Evolving Motor Techniques for Artificial Life

1
Evolving Motor Techniques for Artificial Life
Kelley Hecker, Period 7
2
Evolving Creatures

• Creatures develop more advanced motor techniques
• Progression from random movements to
  sophisticated patterns
• Possibility of specialized creatures
• Co-evolution
• Both the body and the brain develop

3
Creature Genomes
Creature Genomes

• Genome represented by a one-dimensional array
• Each array has several nodes
• Nodes represent body segments
• Each node contains dimensions for body part,
  location of parent and child connections, and
  neuron functions
• Genome converted to physical form for simulation

4
Example Genomes
Example Genomes
Example Genomes

• Root Node
• Length 3, Width 2, Height 2
• Child 0
• Length 2, Width 2, Height 3
• Child 1
• Length 1, Width 4, Height 4
• Child 2
• Length 1, Width 3, Height 4
• Child 3
• Length 1, Width 3, Height 2

Note Each node also contains the neuron data,
but since this cannot be seen physically I did
not list it
5
More Genomes
6
Methodology Controller

• Controller object maintains an array of genomes
• Generates new genomes at beginning of simulation
• Displays creatures and runs simulation
• Measures fitness and breeds creatures for next
  generation

7
Methodology Nodes

• Physical dimensions
• Where the body segment connects to its parent and
  children segments
• Neuron functions
• Methods to add children and connection points
• Accessor methods return children, dimensions and
  neurons

8
Methodology Creature GA

• Applies neuron functions to sensor values
• Possible neuron functions
• Oscillating functions sin, cos, atan, saw-wave
• Other functions sum-threshold, sign-of, min,
  max, mem, log, expt, devide, interpolate,
  differentiate
• Returns joint velocity values for the associated
  body segment

9
Circulation of Data
Values received from joint-angle sensors
Values become effectors and modify joint velocity
Values sent to the GA, where they are put through
node's neurons
10
Reproduction

• Creatures are evaluated based on their
  performance in the simulation
• Top fifth of genomes copied directly (asexual)?
• Remaining 4/5 of genomes are crossed over in
  pairs

11
Crossover
12
Crossover

• Children have both physical and control traits of
  their parents
• A portion of the limbs will be physically the
  same and controlled in the same way as one of the
  parents, while the remaining limbs will be
  identical to the second parent
• Allows for co-evolution both the body and brain
  change

13
Simulation Process

• Population is simulated in the physical
  environment
• All of the creatures are displayed at once
• Final fitnesses are evaluated and reproduced
• Repeated with next generation for n generations

14
Example Simulation
One creature is copied directly to the second
generation. Can you tell which one?
http//www.youtube.com/watch?va_jyKuzrBRM
15
Testing

• Fitness tests
• Measures the success of a motor method
• Progression of fitness level shows evolution of
  technique
• Create graph of fitness level over time

16
4th Quarter

• Continue simulation for more than two generation
• Implement mutation
• Graph fitness values over time
• About half the creatures are duds. Is there a
  way to fix this besides repeated generations?