Automatic situation recognition in collaborative multiplayer serious games

Abstract

With the establishment of Serious Games during the last decade, various approaches and concepts for multiplayer Serious Games have been proposed in the last years, many of those for use in training groups or in classroom. One major problem in this field is the adaptation of a multiplayer Serious Game to the needs of a whole group of players, including difficulty, content adaptation, and game pace. This can be done by a human instructor who is responsible for various tasks like coaching, moderating, or guiding the learners, to take care of game pace, difficulty and game related problems. All actions and measures performed by an instructor are usually based on human reasoning. The instructor processes information about the game - the game state, player actions and the overall situation - and fells a decision about if and how to intervene if necessary. Whereas a human instructor can rather easily recognize and judge what a player or a group of players is doing at a certain moment during the game session by observing the scene, his/her background knowledge of the game, and human reasoning, this is extremely difficult to recognize automatically. Especially in game genres where players can move freely in a game world, deciding for themselves about where to go next, what to do and how, it is a challenge to automatically recognize what a player - or a team - is doing at a certain moment. In this paper, we propose an approach for automatic situation recognition in multiplayer Serious Games. The goal is to automatically recognize what a single player or a group of players are likely doing at a certain point in a game, using information about their locations, their movements, their actions, their interactions, and the game state. Therefore, we define an interface to access elementary and abstract game states, current and past player actions, game quests and (learning) tasks, and game relevant attributes. Moreover, an algorithm is designed to calculate probabilities of possible game situations using the specified game data. We implemented our concept as an extension of the existing collaborative multiplayer Serious Game Escape From Wilson Island and performed an initial study to evaluate the soundness and correctness of our approach with promising results. Our approach can generically be transferred to similar multiplayer games (open world, avatar-based action adventure-like games).