Aus Aifbportal
Wechseln zu:Navigation, Suche

Manöver- / Trajektorienplanung unter Unsicherheiten

Information on the Thesis

Type of Final Thesis: Bachelor, Master
Supervisor: Philip Schörner
Research Group: Applied Technical Cognitive Systems

Archive Number: 4.562
Status of Thesis: Open
Date of start: 2020-03-01

Further Information

Uncertainties occur in all components of the driving functions of an autonomous vehicle, from measurement uncertainties of the sensors to the own localization and the prediction of other road users up to the execution of the planned trajectory. In addition, there are uncertainties due to hidden areas, which only become clear when a situation is viewed in its entirety. In order to be able to drive safely and autonomously, these uncertainties must be recognized and taken into account.


In this context, different tasks in the field of environment representation, scene interpretation and maneuver/trajectory planning are assigned to extend existing components and to develop new components with the aim to make autonomous driving safer and more risk conscious. The work may include the following topics:

  • (Further) development of environment models
  • Determination of the field of view, detection of occlusions and determination of free space
  • Applying Reachable Sets
  • Work with probabilistic planning procedures such as Partially Observable Markov Decision Processes
  • Integration of uncertainties of environmental perception, localization and execution into the planning components
  • Evaluation and interpretation of the results in simulation, on real data or an test vehicle


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


  • Ability to implement both state of the art, as well as experimental algorithms
  • Good C++ (C++11, STL, etc.) Skills
  • Sound English skills
  • High creativity and productivity
  • Experiences with planning procedures are a plus


  • current transcript of records
  • CV


Philip Schörner