Tactical AI in Real Time

1
Tactical AI in Real Time

• Supervisor Aleks Jakulin
• Crew
• Damir Arh, Matija Jekovec, Mitja Luštrek
• Gregor Leban, Martin Žnidaršic, Uroš Cibej

Translation A. Jakulin
2
Task

• real-time strategy
• objective survive
• based on physical simulation
• computer assists the player (intelligence
  amplification instead of artificial intelligence)
• teams of AI units
• the player does not control individual units
  behavior
• units perform team-allocated duties

3
Program Structure 1/2

• Two separate applications
• server
• client
• Client
• graphics
• user interface
• server connection

4
Program Structure 2/2

• Server
• communication with clients
• physics
• pathfinding
• Hierarchical AI

5
Physical Model 1/3

• Terrain
• 2D map
• passable / impassable kvadratki
• continuous space and time
• map fully revealed to AI
• enemies only seen if at least one of units has
  visual contact

6
Physical Model 2/3

• Unit properties
• movement
• poses walking, sneaking, crawling
• movement speed dependent on orientation and
  health
• separate movement direction and orientation
• 3 shooting modes
• health-, speed- and orientation dependent
• view angle depends on speed of movement (F-01)

7
Physical Model 3/3

• Collision detection
• unit collisions
• bullet collisions
• Raycasting
• map intersections
• object intersections

8
Visibility Graph

• expand the walls for unit radius
• visibility graph nodes are convex corners
• mutually visible corners are connected
• before pathfinding, insert start and goal points
  in the graph
• search with A (F-02), heuristics (F-03)

9
Boids

• Basic rules
• a unit tries to move towards the center of the
  team
• a unit tries to keep a minimum distance from
  walls and objects
• try to match team speed
• These Rules are too local!

10
Teams

• Units in different teams are separate from one
  another (F-04)
• Significance
• hierarchical pathfinding
• minimize team exposure
• maximize team cohesion
• formations

11
Teams Pathfinding

• Player sets the goal point, team adjusts
  individual unit movement given the requirements
  (F-05)
• Pathfinding requirements
• safety
• accessibility
• proximity to goal
• team cohesion

12
Teams Exposure

• Seek proximity of walls and corners, where the
  ratio between the visible covered terrain and
  uncovered terrain is minimal.
• Note we ignore mobility

13
Teams Cohesion

• It is more desirable for units of a team to
  remain close and cover the terrain together.
  (F-06)
• Note in reality its the ease of signaling and
  directed firepower that matter.

14
Finite State Machine

• Controls the units of a team
• simple well-known concept
• readable states are clearly separated
• extensible simple to add new states and
  transitions
• adjustable we choose to do whatever we please
  in a given state
• We have state-dependent weights, adjusting the
  boids model.

15
MDM FSM (F-07)
Mitja Luštrek, Damir Arh, Matija Jekovec
move
init
advance
idle
attack
Seek cover
retreat
prone
16
Maintaining Terrain Visibility

• During movement, the team leader is looking left
  and right, if there is no wall. (F-08)
• Other units are trying to cover 360 degrees
  around the team.
• If there are enough units to cover everything,
  increase the coverage of interesting areas.
• Interestingness of the area depends on proximity
  to walls and dangerous areas, tagged by the
  player. (F-09)

Danger area
17
Shooting Formation

• When enemy is spotted, everyone moves to face the
  enemy, or everyone goes into retreat.
• Units move to avoid shooting one another.
• Units seek positions with better coverage of the
  enemies.

18
Seeking a Safe Position

• If player gives no orders, team moves to a safe
  position.
• Seek proximity of cover.
• Seek good coverage. (F-10)

19
GUM FSM (F-11)

• Gregor Leban, Uroš Cibej, Martin Žnidaršic

init
normal
cover
assault
20
Determining Orientation

• Compute four viewing orientations for each unit.
• Orientations depend on openness of terrain and
  tagged danger areas.
• Pick the most important orientation that is not
  yet covered.

21
Assault

• When enemy is spotted, everyone faces it and
  assaults.
• Every unit picks the closest enemy and fires.
• Move if a friendly unit close near the firing
  direction.
• The player may adjust the formation during
  combat.
• High mobility during an attack.

22
Technical Details

• Development environment Visual C
• Libraries
• Simple DirectMedia Layer (SDL)
• Video for Windows (VFW)
• winsock
• 450 KB of code
• over 17000 lines in 110 files

23
Conclusions

• High computational load.
• Many parameters.
• Weight tuning is complex.
• Machine learning hard to use.
• Commercial games use simpler logic.