【正文】 raffic control. The proposed ITSAprediction model agent estimates the states of the traffic in the near future via its own prediction model. The prediction metamodel pares the accuracy of the predictions with current traffic and will adjust the prediction parameters if the predictions were insufficient or not accurate. The prediction model agent is fed by several inputs: vehicle detection system, relevant road conditions, control strategies, important data on this intersection and its traffic condition, munication with ITSA’s of nearby intersections and higher level agents. The agent itself has a rulebase, forecasting equations, knows constraints regarding specific intersections and gets insight into current (traffic) conditions. With these data future traffic situations should be calculated by its internal traffic forecasting model. The predicted forecast is valid for a limited time. Research has shown that models using historic, upstream and current link traffic give the best results (Hobeika amp。s and all its traffic lights. Here we use the agent technology to implement a distributed planning algorithm. The route agents’ tasks are controlling, coordinating and leading the ITSA’s towards a more global optimum. Using all available information the ITSA (re)calculates the next, most optimal, states and control strategy and operates the traffic signals accordingly. The ITSA can directly influence the control strategy of their intersection(s) and is able to get insight into oning traffic The internals of the ITSA model Traffic dependent intersection control normally works in a fast loop. The detector data is fed into the control algorithm. Based upon predetermined rules a control strategy is chosen and the signals are operated accordingly. In this research we 5 suggest the introduction of an extra, slow, loop where rules and parameters of a prediction model can be changed by a higher order metamodel. ITSA model The internals of an ITSA consists of several agents. For a better overview of the internal ITSA modelagents and agent based functions see figure 2. Data collection is partly placed at the RSA39。s have direct munication with neighbouring ITSA39。 control (operate the signals according to cycle plan). In figure 1 a more specific example of a simplified, agent based, UTC system is given. Here we have a route agent controlling several intersection agents, which in turn manage their intersection controls helped by RSA39。 decision making (with other agent deciding what to use for next cycle。 detect current traffic problems)。s on other adjoining signalised intersections)。s (InTerSection Agent).,some authority agents (area and route agents) and optional Road Segment Agents (RSA). The ITSA makes decisions on how to control its intersection based on its goals, capability, knowledge, perception and data. When necessary an agent can request for additional information or receive other goals or orders from its authority agent(s). For a specific ITSA, implemented to serve as an urban traffic control agent, the following actions are incorporated (Roozemond, 1998): data collection / distribution (via RSA information on the current state of traffic。t solve. This represents current traffic control implementations and idea39。 model the world they operate in and plan and predict consequences of actions and evaluate alternatives. The problem solving ponent of an intelligent agent can be a rulebased system but can also be a neural work or a fuzzy expert system. It may be obvious that finding a feasible solution is a necessity for an agent. Often local optima in decentralised systems, are not the global optimum. This problem is not easily solved. The solution has to be found by tailoring the interaction mechanism or to have a supervising agent coordinating the optimisation process of the other agents. Intelligent agents in UTC,a helpful paradigm Agent technology is applicable in different fields within UTC. The ones most important mentioning are: information agents, agents for traffic simulation and traffic control. Currently, most applications of intelligent agents are information agents. They collect information via a work. With special designed agents user specific information can be provided. In urban traffic these intelligent agents are useable in delivering information about weather, traffic jams, public transport, route closures, best routes, etc. to the user via a Personal Travel Assistant. Agent technology can also be used for aggregating data for further distribution. Agents and multi agent systems are capable of simulating plex systems for traffic simulation. These systems often use one agent for every traffic participant (in a similar way as object oriented programs often use objects). The application