Dynamic Motion Control Game|Tech 2004

Slides:



Advertisements
Similar presentations
Relevant characteristics extraction from semantically unstructured data PhD title : Data mining in unstructured data Daniel I. MORARIU, MSc PhD Supervisor:
Advertisements

Parallelized Evolution System Onur Soysal, Erkin Bahçeci Erol Şahin Dept. of Computer Engineering Middle East Technical University.
Adaptive Multi-objective Differential Evolution with Stochastic Coding Strategy Wei-Ming Chen
(Intro To) Evolutionary Computation Revision Lecture Ata Kaban The University of Birmingham.
1 Genetic Algorithms. CS The Traditional Approach Ask an expert Adapt existing designs Trial and error.
Genetic Algorithm for Variable Selection
1 Genetic Algorithms. CS 561, Session 26 2 The Traditional Approach Ask an expert Adapt existing designs Trial and error.
Artificial Intelligence in Information Processing Genetic Algorithms by Theresa Kriese for Distributed Data Processing.
Coordinative Behavior in Evolutionary Multi-agent System by Genetic Algorithm Chuan-Kang Ting – Page: 1 International Graduate School of Dynamic Intelligent.
Genetic Algorithms Overview Genetic Algorithms: a gentle introduction –What are GAs –How do they work/ Why? –Critical issues Use in Data Mining –GAs.
GAlib A C++ Library of Genetic Algorithm Components Vanessa Herves Gómez Department of Computer Architecture and Technology,
Lecture 8: 24/5/1435 Genetic Algorithms Lecturer/ Kawther Abas 363CS – Artificial Intelligence.
Optimization Problems - Optimization: In the real world, there are many problems (e.g. Traveling Salesman Problem, Playing Chess ) that have numerous possible.
G ENETIC A LGORITHMS Steve Foster. I NTRODUCTION Genetic Algorithms are based on the principals of evolutionary biology in order to find solutions to.
EE459 I ntroduction to Artificial I ntelligence Genetic Algorithms Kasin Prakobwaitayakit Department of Electrical Engineering Chiangmai University.
Genetic Algorithms. Evolutionary Methods Methods inspired by the process of biological evolution. Main ideas: Population of solutions Assign a score or.
2005MEE Software Engineering Lecture 11 – Optimisation Techniques.
Learning by Simulating Evolution Artificial Intelligence CSMC February 21, 2002.
1 Genetic Algorithms and Ant Colony Optimisation.
Evolutionary Robotics
Improving the Genetic Algorithm Performance in Aerial Spray Deposition Management University of Georgia L. Wu, W.D. Potter, K. Rasheed USDA Forest Service.
Introduction to Genetic Algorithm Principle: survival-of-the-fitness Characteristics of GA Robust Error-tolerant Flexible When you have no idea about solving.
Genetic Algorithms. 2 Overview Introduction To Genetic Algorithms (GAs) GA Operators and Parameters Genetic Algorithms To Solve The Traveling Salesman.
GENETIC ALGORITHMS Tanmay, Abhijit, Ameya, Saurabh.
Genetic Algorithms MITM613 (Intelligent Systems).
Genetic Algorithms and TSP Thomas Jefferson Computer Research Project by Karl Leswing.
Optimization of a Dynamic Vaulting Behavior for LittleDog Alex Grubb and Nathan Ratliff ACRL 04/28/09.
Advanced AI – Session 6 Genetic Algorithm By: H.Nematzadeh.
Autonomous Dynamically Simulated Creatures for Virtual Environments Paul Urban Supervisor: Prof. Shaun Bangay Honours Project 2001.
Genetic Algorithms. Solution Search in Problem Space.
Genetic Algorithms And other approaches for similar applications Optimization Techniques.
Genetic Algorithm(GA)
George Yauneridge.  Machine learning basics  Types of learning algorithms  Genetic algorithm basics  Applications and the future of genetic algorithms.
Advanced AI – Session 7 Genetic Algorithm By: H.Nematzadeh.
A MapReduced Based Hybrid Genetic Algorithm Using Island Approach for Solving Large Scale Time Dependent Vehicle Routing Problem Rohit Kondekar BT08CSE053.
Distance (m) Time (s) What is the position of the car at the instant of time t = 2 s? What is the position of the car at the instant of time t = 4 s? Starting.
Genetic Algorithm (Knapsack Problem)
Introduction to Genetic Algorithms
Using GA’s to Solve Problems
Optimization Of Robot Motion Planning Using Genetic Algorithm
Dr. Kenneth Stanley September 11, 2006
Genetic-Algorithm-Based Instance and Feature Selection
Date of download: 10/25/2017 Copyright © ASME. All rights reserved.
Genetic Algorithms GAs are one of the most powerful and applicable search methods available GA originally developed by John Holland (1975) Inspired by.
A Study of Genetic Algorithms for Parameter Optimization
V. How Does Evolution Work?
Genetic Algorithm and Their Applications to Scheduling
Genetic Algorithms GAs are one of the most powerful and applicable search methods available GA originally developed by John Holland (1975) Inspired by.

Genetic Algorithms, Search Algorithms
Y X.
Yu-Chi Ho Jonathan T. Lee Harvard University Sep. 7, 2000
Genetic Algorithms Artificial Life
Y X.
Multi-Objective Optimization
Changes in physical fitness between baseline, 3-month and 12-month follow-up: (A) Mobility limitations in neck-shoulder area; % with severe limitations,
THe University of Georgia Genetic Algorithm BOT
Dividing Fractions and Mixed Numbers Guided Notes
What is allele frequency?
Applications of Genetic Algorithms TJHSST Computer Systems Lab
Genetic algorithms: case study
A Tutorial (Complete) Yiming
Realtime Recognition of Orchestral Instruments
Evolution Notes.
Training Feedforward Neural Networks Using Genetic Algorithms
V. How Does Evolution Work?
Adaptations.
Steady state Selection
Coevolutionary Automated Software Correction
Population Methods.
Presentation transcript:

Dynamic Motion Control Game|Tech 2004 Torsten Reil NaturalMotion Ltd Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Passive Body Dynamics Game|Tech 2004 © NaturalMotion 2004

Passive Body Dynamics Dimensions Mass Distribution Passive Lower Leg Swing Game|Tech 2004 © NaturalMotion 2004

Passive Body Dynamics Game|Tech 2004 © NaturalMotion 2004

Actuators Game|Tech 2004 © NaturalMotion 2004

AI Controllers Game|Tech 2004 © NaturalMotion 2004

AI Controllers Game|Tech 2004 © NaturalMotion 2004

Controller Optimisation Genetic Algorithm Rank-based selection Fittest fraction: 0.5 Parameters coded as real values Mutation size: adjusted Gaussian Distribution Mutation rate: approx. 1/chromosome No crossover Game|Tech 2004 © NaturalMotion 2004

Controller Optimisation Basic fitness function: Distance travelled from origin. Game|Tech 2004 © NaturalMotion 2004

Result Game|Tech 2004 © NaturalMotion 2004

Controller Optimisation Guided Evolution Create initially permissive environment Weak trunk-stabilising controller After x generations, continue evolution without stabilising controller  Bike stabilisers Game|Tech 2004 © NaturalMotion 2004

Results Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Passive Dynamics Game|Tech 2004 © NaturalMotion 2004

AI-enabled (upper body) Game|Tech 2004 © NaturalMotion 2004

AI-enabled (whole body) Game|Tech 2004 © NaturalMotion 2004

Adaptive Behaviour Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Game|Tech 2004 © NaturalMotion 2004

Q&A torsten.reil@naturalmotion.com www.naturalmotion.com Game|Tech 2004 © NaturalMotion 2004