Aus Aifbportal
Wechseln zu:Navigation, Suche

Machine Learning applied to Automated/Autonomous Driving - Learning Cost Metrics for Cooperative Driving

Information on the Thesis

Type of Final Thesis: Master
Supervisor: Karl Kurzer
Research Group: Applied Technical Cognitive Systems

Archive Number: 4.406
Status of Thesis: In Progress
Date of start: 2019-11-27

Further Information

Automated, cooperative vehicles have to make decisions in road traffic in a highly dynamic, interacting and incompletely perceptible environment. Previous attempts are usually limited to situation assessment from an egocentric perspective, without taking cooperation aspects into account, or interactions between other road users.


The goal of this work is to use the create behavior models of drivers in situations that require cooperation. As the manual creation of such models is difficult and time consuming, it should be learned from data, specifically with the help of inverse reinforcement learning. Instead of using a reward function as in classical reinforcement learning, now the reward function or a parameterization of the same is being optimized to fit the data, leading to a concise description of the behavior.


  • An interdisciplinary research environment with partners from science and industry
  • A constructive collaboration with bright, motivated employees
  • A pleasant working atmosphere


  • Knowledge in depth and breadth in the field of artificial intelligence, game theory or closely related areas
  • Ability to implement both state of the art, as well as experimental algorithms
  • Good C++ (C++11, STL, etc.) and Python Skills
  • Sound English skills
  • High creativity and productivity
  • Experiences with planning procedures, e.g. Monte Carlo Tree Search/Reinforcement Learning are a plus


  • current transcript of records
  • CV


Karl Kurzer