Sale!
Placeholder

Genetic Robots Play Football

10,000 3,000

56 Pages | chapter 1-5 | PDF and Microsoft Format

Topic Description

Genetic Robots Play Football

Summary/abstract
This project is an investigation into the possibilities of neural networks to be used as autonomous robot controllers, to be used on the LEGO Mindstorms platform. The aim of this project is to use neural networks and genetic algorithms to train a robot to locate a football. The minimum requirements for this project were:
• Build a robot for the purpose of playing football
• To extend the genetic algorithm and neural network built by Marston (2002)
• To show that a combination of a neural network and genetic algorithm can be used to train a robot to play football
• Demonstrate and evaluate the learnt behaviour in the robot. During the course of the project the following achievements were made
• A genetic algorithm was modified to be capable of evolving neural networks
• A neural network was developed for the LEGO Mindstorms RCX
• A successful neural network was evolved that could locate a football on the football pitch

Table of contents
Summary……………………………………………………………………………………………………………..ii
Acknowledgements…………………………………………………………………………………………….iii
Table of contents………………………………………………………………………………………………….iv
Table of Figures…………………………………………………………………………………………………..vi
Chapter 1……………………………………………………………………………………………………………..1
Introduction…………………………………………………………………………………………………………1
1.1 Chapter summary……………………………………………………………………………………….1
1.2 The problem………………………………………………………………………………………………..1
1.3 LEGO Mindstorms and Robocup Junior……………………………………………………..2
1.4 Why not use traditional programming techniques?…………………………………….3
1.5 Artificial Neural Networks………………………………………………………………………….4
1.6 Genetic Algorithms……………………………………………………………………………………..9
1.7 Previous work done using bio inspired techniques for robot control…………10
Chapter 2……………………………………………………………………………………………………………11
The neural network…………………………………………………………………………………………….11
2.1 Summary…………………………………………………………………………………………………..11
2.2 Types of neural network……………………………………………………………………………11
2.2.1 Feed forward neural networks……………………………………………………………11
2.2.2 Kohonen Networks…………………………………………………………………………….12
2.2.3 Recurrent networks…………………………………………………………………………….12
2.2.4 Gas Nets……………………………………………………………………………………………..14
2.3 Choice of Neural network…………………………………………………………………………14
Chapter 3……………………………………………………………………………………………………………16
The genetic algorithm…………………………………………………………………………………………16
3.1 Summary…………………………………………………………………………………………………..16
3.2 The fitness function…………………………………………………………………………………..16
3.3 Choice of population size………………………………………………………………………….17
3.4 Choice of selection method………………………………………………………………………..17
3.5 Elitism……………………………………………………………………………………………………….18
3.6 Choice of reproduction……………………………………………………………………………..19
Chapter 4……………………………………………………………………………………………………………20
iv
Design and Implementation……………………………………………………………………………….20
4.1 Summary…………………………………………………………………………………………………..20
4.2 Design of the robot……………………………………………………………………………………20
4.3 Design of the software system…………………………………………………………………..21
4.4 Design of the robot control system…………………………………………………………….23
4.5 Design of the Genetic Algorithm……………………………………………………………….23
4.6 Design of the vision system……………………………………………………………………….24
4.7 Design of the script……………………………………………………………………………………25
4.8 Implementation of the robot control software……………………………………………25
4.9 Implementation of the genetic algorithm…………………………………………………..26
4.10 Implementation of the vision system……………………………………………………….26
Chapter 5……………………………………………………………………………………………………………29
Results………………………………………………………………………………………………………………..29
5.1 Summary…………………………………………………………………………………………………..29
5.2 Evaluation of the neural network………………………………………………………………29
5.3 Emergent behaviour………………………………………………………………………………….30
5.4 Evaluation of the genetic algorithm…………………………………………………………..34
Chapter 6……………………………………………………………………………………………………………36
Conclusions………………………………………………………………………………………………………..36
6.1 Summary…………………………………………………………………………………………………..36
6.2 Neural nets………………………………………………………………………………………………..36
6.3 Genetic Algorithms……………………………………………………………………………………36
6.4 Onboard learning………………………………………………………………………………………36
Chapter 7……………………………………………………………………………………………………………38
Evaluation………………………………………………………………………………………………………….38
7.1 Summary…………………………………………………………………………………………………..38
7.2 Success of the project…………………………………………………………………………………38
7.3 Further requirements………………………………………………………………………………..39
7.4 Further work……………………………………………………………………………………………..39
References…………………………………………………………………………………………………………..40
Appendix A – Personal reflection……………………………………………………………………….43
Appendix B – Code for the neural network………………………………………………………..44
Appendix C – Code for the genetic Algorithm……………………………………………………

GET COMPLETE PROJECT