In this paper we present an approach to control a real car with brain signals. To achieve this, we use a brain computer interface (BCI) which is connected to our autonomous car. The car is equipped with a variety of sensors and can be controlled by a computer. We implemented two scenarios to test the usability of the BCI for controlling our car. In the first scenario our car is completely brain controlled, using four different brain patterns for steering and throttle/brake. We will describe the control interface which is necessary for a smooth, brain controlled driving. In a second scenario, decisions for path selection at intersections and forkings are made using the BCI. Between these points, the remaining autonomous functions (e.g. path following and obstacle avoidance) are still active. We evaluated our approach in a variety of experiments on a closed airfield and will present results on accuracy, reaction times and usability.