36
Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Embed Size (px)

Citation preview

Page 1: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Battle Swarm: An Evolutionary Approach to

Complex Swarm Intelligence

Russel Ahmed Apu

Marina Gavrilova

Page 2: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Brief Outline

• Battle Swarms

• Tactics and battle efficiency

• Swarm Intelligence: Missile Genotype Encoding

• Evolutionary strategies for battle swarms

• Experimental results and analysis

Page 3: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Objective:To utilize swarm based tactics & evolutionary

swarm strategies to increase tactical efficiency for offensive and defensive agents

Page 4: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Battle Swarms Agents

• MISSILES

• Autonomous• Limited sensory

capabilities• Limited intelligence• Single objective: Hit ship• Complex dynamic system• Behavior of one missile

effect other missiles in the swarm

• Evolutionary Strategy

• DEFENSE TURRETS

• Point Defense system• Only Visual/radar

capabilities• Limited coverage• Single Objective: Destroy

missiles • Simple rule, complex

outcome: Select and fire• Behavior and efficiency

cruicial to survival• Fixed Strategy

Page 5: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Defense Mechanism

Missile

Missile

Missile

Point Defense

Reaction Radius

Reaction

Page 6: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Actions of a Missile

Constant Thrust

Right

Up

Heading

ROLL LEFT

ROLL RIGHT

PITCH DOWN

Action Encoding Set: {LRUDNMFAXYZ}* X=Rand Y=Converge*

L= Roll Left U=Pitch Up N=NOP F=Follow* Z=Diverge*

R=Roll Right D=Pitch Down M=Memory A=Avoid*

* Discussed in the next few slides

PITCH UP

Page 7: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Basic Sensory Encoding and Actions

COG

Follow Target

Projection Plane

(1)

Roll to match proj(v)=proj(u)

(2)

Pitch upProj(v)

Proj(u)

Page 8: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Basic Sensory Encoding and Actions

COG

Avoid Target

Projection Plane

(1)

Roll to match proj(v).proj(u)=0

(2)

Pitch up

Proj(v)

Proj(u)

Page 9: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Target Relative Coordinate(Range, Heading, Bearing)

x y zf ,f ,f Forward Vector of missile m

Up vector of missile m

Location of the missile m

Location of the Target

m

m

m

F

u

p

T

= =

=

=

=

r

r

( )

( )

( )

( )

2x x y x z

2xx y y z

2xx z y z

f1- -ff -ff

f-ff 1- -ff=

f-ff -ff 1-

Heading, mm ph F

é ùê úê úê úê úê úê úë û

= ·

M

Mr

Range, pM TR -=

( ) ( )( )( )Bearing, mm mm mb FT p T pu u= × ·- -· ´M Mr r

Page 10: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Target relative: Heading

Page 11: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Target Relative: Bearing

COG

Projection Plane

u

PRproj

b Rproj

F

Page 12: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Swarm Relative Encoding

• Regulates the probability of Flocking Tendency• ‘Y’ Flock and increase tendency (probability of

Boids flocking)• ‘Z’ Diverge from flock and decrease tendency• If an agents decides to flock (prob= ), the direction is

determined using modified BOIDS

Boids flocking: From left to right rules of cohesion, separation and alignment [2].

Page 13: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Decision Making• Event related decision are made by the

swarm implicitly

• Avoiding Incoming fire: Ionization trail gives negative pheromone to allow flocking out of a region

• Finding Weakness in Defense: Combined usage of flocking tendency, gas and ionization pheromone trail

Page 14: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Basic Encoding of Missile genotype

• String of Possible Action (I.e [LYUXLY])

• Action string is circular (iterative)

• Missile DNA=Gene_String[]

• Continuous execution of the string

• Each action executed for an infinite time

• Regulates Swarm Behavior/Tendency

Page 15: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Encoding Basic Maneuvers

• Maintain Current Heading = [N]• Homing the Target = [F]• Ring Motion = [U] • Cork Screw = [LU], [LUMMM]• Evasive Approach = [XF], [XMMMF]• Basic Evasive Action = [A], [AMMMX]• Fall Back = [XU], [XMMMU], [AU]• Scramble = [X]

Page 16: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Basic Maneuvers

[N]

[A]

[U]

[F] [XF]

[LU]

Page 17: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Different Complex Maneuvering Tactics

• Retaliation – frontal attack• Evasive – avoid fire at all costs• Convergent approach – approach target from a

particular direction• Divergent approach – surround and approach from

different directions• Trail wind flocking –one missile leads others • Distract and draw fire

Page 18: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Different Complex Maneuvering Tactical strategies

(a) Diversion (b) Trail Wind Flocking

(c) Retaliation (d) Divergence

Page 19: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Mutating and Evolving the Missile Genotype

• Fitness: Define a fitness function for the desired action

• Crossover: Augment/concatenate Genes

{[LUMU] [AMD]} {[LUAMDMU] [LUMD] [AMDUMU] [LMDMU]…}

• Randomization: Replace arbitrary symbols with “X”… run the simulation and convert meta genes to real genes

[FFLLU] [FXLXU] {[FULLU], [FFLFU], [FNLNU], [FMLNU]} Best{[FULLU], [FNLNU]}

Page 20: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Induced Evolution• We can introduce certain desired behavior

in addition to natural evolution

• Step 1: Train Missiles separately to obtain certain desired behavior without any other consideration. Obtain Viral strain W=[…]

• Step 2: Infect All current Genotype with viral Strain W (crossover)

Page 21: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

The Game: Co-evolution

1. Implement basic missile [F] and basic Turret {Select X, Fire@trajectory}

2. Adjust physical property to match– Fitness=50% (50% missiles hit the target)

3. Evolve Missiles and turrets against previous strain

4. Repeat step 3 for several Games cycles

5. If fitness falls or rises dramatically increase physical strength of opposing swarm (Missile: Acceleration, velocity, turning. Turrets: Speed of fire, number of turrets, firing frequency)

Page 22: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

The Fitness Function: Hetero-Sexual Mating

• Use a two dimensional Fitness Function• Every missile has a masculine and a feminine fitness• Masculine: Ability to Attack• Feminine: Ability to Survive

,i iiW W= J,i iiW W= J

# of missile hitting the target# of missiles launched

# of gunshots successfully evaded# of missiles destroyed+1

i

i

W =

=J

Page 23: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Results

- Strategies evolved, Runtime and other aspects

Page 24: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Fitness Function

0

5

10

15

20

25

30

35

40

45

50

0 20 40 60 80 100

Masculine

Fem

inin

e

Randomized No Randomization

Evasive

Dispersion

DistractionSwarm: Trail Wind

Assult

Page 25: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Complex Tactics: Convergent Approach

• Strength in numbers

• Less exposure to incoming fire

• Increase of spatial threat

• Decrease of temporal threat

• High Efficiency

• Low evasion

• Highly Masculine

Page 26: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Complex Tactics: Divergent Approach• Cause more distraction and

confuse the defense system

• Less likelihood for a missile to draw fire

• Decrease of spatial threat

• Increase of temporal threat

• Lower Efficiency

• Highly Evasive

• Highly Feminine

Page 27: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Convergent VS Divergent Approach

• CONVERGENT• Less defense turrets• Draw less fire• Easy to shoot down

• DIVERGENT• More defense turrets• Draw more fire• Distracting and hard to

shoot down

Page 28: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Complex Tactics: Trail Wind Flocking

• Better than “Convergent Approach”

• Least exposure to incoming fire

• Lot of opportunity for diversion/distraction

• Decrease of spatial threat

• Decrease of average temporal threat

Page 29: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

More Results

(a) Funnel Shaped Assault

(b) Parachute Phase 1: Forming a moth ball

(c) Parachute Phase 2: Dispersing

(d) Parachute Phase3: Forming a Head

(e) Parachute Phase 4: Trail Wind Attack

(f) Divergent Attack

Page 30: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

More Results

Figure 11: Formation of Distraction, Organic and Deception pattern

(h) Distraction 2: Assault in progress

(g) Distraction 1: Early missiles draw fire

(i) Organic motion pattern

(j) Deception 1: Lead Assault

(k) Deception 2: Overshooting the target

(l) Deception 3: Come about and attack

Page 31: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

More Results

See Animation Demos

Page 32: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Rendering and Physical Engine

• Regular physics engine will not suffice– Approximation aggravates trajectory

computation

• Construct everything from scratch– Advanced look-ahead estimation based physics

engine – Robust Rendering engine:

• Anisotropic Texture filtering • Multiple LOD based geometry rendering• Particle engine • Highly optimized exclusive API for performance• Flexibility

Page 33: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

The Simulation Engine

• Robust design: Separation of Rendering modules from the simulation

• Implements Command Console• Runtime performance is highly efficient• For 50 missiles:

– Full quality rendering@ 50FPS !!!– Simulation runs upto 50 times faster

(FPS=2200+) is rendering is turned off (for evolutionary algorithm)

– Excellent Rendering quality (anisotropic texture mapping, particle engine)

Page 34: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Runtime PerformancePerformance of Different Runtime Modes

38.16

98.72

391.74

48.77

110.33

715.73

0

100

200

300

400

500

600

700

800

Mode

Fra

me

/Se

co

nd

Page 35: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Summary• Using Swarm Intelligence to evolve battle tactics for

– Missiles– Point Defense Turrets

• Evolutionary strategies:– Gene_String[] evolution– The novel “Induced Evolution” strategy– Co-evolutionary strategy

• Implementation: – Rendering and physical Engine– Genotype encoding– Basic maneuvers– Complex maneuvers– Integration

Page 36: Battle Swarm: An Evolutionary Approach to Complex Swarm Intelligence Russel Ahmed Apu Marina Gavrilova

Thank you