No description available.

abstract: The autonomous vehicle technology has come a long way, but currently, there are no companies that are able to offer fully autonomous ride in any conditions, on any road without any human supervision. These systems should be extensively trained and validated to guarantee safe human transportation. Any small errors in the system functionality may lead to fatal accidents and may endanger human lives. Deep learning methods are widely used for environment perception and prediction of hazardous situations. These techniques require huge amount of training data with both normal and abnormal samples to enable the vehicle to avoid a dangerous situation. The goal of this thesis is to generate simulations from real-world tricky collision scenarios for training and testing autonomous vehicles. Dashcam crash videos from the internet can now be utilized to extract valuable collision data and recreate the crash scenarios in a simulator. The problem of extracting 3D vehicle trajectories from videos recorded by an unknown monocular camera source is solved using a modular approach. The framework is divided into two stages: (a) extracting meaningful adversarial trajectories from short crash videos, and (b) developing methods to automatically process and simulate the vehicle trajectories on a vehicle simulator. / Dissertation/Thesis / Video Demonstration / Masters Thesis Computer Science 2019

The aim of this study was to investigate, whether the aspect of interactivity (meaning problem solving interactivity) implemented in multimedia learning materials would positively influence learning outcomes of students. The third and fourth-grade pupils had been split up in two groups and they learned about a topic of natural sciences for about 20 minutes. The first group were studying from an interactive material - short educational game. The second group were studying from a noniteractive material - short educational animation. As variables we have chosen the following - the learning outcomes of the pupils, the amount of motivation to manipulate with the educational tool and the evaluation of atractivity of this tool. Based on multimedia learning theories (CTML, CATLM), we assumed that interactivity would enhance the extent of motivation, evaluation of atractivity and the learning outcomes. Our results partially confirmed our hypothesis. We found positive effect on motivation and evaluation, nevertheless we found no effect on learning outcomes - there was no difference between the groups within this domain. As one of the possible explanations we propose Sweller's cognitive load theory. KEYWORDS Multimedia learning, interactivity, educational animation, educational game, learning outcomes

Von der Professur Montage- und Handhabungstechnik der Fakultät für Maschinenbau der Technischen Universität Chemnitz wird seit 2009 das jährliche Simulationsanwendertreffen SAXSIM organisiert. Ausgewählte Beiträge werden in Form eines Tagungsbandes veröffentlicht. Das 7. Anwendertreffen SAXSIM fand am 31.03.2015 an der TU Chemnitz statt.