@mastersthesis {PUBA309,
	title = {Autonomous learning for understanding traffic situations},
	author = {Stefan Klingelschmitt},
	year = {2013},
	abstract = {This thesis is concerned with developing and implementing a self-referential control architecture for autonomous learning. As current approaches towards situation understanding and scene analysis are based on visual methods or statistical learning techniques, they fail to provide a sufficient performance for proper scene understanding in more complex scenarios. Current driver assistance systems mainly provide comfort and simple safety functions like automatic cruise control, traffic light or pedestrian recognition. However, the ability of scene understanding will be an important aspect for emerging driver assistance systems that intend to assist the driver to a level of partial autonomous or automated driving. The mentioned self-referential approach for learning situation representations as well as adapting a correct behavior within the environment is explained in detail. The required components and the architecture of the self-referential system is outlined. Furthermore, a variety of learning algorithms concerning the self-referential approach are presented. Finally, the introduced architecture is implemented within an existing simulation environment and the developed algorithms are tested and evaluated.},
	publisher = {TU Darmstadt},
	booktitle = {Master thesis},
	institution = {TU Darmstadt}
}