Directable behavior models for virtual driving scenarios

We present a model for autonomous driving behavior useful for creating ambient traffic as well as experiment-specific scenarios for driving simulation. This model follows roadways, obeying the rules of the road. It reacts to nearby vehicles and traffic control devices. The model supports a range of behaviors including passing, lane changes, and safe navigation through intersections. The model is parameterized by traits that influence the personality of the driver such as aggressiveness, attentiveness, impatience, and law-abidance. In addition, the model responds to behavior-oriented directives that can be used to coordinate groups of vehicles for the creation of complex scenarios. We present the details of the behavior model and give an example of its use in creating a scenario.