Master Thesis in Perception for Automated Driving from June 2023

We are committed to shape the future of automotive mobility by developing highly automated driving systems for both highway and urban areas. Our development teams in Germany and California work with state-of-the-art technologies to develop innovative and class-leading systems to provide our customers with the best experience possible. To master this challenge, we are looking for energetic and committed master students to conduct research within our Perception Team in Stuttgart in the following area:



Since current trajectory prediction methods tend to fail in abnormal scenarios, it is of major interest to test the prediction algorithms in all possible situations. However, the abnormal scenarios are rare and often not available in the recorded data. Therefore, the focus of your master thesis will be on the development of learning-based scenario generation for the training and the evaluation of the prediction algorithms. This includes the development of generative models as well as the evaluation of the quality of the generated scenes.

Responsibilities

• Assessment of the current state-of-the-art in the area of trajectory generation
  
• Development of learning-based trajectory generation algorithms using machine-learning techniques
  
• Implementation of a corresponding training and evaluation concept
  
• Evaluation of the scenario generation method in terms of fidelity, diversity, criticality and controllability
  

The final thesis selection is made in close consultation with you, the university and us.

• Master’s student in computer science, robotics, physics, mathematics, electrical engineering or adjacent fields
  
• Excellent programming skills in Python
  
• Strong knowledge and in-depth understanding of machine learning techniques, especially neural networks, and the corresponding software frameworks
  
• Experience with Linux and development on Linux Systems
  
• Fluency in spoken and written English
  
• Ability to think ahead / Independence
  

Preferred Qualifications

• Knowledge in the area of generative models and motion prediction
  
• Excellent communication skills and desire to work as part of a global team in a multi-cultural environment
  
• High intrinsic motivation to perform cutting-edge research
  
• Fluent proficiency in spoken and written German (optional)
  

Additional information:

The job will be full time at our research and development location in Sindelfingen.

It doesn’t work completely without formalities. When sending your online application, please attach your CV, certificate of enrollment, current performance record, relevant certificates (max. 5 MB) and mark your application documents as "relevant for this application" in the online form.

Please find the criteria of empl oyment here.
Citizens of countries outside the European Trade Union please send, if applicable, your residence / work permit.

We particularly welcome online applications from candidates with disabilities or similar impairments in direct response to this job advertisement. If you have any questions, you can contact the local disability officer once you have submitted your application form, who will gladly assist you in the onward application process: SBV-Sindelfingen@mercedes-benz.com.

Please understand that we no longer accept paper applications and that there is no right to get your documents returned.

If you have any questions regarding the application process, please contact HR Services by e-mail at hrservices@mercedes-benz.com or t he Chat-Bot on our career page via the plus symbol.

Optional: If you have any questions concerning the position, please contact Julian Wiederer at the following mail julian.wiederer@mercedes-benz.com.