Target Selection for AI Companions in FPS Games - 0 views
-
Garrett Eastman on 18 May 13Abstract: "Non-player Characters (NPCs) that accompany the player en- able a single player to participate in team-based experiences, improving immersion and allowing for more complex game- play. In this context, an Artificial Intelligence (AI) teammate should make good combat decisions, supporting the player and optimizing combat resolution. Here we investigate the target selection problem, which consists of picking the op- timal enemy as a target in a modern war game. We look at how the companion's different strategies can influence the outcome of combat, and by analyzing a variety of non-trivial First Person Shooter (FPS) scenarios show that a mathemat- ically simple approach significantly improves over common strategies typically found in games, and can achieve results similar to much more expensive look-up tree approaches. This work has applications in practical game design, show- ing that simple, computationally efficient target selection can make an excellent target selection heuristic"