Multi-agent control of urban networks - Algorithm and case study

Reference:
R.T. van Katwijk and B. De Schutter, "Multi-agent control of urban networks - Algorithm and case study," Proceedings of the 16th ITS World Congress, Stockholm, Sweden, Sept. 2009. Paper 3017.

Abstract:
As a result of increasing congestion and the sharper constraints on the traffic system with respect to throughput, safety, and air quality, the number of traffic control instruments will increase both in number and in heterogeneity. As more and more traffic control instruments are installed to promote the flow of traffic the probability increases that conflicts will arise or that coordination opportunities are lost when traffic control instruments are applied in the same area. Traffic control instruments can thus no longer be considered separately, but have to be considered as part of a larger network. By modeling the separate instruments as intelligent agents, the actions of the individual instruments can be coordinated. This paper illustrates the benefits of multi-agent coordination and defines a procedure and a new movement-based look-ahead traffic-adaptive control algorithm through which coordination between traffic control instruments can be achieved.