A Game AI Engine Based On Multi-Agent System

Until recently, technology in games was driven by a desire to achieve real-time, photo-realistic graphics. To a large extent, this has now been achieved. As game developers look for new and innovative technologies to drive games development, AI is coming to the fore. Because of the dependence on game design, there are not so much popular AI engines as graphical engines in game developing. In this paper, a game AI engine suits team-sports game is developed based on multi-agent system.The Multi-Agent system in game AI engine is modeled, according to the special requirements of game engine. The models includes perceptive system model, movement system model and decision-making system model of single agent and communication system model and collaboration model of multi-agent. Based on a Finite State Machine, the architecture of the AI engine is established, integrating message handling. Further more, an entire soccer-simulating game including input control, graphical render and other aspects is developed based on our game AI engine. In our game, the intelligence of the agents is satisfied, as well as the collaboration among the agents. In this paper, the effect of using multi-agent model in the design of game AI engine is validated and the experiment is a successful attempt to develop a common game AI engine. We believe that using our game AI engine, developers could develop the AI in games efficiently.