Thesis in the field of expansion and validation of an AI-based comfort Full-time

Aufgaben In view of the constantly increasing availability of data and growing customer demands, the use of machine learning (ML) in the vehicle sector is becoming more and more relevant. Driving functions based on ML algorithms are increasingly being researched and developed, particularly in the powertrain area
When starting off with high acceleration or on difficult surfaces such as ice or snow, a lack of grip can cause the wheels to spin. Although conventional traction control (ASR) prevents the wheels from spinning, abrupt interventions can occur that strongly influence the torque desired by the driver. The aim of the work is to further develop an existing AI model for the early detection of spinning wheels in the drivetrain. In addition, uncertainty estimation (UE) approaches are to be implemented in order to investigate the robustness of the predictions and increase confidence in the model. Subsequently, it will be evaluated to what extent UE approaches are suitable for detecting incorrect model predictions
The work includes the following tasks:

• Conducting a literature review on the current state of the art
• Checking the measurement data and associated labels for plausibility and extracting relevant time series for training the model
• Selection and adaptation of a suitable model architecture through hyperparameter tuning to optimize model performance
• Validation of the trained model using test data
• Selection and implementation of UE methods for multivariate time series
• Evaluation of the effectiveness of UE methods for detecting implausible model predictions

The final topic will be determined in consultation with the university, you and us
Qualifikationen

• Master’s degree in engineering, computer science, mathematics, data science or a comparable course of study
• Language skills: Very good written and spoken German and English skills
• Other knowledge
  • Very good knowledge in the field of machine learning
  • Good knowledge of Python and data science libraries
• Personal skills: Structured and independent work, communication skills, commitment, creativity and initiative

Additional information:
Of course, we are not completely without formalities. Please apply online only and enclose a CV, current certificate of enrolment stating the semester of study, current transcript of records, relevant certificates (max. total size of attachments 5 MB) and mark your application documents as “relevant for this application” in the online form.
Further information on the recruitment criteria can be found”here”
Nationals from countries outside the European Economic Area should send their residence/work permit with their application
We particularly welcome online applications from severely disabled persons and persons with equivalent disabilities. If you have any questions, you can also contact the site’s representative for severely disabled employees at SBV-Sindelfingen@mercedes-benz.com, who will be happy to support you in the further application process after your application
Please understand that we no longer accept paper applications and that there is no entitlement to return postage
If you have any questions about the application process, please contact HR Services by e-mail at myhrservice@mercedes-benz.com or by phone: 0711/17-99000 (Monday to Friday between 10 a.m. – 12 p.m. and 1 p.m. – 3 p.m.)