Few concepts embody the goals of artificial intelligence as well as fully autonomous robots. Countless films and stories have been made that focus on a future filled with autonomous agents that complete menial tasks or run errands that humans do not want or are too busy to carry out. One such task is driving automobiles. In this paper, we summarize the work we have done towards a future of fully-autonomous vehicles, specifically coordinating such vehicles safely and efficiently at intersections. We then discuss the implications this work has for other areas of AI, including planning, multiagent learning, and computer vision.
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. Intelligent Transportation Systems (ITS) is the field that focuses on integrating information technology with vehicles and transportation infrastructure to make transportation safer, cheaper, and more efficient. Recent advances in 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 Current methods of vehicle coordination, which are all designed to work with human drivers, will be outdated.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. We believe current methods for controlling traffic, specifically at intersections, will not be able to take advantage of the increased sensitivity and precision of autonomous vehicles as compared to human drivers. In this article, we suggest an alternative mechanism for coordinating the movement of autonomous vehicles through intersections. Drivers and intersections in this mechanism are treated as autonomous agents in a multiagent system. In this multiagent system, intersections use a new reservation-based approach built around a detailed communication protocol, which we also present. We demonstrate in simulation that our new mechanism has the potential to significantly outperform current intersection control technology -- traffic lights and stop signs. Because our mechanism can emulate a traffic light or stop sign, it subsumes the most popular current methods of intersection control. This article also presents two extensions to the mechanism. The first extension allows the system to control human-driven vehicles in addition to autonomous vehicles. The second gives priority to emergency vehicles without significant cost to civilian vehicles. The mechanism, including both extensions, is implemented and tested in simulation, and we present experimental results that strongly attest to the efficacy of this approach.
Imagine a life where you don't have to stop at all, not even at a traffic red light or a signal. What if your car was smart enough to communicate with other cars and you just don't have to deal with traffic at all. This future is not very far, carmakers across the world are working towards connected cars that could coordinate their movements in order to go through them at intersections or traffic signals without stopping. Ford is already working to make this dream a reality and has made quite a bit of progress on this end. Ford is currently testing this technology in the United Kingdom and says that this will reduce the travel time and also reduce crashes at the intersection.
Traffic congestion and automobile accidents are two of the leading causes of decreased standard of living and lost productivity in urban settings. Recent advances in artificial intelligence suggest that autonomous vehicle navigation will be possible in the near future. Individual cars can now be equipped with features of autonomy such as adaptive cruise control, GPSbased route planning (Rogers, Flechter, & Langley 1999; Schonberg et al. 1995), and autonomous steering (Pomerleau 1993). Once individual cars become autonomous, many of the cars on the road will have such capabilities, thus opening up the possibility of autonomous interactions among multiple vehicles. In earlier work, we proposed a novel Multiagent Systems-based approach to alleviating traffic congestion and collisions, specifically at intersections (Dresner & Stone 2005).
In the world of autonomous vehicles, Pittsburgh and Silicon Valley are bustling hubs of development and testing. But ask those involved in self-driving vehicles when we might actually see them carrying passengers in every city, and you'll get an almost universal answer: Not anytime soon. An optimistic assessment is 10 years. Many others say decades as researchers try to conquer a number of obstacles. The vehicles themselves will debut in limited, well-mapped areas within cities and spread outward.