Artificially Intelligent Traffic Model for Training Simulation

Roadway safety continues to be a major public health concern.   Recent statistics show that more than 30,000 fatalities occur due to motor vehicle accidents, and in the year 2012, motor vehicle crashes resulted in more than 2 million injuries. As a result of these ongoing trends, simulators continue to become more abundant in applications ranging from Intelligent Transportation Systems (ITS) research, autonomous driving, human factors studies, rehabilitation, and driver training and workload applications. However, many current simulators lack realism with regards to accompanying traffic, which often does not satisfactorily respond to the real-time actions of the human subject who is operating the simulation. Artificial traffic simulation models found within many modern-day driving simulators are often “macroscopic” in nature – they aggregate the description of overall traffic flow, which is based on “idealistic” driver behavior. This lack of network realism (particularly in the vicinity of the human subject operating the simulator) limits the application scope. In this research, we evaluate traffic simulation models for supporting next-generation ITS research applications. This survey justified the need for the design and development of a microscopic Artificially Intelligent Traffic Model (AITM) intended for civilian ground vehicle research applications. The AITM generates a fleet of semi-intelligent vehicles with which a human driver interacts within a virtual driving simulation environment. The behavior of the vehicles is based upon the basic principles of rigid body physics and real-time collision detection, and includes a rule-base for: road-appropriate travel speed behavior, behavior at intersections (e.g., stop signs, street lights), and interactions with other AI and human-driven vehicles on the virtual roads (i.e., lane changing, headway distance). In this research, the design and development of the baseline AITM is described, and a use-case application is presented, along with recommendations for improvements required subsequent to the deployment of the preliminary model.