Analysis of Evolutionary Algorithms in the Control of Path Planning Problems
| Main Author: | |
|---|---|
| Language: | English |
| Published: |
Wright State University / OhioLINK
2018
|
| Subjects: | |
| Online Access: | http://rave.ohiolink.edu/etdc/view?acc_num=wright1535549741081137 |
| id |
ndltd-OhioLink-oai-etd.ohiolink.edu-wright1535549741081137 |
|---|---|
| record_format |
oai_dc |
| spelling |
ndltd-OhioLink-oai-etd.ohiolink.edu-wright15355497410811372021-08-03T07:08:29Z Analysis of Evolutionary Algorithms in the Control of Path Planning Problems Androulakakis, Pavlos Electrical Engineering Path Planning Evolutionary Algorithms Control Open Loop Closed Loop Trajectory Optimization The purpose of this thesis is to examine the ability of evolutionary algorithms (EAs)to develop near optimal solutions to three different path planning control problems. First,we begin by examining the evolution of an open-loop controller for the turn-circle interceptproblem. We then extend the evolutionary methodology to develop a solution to the closedloopDubins Vehicle problem. Finally, we attempt to evolve a closed-loop solution to theturn constrained pursuit evasion problem.For each of the presented problems, a custom controller representation is used. Thegoal of using custom controller representations (as opposed to more standard techniquessuch as neural networks) is to show that simple representations can be very effective ifproblem specific knowledge is used. All of the custom controller representations describedin this thesis can be easily implemented in any modern programming language without anyextra toolboxes or libraries.A standard EA is used to evolve populations of these custom controllers in an attemptto generate near optimal solutions. The evolutionary framework as well as the process ofmixing and mutation is described in detail for each of the custom controller representations.In the problems where an analytically optimal solution exists, the resulting evolvedcontrollers are compared to the known optimal solutions so that we can quantify the EA’sperformance. A breakdown of the evolution as well as plots of the resulting evolved trajectoriesare shown for each of the analyzed problems. 2018-08-31 English text Wright State University / OhioLINK http://rave.ohiolink.edu/etdc/view?acc_num=wright1535549741081137 http://rave.ohiolink.edu/etdc/view?acc_num=wright1535549741081137 unrestricted This thesis or dissertation is protected by copyright: some rights reserved. It is licensed for use under a Creative Commons license. Specific terms and permissions are available from this document's record in the OhioLINK ETD Center. |
| collection |
NDLTD |
| language |
English |
| sources |
NDLTD |
| topic |
Electrical Engineering Path Planning Evolutionary Algorithms Control Open Loop Closed Loop Trajectory Optimization |
| spellingShingle |
Electrical Engineering Path Planning Evolutionary Algorithms Control Open Loop Closed Loop Trajectory Optimization Androulakakis, Pavlos Analysis of Evolutionary Algorithms in the Control of Path Planning Problems |
| author |
Androulakakis, Pavlos |
| author_facet |
Androulakakis, Pavlos |
| author_sort |
Androulakakis, Pavlos |
| title |
Analysis of Evolutionary Algorithms in the Control of Path Planning Problems |
| title_short |
Analysis of Evolutionary Algorithms in the Control of Path Planning Problems |
| title_full |
Analysis of Evolutionary Algorithms in the Control of Path Planning Problems |
| title_fullStr |
Analysis of Evolutionary Algorithms in the Control of Path Planning Problems |
| title_full_unstemmed |
Analysis of Evolutionary Algorithms in the Control of Path Planning Problems |
| title_sort |
analysis of evolutionary algorithms in the control of path planning problems |
| publisher |
Wright State University / OhioLINK |
| publishDate |
2018 |
| url |
http://rave.ohiolink.edu/etdc/view?acc_num=wright1535549741081137 |
| work_keys_str_mv |
AT androulakakispavlos analysisofevolutionaryalgorithmsinthecontrolofpathplanningproblems |
| _version_ |
1719454656485130240 |