+++ At DLR, we are always looking for bright minds – even during the current exceptional circumstances. Our current vacancies can be found here. +++

My knowledge is shaping the future.

Bookmark
Course paper / final thesis

Machine learning in traffic control

Starting date

1 November 2021

Duration of contract

6 months

Type of employment

Full-time (part-time possible)

Traffic management is the key to increasing road traffic efficiency. What is needed here are new concepts for the organisation and operation of transport. We deliver them as the result of well-founded research. Important: The corresponding information on the current traffic situation must be recorded as the basis for all traffic control procedures.The tasks can thus be divided into two areas: the development of innovative methods for monitoring traffic (traffic recording) and the development of methods for influencing traffic flows (traffic influencing). The Institute's work focuses primarily on the management of large transport systems, for example in conurbations and at catastrophes and major events.

The Institute of Transportation Systems in Berlin is researching new methods for developing future-oriented solutions in the field of traffic control with the help of vehicle-to-infrastructure communication (V2I). Emergency vehicles play a significant role here. The prioritization of these in emergency cases poses major challenges for safe and efficient traffic control. The task of modern traffic management will therefore be, to provide an intelligent infrastructure that enables such vehicles to drive quickly and safely while at the same time having minimal effects on other road users. For this purpose, new technologies of connectivity and artificial intelligence are to be accessed.

Using a special method from the field of machine learning, so-called reinforcement learning, strategies for prioritizing emergency vehicles in a connected traffic system are to be examined. With the help of the microscopic traffic simulator SUMO and the use of existing machine learning libraries, selected traffic scenarios from the application of connected driving will be implemented. The training results are to be analyzed with regard to possible improvements for traffic behavior through these control strategies. The aim is to  understand whether such ai controllers can provide feasible optimizations for traffic management.

This topic should be worked on in the context of existing project tasks in combination with a bachelor's or master's thesis.

Your qualifications:

  • Field of study: engineering or computer science, ideally with reference to traffic, automotive or similar
  • Programming: good knowledge of Python
  • Basic knowledge of machine learning
  • Basic knowledge in dealing with SUMO
  • Interest in traffic research, motivation, commitment and independent work

Your benefits:

Look forward to a fulfilling job with an employer who appreciates your commitment and supports your personal and professional development. Our unique infrastructure offers you a working environment in which you have unparalleled scope to develop your creative ideas and accomplish your professional objectives. Our human resources policy places great value on a healthy family and work-life-balance as well as equal opportunities for persons of all genders (f/m/x). Individuals with disabilities will be given preferential consideration in the event their qualifications are equivalent to those of other candidates.

  • Apply online now
  • You can send this job advertisement via e-mail and complete your application on a personal computer or laptop.

    We need your digital application documents (PDF). The document upload function is not supported by all mobile devices. Please complete your application on a PC/laptop.

    Complete application on PC

Technical contact

Robert Alms
Institute of Transportation Systems

Phone: +49 30 67055-9680

Send message

Vacancy 59096

HR department Berlin

Send message

DLR site Berlin

To location

DLR Institute of Transportation Systems

To institute