the supervision of Prof. Dr. rer. nat. Hermann Winner. In the European project "ENABLE-S3" he led the work package for simulation and stimulation and in the German project "PEGASUS" he was responsible for the development and validation of sensor models. Recently, he was involved in the German projects "SET Level" and "Verification & Validation Methods" to continue his work on model development and validation. He is also a founding member and part of the Change Control Board of the ASAM OSI standard. Together with his research group at TUDa FZD, he founded the PerCollECT initiative to collect and provide perception sensor cause-effect chains in a tree-like ontology. Furthermore, he is an active contributor to the open source perception sensor models of the asc(s e.V. - ENVITED Open Source Model & Simulation Library.
| Date | Language | Price | Code |
|---|---|---|---|
| 30 Oct 2025 | Deutsch 
|
890 EUR (1090 EUR from 03 Oct 2025 ) | 4682 |
| Venue | |||
| Alzenau (carhs.training gmbh, Siemensstraße 12, 63755 Alzenau) | » Register | ||
| Instructor | |||
| Philipp Rosenberger (Persival GmbH) | |||
| Seminar hours | |||
| Thursday | 09:00 - 17:00 | ||
| Date | Language | Price | Code |
|---|---|---|---|
| 12 May - 13 May 2026 | English  |
890 EUR (1090 EUR from 15 Apr 2026 ) | 4684 |
| Venue | |||
| Online (Online-Seminar) | » Register | ||
| Instructor | |||
| Philipp Rosenberger (Persival GmbH) | |||
| Seminar hours | |||
| Tuesday | 09:00 - 13:00 | ||
| Wednesday | 09:00 - 13:00 | ||
| Date | Language | Price | Code |
|---|---|---|---|
| 08 Oct 2026 | Deutsch
|
890 EUR (1090 EUR from 11 Sep 2026 ) | 4683 |
| Venue | |||
| Alzenau (carhs.training gmbh, Siemensstraße 12, 63755 Alzenau) | » Register | ||
| Instructor | |||
| Philipp Rosenberger (Persival GmbH) | |||
| Seminar hours | |||
| Thursday | 09:00 - 17:00 | ||
This course is available as an in-house seminar. The trainer comes to your site - you save travel expenses and travel time. Get an offer.
Your contact person
Dr. Dirk Ulrich
Phone.: 06023 - 96 40 - 66
E-Mail: dirk.ulrich@carhs.de
All prices are exclusive of VAT.