AIM: autonomous intersection management

Artificial intelligence research is ushering in a new era of sophisticated, mass-market transportation technology. While computers can already fly a passenger jet better than a trained human pilot, people are still faced with the dangerous yet tedious task of driving automobiles. Recent advances in artificial intelligence, multiagent systems (MAS), and Intellgient Transportation Systems (ITS) point to a future in which vehicles themselves handle the vast majority of the driving task. Once autonomous vehicles become popular, autonomous interactions amongst multiple vehicles will be possible. Current methods of vehicle coordination, which are all designed to work with human drivers, will be outdated. The bottleneck for roadway efficiency will no longer be the drivers, but rather the mechanism by which those drivers’ actions are coordinated. While open-road driving is a well-studied and more-or-less-solved problem, urban traffic scenarios, especially intersections, are much more challenging. This thesis addresses the question: “To what extent and how can a multiagent intersection control mechanism take advantage of the capabilities of autonomous vehicles in order to make automobile travel safer and faster?” First, I introduce and specify the problem of intersection management as a multiagent system and define a metric by which solutions can be evaluated. Next, I propose a novel multiagent intersection control mechanism in which autonomous driver agents “call ahead” and reserve space-time in the intersection, pending the approval of an arbiter agent called an intersection manager, which is located at the intersection. I also define a detailed protocol by which the driver agents and intersection managers communicate. The protocol, which consists of message types and associated semantics, defines a space of behaviors for the two types of agents. This space is extensively explored, and algorithms are presented for the agents that enable the system as a whole to achieve performance levels far beyond those of current intersection control mechanisms like stop signs and traffic lights. To demonstrate the superiority of the mechanism, I present empirical data from a custom simulator developed specifically for this work. Finally, I discuss the feasibility of implementation and deployment of such a system in the real world. Though motivated by the specific problem of intersection management, these contributions generalize to the larger problem of coordinating multiple autonomous, heterogeneous, physical agents that desire access to the same exclusive physical space. By associating an arbiter agent with each resource, a scalable, distributed control mechanism is created that grants more autonomy and is more failure-resistant than a centralized system, while providing fine-grained control that creates a more efficient system than current, coarsegrained methods.