Sensor data fusion for automated driving: Toward robust perception in adverse weather conditions

The aim of the thesis is to develop methods and algorithms for the development of a robust perception system that is capable of dealing with adverse weather conditions. Robust environmental perception is important in order to guarantee safety for the automated vehicle and the road users in the neighborhood. To create a robust perception system, a sensor setup should be selected with multiple sensing modalities. Commonly used sensing modalities in the field of intelligent vehicles are lidar, camera and radar sensors. This thesis addresses three subjects that are important for robust perception, namely sensor selection, extrinsic calibration and object tracking....