The availability of several Advanced Driver Assistance Systems has put a correspondingly large number of inexpensive, yet capable sensors on production vehicles. By combining this reality with expertise from the DARPA Grand and Urban Challenges in building autonomous driving platforms, we were able to design and develop an Autonomous Valet Parking (AVP) system on a 2006 Volkwagen Passat Wagon TDI using automotive grade sensors. AVP provides the driver with both convenience and safety benefits -the driver can leave the vehicle at the entrance of a parking garage, allowing the vehicle to navigate the structure, find a spot, and park itself. By leveraging existing software modules from the DARPA Urban Challenge, our efforts focused on developing a parking spot detector, a localization system that did not use GPS, and a back-in parking planner. This paper focuses on describing the design and development of the last two modules.

For vehicle dynamics applications, automotive companies are interested in determining the precise vehicle state in every driving situation in real-time. Part of the vehicle state is the side slip angle—the angle between the vehicle heading and its direction of movement. Currently the side slip angle is not measured in stock cars. To fill the gap this paper presents a basic proof of concept to measure the side slip angle using stock car components for sensing. These include an automotive camera and additional movement information provided in current production passenger cars. A basic computer vision algorithm allows determination of camera movement through the identification of static objects in consecutive camera images. In conjunction with a kinematical model, this data is then used to derive the car’s side slip angle. Finally, the method is evaluated on a real vehicle, with dGPS providing ground truth.