Situation Creator: A Pedagogical Agent Creating Learning Opportunities Yongwu Miao*, Ulrich Hoppe**, Niels Pinkwart*** * Educational Technology Expertise Center, Open University of the Netherland, ** Institute of Computer Science and Interactive Systems, University of Duisburg-Essen *** Computer Science Institute, Clausthal University of Technology Abstract. In a multi-user, real-time, and situation-based learning environment, the availability of enough and appropriate situations is crucial for success. In order to improve effectiveness and efficiency of learning, we develop a new type of pedagogical agent: situation creator. Such an agent intentionally creates specific situations in the shared virtual driving place according to users’ performance information. We conduct a pilot evaluation and found that the situation creators significantly increase the number of situations that a learner can expect to encounter while using the system. Introduction In a typical training course with a simulator, an individual trainee interacts with the simulation system through a series of pre-defined situations. We adopted an alternative design approach to a car-driving simulation environment for learning. Rather than a single user going through a series of pre-defined driving scenarios, in our learning environment geographically distributed users can learn to handle various situations by virtually driving in a shared driving place in a way analogous to driving in the real world. If a user needs help or can not behavior correctly, an coach agent will provide a specific guidance to the user based on the user's experience concerning the current situation [1]. In addition, in order to increase the volume of traffic and traffic situations, we introduced driver agents, which head for random destinations on the roads and never consider the needs of learners. The problem of using randomly acting driver agents is that they are not highly effective in situation generation, although they make the virtual driving place more crowded. In order to improve effectiveness and efficiency of learning, we develop a concept of situation creator [2]. Such an pedagogical agent intentionally creates specific situations in the shared virtual driving place according to users’ performance information. In this paper, we present the design and implementation of a situation creator example and report the result of a pilot study with the system. 1. Design and Implementation of an Situation Creator Figure 1 shows the algorithm for the situation creator example. Once it becomes active, it starts to automatically navigate from a parking place to the shared driving place where the learners practice driving. The situation creator then seeks cars controlled by learners. As long as there are learners in the shared driving place, the situation creator will try to create a learning opportunity for one of them. The agent first selects its “target” learner as the one whose car is closest to his own. It looks up in the learner model in which situations the