2026-09-20T20:42:38Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/466152022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022

Leslie Kaelbling and Tomás Lozano-Pérez. Finney, Sarah, 1974- Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2009-08-26T17:04:10Z 2009-08-26T17:04:10Z 2009 2009 http://hdl.handle.net/1721.1/46615 426039911 Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2009. Includes bibliographical references (p. 119-129). Robotic motion planning is a hard problem for robots with more than just a few degrees of freedom. Modern probabilistic planners are able to solve many problems very quickly, but for difficult problems, they are still unacceptably slow for many applications. This thesis concerns the use of previous planning experience to allow the agent to generate motion plans very quickly when faced with new but related problems. We first investigate a technique for learning from previous experience by simply remembering past solutions and applying them where relevant to new problems. We find that this approach is useful in environments with very low variability in obstacle placement and task endpoints, and that it is important to keep the set of stored plans small to improve performance. However, we would like to be able to better generalize our previous experience so we next investigate a technique for learning parameterized motion plans. A parameterized motion plan is a function from planning problem parameters to a motion plan. In our approach, we learn a set of parameterized subpaths, which we can use as suggestions for a probabilistic planner, leading to substantially reduced planning times. We find that this technique is successful in several standard motion planning domains. However, as the domains get more complex, the technique produces less of an advantage. We discover that the learning problem as we have posed it is likely to be intractible, and that the complexity of the problem is due to the redundancy of the robotics platform. We suggest several possible approaches for addressing this problem as future work. by Sarah J. Finney. Ph.D. 129 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. On learning task-directed motion plans Thesis application/pdf Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="afd2ff36-97a8-4a7b-9a10-d35f6904a7e2"> <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 task-directed motion plans</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2009</PublicationDate> <Authors> <Author> <DisplayName>Finney, Sarah, 1974-</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>Robotic motion planning is a hard problem for robots with more than just a few degrees of freedom. Modern probabilistic planners are able to solve many problems very quickly, but for difficult problems, they are still unacceptably slow for many applications. This thesis concerns the use of previous planning experience to allow the agent to generate motion plans very quickly when faced with new but related problems. We first investigate a technique for learning from previous experience by simply remembering past solutions and applying them where relevant to new problems. We find that this approach is useful in environments with very low variability in obstacle placement and task endpoints, and that it is important to keep the set of stored plans small to improve performance. However, we would like to be able to better generalize our previous experience so we next investigate a technique for learning parameterized motion plans. A parameterized motion plan is a function from planning problem parameters to a motion plan. In our approach, we learn a set of parameterized subpaths, which we can use as suggestions for a probabilistic planner, leading to substantially reduced planning times. We find that this technique is successful in several standard motion planning domains. However, as the domains get more complex, the technique produces less of an advantage. We discover that the learning problem as we have posed it is likely to be intractible, and that the complexity of the problem is due to the redundancy of the robotics platform. We suggest several possible approaches for addressing this problem as future work.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>