As computers inevitably begin to replace humans as the drivers of automobiles, our current human-centric traffic management mechanisms will give way to hyper-efficient systems and protocols specifically designed to exploit the capabilities of fully autonomous vehicles. We have introduced such a system for coordinating large numbers of autonomous vehicles at intersections. Our experiments suggest that this system could alleviate many of the dangers and delays associated with intersections by allowing vehicles to ``call ahead'' to an agent stationed at the intersection and reserve time and space for their traversal. Unfortunately, such a system is not cost-effective at small intersections, as it requires the installation of specialized infrastructure. In this paper, we propose an intersection control mechanism for autonomous vehicles designed specifically for low-traffic intersections where the previous system would not be practical, just as inexpensive stop signs are used at intersections that do not warrant a full traffic light installation. Our mechanism is based on purely peer-to-peer communication and thus requires no infrastructure at the intersection. We present experimental results demonstrating that our system, while not suited to large, busy intersections, can significantly outperform traditional stop signs at small intersections: vehicles spend less time waiting and consume less fuel.

PDF, PS, HTML

In AAMAS Workshop on Agents in Traffic and Transportation, pp. 94-101, Estoril, Portugal, May 2008.

@InProceedings{ATT08-vanmiddlesworth, title={Replacing the Stop Sign: Unmanaged Intersection Control for Autonomous Vehicles}, author={Mark VanMiddlesworth and Kurt Dresner and Peter Stone}, booktitle={AAMAS Workshop on Agents in Traffic and Transportation}, month={May}, address={Estoril, Portugal}, pages={94-101}, url="http://www.cs.utexas.edu/users/ai-lab?ATT08-vanmiddlesworth", year={2008} }