game design game ai n.
Skip this Video
Loading SlideShow in 5 Seconds..
Game Design, Game AI PowerPoint Presentation
Download Presentation
Game Design, Game AI

Loading in 2 Seconds...

play fullscreen
1 / 29

Game Design, Game AI - PowerPoint PPT Presentation

  • Uploaded on

Game Design, Game AI. and, sadly, reality Doug Church 5 October 2001. Outline of Talk. What are Games, What are AI’s Where they have met, and failed to meet Where are opportunities What’s My Agenda … with lots of examples … and time for Q&A. Background.

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
Download Presentation

Game Design, Game AI

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
game design game ai

Game Design, Game AI

and, sadly, reality

Doug Church

5 October 2001

outline of talk
Outline of Talk
  • What are Games, What are AI’s
  • Where they have met, and failed to meet
  • Where are opportunities
  • What’s My Agenda
  • … with lots of examples
  • … and time for Q&A


What is it that we are talking about

background terms
Background: Terms
  • Games – specifically computer, here
  • AI – notion of algorithmic decision maker?
  • Game Design – procedural authorship
  • Game Industry – market, customer, ship
background ai
Background: AI
  • Character, Emotion
  • Understanding Environments
  • Solving Logic, Resolving Rules
  • Decision making, w/Attitude Bias
  • Not yet “virtual people”, as such
background game genres
Background: Game Genres
  • Racing – other cars
  • Action – enemies, allies
  • RTS –units, commanders (for both sides)
  • RPG – monsters, party members, NPC’s
  • Sports – players, coaches, commentators
  • Shooter – targets, more targets
examples of game ai

Examples of Game AI

Situations where “AI” might be, could be, should be, and is used in Games

obvious examples
Obvious Examples
  • Car Game – write a virtual driver
  • Shooter – write a virtual player
  • Sports Games – write a virtual coach
  • RTS – write a virtual general
mini case study racing game history
Mini Case Study: Racing Game History
  • No “AI” cars, only real players are drivers
  • “AI” cars which follow scripted path
  • Follow path, adjust speed
  • Feedback system to follow path
  • “Rubber band” near player
  • Attempt to have driver “personality”
somewhat real examples
Somewhat Real Examples
  • Car Game – write AI to keep races close
  • Shooter – enemies die lots, win little
  • Sports – commentators, help player
  • RTS – generals who work on pacing
  • It is A Question of Design Purpose
specific random examples
Specific Random Examples
  • Terra Nova “army field manual” irrelevant
  • Burnout city drivers - want cars to crash
  • System Shock – security camera “system”
  • Commentator – explain “internal” rules
  • UW “Correct distance” – to help draw code
mini case study deus ex ai
Mini Case Study: Deus Ex AI
  • “goal is realism” – not!
  • Initial focus on performance, sense rules
  • Player often had no idea what had happened
  • Made sure AI’s “announce” all actions
  • Artificial behaviors to support player actions
game process

Game Process

How games get built

  • What is the goal for Player Experience?
  • How is the AI going to further that goal?
  • Role of the designer
  • Role of the programmer
  • How “design” evolves
  • Constraints
roles of a game ai
Roles of a Game AI
  • Tool for the designer
  • Foil for the player, creates opportunity
  • Dynamic challenge
  • Events: Emulation v. Simulation
  • Assists in Driving the action
shipping games vs test code
Shipping Games vs. Test Code
  • Hard constraint on CPU usage
  • Reproducibility is vital, for test and design
  • Must be fun, not correct
  • Must succeed, finish, do something, always
mini case study

Mini Case Study

The Thief AI

design goals
Design Goals
  • Player is going to be a Thief
  • I.e. Sneak Around, Ambush, Hide, Steal
    • AI must allow players to make plans
    • And react to player actions, provide challenge
  • Game will feature a loose overall story
    • Ability to script/override behavior
    • In game actions fed back out to story control
watch able by the player
“Watch-able” by the player
  • Has to “go about it’s business” with intent
  • Actions must make sense to player
    • “interestingly predictable”
    • present play opportunities for player
  • Overemphasize thoughts
    • Telegraph all actions
    • Goals must be very explicit
  • Model senses, detection, awareness
  • Simple event based “reaction” scripts
  • Tagging of world objects which notify AI
  • Patrol paths, dynamic “go-to-object”
  • Rule based match database for speech
  • Heavily designer driven, toolset approach
mini case study1

Mini Case Study

Sports Games

commentator examples
Commentator Examples
  • Excitement, plus reason for play result
  • Finite range of possible utterances
    • “decision quality” is often less important than the “media asset quality”
  • Better to be silent than stupid
  • Correct isn’t good enough
    • [take a knee != loss of 2]
on computer opponents
On Computer Opponents
  • Give player ways to make the big play
  • Predictable often more important than smart
  • Machine opponents are babysitters, not ruthless opponents
  • Clever AI decision no better than secret special knowledge if player cant tell
  • Players aren’t pro players, or pro strategists


Did any of this make sense?

  • Focus on the Player Experience
  • Allow player to understand AI actions
  • Needs to achieve design aim (and fun)
  • Configurable, Override-able, Testable
  • Satisfies data and speed constraints
  • Player Player Player Player Player Player
  • How can AI enhance player experience
  • AI is facilitator of the “fun”
  • Enable creative expression for player
    • Allow player to impact the world
    • Put player in interesting situations
  • Game Masters – AI for dramatic arc
  • Sports/Racing – personality, not just better die rolls or performance
  • NPC’s with real goals players can aid/foil
  • Adaptive Difficulty based on player
  • Progress can become less mechanical
  • No more save/load till you get it “right”
my agenda
My Agenda
  • For AI to impact game play, designers need better tools, and ones that they understand
  • With more sophisticated foils can we give players interesting challenges
  • Said challenges lead to experience more about the player, and what player wants
  • Games about players are more interesting than games about designers
Games are still usually things to “Solve”

When they become things to experience, the player will be able to invest far more, and thus the reward for playing will be higher.