Deep Learning has emerged as the most successful field of machine learning with overwhelming success in industrial speech, language and vision benchmarks. Consequently it evolved into the central field of research for IT giants like Google, facebook, Microsoft, Baidu, and Amazon. Deep Learning is founded on novel neural network techniques, the recent availability of very fast computers, and massive data sets. In its core, Deep Learning discovers multiple levels of abstract representations of the input.
Currently the development of self-driving cars is one of the major technological challenges across automotive companies. We apply Deep Learning to improve real-time video data analysis for autonomous vehicles, in particular, semantic segmentation. Besides video stream analysis, our goal is to integrate via Deep Learning other automotive sensor data like LIDAR, radar, and GPS together with high-resolution maps for making driving decisions. We go beyond state-of-the-art which analyzes data from a particular time point and use LSTM, a recurrent neural network, for combining information over time to make more robust, more confident, and timelier decisions in autonomous driving. Furthermore, LSTM networks serve to integrate the aspect of attention into self-driving systems. Attention promises huge improvements in terms of speed and precision in processing data from traffic scenes.