Evolution of AI in Video Games PowerPoint Presentation

Slide 1 -

By Brian Bell Evolution of Artificial Intelligence In Video Games

Slide 2 -

What is Artificial Intelligence? The term Artificial Intelligence (AI) was coined by John McCarthy in 1956 As a Noun The Intelligence of Machines. As a Field “The science and engineering of making intelligent machines.”

Slide 3 -

How does AI apply to games? Game AI is game design, implemented.

Slide 4 -

Overview Step through the History of Video Games Highlight certain AI techniques and trends Go over some of the pitfalls of modern AI development in the Video Game Industry

Slide 5 -

Pong One of the First Video Games Manufactured by Atari Released in 1972 Designed for 1 or 2 players. Essentially just table tennis in 2 dimensions.

Slide 6 -

The AI of Pong There is Logic to how the Computer moves the paddle. The computer predicts where the ball with end up based on a number of factors then moves the paddle to that predicted location. To simulate Human error the computer is designed to skip its adjustment every 8 frames.

Slide 7 -

Pac-Man Developed by Namco Distributed by Midway (in US) Released: 1980 Single player only Simple maze game

Slide 8 -

Ghosts While the Ghosts appear to move in a random order this is not always the case. As each Ghost has its own Algorithm to control its actions. Chases Pac-Man Try to get in front of Pac-Man Moves at Random*

Slide 9 -

Super Mario Bros. Developed by Nintendo Released in 1985 Classic example of the Platformer

Slide 10 -

Scripted AI Enemy units in the game are designed to follow a scripted pattern. Either move back and forth in a given location or attack a player if nearby Became a staple technique for AI design.

Slide 11 -

ppt slide no 11 content not found

Slide 12 -

Sim City Developed by Maxis Published by Electronic Arts Released in 1989 First in a series of Simulation Games which are often at the forefront of AI technology

Slide 13 -

A Living World The player is able to manipulate certain aspects of the city. The population of the City acts somewhat autonomously. Furthermore the game will simulate random disasters.

Slide 14 -

The Sims Developed by Maxis Published by Electronic Arts Released in 2000 A life simulation game in which the player has control over a semi-autonomous people.

Slide 15 -

Complex characters The Sims characters can be manipulated by the player but will also carry out day to day tasks on their own. Characters also have defined needs and personality traits that dictate how they act in given situations.

Slide 16 -

Complex Object Interactions Characters are able to interact with an arrangement of objects in the environment due to unique object logic.

Slide 17 -

Black and White Developed by Lionhead Studios Published by EA games Released in 2001 Simulation game in which you play God.

Slide 18 -

Black and White Similar to Sim City You had more control over the environment and the people in the game You could also create armies and wage war

Slide 19 -

AI Learning You could control and train large creatures You could then punish or reward the creatures based on how they complete tasks. Over time the creatures will learn how you wish tasks to be done based on how they are treated.

Slide 20 -

Combat Oriented Games Simulation games are more advanced Combat Oriented Games are more Popular Evolution of AI in combat games has advanced quite a bit in the past 10 years.

Slide 21 -

Halo: Combat Evolved Developed by Bungi Published by Microsoft Released in 2001 First person shooter that garnered fame for competently brining the genre to Consoles

Slide 22 -

Dynamic Enemy AI Enemies reacted in dynamic ways. Different enemies would react differently in different situations. Enemies would work together against the player.

Slide 23 -

Behavior Trees

Slide 24 -

Tasks Condition Action Conditional Nodes represent read only functions. These functions are when the AI unit observes some information about its environment Examples: Searching for enemies or nearby cover, determining orientation. Actions Represent actual performed functions. These functions are generally reflected in the graphical representation. Examples: Firing on an enemy, throwing a grenade, reloading, ducking behind cover.

Slide 25 -

Sequences and Selectors Sequences Selectors A sequence represents a group of tasks that must be carried out in order for the overall task to complete A selector will ultimately only carry out one task but attempt to run each of its child task until it finds the correct task for the situation. 1 2 3 ? 1 2 3

Slide 26 -

Behavior Tree ? ? ? ? Patrol Investigate Attack

Slide 27 -

Behavior Trees: Good and Bad Benefits Costs Allows AI units to act in dynamic ways depending on the situation Allows designers to group different actions together for different situations Allows for enemy differentiation Can be time consuming to generate More complex actions require more complex trees Running through all the possible actions can take a lot of time.

Slide 28 -

Behavior Trees Bottom Line Are a good way to provide dynamic actions to individual AI Units Generally require a larger AI control structure for proper implementation.

Slide 29 -

Left 4 Dead Developed and published by Valve Released in 2008 A co-op first person shooter set in a zombie apocalypse.

Slide 30 -

ppt slide no 30 content not found

Slide 31 -

AI Director The game utilizes an AI director that will change the game based on how well the player(s) are doing. This can make the game more or less difficult for players with different skill levels. This also changes the events of the game between different play sessions.

Slide 32 -

The Elder Scrolls V: Skyrim Developed and Published by Bethesda Game Studios Released in 2011 Open World RPG set in a fantasy world

Slide 33 -

Unbalanced AI Non Playable characters (NPCs) and enemies within the game world react dynamically with the player and each other.

Slide 34 -

Unbalanced AI Enemies are not designed to deal with simple obstacles

Slide 35 -

Problems With AI in Gaming There are a number of issues that prevent Video Games from being the best area for the evolution of AI Despite the how far AI in games has come over time no game is perfect. There are a number of reasons as to why this is and will always be the case.

Slide 36 -

Sequels

Slide 37 -

Release Schedule Time The game has to be released at some point and not everything that needs to be addressed can be addressed. Money Games are expensive to make so items are generally prioritized to put the most effort into what is considered most important.

Slide 38 -

Is it fun? Games are about Entertainment While the AI in a game might be very advanced it might not necessarily be entertaining.

Slide 39 -

Future of games

Slide 40 -

Are Video Games good for AI Development? The Good The Bad AI is essential to Games Games provide a simulated world where programmers can experiment The Game Industry is the largest area where AI is being applied. Time and Money are an issue Innovation might not be that important Entertainment is more important then quality

Slide 41 -

References Champandard, A. (2008, December 28). Behavior Trees for Next-Gen AI. Retrieved May 2011, from AiGameDev.com: http://aigamedev.com/insider/presentation/behavior-trees/ Champandard, A. J. (2012, February 9). Trends and Highlights in Game AI for 2011. Retrieved May 2012, from aigamedev.com: http://aigamedev.com/insider/discussion/2011-trends-highlights/ History of Game AI. (n.d.). Retrieved May 2012, from AI Game Programers Guild: http://gameai.com Montfort, N., & Bogost, I. (2009). Racing the Beam: The Atari Video Computer System. The MIT Press. Wexler, J. (2002). Artificial Intelligence in Games: A look at the smarts behind Lionhead Studio’s “Black and White” and where it can and will go in the future. Rochester, NY: University of Rochester.