2026-09-20T15:25:16Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/664152022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Soraya Stevens and Leslie Pack Kaelbling. Fahey, Joseph M Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2011-10-17T21:23:30Z 2011-10-17T21:23:30Z 2011 2011 http://hdl.handle.net/1721.1/66415 755091645 Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011. Cataloged from PDF version of thesis. Includes bibliographical references (p. 34-35). A hybrid envisionment is a novel representation of a simulated state graph, specifying all possible states and transitions of the system, characterized by both qualitative and quantitative state variables. The Deep Green project creates a hybrid envisionment, called a futures graph, to depict all possible occurrences and outcomes of a combat engagement between friendly and enemy units on a battlefield. During combat, Al state estimation techniques are utilized to efficiently track the state of the battle in a futures graph, giving the commander an up-to-date analysis of what is taking place on the battlefield and how it the battle could turn out. Because state estimation of highly complex hybrid envisionments is a relatively unexplored and novel process, it is important to ensure that it is handled efficiently and accurately enough for usage on the field. This paper explores an approach for discerning the behavior in state estimation through the use of an analysis suite. By accompanying Deep Green state estimation with the analysis suite developed, estimation techniques could be benchmarked and analyzed over various implementations through both numerical and graphical metrics. The metrics generated greatly helped to improve the estimation algorithm over the course of its development. by Joseph M. Fahey. M.Eng. 35 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 Electrical Engineering and Computer Science. Real-time futures graph tracking visualization and analysis tool Thesis application/pdf Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="a805eaed-dcb6-4485-872c-52b44687487e"> <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>Real-time futures graph tracking visualization and analysis tool</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2011</PublicationDate> <Authors> <Author> <DisplayName>Fahey, Joseph M</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>Electrical Engineering and Computer Science.</Keyword> <Abstract>A hybrid envisionment is a novel representation of a simulated state graph, specifying all possible states and transitions of the system, characterized by both qualitative and quantitative state variables. The Deep Green project creates a hybrid envisionment, called a futures graph, to depict all possible occurrences and outcomes of a combat engagement between friendly and enemy units on a battlefield. During combat, Al state estimation techniques are utilized to efficiently track the state of the battle in a futures graph, giving the commander an up-to-date analysis of what is taking place on the battlefield and how it the battle could turn out. Because state estimation of highly complex hybrid envisionments is a relatively unexplored and novel process, it is important to ensure that it is handled efficiently and accurately enough for usage on the field. This paper explores an approach for discerning the behavior in state estimation through the use of an analysis suite. By accompanying Deep Green state estimation with the analysis suite developed, estimation techniques could be benchmarked and analyzed over various implementations through both numerical and graphical metrics. The metrics generated greatly helped to improve the estimation algorithm over the course of its development.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>