Master Thesis in Validation and Optimization of Controllers Using Foundation Models

Master Thesis in Validation and Optimization of Controllers Using Foundation Models

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

• During your thesis you will focus on the validation of controllers for nonlinear dynamical systems and explore a data-driven validation approach.
• You will identify requirements for the closed-loop simulation of dynamic systems to enable benchmarking of different controllers.
• For model selection you will conduct a literature review to identify and compare state-of-the-art foundation model architectures for modeling dynamic systems.
• You will design and implement a data-driven workflow, which includes developing a strategy for data selection, data preparation, and fine-tuning the selected foundation models. Additional measurements for data generation can be done when needed.
• Furthermore, you will systematically evaluate the accuracy of the fine-tuned models. This also includes a comparison with traditional physics-based and data-based models and an analysis of the model's performance, especially in identifying of corner cases.
• Additionally, you will integrate the fine-tuned model into a closed-loop simulation environment (e.g., in Python/MATLAB). This will be used to validate the performance of existing controllers and explore possibilities for their optimization.
• Finally, you will analyze the trade-offs between model accuracy, simulation speed, and the required computational resources to provide recommendations for practical applications.

Qualifications

• Education: Master studies in the field of Engineering, Computer Science, Robotics, Mathematics or comparable
• Experience and Knowledge: experience with dynamic systems and simulation, machine learning, system identification and control theory
• Personality and Working Practice: you excel at motivated self-management, communicating complex issues clearly, and independently structuring tasks 
• Work Routine: your on-site presence is required
• Languages: fluent in English

Additional Information

Start: according to prior agreement
Duration: 6 months

Requirement for this thesis is the enrollment at university. Please attach your CV, transcript of records, examination regulations and if indicated a valid work and residence permit.

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity.

Need further information about the job?
Ozan Demir (Functional Department)
+49 711 811 45250
Luiz Douat (Functional Department)
+49 711 811 24526

Work #LikeABosch starts here: Apply now!

#LI-DNI