2026-09-19T04:08:06Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1202332022-01-13T07:54:05Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Kamal Youcef-Toumi. Cui, Yingnan, S.M. Massachusetts Institute of Technology Massachusetts Institute of Technology. Department of Mechanical Engineering. Massachusetts Institute of Technology. Department of Mechanical Engineering 2019-02-05T15:59:49Z 2019-02-05T15:59:49Z 2018 2018 http://hdl.handle.net/1721.1/120233 1083124360 Thesis: S.M., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2018. Cataloged from PDF version of thesis. Includes bibliographical references (pages 95-97). The robot phone disassembly task is difficult in many ways: It has requirements on high precision, high speed, and should be general to all types of cell phones. Previous works on robot learning from demonstration are hardly applicable due to the complexity of teaching, huge amounts of data and difficulty in generalization. To tackle these problems, we try to learn from videos and extract useful information for the robot. To reduce the amounts of data we need to process, we generate a mask for the video and observe only the region of interest. Inspired by the idea that spatio-temporal interest point (STIP) detector may give meaningful points such as the contact point between the tool and the part, we design a new method of detecting STIPs based on optical flow. We also design a new descriptor by modifying the histogram of optical flow. The STIP detector and descriptor together can make sure that the features are invariant to scale, rotation and noises. Using the modified histogram of optical flow descriptor, we show that even without considering raw pixels of the original video, we can achieve pretty good classification results. by Yingnan Cui. S.M. 97 pages eng Massachusetts Institute of Technology MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 Mechanical Engineering. On learning from videos/ Thesis application/pdf false Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="3066d404-774c-48b2-8c2d-878ac3762f53"> <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>On learning from videos/</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2018</PublicationDate> <Authors> <Author> <DisplayName>Cui, Yingnan, S.M. Massachusetts Institute of Technology</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>Mechanical Engineering.</Keyword> <Abstract>The robot phone disassembly task is difficult in many ways: It has requirements on high precision, high speed, and should be general to all types of cell phones. Previous works on robot learning from demonstration are hardly applicable due to the complexity of teaching, huge amounts of data and difficulty in generalization. To tackle these problems, we try to learn from videos and extract useful information for the robot. To reduce the amounts of data we need to process, we generate a mask for the video and observe only the region of interest. Inspired by the idea that spatio-temporal interest point (STIP) detector may give meaningful points such as the contact point between the tool and the part, we design a new method of detecting STIPs based on optical flow. We also design a new descriptor by modifying the histogram of optical flow. The STIP detector and descriptor together can make sure that the features are invariant to scale, rotation and noises. Using the modified histogram of optical flow descriptor, we show that even without considering raw pixels of the original video, we can achieve pretty good classification results.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>