Together with the Technical University Munich (TUM), the fortiss competence field Automated Software Testing offers a brand new practical course for the upcoming winter semester. The course is centered around the topic of autonomous driving testing.

Content

In this course, the students will learn and apply automated testing techniques for the validation of Automated Driving Systems (ADS). The techniques will concern simulation-based testing in a simulation environment but also physical testing of small-scale autonomous vehicles. Nowadays, ADS are already ubiquitous and can be found as parking assistant systems, lane-keeping systems, or automated emergency braking systems. In the future, fully autonomous cars are expected to become a standard transportation source.

However, being ADS AI-based safety-critical systems, they have to be thoroughly tested before they can be deployed on the road. The practicum course will expose students to different problems in testing ADS, a must-have skill in the CV nowadays.

The topics will revolve around automated test generation, sim2real gap mitigation and assessment, simulator development, and explainable AI. The students will work in teams to develop testing approaches and tools to bear these challenges. Open-source simulators and systems will be used, such as an automated lane-keeping system based on a deep neural network. Each team will be guided by a mentor.

In the final event, each group will present their prototype and implementation. By the end of the course, students will have gained a holistic understanding of the ADS testing lifecycle and be well-equipped to tackle the next challenges in autonomous driving.