Master thesis: Advanced AI for time series prediction in automotive safety

at  HighSpeed Dynamics ErnstMachInstitut

The Fraunhofer-Gesellschaft
currently operates 76 institutes and research facilities in Germany and is the world’s leading organization for application-oriented research. Around 30,800 employees work on the annual research volume of 3.0 billion euros.
The Fraunhofer Institute for High-Speed Dynamics, Ernst-Mach-Institut EMI, in Freiburg with its 300 employees offers committed people challenging and varied tasks with responsibility and a lot of creative freedom. We apply the latest scientific and research findings to specific projects in an interdisciplinary manner on behalf of our customers from various sectors of industry and government. The applications are in the fields of defense, security, aerospace, automotive and aviation.
For our institute site in Freiburg, we are offering a master thesis in the Digital Engineering group on the subject of: Advanced AI for time series prediction in automotive safety engineering.

INTERESTED? APPLY ONLINE NOW. WE LOOK FORWARD TO GETTING TO KNOW YOU!

Please apply online with your complete application documents (cover letter, CV, certificate of enrollment, work permit if applicable)!
For questions about this position, please contact:
Katriya Seitz
Recruiting
Katriya.Seitz@emi.fraunhofer.de
Fraunhofer Institute for High-Speed Dynamics, Ernst-Mach-Institut EMI
Requisition Number: 72964

TASKS:

The spectrum of tasks will follow an end-to-end CRISP-DM cycle, with tasks varying in intensity according to preferences and resource allocation. Key tasks include:

• Researching and evaluating existing deep learning architectures suitable for the application at hand.
• Developing and implementing custom deep learning models tailored for predicting crash simulation propagation over time building on existing solutions.
• Designing and conducting experiments to optimize model hyperparameters and architecture.
• Evaluating model performance using appropriate metrics and validation techniques.
• Investigating techniques to improve model interpretability and explainability.
• Collaborating with domain experts to validate model predictions and refine the predictive capabilities.

• Documenting research findings, methodologies, and results for dissemination and publication.Exploring opportunities to integrate the developed models into existing crash simulation frameworks.