Evolving Virtual Creatures by Karl Sims 1995 Adelein Rodriguez

1
Evolving Virtual Creaturesby Karl Sims
(1995)Adelein Rodriguez
2
Outline

• Goal Perspective
• Motivation
• Creatures
• Morphology
• Control
• Evolution
• Coevolution
• Demo
• Comments
• Other Work

3
Goal

• Automatically create creatures by evolving its
  morphology and behaviour.
• Creatures will be optimized for specific tasks
  such as walking, jumping, and swimming.
• Perspective
• Karl Sims had previously evolved expressions for
  creating virtual plants, particle effects, and
  others.
• Genetic Programming recently invented (1992),
  evolving of variable length genomes.
• MIT Media Lab
• This work has been referenced 440 times.

4
Motivation

• Tedious coding process for creating behaviours
  that look realistic.
• Entertainment industry
• Creating film effects
• Creating characters
• Need specific behaviours, thus optimization
  technique such as evolution can help bias.
• Previous work evolved either the morphology, or
  the control structure, but not both.
• Here we want to evolve a control for a structure,
  and a structure for the control.

5
The big picture

• Genotype
• Directed graphs of nodes and connections. Graphs
  provide instructions for building a creature and
  cycles for repeating same part.
• Phenotype
• Body parts are made by starting at the root node
  of the directed graph and following the
  connections.

6
Morphology

• Node
• Dimensions
• Joint type Defines degrees of freedom type of
  movement relative to parent part.
• Revolute
• Rigid
• Twist
• Universal
• Etc...
• Joint Limits Point at which need to exert string
  forces.

7

• Node (cont)
• Recursive Limit No. of times it can generate a
  part from a cycle.
• Neurons Given an input perform a function to
  produce and output.
• Connections to other nodes (parts)
• Position, orientation, scale, and reflection,
  terminal only flag.

8
Example Hand Designed Topologies
9
Control
10
Sensors

• Connected to
• Effector
• Neuron
• Embedded in body parts
• Joint angle sensors monitors values of degrees
  of freedom.
• Contact Sensors Positive activation (1,0) if
  contact. Negative activation (-1,0) if no
  contact. Present on all surfaces.
• Photosensors 3 sensors combined to get
  coordinates of global light source.
• Sensors enabled depending on environment.
  (Manually?)

11
Neurons

• Functions sum, product, threshold, min, max, if,
  sigmoid, oscillate-wave, etc.
• Two types of functions
• Operate on input and give output directly
• Recurrence, output depends on time step. Can give
  different output even if inputs is constant.
  Memory.

12
Effectors

• Connected to
• Sensor
• Neuron
• Value is exerted as a joint force
• Maximum strength proportional to the max cross
  sectional area of the 2 parts it joins. Force
  scales with area.

13
Going from genotype to phenotype

• Iterate over directed graph to create body parts
• Blocks of neural circuitry can be replicated
  together with morphological nodes.
• There can be connections between adjacent parts .
  Sensors, neurons and effectors from one part can
  connect to sensors, neurons and effectors from
  other part. Allows coordination.
• There is a separate graph of neurons not tied to
  any part. Phenotype has only one copy of this
  graph. Brain ?
• Can allow centralized control

14
How it all comes together

• Nodes contain sensors, neurons (graphs), and
  effectors.
• Connections allow flow of signals between nodes.

15
(No Transcript)
16
The idea

• Similar to Nervous System
• Localized distributed control (neurons for every
  part)
• Central control (separate groups of neurons)

17
Phenotype Brain
Phenotype Morphology
18
This creature swims by making paddling motions
with the flippers
19
Evolution

• Initial population random genotypes and previous
  evolution genotypes.
• Population size 300
• Selection Top fit 1/5 of population survives to
  next generation.
• Fitness evaluation place creature in a simulated
  environment, goal is to optimize for specific
  task or behaviour (e.g. jumping).
• Pre-screening process.

20
Fitness Evaluation

• 4 Different Evolutions, each with different
  tasks
• Swimming
• Walking
• Jumping
• Following

21
Swimming

• Simulated environment has no gravity.
• Viscosity effect.
• Faster it swims, higher fitness.
• Straight swimming gets higher fitness than
  circling.
• Continuous movement gets higher fitness than
  initial drastic jumps.

22
Walking

• Walking kind of moving on land.
• Gravity and friction.
• Faster it moves, better. Vertical movement is
  ignored.
• Environment could have other objects.

23
Jumping

• Measure vertical movement.

24
Following

• Task is to follow a light source
• Many trials with light source at different
  positions
• Faster it moves towards light source better.
• Land and water environments.

25
Evolution (Cont)

• Get surviving creatures, mate and/or mutate them.
  
• Reproduction Only highest fit can reproduce,
  higher fit reproduce more.
• To create an offspring you can mutate a parent,
  or mate two parents by either one of two
  crossover types.

26
Mutation

• Graph mutation steps
• 1) Node's internal parameters
• Boolean values change from true to false and vice
  versa.
• Scalar values change according to a Gaussian
  scale (Small adjustments are more likely than
  drastic ones)
• 2) Add a new node to graph
• Must be followed by a mutation that adds a
  connection to it in order to have effect.

27
Mutation (Cont)

• Graph mutation steps (cont)
• 3) Connection's internal parameters
• 4) Add/Remove a connection (can only happen in
  morphological graphs, nor neural ones)
• 5) Remove unconnected nodes and neurons.
• Morphology graphs mutated first, then inner
  graphs.

28
Mating

• Combines structures from two parent genotypes to
  make an offspring.
• Used two mating types
• Crossover
• Graft

29
Evolution (Cont)

• Some creatures from one evolution were used as
  seeds for other evolutions.
• A creature from one medium could be used for
  evolution in another medium.

30
Co Evolution

• Evolving 3D Morphology and Behaviour by
  Competition (1994)
• Place pairs of creatures in an arena to compete
  for a common resource.
• Taller creatures start further back.

31
(No Transcript)
32
How to pair individuals

• Each to all
• Very expensive
• Each to some
• Might not get correct idea of fitness relative to
  others.
• Species intrabreeding
• Species interbreeding

33
Interesting results

• Interspecie competition was observed where both
  species developed different techniques for
  grabbing the cube, then tried to add techniques
  to stop the other from grabbing it.
• Push cube from opponent, then follow it.

34

• Demo

35
Additional Comments

• Genotype-Phenotype encoding allows to specify the
  structure and behaviour in a compact way.
  Indirect encoding.
• Only need to specify a few building blocks and
  the rules for how to combine the building blocks
• Information reuse, modularity.
• Avoids hardships of hand coded designs. Very
  useful for automatic content creation (Games)
• Use of evolutionary search allows for parallel
  search over many possible structures and
  behaviours.
• Neural structure is added as needed and tightly
  connected to the morphological structure.
  Co-adapation.

36
Additional Comments (Cont)

• Evolution attempts to find (learn) the best
  mapping of sensors and effectors by being exposed
  to the environment.
• Downside Fitness function and genotype language
  encoding need a lot of hand design.

37
Other Related Work

• http//sodarace.net/
• http//www.frams.alife.pl/a/al_pict.html