Perception for Autonomous Systems

Content: Autonomous vehicles, such as mobile robots or self-driving cars, must be able to perceive their environment and correctly interpret it depending on the situation in order to derive the desired behavior. Various types of sensors are used for perception, such as cameras for computer vision, Light Detection and Ranging (LiDAR), and Radio Detection and Ranging (Radar). To compensate for the respective disadvantages of individual sensors, sensor data fusion is performed, and machine learning methods are used to interpret the sensor values (object detection and classification). The module provides an overview of current methods for evaluating, fusing, and interpreting sensor data for situational awareness. In the practical part, students work on small project tasks, implement algorithms, and test them experimentally. Further information on the content can be found on the professorial chair's website.

Learning Objectives: Students are familiar with the current state of research in this field and are capable of independently acquiring advanced specialized knowledge, applying it in practice, and presenting their results.

More information about the course will be posted here shortly.