【正文】 of agents in (Urban) Traffic Control is the one that has our prime interest. Here we ultimately want to use agents for proactive traffic light control with online optimisation. Signal plans then will be determined based on predicted and measured detector data and will be tuned with adjoining agents. The most promising aspects of agent technology, the flexibility and proactive behaviour, give UTC the possibility of better anticipation of traffic. Current UTC is not that flexible, it is unable to adjust itself if situations change and can39。 generalise。 have goals and intentions。 the ability of managing, learning, self adjusting and responding to nonrecurrent and unexpected events (Ambrosino et al.., 1994). What are intelligent agents ? 2 Agent technology is a new concept within the artificial intelligence (AI). The agent paradigm in AI is based upon the notion of reactive, autonomous, internallymotivated entities that inhabit dynamic, not necessarily fully predictable environments (Weiss, 1999). Autonomy is the ability to function as an independent unit over an extended period of time, performing a variety of actions necessary to achieve predesignated objectives while responding to stimuli produced by integrally contained sensors (Ziegler, 1990). MultiAgent Systems can be characterised by the interaction of many agents trying to solve a variety of problems in a cooperative fashion. Besides AI, intelligent agents should have some additional attributes to solve problems by itself in realtime。 but almost none of the current available tools behave proactively or have metarules that may change behaviour of the controller incorporated into the system. The next logical step for traffic control is the inclusion of these metarules and pro active and goaloriented behaviour. The key aspects of improved control, for which contributions from artificial intelligence and artificial intelligent agents can be expected, include the capability of dealing with conflicting objectives。 1 外文資料 Agent controlled traffic lights Introduction The quality of (urban) traffic control systems is determined by the match between the control schema and the actual traffic patterns. If traffic patterns change, what they usually do, the effectiveness is determined by the way in which the system adapts to these changes. When this ability to adapt bees an integral part of the traffic control unit it can react better to changes in traffic conditions. Adjusting a traffic control unit is a costly and timely affair if it involves human attention. The hypothesis is that it might offer additional benefit using selfevaluating and selfadjusting traffic control systems. There is already a market for an urban traffic control system that is able to react if the environment changes。the so called adaptive systems. Real adaptive systems will need proactive calculated traffic information and cycle plans based on these calculated traffic conditions to be updated frequently. Our research of the usability of agent technology within traffic control can be split into two parts. First there is a theoretical part integrating agent technology and traffic control. The final stage of this research focuses on practical issues like implementation and performance. Here we present the concepts of agent technology applied to dynamic traffic control. Currently we are designing a layered model of an agent based urban traffic control system. We will elaborate on that in the last chapters. Adaptive urban traffic control Adaptive signal control systems must have a capability to optimise the traffic flow by adjusting the traffic signals based on current traffic. All used traffic signal control methods are based on feedback algorithms using traffic demand data varying from years to a couple of minutes in the past. Current adaptive systems often operate on the basis of adaptive green phases and flexible coordination in (sub)works based on measured traffic conditions (., UTOPIAspot,SCOOT). These methods are still not optimal where traffic demand changes rapidly within a short time interval. The basic premise is that existing signal plan generation tools make rational decisions about signal plans under varying conditions。 the capability of making proactive decisions on the basis of temporal analysis。 understand information。 draw distinctions between situations。 synthesise new concepts and / or ideas。t handle unprogrammed situations. Agent technology can also be implemented on several different control layers. This gives the advantage of being close to current UTC while leaving considerable freedom at the lower (intersection) level. Designing agent based urban traffic control systems The ideal system that we strive for is a traffic control system that is based