This item is non-discoverable
Application of Genetic Algorithms to a Multi-Agent Autonomous Pilot of Motorcycles
Loading...
If you need an accessible version of this item, please email your request to iusw@iu.edu so that they may create one and provide it to you.
Date
2005-05-10
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Indiana University South Bend
Permanent Link
Abstract
The physics behind motorcycle driving are well understood and implemented by studying the laws of kinetics and kinematics behind the operation of the single track motor vehicle. In this thesis I worked with an application which is currently using OpenGL and implements an interactive motorcycle simulator which is based on the laws of physics. This application involves a multi-agent pilot capable of autonomously driving the vehicle using some configurable equations. I have applied genetic algorithms to find suitable values for the parameters of the pilot by testing it in a non graphical environment, and I visually verified the results of the genetic algorithms with the graphical interface application. The performance of the pilot derived by the genetic algorithms is also compared with the manually configured pilot.
Description
Thesis (M.S) -- Indiana University South Bend, 2005.
Keywords
Dissertations, Academic--Indiana--South Bend., Indiana University South Bend--Dissertations., Genetic algorithms, Computer simulation, Automated vehicles
Citation
DOI
Link(s) to data and video for this item
Relation
Rights
Type
Thesis