Evolutionary Testing is a promising approach for automating the testing of software-based systems. A number of papers have been published in the last years which have successfully applied evolutionary algorithms for test data generation. However, none of these papers address functional testing - the testing of the system's logical behavior on the basis of the system specification - which is, in practice, the most important and most common class of the methods. In this work we present the application of evolutionary testing to the functional testing of an automatic parking system which could automate the parking procedure in future cars. A test environment is described which automatically generates interesting driving maneuvers, performs a simulation of the system with the generated maneuvers and continuously improves the test quality.