Title: Emergent Design
1Emergent Design
Martin Hemberg Imperial College 2004 Emergent
Design
2Who's that guy and what's he doing up there?
- Martin Hemberg
- Developed Genr8 with the Emergent Design Group
(EDG) - Work at Emergent Design Technologies (EmTech)
Architectural Association (AA)
Martin Hemberg Imperial College 2004 Emergent
Design
3Agenda
- Motivation
- Evolutionary Computation (EC)
- Artificial Life (Alife)
- EC and Alife combine well for design tasks
- Example applications
Martin Hemberg Imperial College 2004 Emergent
Design
4Motivation, Architecture
- Break new grounds in architecture
- ED uses a different logic
- Natural form has aesthetic and functional values
- Hard to obtain using ordinary methods
Martin Hemberg Imperial College 2004 Emergent
Design
5Motivation, Computer Science
- Application of EC
- Exploration, not optimisation
- Fitness evaluation
- Use computers creatively
- Beyond CAD-tools
- Requires new algorithms
Martin Hemberg Imperial College 2004 Emergent
Design
6Evolutionary Computation
- Optimisation method
- Randomized
- Inspired by natural evolution
- Population adaption generation by generation
- Comes in many flavours GA, GP, ES, GE, etc
Martin Hemberg Imperial College 2004 Emergent
Design
7Neo Darwinian Evolution
- Survival of the fittest
- Selection on phenotype
- Through environment
- Genotypic inheritance
- Reproduction
- Blind variation
Martin Hemberg Imperial College 2004 Emergent
Design
8Artificial Evolution
- Pseudocode for an EA
- generation 0initialize populationwhile
generation lt max-generation evaluate fitness of
population members for i from 1 to
population-size select two parents crossover
parents -gt child mutate child insert child
into next generations population endfor gener
ation update current populationendwhile
Martin Hemberg Imperial College 2004 Emergent
Design
9Selection
- Selection ensures that fitter individuals have a
higher probability of being selected for the next
generation - Tournament
- Proportional
Martin Hemberg Imperial College 2004 Emergent
Design
10Fitness
- A leap from natural evolution
- A quantified numerical value is assigned to each
member - Try each member on the problem and rank them or
quantify their performance
Martin Hemberg Imperial College 2004 Emergent
Design
11Fitness Evaluation
- How to assign fitness according to aesthetic
criteria? - EA are good at finding optimal solutions
- Need to figure out what to optimize
- Open problem
Martin Hemberg Imperial College 2004 Emergent
Design
12Fitness Evaluation, strategies
- Rule based
- Hard to define and encode rules
- Learn user preference with neural network
- Too many parameters, fails in practice
- User acts as fitness function
- Human fatigue, short runs
- Co-evolve critics
Martin Hemberg Imperial College 2004 Emergent
Design
13Fitness Evaluation, my view
- Put the user in the loop
- Create tools with the designer in mind
- Make them open-ended
- Can't predict user's need and context
- Parameterized fitness function
- User has high level control of evaluation
- Fitness emerges as a combination of factors
Martin Hemberg Imperial College 2004 Emergent
Design
14What is Artificial Life
- How does life arise from the non-living?
- What are the potentials and limits of living
systems? - How is life related to mind, machines, and
culture?
Martin Hemberg Imperial College 2004 Emergent
Design
15Two definitions of emergence
- The whole is greater than the sum of the parts
- Emergence is the phenomenon wherein complex,
interesting high-level function is produced as a
result of combining simple low-level mechanisms
in simple ways. - Examples include brain, society
Martin Hemberg Imperial College 2004 Emergent
Design
16Alife and EC for Design
- Evolutionary computation
- Creative and generative qualities
- Discovery and adaptation more than optimization
- ALife
- Agents interacting with environment can model
elements of design and conditions of the problem - Emergent properties in outcome from bottom-up
approach
Martin Hemberg Imperial College 2004 Emergent
Design
17Surface Component System
- Simple growth model
- Select tiles from a predefined set
- Rules for which tiles are allowed
- Incorporates structural analysis in the EA
Martin Hemberg Imperial College 2004 Emergent
Design
18Using the tool
- Implemented as a MEL script
- FEA inAnsys
Martin Hemberg Imperial College 2004 Emergent
Design
19Geometric Fitness criteria
- Fast and easy to evaluate and understand
- Number of support points
- Support point distance
- Height
- Holes
Martin Hemberg Imperial College 2004 Emergent
Design
20Structural Fitness criteria
- FEA is computationally costly
- Don't evaluate each generation
Martin Hemberg Imperial College 2004 Emergent
Design
21Genr8 A Design Tool for Surface Generation
- Combines EC and an organic growth model
- Surface are grown in a reactive simulated
physical environment
Martin Hemberg Imperial College 2004 Emergent
Design
22Lindenmayer Systems
- Organic growth model
- Widely applied to model plant growth in computer
graphics - L-systems are important in formal language theory
Martin Hemberg Imperial College 2004 Emergent
Design
23Rewriting systems
- A set of production rules are repeatedly applied
to a seed - Rules are expressed as a grammarSeed aRule a
-gtab b-gtba
Martin Hemberg Imperial College 2004 Emergent
Design
24Turtle Graphics
- Turtle graphics is a way to visualize the grammar
- Rules are interpreted as instructions for moving
and drawing in 3D spaceSeed aRule a-gtaa--a
aAngle 60
Martin Hemberg Imperial College 2004 Emergent
Design
25Plant Models
- Operators (push state on stack) and (pop
state from stack) allows branching - Time delay
- Stochasticity
- Environmen (tropism)Seed aRule a-gtaaaAng
le 45
Martin Hemberg Imperial College 2004 Emergent
Design
26Map L-Systems
b -gt b
b
b
Martin Hemberg Imperial College 2004 Emergent
Design
27HEMLS
- 3D
- Scaling
- More complex productions
- Context sensitivity
- Time variation
- Stochastic
Martin Hemberg Imperial College 2004 Emergent
Design
28Environment
- Forces
- Attractors
- Repellors
- Gravity
- Boundary
Martin Hemberg Imperial College 2004 Emergent
Design
29Evolution
- Search the universe of possible surfaces
- Find a grammar corresponding to the surface that
the designer has in mind - Explore the universe to find interesting forms
Martin Hemberg Imperial College 2004 Emergent
Design
30Grammatical Evolution
- Automatic generation of grammars
- Very hard to construct by hand
- Many constraints -gt problematic for GP
- Grammatical Evolution allows any language
- Use Backus-Naur Form (BNF) to map linear genome
into a grammar - Genetic operations are separated from language
Martin Hemberg Imperial College 2004 Emergent
Design
31Mappings
- Genr8 contains several mappings
- Increases the complexity
- Individuals represented by linear genome
- Selection on the phenotype that is expressed
through an environment
Martin Hemberg Imperial College 2004 Emergent
Design
32Design Evaluation and Fitness
- Fitness function with multiple parameters
- Size
- Smoothness
- Soft boundary
- Subdivisions
- Symmetry
- Undulation
Martin Hemberg Imperial College 2004 Emergent
Design
33Fitness Criteria
- User determines target values and weight for the
criteria - Multiparameter optimization
- Trade-off between criteria
- Population gives a family of solutions
Martin Hemberg Imperial College 2004 Emergent
Design
34Interruption, Intervention and Resumption (IIR)
- Traditionally, EA are monolithic
- User can guide the evolution by interacting and
interfering - Allows for greater control
- The tool cooperates with the user
Martin Hemberg Imperial College 2004 Emergent
Design
35Using Genr8
- Set up environment
- Define fitness criteria and other parameters
- Run a few generations
- Analyze the results, adjust parameters and
environment
Martin Hemberg Imperial College 2004 Emergent
Design
36More on Emergent Design
- Genr8 websitehttp//www.ai.mit.edu/projects/emerg
entDesign/genr8/ - EDG websitehttp//web.mit.edu/arch/edg/
- EmTech website
- http//www.aaschool.ac.uk/et
Martin Hemberg Imperial College 2004 Emergent
Design