Thursday, August 03, 2023
Scenario fusion: Generation of driving scenarios combining real-world and generated data for automated driving
Topic and Goal of the Thesis
Vehicles are increasingly automated. But how can we prove that these vehicles are safe?
This is the central question for safety assurance of automated vehicles. For the verification, scenarios are tested simulatively. These can either be created parameterized or played directly from real-world data. While flexibility in creation is possible through parameters, too many parameters require a lot of data
Therefore, the thesis will develop an approach to combine both methods. New scenarios will be generated and tested in simulation in a second step.
- Literature research on the topics of scenario generation
- Development of a methodology to combine a replay approach with a parametric approach
- Generation of scenarios on intersections using the developed methodology
- Analysis and validation of generated scenarios
- Good English or German language skills
- Reliability, commitment and enjoyment of working independently as well as methodically
- Experience with Python
Note: Please attach brief resume and grade summary.