2026-09-19T22:53:56Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/466842022-01-13T07:54:11Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Anuradha Annaswarmy.
Perel, Ron Yitzhak, 1975-
Massachusetts Institute of Technology. Dept. of Aeronautics and Astronautics.
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
2009-08-26T17:21:22Z
2009-08-26T17:21:22Z
1999
1999
http://hdl.handle.net/1721.1/46684
44616043
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Aeronautics and Astronautics, 1999.
Includes bibliographical references (p. 132-134).
Over the last few decades, control theory has developed to the level where reliable methods exist to achieve satisfactory performance on even the largest and most complex of dynamical systems. The application of these control methods, though, often require extensive modelling and design effort. Recent techniques to alleviate the strain on modellers use various schemes which allow a particular system to learn about itself by measuring and storing a large, arbitrary collection of data in compact structures such as neural networks, and then using the data to augment a controller. Although many such techniques have demonstrated their capabilities in simulation, performance guarantees are rare. This thesis proposes an alternate learning technique, where a controller, based on minimal initial knowledge of system dynamics, acquires a prescribed data set on which a new controller, with guaranteed performance improvements, is based.
by Ron Yitzhak Perel.
S.M.
134 p.
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Aeronautics and Astronautics.
Learning control for a class of discrete-time, nonlinear systems
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="fa36d0ab-8c54-4f40-a5d9-92056656eef8">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Learning control for a class of discrete-time, nonlinear systems</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>1999</PublicationDate>
<Authors>
<Author>
<DisplayName>Perel, Ron Yitzhak, 1975-</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Aeronautics and Astronautics.</Keyword>
<Abstract>Over the last few decades, control theory has developed to the level where reliable methods exist to achieve satisfactory performance on even the largest and most complex of dynamical systems. The application of these control methods, though, often require extensive modelling and design effort. Recent techniques to alleviate the strain on modellers use various schemes which allow a particular system to learn about itself by measuring and storing a large, arbitrary collection of data in compact structures such as neural networks, and then using the data to augment a controller. Although many such techniques have demonstrated their capabilities in simulation, performance guarantees are rare. This thesis proposes an alternate learning technique, where a controller, based on minimal initial knowledge of system dynamics, acquires a prescribed data set on which a new controller, with guaranteed performance improvements, is based.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>