Evolving Motor Techniques for Artificial Life Kelley Hecker, Period 7.

Slides:



Advertisements
Similar presentations
Genetic Algorithm.
Advertisements

CS6800 Advanced Theory of Computation
Student : Mateja Saković 3015/2011.  Genetic algorithms are based on evolution and natural selection  Evolution is any change across successive generations.
Valery Frolov.  The algorithm  Fitness function  Crossover  Mutation  Elite individuals  Reverse mutations  Some statistics  Run examples.
1 Lecture 8: Genetic Algorithms Contents : Miming nature The steps of the algorithm –Coosing parents –Reproduction –Mutation Deeper in GA –Stochastic Universal.
Study of a Paper about Genetic Algorithm For CS8995 Parallel Programming Yanhua Li.
COMP305. Part II. Genetic Algorithms. Genetic Algorithms.
Introduction to Genetic Algorithms Yonatan Shichel.
T.J. Hartnett CSE 704 Seminar Dr. Miller Spring ‘11 EVOLVING CREATURES.
Research Trends in Artificial Intelligence Muhammad Younas Hassan Javid Danish Shah
Imagine that I am in a good mood Imagine that I am going to give you some money ! In particular I am going to give you z dollars, after you tell me the.
COMP305. Part II. Genetic Algorithms. Genetic Algorithms.
Research Trends in AI Maze Solving using GA Muhammad Younas Hassan Javaid Danish Hussain
Genetic Algorithm What is a genetic algorithm? “Genetic Algorithms are defined as global optimization procedures that use an analogy of genetic evolution.
Genetic Programming System for Music Generation With Automated Fitness Raters.
Genetic Programming.
Initial Value Problem: Find y=f(x) if y’ = f(x,y) at y(a)=b (1) Closed-form solution: explicit formula -y’ = y at y(0)=1 (Separable) Ans: y = e^x (2)
Evolutionary Algorithms and Artificial Intelligence Paul Grouchy PhD Candidate University of Toronto Institute for Aerospace Studies
Ranga Rodrigo April 6, 2014 Most of the sides are from the Matlab tutorial. 1.
Genetic Algorithm.
Aesthetically Evolved Virtual Pets Tom Ray Zoology, University of Oklahoma ATR Human Information Processing Research Laboratories, Kyoto.
Evolutionary Intelligence
Evolutionary Robotics NEAT / HyperNEAT Stanley, K.O., Miikkulainen (2001) Evolving Neural Networks through Augmenting Topologies. Competing Conventions:
Evolving a Sigma-Pi Network as a Network Simulator by Justin Basilico.
Section 3: Beyond Darwinian Theory
Introduction to Genetic Algorithms and Evolutionary Computation
SOFT COMPUTING (Optimization Techniques using GA) Dr. N.Uma Maheswari Professor/CSE PSNA CET.
Evolution Strategies Evolutionary Programming Genetic Programming Michael J. Watts
Zorica Stanimirović Faculty of Mathematics, University of Belgrade
Genetic Algorithms Genetic algorithms imitate a natural optimization process: natural selection in evolution. Developed by John Holland at the University.
More on Heuristics Genetic Algorithms (GA) Terminology Chromosome –candidate solution - {x 1, x 2,...., x n } Gene –variable - x j Allele –numerical.
The Generational Control Model This is the control model that is traditionally used by GP systems. There are a distinct number of generations performed.
Applying Genetic Algorithm to the Knapsack Problem Qi Su ECE 539 Spring 2001 Course Project.
Evolving Virtual Creatures & Evolving 3D Morphology and Behavior by Competition Papers by Karl Sims Presented by Sarah Waziruddin.
Machine Learning 1 Machine Learning 1 Genetic Algorithms.
Evolutionary Computation Dean F. Hougen w/ contributions from Pedro Diaz-Gomez & Brent Eskridge Robotics, Evolution, Adaptation, and Learning Laboratory.
Learning by Simulating Evolution Artificial Intelligence CSMC February 21, 2002.
Iterative Improvement Algorithm 2012/03/20. Outline Local Search Algorithms Hill-Climbing Search Simulated Annealing Search Local Beam Search Genetic.
Evolving Motor Techniques for Artificial Life Kelley Hecker Period 7.
Evolving Virtual Creatures Karl Sims – SIGGRAPH ‘94 Presented by Andy Snyder.
Genetic Algorithms Przemyslaw Pawluk CSE 6111 Advanced Algorithm Design and Analysis
Evolving Virtual Creatures by Karl Sims (1995) Adelein Rodriguez.
Evolving Motor Techniques for Artificial Life Kelley Hecker, Period 7.
Introduction to Genetic Algorithms. Genetic Algorithms We’ve covered enough material that we can write programs that use genetic algorithms! –More advanced.
Genetic Algorithms What is a GA Terms and definitions Basic algorithm.
ECE 103 Engineering Programming Chapter 52 Generic Algorithm Herbert G. Mayer, PSU CS Status 6/4/2014 Initial content copied verbatim from ECE 103 material.
PRIORITY QUEUES AND HEAPS Slides of Ken Birman, Cornell University.
Lecture 8 : Priority Queue Bong-Soo Sohn Assistant Professor School of Computer Science and Engineering Chung-Ang University.
HEAPS. Review: what are the requirements of the abstract data type: priority queue? Quick removal of item with highest priority (highest or lowest key.
GENETIC ALGORITHM Basic Algorithm begin set time t = 0;
D Nagesh Kumar, IIScOptimization Methods: M8L5 1 Advanced Topics in Optimization Evolutionary Algorithms for Optimization and Search.
Local Search. Systematic versus local search u Systematic search  Breadth-first, depth-first, IDDFS, A*, IDA*, etc  Keep one or more paths in memory.
Genetic Algorithms. Underlying Concept  Charles Darwin outlined the principle of natural selection.  Natural Selection is the process by which evolution.
Genetic Algorithm Dr. Md. Al-amin Bhuiyan Professor, Dept. of CSE Jahangirnagar University.
Self-Replicating Machines Source: NASA Conference Publication 2255 (1982), based on the Advanced Automation for Space Missions NASA/ASEE summer study Held.
Artificial Intelligence By Mr. Ejaz CIIT Sahiwal Evolutionary Computation.
1 Comparative Study of two Genetic Algorithms Based Task Allocation Models in Distributed Computing System Oğuzhan TAŞ 2005.
An application of the genetic programming technique to strategy development Presented By PREMKUMAR.B M.Tech(CSE) PONDICHERRY UNIVERSITY.
Evolving robot brains using vision Lisa Meeden Computer Science Department Swarthmore College.
Genetic Algorithm. Outline Motivation Genetic algorithms An illustrative example Hypothesis space search.
Genetic Algorithms and Evolutionary Programming A Brief Overview.
Hirophysics.com The Genetic Algorithm vs. Simulated Annealing Charles Barnes PHY 327.
Genetic Algorithm (Knapsack Problem)
Chapter 14 Genetic Algorithms.
Selected Topics in CI I Genetic Programming Dr. Widodo Budiharto 2014.
Genetic Algorithms.
Evolution Strategies Evolutionary Programming
USING MICROBIAL GENETIC ALGORITHM TO SOLVE CARD SPLITTING PROBLEM.
Wednesday, April 18, 2018 Announcements… For Today…
Md. Tanveer Anwar University of Arkansas
Presentation transcript:

Evolving Motor Techniques for Artificial Life Kelley Hecker, Period 7

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

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 Creature 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 Example Genomes Note: Each node also contains the neuron data, but since this cannot be seen physically I did not list it

More Genomes

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

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

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

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

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

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

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

Example Simulation One creature is copied directly to the second generation. Can you tell which one?

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

4 th 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?