dc.contributor.author |
Bishop, Russell C. |
|
dc.contributor.other |
Youngstown State University. Department of Electrical and Computer Engineering. |
|
dc.date.accessioned |
2021-10-19T15:35:36Z |
|
dc.date.available |
2021-10-19T15:35:36Z |
|
dc.date.issued |
2008 |
|
dc.identifier.other |
277047747 |
|
dc.identifier.other |
B20382510 |
|
dc.identifier.uri |
https://jupiter.ysu.edu:443/record=b2038251 |
|
dc.identifier.uri |
http://hdl.handle.net/1989/16668 |
|
dc.description |
viii, 105 leaves : ill. ; 29 cm. Thesis (M.S.)--Youngstown State University, 2008. Includes bibliographical references (leaves 104-105). |
en_US |
dc.description.abstract |
This thesis presents a method of generating neural-network based control systems for walking robots. A genetic learning rule is combined with a physics simulation and scoring system in order to find appropriate weights for these networks. This approach produces highly robust neural-network control mechanisms that are capable of handling a wide variety of conditions, such as rough terrain and randomly varying robot proportions. In each of two test runs, the system was able to make the robot walk approximately 1.75 meters (5.8 body lengths) in the physics simulation, over very rough terrain, in 14 seconds of simulation-world time. |
en_US |
dc.description.sponsorship |
Youngstown State University. Department of Electrical and Computer Engineering. |
en_US |
dc.language.iso |
en_US |
en_US |
dc.relation.ispartofseries |
Master's Theses;no. 1121 |
|
dc.subject |
Robots -- Control systems. |
en_US |
dc.subject |
Mobile robots -- Design and construction. |
en_US |
dc.subject |
Neural networks (Computer science) |
en_US |
dc.title |
A method for generating robot control systems |
en_US |
dc.type |
Thesis |
en_US |