course: Cognitive Sensorik
- teaching methods:
- lecture with tutorials
- responsible person:
- Prof. Dr.-Ing. Thomas Musch
- Dr.-Ing. Stefan Brüggenwirth (extern)
- offered in:
- winter term
dates in winter term
- start: Thursday the 17.10.2019
- lecture Thursdays: from 14:15 to 15.45 o'clock in ID 03/419
- lab exercise Thursdays: from 16:00 to 17.30 o'clock in ID 03/349
All statements pertaining to examination modalities (for the summer/winter term of 2020) are given with reservations. Changes due to new requirements from the university will be announced as soon as possible.
Date according to prior agreement with lecturer.
|Form of exam:||oral|
|Registration for exam:||FlexNow|
Students learn the basics for cognitive sensor data processing and management.
This lecture is all about signal processing for cognitive and robotic systems. A first focus lies on machine learning methods in general and deep learning techniques by means of Convolutional Neural Networks (CNN) in particular. These methods will be applied to the practical context of autonomous driving, sensor date processing in frame of automation and industry 4.0 . Students will implement their own, simple neural network in MATLAB for radar signal classification. Training data will be provided by means of back projection algorithms. Furthermore, industry relevant software will be presented and discussed. A second focus lies on the environment surveillance with multi-sensor approaches. Here, basics regarding Kalman- and Particle filters are repeated and are applied on simultaneous localization and mapping (SLAM) methods, data fusion for sensor and GNSS signals, and automotive radar tracking. Finally, algorithms for resource optimization and management for distributed and multi sensor systems are introduced and discussed. The practical examples are mostly focused on RADAR and LIDAR sensors.
Content of the lecures system theorie 1-3