Thesis in Improvement of situation prediction for real-world traffic scenarios starting October 2021

I like to invite you to shape with us the future of mobility around self-driving cars. Our department in Böblingen-Hulb designs and develops new approaches for the field of autonomous driving to increase driving comfort and safety. In this Master Thesis, you have the opportunity to gain insights into the future technology of autonomous driving. Looking further into the future, studies on cooperative maneuver tuning concepts are required.

For this purpose, we share a common environment model over all participating road agents. This means that all cooperative vehicles communicate objects detected with their on-board sensors to other road users via V2X communication. With this information, a common environment is constructed. This provides the possibility, to enlarge the vehicle’s sensor range, virtually. Moreover, the prediction of the traffic situation regarding all involved traffic participants is an important issue. In our department, we developed data driven machine-learning models for situation prediction. As part of this work, we want to control interacting vehicles, e. g. during on-ramp merge, with this network. This extension is intended to integrate real-world traffic behavior (especially at intersection areas) into the simulation.
Goal:

• Incorporation into the existing neural network
  
• Analyze the network for the suitability of the new, extended approach
  
• Possibly adaptation of the network
  
• Implementation of the simulation environment for following the predicted trajectories
  
• Evaluation and analysis of the simulation environment

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

Are you ready for #nextbigthing?

Professional qualifications

• Experience in the field of neural networks
  
• Java, C, C++, Python
  
• Master’s students in (technical) computer science, electrical engineering, mechatronics, science subjects such as physics/mathematics or similar disciplines
  
• Fluent language skills in German and English, both orally and in writing
  
• First experience in software development (preferably in Python/Matlab)
  
• Knowledge in the field of classification/machine learning/deep learning in particular data handling (clean separation of test & evaluation data sets) & metrics as well as in handling Unix/Linux systems are an advantage
  

Personal skills

• Pleasure in scientific work and practical problem solving
  
• Independent and engaged style of work

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).
Please find the criteria of employment 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@daimler.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@daimler.com. or the chatbot on our career page via the plus symbol.