A Distributed Approach for Coordination of Traffic Signal Agents

Abstract

Innovative control strategies are needed to cope with the increasing urban traffic chaos. In most cases, the currently used strategies are based on a central traffic-responsive control system which can be demanding to implement and maintain. Therefore, a functional and spatial decentralization is desired. For this purpose, distributed artificial intelligence and multi-agent systems have come out with a series of techniques which allow coordination and cooperation. However, in many cases these are reached by means of communication and centrally controlled coordination processes, giving little room for decentralized management. Consequently, there is a lack of decision-support tools at managerial level (traffic control centers) capable of dealing with decentralized policies of control and actually profiting from them. In the present work a coordination concept is used, which overcomes some disadvantages of the existing methods. This concept makes use of techniques of evolutionary game theory: intersections in an arterial are modeled as individually-motivated agents or players taking part in a dynamic process in which not only their own local goals but also a global one has to be taken into account. The role of the traffic manager is facilitated since s/he has to deal only with tactical ones, leaving the operational issues to the agents. Thus the system ultimately provides support for the traffic manager to decide on traffic control policies. Some application in traffic scenarios are discussed in order to evaluate the feasibility of transferring the responsibility of traffic signal coordination to agents. The results show different performances of the decentralized coordination process in different scenarios (e.g. the flow of vehicles is nearly equal in both opposing directions, one direction has a clearly higher flow, etc.). Therefore, the task of the manager is facilitate once s/he recognizes the scenario and acts accordingly.

An Intersection-Centric Auction-Based Traffic Signal Control Framework

“…Bazzan [2] constructed a decentralised method of traffic control that utilises Evolutionary Game Theory. The traffic controller facilitates coordination among intersections while minimising communication overhead.…”

“…Intersection agents experience a learning phase which allows them to update their mixed strategy taking into account most recent payoffs over past payoffs. In [2], there is an entity, "Nature", that has a global view of traffic and is able to see (and process) information from a macroscopic level. Nature recognises global traffic changes and initiates the change from local to global state in intersection agents.…”

“…Traffic control can be viewed as the management of a set of traffic signals in a road network in order to minimise, for example, the delay experienced by vehicles traversing the network. If traffic signals are considered agents, traffic control can be viewed as a coordination problem [2] where traffic signals work together to prevent congestion and keep traffic flowing. This perspective on traffic control is important as it drives our MAS design choices and sets us apart from other MAS solutions to traffic control thus far, as explained next.…”

Self-management in Urban Traffic Control: An Automated Planning Perspective

“…This means that signal heads will be able to control traffic as long as the traffic pattern is closed to the programmed or learned pattern [27]. Changes to the state of a traffic network are under the influence of various disturbances.…”

“…The most common learning technique in UTC research systems is reinforcement learning: this learns appropriate actions for traffic patterns over a period of time, utilising the idea of assigning blame or positive feedback over repeated trials [27,32]. Learning has also been implemented in several planning applications.…”