Advanced urban traﬃc control systems are often based on feed-back algorithms. They use road traﬃc data which has been gathered from a couple of minutes to several years. For instance, current traﬃc control systems often operate on the basis of adaptive green phases and ﬂexible co-ordination in road (sub) networks based on measured traﬃc conditions. However, these approaches are still not very eﬃcient during unforeseen situations such as road incidents when changes in traﬃc are requested in a short time interval. For such anomalies, we argue that systems are needed that can sense, interpret and deliberate with their actions and goals to be achieved, taking into consideration continuous changes in state, required service level and environmental constraints. The requirement of such systems is that they can plan and act eﬀectively after such deliberation, so that behaviourally they appear self-aware. This chapter focuses on the design of a generic architecture for auto- nomic urban traﬃc control, to enable the network to manage itself both in normal operation and in unexpected scenarios. The reasoning and self- management aspects are implemented using automated planning techniques inspired by both the symbolic artiﬁcial intelligence and traditional control engineering.Preliminary test results of the plan generation phase of the architecture are considered and evaluated.
|Title of host publication||Autonomic Road Transport Support Systems|
|Editors||Thomas Leo McCluskey, Apostolos Kotsialos, Jorg P. Muller, Franziska Klugl, Omer Rana, Rene Schumann|
|Place of Publication||Switzerland|
|Publisher||Birkhauser Verlag Basel|
|Number of pages||18|
|Publication status||Published - 2016|