Tactical AI 3

1
Tactical AI 3

• Michael Zyda
• Zyda_at_usc.edu

2
Week 5 Autonomous Game Play Interaction

• Project 5 Develop an AI client that fights/plays
  against the live players in the networked game
  using the internal representation of the state of
  the game built for project 4. Use a finite state
  machine architecture for this.
• Reading http//www.aiwisdom.com/bytopic_statemach
  ines.html

3
Week 6 Genetic Algorithms Evolutionary
Behaviors

• Project 6 Continue developing the fight/play
  behavior of your AI client. Consider how to
  develop clients that can dynamically evolve and
  develop new tactics and behaviors. Consider
  developing an entire evolving architecture of
  characters that fight/play against the live
  characters in the networked game.
• Reading http//www.aiwisdom.com/bytopic_genetic.h
  tml
• http//www.aiwisdom.com/bytopic_genetic.html
• http//aiwisdom.com/bytopic_strategy.html
• http//aiwisdom.com/bytopic_strategy.html

4

• Squad Tactics Team AI and Emergent Maneuvers
• William van der Sterren (CGF-AI)
• AI Game Programming Wisdom, 2002.
• Topics Strategy, Tactical, Coordinated Movement,
  Cooperation Genres FPS, Action
• Abstract AI squad behavior is made up of
  coordinated individual actions towards a joint
  goal. There are two basic coordination styles
  centralized control by a leader, and
  decentralized cooperation between individuals.
  This chapter discusses the latter style in
  detail. Decentralized cooperation can already be
  realized with minor changes to "standard
  individual AI". This chapter illustrates how some
  tactical squad maneuvers can emerge from these
  coordinating individual AIs, using a squad
  assault as an example. The limitations of the
  approach are illustrated using a second example
  a squad ambush. This chapter precedes and
  complements the chapter "Squad Tactics Planned
  Maneuvers".

5
Squad Tactics

• When the AI operates in squads, it can do a lot
  for a tactical combat game the squads behavior
  communications create a more realistic
  atmosphere.
• Squads fighting against the player will challenge
  his tactical capabilities, and squads fighting
  with the player might offer him a commander role.

6
Decentralized vs centralized approach

• It is easy to answer why squad AI should be part
  of a combat game.
• However, it is not so easy to answer how to add
  squad AI to that game!
• There are many approaches to realize (part of)
  the required squad behavior, but none of these is
  complete or perfect.
• This article and the next discuss two ways of
  realizing squad AI and squad tactics (Fig 5.3.1).

7
(No Transcript)
8

• This article presents a decentralized approach to
  squad AI - interactions between squad members,
  rather than a single squad leader, determine the
  squad behavior.
• And from this interaction, squad maneuvers
  emerge.
• This approach is attractive because it is a
  simple extension of individual AI, and because it
  can be easily combined with level-specific
  scripting.
• However, this approach is weak at maneuvers
  requiring autonomy or tight coordination.

9

• The next article discusses a centralized approach
  to squad AI, with a single squad level AI making
  most of the decisions.
• That squad-level AI autonomously plans and
  directs complex team maneuvers.
• However, that squad-level AI has trouble dealing
  with the strengths and needs of individual squad
  members.

10

• This article briefly defines the key concepts of
  squad ai and squad tactics.
• It discusses the decentralized design, and its
  elements.
• Two examples are used to illustrate how this
  design enables squad tactics - a squad attack,
  and an ambush.
• Based on the example, this article discusses the
  strengths and weaknesses of the decentralized
  design, and some of the workarounds for the
  weaknesses.
• For clarity and brevity, the squad here is
  assumed to consist of infantry soldiers, but the
  ideas presented also apply to many other small
  combat formations (tank platoons, trolls, naval
  vessels, giant robots, and so forth).

11
Squads leadership style

• A squad is a small team, consisting of up to a
  dozen members, with its own goals.
• The squad tries to accomplish its goals through
  coordinated actions of its members, even under
  adverse conditions.
• Casualties and regroupings cause variations in
  the squads structure.
• Moreover, nearby operating friendly squads might
  interfere with the squads operations.

12
Squad leader

• Squads typically have a leader.
• In some cases, this leader is very visible and
  has a different role than the other squad
  members.
• In other cases, such as in room-clearing actions,
  the leader acts like any other squad member - the
  success of the action is primarily due to
  training, rather than the leader.

13

• The squad selects and executes certain maneuvers
  to accomplish its goals.
• Such a maneuver provides each squad member with a
  role and task.
• A squad maneuver can be tightly or loosely
  coordinated.
• In a tightly coordinated maneuver, squad members
  rely on detailed repeatedly rehearsed drills, and
  continuously exchange information to synchronize
  and adjust their actions.
• Much of the synchronization is done through
  quick, nonverbal communications, such as
  predefined hand signals.

14

• In a loosely coordinated maneuver, squad members
  synchronize their actions less often, or just
  with part of the squad.
• The squad relies less on well-known standard
  procedures, and needs larger (verbal)
  communications to synchronize the actions.
• In designing squad ai, these concepts play an
  important role.

15
Squad AI through cooperating members

• One approach to squad ai is the decentralized
  approach, in which the squad members coordinate
  their actions without the need for an ai squad
  leader.
• This approach is attractive for a variety of
  reasons
• It simply is an extension of the individual AI.
• It robustly handles many situations.
• It deals well with a variety of capabilities
  within the team.
• It can easily be combined with scripted squad
  member actions.
• This combination of properties makes the
  decentralized approach an attractive choice for
  games that have the player fight through levels
  of manually positioned teams of opponents.

16
Concept behind decentralized AI

• The design of the decentralized approach is show
  in Fig 5.3.2.
• The squad consists of AI members who all publish
  the following info to nearby squad members
• Their intentions
• Their observations

17
Solo versus Squad Think Loops
18
Where is the squad behavior?

• In this decentralized approach, we find the squad
  behavior in the interactions of the squad
  members, rather than in their individual actions.
• Emergent behavior
• Emergent behavior (or self-organizing behavior)
  is functionality originating from the
  interactions of elements, rather than from
  individual actions.
• The emergent behavior is generated from
  lower-level, simpler behavior.
• The tactical behavior of our squad should emerge
  from the interaction of the squad members.
• More specifically, it should emerge from the
  exchanged observations and intentions, and how
  this info is used in planning and executing
  individual squad member actions.

19
Emergent Fire-and-Maneuver Behavior

• Lets assume that our solo ai features some
  simple combat behavior - it either fires at a
  threat, or moves via the shortest path to a
  better position to fire again.
• By moving, the ai is able to close in on threats,
  and prevents the threat from getting a stable aim
  on him.
• See Figure 5.3.3

20
Solo AI versus Squad Member AI
21

• See the timeline and communications between the
  three interacting squad members.
• These interactions are easily translatable to
  audible communications, making the squad behavior
  become more expressive and real.
• Robust against casualties
• Can also handle different or special capabilities
  of the squad members.
• But his is not all there is to squad tactics.

22

• Imagine the following - a 4-man patrol,
  consisting of a patrol leader, a rifleman, a
  machine gunner, and a sniper, runs into an enemy
  position, and launches an attack (Fig 5.3.5)

23

• Now, we want our squad to do more than just fire
  and move - the squad is to employ proper tactical
  behavior, including
• Stay close to cover
• Prevent blocking other team members
  lines-of-fire.
• Take weapon capabilities into account.
• Maintain team cohesion - in particular, stay
  within audible range and preferably maintain a
  line-of-sight to other squad members (analogous
  to flocking rules for separation, cohesion, and
  avoidance).
• Spread out, and prevent becoming a bunched-up
  target.
• Stay aware of enemy positions and movement thus,
  try to keep a line-of-sight on the enemy and his
  surroundings.

24

• We can deal with these requirements in a
  straightforward way if we extend -
• The squad members mental picture (the
  CombatSituation class).
• The messages exchanged between the squad members.
• To include additional tactical info about the
  other squad members and their positions,
  capabilities and actions.
• We also need to process this extra info, which is
  done using
• A next position to move to algorithm, picking
  the tactically most suitable destination.
• Squad member subclasses (leader, rifleman,
  machine gunner, and sniper) defining the
  parameters for their specific behavior.

25
(No Transcript)
26
Communication among squad members - the messages

• The messages exchanged between the squad members
  convey the intentions and observations of the
  squad members.
• The messages should contain all the info needed
  by the receiving squad member to update his
  mental picture.

27

• Each message also includes the id of the sender.
• Upon receiving the message, the squad member
  updates his CombatSituation accordingly.
• Depending on the squad coordination style, you
  might need to introduce additional messages for
  tighter synchronization.

28

• Why use messages to pass squad member state info
  around, when this info is also available by
  inspecting SquadMemberAI objects directly?
• You can model communication latency by briefly
  queueing the messages.
• You can present the message in the game using
  animations or sound.
• You can filter out messages to the player to
  rpevent overloading him.
• The squad member will send messages to dead squad
  members it assumes still to be alive, adding to
  the realism (and preventing perfect knowledge).
• You can use scripted entities to direct one or
  more squad members by having the scripted
  entities send messages to these squad members.
• You can accommodate human squad members, whose
  state info is largely unavailable, but for whom
  the AI can emulate messages with observations and
  intentions.

29
Picking a tactically sound next position

• Acting tactically requires being in the right
  spot.
• For a squad member involved in our maneuver, this
  right spot depends on his personal capabilities
  and needs, on the needs of his squad members, and
  on the positions of the enemy (see Fig 5.3.6).
• In the maneuver, squad members employ brief
  moves, taking just a few seconds.
• Therefore, if each squad member repeatedly moves
  to the tactically best nearby position, given
  the positions of all squad members and threats,
  some tactically sound maneuvering is likely to
  emerge.
• Each squad member uses an evaluation function to
  pick the most suitable spot from all nearby
  spots.
• This function evaluates many tactical aspects of
  each position, based on the squad members state
  and preferences, known squad claims on positions,
  and the threats (Listing 5.3.2).

30
(No Transcript)
31
(No Transcript)
32

• The evaluation function is robust - it will
  return a spot to move to in all types of
  situations and terrain, as long as sufficient
  maneuver space is available.
• Note that the best next position evaluation
  criteria are reactive these criteria are largely
  determined by the behavior of the threat and
  other squad members.
• This reactivity typically leads to varied
  behavior when the battle is repeated.

33

• However, this reactivity does not provide good
  results in the absence of threats.
• In such a situation, the squad should occupy
  sound tactical locations that in general provide
  a good fighting position against any threat.
• The squad can do so by avoiding any spot that
  limits the ability to attack, such as ladders,
  deep water, or elevators.
• Additionally, the squad member can try to
  maintain its position in the squads formation
  (and pay a penalty for spots away from that
  position).

34
Personalizing the squad member behavior

• Different squad members have different prefs for
  a position to move to.
• These diffs are due to the squad members
  capabilities, the state of the squad member and
  his equipment, and the circumstances.
• Riflemen behave differently from machine gunners
  and snipers - riflemen move quick and often, and
  are expected to close in with the enemy.
• Machine gunners, on the other hand, will be
  slowed by their load, and prefer delivering
  support fire from a rather static position.

35

• Machine gunners will not move very often, and
  consequently need a position providing sufficient
  concealment and cover.
• A sniper will not close in, but engage the enemy
  from a distance.
• Having a clear view and some cover is important
  for the sniper.
• The squad members state also influences the
  position preferences - cover is more preferred
  when the squad member is wounded or has to reload.

36

• The presence of threats and friendly forces
  influences how the squad member moves - a large
  number of friendly forces and few threats cause
  aggressive and audacious moves, whereas the
  reverse situation results in more cautious
  position choices.

37
Waiting in ambush - pros and cons

• Our squad is to perform an L-shaped ambush from a
  position near the edge of the woods.
• To execute this ambush, our squad needs to be
  able to
• Wait until the enemy moves into the kill zone,
  after which the squad is to aggressively attack
  the enemy.
• Pull back to a predefined rally point shortly
  after engaging the threats.
• Return fire, leave the ambush, and pull back to
  the rally point when discovered (and engaged) by
  the enemy before it reaches the kill zone (Fig
  5.3.7).

38
(No Transcript)
39

• This decentralized approach to squad ai deals
  well with half of these ambush requirements.
• First, each of the squad members will return fire
  when being attacked, without relying on
  instructions from a team leader.
• It will not be easy for the enemy to take out the
  ambush from a distance.
• Second, this ai is easily enhanced to include a
  strong pref for being near the rally point.
• As a result, the squad members will fire and
  maneuver toward the rally point.
• To enable this behavior, the level designer
  should be given access to such an optional,
  editable squad member property.

40

• By implementing a squad member aggression level
  that depends on the number of nearby team
  members, and on the number of threats it is
  engaging, we can get the squad to briefly engage
  the enemy, and fall back when taking casualties.
• However, our decentralized approach has trouble
  dealing with the other ambush requirements.
• Most important, a squad org based on cooperation
  rather than an explicit leader will have serious
  trouble reaching a decision and executing it
  unanimously.

41

• For our ambush, this means that our squad is not
  organized to collectively hold fire until the
  threats reach the kill zone.
• We would have to introduce a sleep state, and
  wake up the squad either when receiving hostile
  fire, or when hostile forces activate a trigger
  positioned at the kill zone.
• Additionally, the squad lacks autonomy.
• Whereas the squad does consist of autonomous
  members, nobody has been tasked to think for the
  squad.
• If the enemy moves toward the kill zone, but
  decides to pull back before reaching it, nobody
  in the squad will bother to assault.
• Sensors, perception, goals hierarchy missing
• Due to the same lack of autonomy, the squad would
  never initiate the L-shape ambush itself.
• It is up to the level designers to invent the
  ambush and position th squad.

42

• Squad Tactics Planned Maneuvers
• William van der Sterren (CGF-AI)
• AI Game Programming Wisdom, 2002.
• Topics Strategy, Tactical, Coordinated Movement,
  Cooperation Genres FPS, Action
• Abstract AI squad behavior can also be realized
  by designing an explicit team leader, responsible
  for planning and managing the squad's maneuver.
  This AI team leader assesses the squad's state,
  picks and plans the most appropriate squad
  maneuver. He executes the squad maneuver by
  issuing orders, and by interpreting feedback and
  information from the squad members. This is
  illustrated using a bounding overwatch squad
  advance. This centralized style to squad AI is
  more complex than the emergent behavior in "Squad
  Tactics Team AI and Emergent Maneuvers".
  However, it does provide largely autonomous
  operating squads, able to execute complex
  maneuvers, and often combines well with some
  decentralized cooperation among squad members.

43
(No Transcript)
44
(No Transcript)
45
(No Transcript)
46
(No Transcript)
47
(No Transcript)
48
(No Transcript)
49
(No Transcript)
50
(No Transcript)
51
(No Transcript)