Presentation is loading. Please wait.

Presentation is loading. Please wait.

Oct 30, Fall 2006IAT 4101 AI in games Simple steering, Flocking Production rules FSMs, Probabilistic FSMs Path Planning, Search Unit Movement Formations.

Similar presentations


Presentation on theme: "Oct 30, Fall 2006IAT 4101 AI in games Simple steering, Flocking Production rules FSMs, Probabilistic FSMs Path Planning, Search Unit Movement Formations."— Presentation transcript:

1 Oct 30, Fall 2006IAT 4101 AI in games Simple steering, Flocking Production rules FSMs, Probabilistic FSMs Path Planning, Search Unit Movement Formations

2 Oct 30, Fall 2006IAT 4102 AI in video games  5-10% of CPU for Realtime  25-50% of CPU for Turn-based –Chase/Escape behaviors –Group behaviors –Finite State machines –Adaptation/Learning

3 Oct 30, Fall 2006IAT 4103 Questions  How good should the AI be?  Why are people more fun than NPC’s?  Will networked games reduce AI?  New directions for AI in games?

4 Oct 30, Fall 2006IAT 4104 Learning/Adaptation  Increment aggressiveness if player is doing well –The Computer-Based SATs do this!  Levels are a pre-programmed version of adaptation  Tuning  Stability  How might adaptation make play Better or Worse?

5 Oct 30, Fall 2006IAT 4105 Adaptation vs. Play quality  Do you want the monsters in Quake to get better as you get better?  Force the user to live with the consequences of his/her actions  Can surprise the designer (Creatures)  Pit AI creatures against each other to find bugs or tune actions  Robotwar

6 Oct 30, Fall 2006IAT 4106 What is good AI?  Perceived by user as challenging –Cruel, but fair!  User is surprised by the game –but later understands why  Feeling that reality will provide answers –able to make progress solving problem  What games have used AI effectively?

7 Oct 30, Fall 2006IAT 4107 Chase/Evade  Algorithm for the predator?

8 Oct 30, Fall 2006IAT 4108 Enhancements to Chase  Speed Control –Velocity, Acceleration max/min –Limited turning Radius  Randomness –Moves –Patterns

9 Oct 30, Fall 2006IAT 4109 Enhancements to Chase Anticipation Build a model of user behavior

10 Oct 30, Fall 2006IAT Steering Behaviors  Pursue  Evade  Wander  Obstacle Avoidance  Wall/Path following  Queuing  Combine behaviors with weights  What could go wrong?

11 Oct 30, Fall 2006IAT Group Behaviors  Lots of background characters to create a feeling of motion  Make area appear interesting, rich, populated

12 Oct 30, Fall 2006IAT Flocking -- (HalfLife, Unreal)  What might go wrong? Simple version: Compute trajectory to head towards centroid

13 Oct 30, Fall 2006IAT Group Behaviors  Reaction to neighbors -- Spring Forces Craig Reynolds SIGGRAPH 1987

14 Oct 30, Fall 2006IAT What could go wrong?  Repulsive springs around obstacles  Does not handle changes in strategy Exactly aligned Forces balance out in dead end

15 Oct 30, Fall 2006IAT “Perceptual” Models

16 Oct 30, Fall 2006IAT Production Rules If( enemy in sight ) fire If( big enemy in sight ) run away If( --- ) ----  Selecting among multiple valid rules –Priority weighting for rules or sensor events –Random selection  No state (in pure form)

17 Oct 30, Fall 2006IAT Finite State Machines  States: Action to take –Chase –Random Walk –Patrol –Eat  Transitions: –Time –Events –Completion of action Chopping Take Wood to closest depot Enough wood Drop wood: Go back to woods At depot At woods

18 Oct 30, Fall 2006IAT State Machine Problems  Predictable –Sometimes a good thing –If not, use fuzzy or probabilistic state machines  Simplistic –Use hierarchies of FSM’s (HalfLife)

19 Oct 30, Fall 2006IAT Probabilistic State Machines  Personalities –Change probability that character will perform a given action under certain conditions

20 Oct 30, Fall 2006IAT Probabilistic Example Fire At Enemy Run out of Range Enemy Within Hand- to-Hand Range 50% Far Enough to Take Shot Run Away Enemy Within Hand- to-Hand Range 50%

21 Oct 30, Fall 2006IAT Probabilistic State Machines  Other aspects: –Sight –Memory –Curiosity –Fear –Anger –Sadness –Sociability  Modify probabilities on the fly?

22 Oct 30, Fall 2006IAT Planning  Part of intelligence is the ability to plan  Move to a goal –A Goal State  Represent the world as a set of States –Each configuration is a separate state  Change state by applying Operators –An Operator changes configuration from one state to another state

23 Oct 30, Fall 2006IAT Path Planning  States: –Location of Agent/NPC in space –Discretized space Tiles in a tile-based game Floor locations in 3D Voxels  Operator –Move from one discrete location to next

24 Oct 30, Fall 2006IAT Path Planning Algorithms  Must Search the state space to move NPC to goal state  Computational Issues: –Completeness Will it find an answer if one exists? –Time complexity –Space complexity –Optimality Will it find the best solution

25 Oct 30, Fall 2006IAT Search Strategies  Blind search –No domain knowledge. –Only goal state is known  Heuristic search –Domain knowledge represented by heuristic rules –Heuristics drive low-level decisions

26 Oct 30, Fall 2006IAT Breadth-First Search  Expand Root node –Expand all Root node’s children Expand all Root node’s grandchildren  Problem: Memory size Root Child1 Child2 Root Child1 Child2 GChild1 GChild2 GChild3 GChild4

27 Oct 30, Fall 2006IAT Uniform Cost Search  Modify Breadth-First by expanding cheapest nodes first  Minimize g(n) cost of path so far Root Child1 Child2 GChild1 9 GChild2 5 GChild3 3 GChild4 8

28 Oct 30, Fall 2006IAT Depth First Search  Always expand the node that is deepest in the tree Root Child1 GChild1 GChild2 Root Child1 Root Child1 GChild1

29 Oct 30, Fall 2006IAT Depth First Variants  Depth first with cutoff C –Don’t expand a node if the path to root > C  Iterative Deepening –Start the cutoff C=1 –Increment the cutoff after completing all depth first probes for C

30 Oct 30, Fall 2006IAT Iterative Deepening Root Child1 Root Child1 GChild1 Root Child1 Child2 Root Child1 GChild1 GChild2 Root Child2 GChild3 GChild4

31 Oct 30, Fall 2006IAT Bidirectional Search  Start 2 Trees –Start one at start point –Start one at goal point

32 Oct 30, Fall 2006IAT Avoid Repeating States  Mark states you have seen before  In path planning: –Mark minimum distance to this node

33 Oct 30, Fall 2006IAT Heuristic Search  Apply approximate knowledge –Distance measurements to goal –Cost estimates to goal  Use the estimate to steer exploration

34 Oct 30, Fall 2006IAT Greedy Search  Expand the node that yields the minimum cost –Expand the node that is closest to target –Depth first –Minimize the function h(n) the heuristic cost function  Not Complete!  Local Minima

35 Oct 30, Fall 2006IAT A* Search  Minimize sum of costs  g(n) + h(n) –Cost so far + heuristic to goal  Guaranteed to work –If h(n) does not overestimate cost  Examples –Euclidean distance

36 Oct 30, Fall 2006IAT A* Search  Fails when there is no solution –Avoid searching the whole space –Do bi-directional search –Iterative Deepening

37 Oct 30, Fall 2006IAT Coordinated Movement  Somewhat more difficult than moving just one NPC –Disappearing goal –New obstacles in path –Collisions with other NPCs –Groups of units –Units in formation

38 Oct 30, Fall 2006IAT Coordinated Elements  Collision detection –Detection of immediate collisions –Near future  Perform the usual collision detection optimizations –Spatial hierarchies –Simplified tests –Unit approximations

39 Oct 30, Fall 2006IAT Collision Detection  Levels of collision –Hard radius (small) Must not have 2 units overlap hard radius –Soft radius (large) Soft overlap not preferred, but acceptable

40 Oct 30, Fall 2006IAT Collision Detection  With movement, need to avoid problems with bad temporal samples –Sample frequently –Detect collisions with extruded units –Use a movement line –Detect distance from Line segment

41 Oct 30, Fall 2006IAT Unit Line  Unit line follows path  Can implement minimum turn radius  Gives mechanism for position prediction  Connected line segments –Time stamps per segment –Orientation per segment –Acceleration per segment

42 Oct 30, Fall 2006IAT Prediction line  Given prediction, use next prediction as move  Prediction must have dealt with collisions already

43 Oct 30, Fall 2006IAT Collision Avoidance Planning  Don’t search a new path at each collision  Adopt a Priority Structure –Higher priority items move –Lower priority items wait or get out of the way  Case-based reasoning to perform local path reordering  Pairwise comparison

44 Oct 30, Fall 2006IAT Collision Resolution Summary  Favor: –High priority NPCs over Low Priority –Moving over non-moving  Lower Priority NPCs –Back out of the way –Stop to allow others to pass  General –Resolve all high-priority collisions first

45 Oct 30, Fall 2006IAT Avoidance  Case 1: Both units standing –Lower priority unit does nothing itself –Higher unit Finds which unit will move Tells that unit to resolve hard collision by shortest move

46 Oct 30, Fall 2006IAT Avoidance  Case 2: I’m not moving, other unit is moving –Non-moving unit stays immobile

47 Oct 30, Fall 2006IAT Avoidance  Case 3: I’m moving, other is not: –If lower priority immobile unit can get out of the way: Lower unit gets out of way Higher unit moves past lower to get to collision free point –Else If we can avoid other unit Avoid it!

48 Oct 30, Fall 2006IAT Avoidance  Case 3: I’m moving, other is not: –Else: Can higher unit push lower along Push! –Else: Recompute paths!

49 Oct 30, Fall 2006IAT Avoidance  Case 4: Both units moving –Lower unit does nothing –If hard collision inevitable and we are high unit Tell lower unit to pause –Else: If we are high unit Slow lower unit down and compute collision-free path

50 Oct 30, Fall 2006IAT Storage  Store predictions in a circular buffer  If necessary, interpolate between movement steps

51 Oct 30, Fall 2006IAT Planning  Prediction implies –A plan for future moves  Once a collision has been resolved –Record the decision that was made –Base future movement plans on this Blocking unit Get-To Point Predicted Position

52 Oct 30, Fall 2006IAT Units, Groups, Formations  Unit –An individual moving NPC  Group –A collection of units  Formation –A group with position assignments per group member

53 Oct 30, Fall 2006IAT Groups  Groups stay together –All units move at same speed –All units follow the same general path –Units arrive at the same time Obstruction Goal

54 Oct 30, Fall 2006IAT Groups  Need a hierarchical movement system  Group structure –Manages its own priorities –Resolves its own collisions –Elects a commander that traces paths, etc Commander can be an explicit game feature

55 Oct 30, Fall 2006IAT Formations  Groups with unit layouts –Layouts designed in advance  Additional States –Forming –Formed –Broken  Only formed formations can move

56 Oct 30, Fall 2006IAT Formations  Schedule arrival into position –Start at the middle and work outwards –Move one unit at a time into position –Pick the next unit with Least collisions Least distance –Formed units have highest priority Forming units medium priority Unformed units lowest

57 Oct 30, Fall 2006IAT Formations Not so good… Better…

58 Oct 30, Fall 2006IAT Formations: Wheeling  Only necessary for non-symmetric formations Break formation here Stop motion temporarily Set re-formation point here

59 Oct 30, Fall 2006IAT Formations: Obstacles Scale formation layout to fit through gaps Subdivide formation around small obstacles

60 Oct 30, Fall 2006IAT Formations  Adopt a hierarchy of paths to simplify path-planning problems  High-level path considers only large obstacles –Perhaps at lower resolution –Solves problem of gross formation movement –Paths around major terrain features

61 Oct 30, Fall 2006IAT Formations  Low-level path –Detailed planning within each segment of high-level path –Details of obstacle avoidance  Implement path hierarchy with path stack High-Level Path Low-Level Path1 High-Level Path Low-Level Path2 High-Level Path Low-Level Path2 Avoidance Path

62 Oct 30, Fall 2006IAT Path Stack High-Level Path Low-Level Path1 High-Level Path Low-Level Path2 High-Level Path Low-Level Path2 Avoidance Path 1 2 Low-level path Avoidance path

63 Oct 30, Fall 2006IAT Compound Collisions  Solve collisions pairwise  Start with highest priority pair –Then, resolve the next “highest priority pair” now colliding

64 Oct 30, Fall 2006IAT General  Optimize for 2D if possible  Use high-level and low-level pathing  Units will overlap!  Understand the update loop –It affects unit movement  Maintain a brief collision history


Download ppt "Oct 30, Fall 2006IAT 4101 AI in games Simple steering, Flocking Production rules FSMs, Probabilistic FSMs Path Planning, Search Unit Movement Formations."

Similar presentations


Ads by Google