2026-09-19T10:36:07Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1227472021-07-05T14:03:20Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Leslie P. Kaelbling and Joshua B. Tenenbaum. Ajay, Anurag. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2019-11-04T20:22:18Z 2019-11-04T20:22:18Z 2019 2019 https://hdl.handle.net/1721.1/122747 1124767014 Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from PDF version of thesis. Includes bibliographical references (pages 77-81). Physics simulators play an important role in robot state estimation, planning and control; however, many real-world control problems involve complex contact dynamics that cannot be characterized analytically. Therefore, most physics simulators employ approximations that lead to a loss in precision. We propose a hybrid dynamics model, combining a deterministic physical simulator with a stochastic neural network for dynamics modeling as it provides us with expressiveness, efficiency, and generalizability simultaneously. To demonstrate this, we compare our hybrid model to both purely analytical models and purely learned models. We then show that our model is able to characterize the complex distribution of object trajectories and compare it with existing methods. We further build in object based representation into the neural network so that our hybrid model can generalize across number of objects. Finally, we use our hybrid model to complete complex control tasks in simulation and on a real robot and show that our model generalizes to novel environments with varying object shapes and materials. by Anurag Ajay. S.M. S.M. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 81 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 Electrical Engineering and Computer Science. Augmenting physics simulators with neural networks for model learning and control Thesis application/pdf 2019-11-04T20:22:17Z Publication Master EECS unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="8335603a-9797-4a61-ac00-ad71839a14b9"> <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>Augmenting physics simulators with neural networks for model learning and control</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2019</PublicationDate> <Authors> <Author> <DisplayName>Ajay, Anurag.</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>Physics simulators play an important role in robot state estimation, planning and control; however, many real-world control problems involve complex contact dynamics that cannot be characterized analytically. Therefore, most physics simulators employ approximations that lead to a loss in precision. We propose a hybrid dynamics model, combining a deterministic physical simulator with a stochastic neural network for dynamics modeling as it provides us with expressiveness, efficiency, and generalizability simultaneously. To demonstrate this, we compare our hybrid model to both purely analytical models and purely learned models. We then show that our model is able to characterize the complex distribution of object trajectories and compare it with existing methods. We further build in object based representation into the neural network so that our hybrid model can generalize across number of objects. Finally, we use our hybrid model to complete complex control tasks in simulation and on a real robot and show that our model generalizes to novel environments with varying object shapes and materials.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>