Applications of Artificial Intelligence to Game Design

Applications of Artificial Intelligence to Game Design Abstract Game development is still in its infancy. But recently there has been a steady growth and somewhat of a revolution in styles in the field of computer and video games. Artificial Intelligence applications are being implemented in these games to produce the illusionary effect of intelligence augmentation in order to give the player a good game play experience.   Game AI is used to create exciting playing strategies which keep the players focused and interested in the game. Players are provided exciting opponents, more intelligent creatures that inhabit the world of their games, which exhibit interesting behavior. The main purpose is that boredom of repetition is avoided.   In this paper we will survey the applications of AI in game design. We will describe the role of AI applications in different genres of games such as action, adventure, role playing, and strategy games. Finally, this paper will show how AI in gaming covers a wide area of AI technologies including path finding, ne ural networks, finite state machines, rule systems, human behavioral modeling and many more. Introduction In the last couple decade there is a great evolution in the computer game industry. When two dimensional games were saturating the market, the introduction of 3D-technology really made the concept of a game world entered to the mainstream (Jonathan, P.1). A major advance in the early part of the next century has included player interactivity and artificial intelligence in game design.   A games story line no longer consists of only one primary character. It must consist of many, all playing an important role in the conflict resolution of their virtual world. This puts a heavy demand on the artificial intelligence required to operate non-player characters. Artificial Intelligence techniques are used to produce the illusion of intelligence in the behavior of non player characters in computer and video games. Creatures must no longer be written so as to react based on a single player, and the realness of their behavior and uniqueness of their tactics will be a more important feature t han it has been in the past (Jonathan, P.1 ). Pathfinding is another common use for AI, widely seen in real-time strategy games. Pathfinding is, as its name applies, the method for determining how to get a non-player characters from one point on a map to another, taking into consideration the terrain, and obstacles.The increased sophistication in the field of computer gaming audience has now shown a bright way to an era in which game developers, who earlier struggled in order to produce game which large amount of demographic can play, are now positioned to work with new, advanced artificial intelligence applications. Artificial intelligence in games is usually used for creating players opponents. The objective of intelligence amplification is rescuing the player from the boredom of repetition and letting him focus just on the interesting aspects of the game. The player gives high-level strategic orders, the computer-controlled units take care of detail. At the same time, the full de tail and dynamics of the game is maintained with the computer control of detail, rather than lost through abstraction. Artificial Intelligence   applications in games design is lately getting better by implementing the incredible complexity of advanced AI engines which has   been developed by the efforts and research of programming groups. There are various techniques used in AI-engines in games designs such as finite state machines, Minimax Trees and Alpha-Beta Pruning, fuzzy logic, genetic algorithms, neural networking path finding, rule systems, human behavioral modeling, sample code and many more.   AI techniques will include features like real-time interrogation of suspects, dynamic movement, and richness of behavior in game design which increase the interaction between creatures and their environment, no longer separated from the consequence of their own actions. Combination of generative and reactive planning algorithms will generate the path for creating customized and novel behavior of the characters which will change each time the game is played so that the character behavior is not l imited in ability which will provide the interest in the player. There are different genus of computer and video games in the market and we can see the role of Artificial intelligence applications in these games. Action Games Action games involve the human player controlling a character in a virtual environment, usually running around and using deadly force to save the world from the forces of evil or conquering an alien monsters or mythical creatures. In pure action games, AI is used to control the enemies. Action games like First person shooter type games usually implement the layered structure of artificial intelligence system, layers located at the bottom handle basic task like determining the optimal path to the target and the higher levels take care of tactical reasoning and selecting the behavior which an AI agent should assume in accordance with its present strategy (Janusz, P. 2). Providing realism in graphics has been the key point of competition for these games; where AI has played a major role as a point of comparison. Recent games have extended the genre so that the human player may be part of a team, including either human or AI partners. In all cases, it is the moment-to-moment reaction of the AI to the human that is most important so that the AI must be tactically savvy with little emphasis on strategy (John E, P.11 ).Latest trend is to use schedule based finite state machines (FSMs) to determine the behavior of the players adversaries(Russell, P. 1 ) Adventure Games Adventure games, and similar kind of interactive fiction, move further from action games, since they do not give importance to armed combat but accentuate more on story, plot and puzzle solving. In these games, players must solve puzzles and interact with other characters, as they progress through an unfolding adventure that is determined in part by their actions. AI can be used to create realistic supporting goal-driven characters that the player must interact with appropriately to further their progress in the game (John E, P.11 ). The majority of these games has fixed scripts and uses many tricks to force the human player through essentially linear stories. However, a few games, such as Blade Runner, have incorporated some autonomy and dynamic scripting into their characters and story line (Castle, P.87 ).Two interesting applications of AI to the adventure game category are the creation of more realistic and engaging non Player Characters and maintaining consistency in dynamic sto rylines (Chris, P. 2 ). Role Playing Games In role-playing games, a player can play different types of human characters, such as a combatant, a conjurer or a thief. The player does various kind of activities like collecting and selling items, fighting with monsters, so that they can expands the capabilities and power of their character like strength, magic or quickness, all in an extended virtual world. The Role playing game format also offers similar kind of challenges to the AI developer as the adventure game with some extra impediment due to the amount of freedom assigned to the player. To maintain a story line consistent for these kind of games becomes a biggest challenge and higher level of sophistication is required in these types of role playing games .Here AI is implemented to take control over enemies similar to action games, partners who travel and adventure with the players and also supporting characters like traveling companion, villagers etc . The massively multiplayer games provide an additional opportunity to use AI to expand and enhance the player to player social interactions (John E, P.11 ).These days major AI research areas on these types of games is to provide human interaction, social intelligence and natural language interfaces to these support characters (Brooks, P. ) (Laird, P. 15).Support characters must provide human-like responses, including realistic move ment (Hayes, P. 195), personality, emotions, natural language understanding and natural language generation. In order to do all this, a large range of integrated AI techniques capabilities are required. Strategy Games In strategy games, the human controls various kind of entities for example military elements like tanks, guns, war machines in order to conduct a battle from a   gods eye view against one or more opponents. Strategy games include reenactments of different types of battles: historical (Close Combat), alternative realities (Command and Conquer), fictional future (Starcraft), and mythical (Warcraft, Myth). The human is faced with problems of resource allocation, scheduling production, and organizing defenses and attacks (Davis, P. 24). Strategy games on the market today are an even mix between mythical, fantasy and science fiction campaigns; and recreations of historical battles. There are two distinct classes of game in this category which are turn based strategy (TBS) games involve each player taking their turn to move units, order production, mount attacks and so on and real time strategy (RTS) games which take place in real-time with players moving units, ordering production etc. in parallel (Chris, P. 2 ). AI is used in two roles: to control the detailed behavior of individual units that the human commands, and as a strategic opponent that must play the same type of game against the human (John E, P. 1). AI in strategy games needs to be applied both at the level of strategic opponents and at the level of individual units. AI at the strategic level involves the creation of computer opponents capable of mounting ordered, cohesive, well planned and innovative campaigns against the human player. This is very chall enging as players quickly identify any rigid strategies and learn to exploit them. At the unit level AI is required in order to allow a players units to carry out the players orders as accurately as possible. Challenges at unit level include accurate path finding and allowing units a degree of autonomy in order to be able to behave sensibly without the players direct control (John E, P. 11). Neural network used to choose the best strategy in a RTS-type game. Based on situation analysis, the network decides how greatly to concentrate on development, arms production, repairs after battles etc. All the parameters required by the game will be provided by the neural network on its output (Janusz, P. 3). Simulation / God Games Another sub-category origin by the strategy game is the simulation/ God game. These cast the player in the role of a protective deity .These games give the player god-like control over a simulated world. The human can modify the environment and, to some extent, its inhabitants. The entertainment comes from observing the effects of his or her actions on individuals, society, and the world. SimCity is the classic example of a simulation, or god game (John E, P. 2). The main factor distinguishing God games from strategy games is in the manner in which the player can take action in the environment. The player creates individual characters that have significant autonomy, with their own drives, goals, and strategies for satisfying those goals, but where God (the human player) can come in and stir things up both by managing the individual characters and their environment. The player has the ability to manipulate the environment – for example to raise or flatten mountains to make the land more hospitable, or to unleash the fury of a hurricane or earthquake – and units are controlled less directly than in strategy games(Laird, P. 15 ). Neural networks are used in this type of games to teach the creature behaviors. Neural networks are used for motor controller, threat assessment, attacking on enemies and for anticipation that is predicting players next move .This AI technique help to develop Human like AI (Russell, P. 12). Team Sports Team sports games have the human play a combination of coach and player in popular sports, such as football, basketball, soccer, baseball, and hockey (Whatley, P. 991). AI is used in two roles that are similar to the roles in strategy games, the first being unit level control of all the individual players. Usually the human controls one key player, like the quarterback, while the computer controls all the other members of the team. A second role is as the strategic opponent, which in this case is the opposing coach (Laird, P. 15). One unique aspect of team sport games is that they also have a role for a commentator, who gives the play by play, and color commentary of the game (Frank, P. 77). In a team sports game the strategic opponent might select a play or strategy for the entire team.   That strategy defines a role and/or approximate path for each player involved in the play.  Ã‚  Ã‚   Game programmers discovered that the A* search algorithm is a powerful and efficient way to calculate these paths in the sport games (John E, P. 2). Individual Sports/Racing Games For individual competitive sports, such as driving, flying, skiing, and snowboarding, the computer provides a simulation of the sport from a first or third person perspective (Laird, P. 15).The human player controls a participant in the game who competes against other human or computer players (Laird, P. 15). The computer player is more like an enemy in an action game than a strategic opponent or unit from a strategy game because the game is usually a tactical, real time competition. Individual sports can also require commentators (Janusz, P.4). Opponents for racing games are some of the most pure applications of artificial intelligence in games. The AI must travel over a course, controlling a vehicle (which could be a car, a boat, a plane, or even a snowboard). The AI for racing opponents almost invariably follows a recorded trace of the behavior of a human player. It is as if there is a line on the course that tells the AI where to go, what speed to use, and possibly any special ma neuvers that should be performed (John E, P.1). Conclusion As per the researchers perspective, in the present era of Internet and network games, Artificial Intelligence for interactive computer games is an emerging application area. Artificial intelligence techniques such as finite state machines, path finding, neural networks etc are applied in different genres of games in order to provide an environment for continual steady advancement and series of increasingly difficult challenges for the players to keep them interested. New advances in AI are opening a door to new game genres and even new game paradigms (Stern, P. 77)