Kurt M. Dresner

Multiagent Traffic Management: A Reservation-Based Intersection Control Mechanism

Traffic congestion is one of the leading causes of lost productivity and decreased standard of living in urban settings. Recent advances in artificial intelligence suggest vehicle navigation by autonomous agents will be possible in the near future. In this paper, we propose a reservation-based system for alleviating traffic congestion, specifically at intersections, and under the assumption that the cars are controlled by agents. First, we describe a custom simulator that we have created to measure the different delays associated with conducting traffic through an intersection. Second, we specify a precise metric for evaluating the quality of traffic control at an intersection. Using this simulator and this metric, we show that our reservation-based system can perform two to three hundred times better than traffic lights. As a result, it can smoothly handle much heavier traffic conditions. We show that our system very closely approximates an overpass, which is the optimal solution for the problem with which we are dealing.

Multiagent traffic management: an improved intersection control mechanism

Traffic congestion is one of the leading causes of lost productivity and decreased standard of living in urban settings. Recent advances in artificial intelligence suggest vehicle navigation by autonomous agents will be possible in the near future. In a previous paper, we proposed a reservation-based system for alleviating traffic congestion, specifically at intersections. This paper extends our prototype implementation in several ways with the aim of making it more implementable in the real world. In particular, we 1) add the ability of vehicles to turn, 2) enable them to accelerate while in the intersection, and 3) augment their interaction capabilities with a detailed protocol such that the vehicles do not need to know anything about the intersection control policy. The use of this protocol limits the interaction of the driver agent and the intersection manager to the extent that it is a reasonable approximation of reliable wireless communication. Finally, we describe how different intersection control policies can be expressed with this protocol and limited exchange of information. All three improvements are fully implemented and tested, and we present detailed empirical results validating their effectiveness.

Multiagent traffic management: opportunities for multiagent learning

Traffic congestion is one of the leading causes of lost productivity and decreased standard of living in urban settings. In previous work published at AAMAS, we have proposed a novel reservation-based mechanism for increasing throughput and decreasing delays at intersections [3]. In more recent work, we have provided a detailed protocol by which two different classes of agents (intersection managers and driver agents) can use this system [4]. We believe that the domain created by this mechanism and protocol presents many opportunities for multiagent learning on the parts of both classes of agents. In this paper, we identify several of these opportunities and offer a first-cut approach to each.

Optimal virtual topologies for one-to-many communication in WDM paths and rings

In this paper we examine the problem of constructing optimal virtual topologies for one-to-many communication in optical networks employing wavelength-division multiplexing. A virtual topology is a collection of optical lightpaths embedded in a physical topology. A packet sent from the source node travels over one or more lightpaths en route to its destination. Within a lightpath, transmission is entirely optical. At the terminus of a lightpath the data is converted into the electronic domain where it may be retransmitted on another lightpath toward its destination. Since the conversion of the packet from the optical to the electronic domain introduces delays and uses limited physical resources, one important objective is to find virtual topologies which minimize either the maximum or average number of lightpaths used from the source to all destination nodes. Although this problem is NP-complete in general, we show that minimizing the maximum or average number of lightpaths in path and ring topologies can be solved optimally by efficient algorithms.

Turning the corner: improved intersection control for autonomous vehicles

Traffic congestion is one of the leading causes of lost productivity and decreased standard of living in urban settings. Recent advances in artificial intelligence suggest vehicle navigation by autonomous agents will be possible in the near future. In a previous paper, we proposed a reservation-based system for alleviating traffic congestion, specifically at intersections. This paper extends our prototype implementation in several ways with the aim of making it more implementable in the real world. In particular, we 1) add the ability of vehicles to turn, 2) enable them to accelerate while in the intersection, 3) give a better sensor model and communication-efficient heuristic to our driver agent, and 4) augment their interaction capabilities with a detailed protocol such that the vehicles do not need to know anything about the intersection control policy. The use of this protocol limits the interaction of the driver agent and the intersection manager to the extent that it is a reasonable approximation of reliable wireless communication. We then use this protocol to implement a new control policy: the stop sign. All three improvements are fully implemented and tested, and we present detailed empirical results validating their effectiveness.

A reservation-based multiagent system for intersection control

Abstract Traffic congestion is one of the leading causes of lost productivity and decreased standard of living in urban settings. Recent advances in artificial intelligence suggest that autonomous vehicle navigation will be possible in the near future. In this paper, we propose a reservation-based system for alleviating traffic congestion, specifically at intersections. First, we describe a custom simulator created to measure the different delays associated with conducting traffic through an intersection. Second, we specify a precise metric for evaluating the quality of traffic control at an intersection. Using this simulator and this metric, we show that the reservation-based system can perform two to three hundred times better than traffic lights. As a result, it can smoothly handle much heavier traffic conditions. We demonstrate that this system very closely approximates an overpass, which is the optimal solution for problem with which we are dealing.