Anomaly Detection for Autonomous Driving

Bachelor thesis, Research assistant, Master thesis, Internships

Research focus: Machine Learning, Mobility, Safe and Intelligent Vehicles
Courses of study: Electrical Engineering, Informatics, Information Engineering, Related Disciplines, Business Informatics

Job Description

Autonomous Driving at FZI

The Technical Cognitive Systems (TKS) department deals with research questions related to autonomous driving. For the scaling of autonomous vehicles, the detection of anomalies, also called corner cases, is enormously important. This can be used to improve models (active learning) or to react live. We are investigating methods that combine camera and lidar sensor data and detect anomalies in relevant areas.

For this, we need support in numerous areas, where you can contribute according to your strengths and interests. Possible topics are Semantic Segmentation, Deep Generative Models, Scene Synthesis, Pseudo-Lidar or State-of-the-art Benchmarking with KITTI, WAYMO, CARLA etc.

Your Responsibilities

  • Literature research, analysis and evaluation of the state of the art
  • Implementation and evaluation of selected algorithms in Python

Our Offer

  • An interdisciplinary working environment with partners from science and industry
  • Challenging tasks in an exciting and highly up-to-date subject area
  • Regular meetups with the students in my team
  • In case of outstanding work, submission of a paper for publication at a conference
  • Free, independent working style with short, structured weekly meetings for regular feedback

Your Profile

  • Good Python programming skills (under Linux with Git)
  • Theoretical knowledge in the area of Machine Learning / Deep Learning
  • Practical experience with Tensorflow or PyTorch
  • Independent thinking and working, motivation and commitment
  • Fluent in English or German
  • Bonus points are given for experience with (un)supervised methods, ROS, CARLA, ClearML and LaTeX


We look forward to receiving your PDF application to Daniel Bogdoll with the following documents:

  • Two sentences about your motivation (in the email)
  • Current transcript of grades (and if available, bachelor's degree certificate)
  • Tabular curriculum vitae

Job Description

  • I will be happy to answer any questions and will consider your suggestions and interests
  • Start: Flexible, preferably immediately
  • Home-Office is possible at any time with SSH access to our GPU-powered workstations
  • Supervising institute at KIT: AIFB | Prof. Dr. J. Marius Zöllner