Advanced Search
DSpace@MIT

Teaching and old robot new tricks : learning novel tasks via interaction with people and things

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.advisor Rodney Brooks. en_US
dc.contributor.author Marjanović, Matthew J. (Matthew Josef) en_US
dc.contributor.other Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. en_US
dc.date.accessioned 2005-06-02T16:17:56Z
dc.date.available 2005-06-02T16:17:56Z
dc.date.copyright 2003 en_US
dc.date.issued 2003 en_US
dc.identifier.uri http://hdl.handle.net/1721.1/17589
dc.description Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2003. en_US
dc.description Includes bibliographical references (p. 169-173). en_US
dc.description.abstract As AI has begun to reach out beyond its symbolic, objectivist roots into the embodied, experientialist realm, many projects are exploring different aspects of creating machines which interact with and respond to the world as humans do. Techniques for visual processing, object recognition, emotional response, gesture production and recognition, etc., are necessary components of a complete humanoid robot. However, most projects invariably concentrate on developing a few of these individual components, neglecting the issue of how all of these pieces would eventually fit together. The focus of the work in this dissertation is on creating a framework into which such specific competencies can be embedded, in a way that they can interact with each other and build layers of new functionality. To be of any practical value, such a framework must satisfy the real-world constraints of functioning in real-time with noisy sensors and actuators. The humanoid robot Cog provides an unapologetically adequate platform from which to take on such a challenge. This work makes three contributions to embodied AI. First, it offers a general-purpose architecture for developing behavior-based systems distributed over networks of PC's. Second, it provides a motor-control system that simulates several biological features which impact the development of motor behavior. Third, it develops a framework for a system which enables a robot to learn new behaviors via interacting with itself and the outside world. A few basic functional modules are built into this framework, enough to demonstrate the robot learning some very simple behaviors taught by a human trainer. en_US
dc.description.abstract (cont.) A primary motivation for this project is the notion that it is practically impossible to build an "intelligent" machine unless it is designed partly to build itself. This work is a proof-of-concept of such an approach to integrating multiple perceptual and motor systems into a complete learning agent. en_US
dc.description.statementofresponsibility by Matthew J. Marjanović. en_US
dc.format.extent 173 p. en_US
dc.format.extent 11201629 bytes
dc.format.extent 11201436 bytes
dc.format.mimetype application/pdf
dc.format.mimetype application/pdf
dc.language.iso eng en_US
dc.publisher Massachusetts Institute of Technology en_US
dc.rights 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. en_US
dc.rights.uri http://dspace.mit.edu/handle/1721.1/7582
dc.subject Electrical Engineering and Computer Science. en_US
dc.title Teaching and old robot new tricks : learning novel tasks via interaction with people and things en_US
dc.type Thesis en_US
dc.description.degree Ph.D. en_US
dc.contributor.department Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. en_US
dc.identifier.oclc 53247440 en_US


Files in this item

Name Size Format Description
53247440-MIT.pdf 20.40Mb PDF Full printable version

This item appears in the following Collection(s)

Show simple item record

MIT-Mirage