What sensors are needed for autonomous driving?

We are witnessing an exciting trend towards vehicle automation. We extend the research on robotic vehicles of several international groups that employ expensive on-roof sensors by investigating whether close-to-market sensor configurations may be sufficient for this task. We show that cognitive and autonomous vehicles with a few close-to-market sensors are feasible. Vision plays the dominant role in our autonomous vehicle. We completely avoid bulky on-roof mounted sensors. The sensor suite enables the vehicle to perceive its environment and automatically navigate through everyday´s traffic. Methods for 3D visual machine perception based mono- and binocular video sensors are presented. The contribution of prior knowledge from digital maps is elaborated as well as its curse in case of erroneous information. Real-time automated decision-making and trajectory planning methods are outlined. Extensive results of automated driving are shown in real world scenarios from our AnnieWAY vehicle, the winner of the 2011 Grand Cooperative Driving Challenge, and from the Bertha vehicle that drove autonomously on the 104 km of the Bertha Benz memorial route from Mannheim to Pforzheim through a highly populated area of Germany.