An unsupervised adaptive strategy for constructing probabilistic roadmaps

Handle URI:
http://hdl.handle.net/10754/597546
Title:
An unsupervised adaptive strategy for constructing probabilistic roadmaps
Authors:
Tapia, L.; Thomas, S.; Boyd, B.; Amato, N.M.
Abstract:
Since planning environments are complex and no single planner exists that is best for all problems, much work has been done to explore methods for selecting where and when to apply particular planners. However, these two questions have been difficult to answer, even when adaptive methods meant to facilitate a solution are applied. For example, adaptive solutions such as setting learning rates, hand-classifying spaces, and defining parameters for a library of planners have all been proposed. We demonstrate a strategy based on unsupervised learning methods that makes adaptive planning more practical. The unsupervised strategies require less user intervention, model the topology of the problem in a reasonable and efficient manner, can adapt the sampler depending on characteristics of the problem, and can easily accept new samplers as they become available. Through a series of experiments, we demonstrate that in a wide variety of environments, the regions automatically identified by our technique represent the planning space well both in number and placement.We also show that our technique has little overhead and that it out-performs two existing adaptive methods in all complex cases studied.© 2009 IEEE.
Citation:
Tapia L, Thomas S, Boyd B, Amato NM (2009) An unsupervised adaptive strategy for constructing probabilistic roadmaps. 2009 IEEE International Conference on Robotics and Automation. Available: http://dx.doi.org/10.1109/robot.2009.5152544.
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2009 IEEE International Conference on Robotics and Automation
KAUST Grant Number:
KUS-C1-016-04
Issue Date:
May-2009
DOI:
10.1109/robot.2009.5152544
Type:
Conference Paper
Sponsors:
This research supported in part by NSF Grants EIA-0103742, ACR-0081510, ACR-0113971, CCR-0113974, ACI-0326350, CRI-0551685, CCF-0833199, CCF-0830753, by the DOE, Chevron, IBM, Intel, HP, and by King Abdullah University of Science and Technology (KAUST) Award KUS-C1-016-04. Tapia supported in part by an NIH Molecular Biophysics Training Grant (T32GM065088), a PEO scholarship, and by a Department of Education (GAANN) Fellowship. Thomas supported in part by an NSF Graduate Research Fellowship, a PEO scholarship, a Dept. of Education Graduate Fellowship (GAANN), and an IBM TJ Watson PhD Fellowship.
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorTapia, L.en
dc.contributor.authorThomas, S.en
dc.contributor.authorBoyd, B.en
dc.contributor.authorAmato, N.M.en
dc.date.accessioned2016-02-25T12:41:48Zen
dc.date.available2016-02-25T12:41:48Zen
dc.date.issued2009-05en
dc.identifier.citationTapia L, Thomas S, Boyd B, Amato NM (2009) An unsupervised adaptive strategy for constructing probabilistic roadmaps. 2009 IEEE International Conference on Robotics and Automation. Available: http://dx.doi.org/10.1109/robot.2009.5152544.en
dc.identifier.doi10.1109/robot.2009.5152544en
dc.identifier.urihttp://hdl.handle.net/10754/597546en
dc.description.abstractSince planning environments are complex and no single planner exists that is best for all problems, much work has been done to explore methods for selecting where and when to apply particular planners. However, these two questions have been difficult to answer, even when adaptive methods meant to facilitate a solution are applied. For example, adaptive solutions such as setting learning rates, hand-classifying spaces, and defining parameters for a library of planners have all been proposed. We demonstrate a strategy based on unsupervised learning methods that makes adaptive planning more practical. The unsupervised strategies require less user intervention, model the topology of the problem in a reasonable and efficient manner, can adapt the sampler depending on characteristics of the problem, and can easily accept new samplers as they become available. Through a series of experiments, we demonstrate that in a wide variety of environments, the regions automatically identified by our technique represent the planning space well both in number and placement.We also show that our technique has little overhead and that it out-performs two existing adaptive methods in all complex cases studied.© 2009 IEEE.en
dc.description.sponsorshipThis research supported in part by NSF Grants EIA-0103742, ACR-0081510, ACR-0113971, CCR-0113974, ACI-0326350, CRI-0551685, CCF-0833199, CCF-0830753, by the DOE, Chevron, IBM, Intel, HP, and by King Abdullah University of Science and Technology (KAUST) Award KUS-C1-016-04. Tapia supported in part by an NIH Molecular Biophysics Training Grant (T32GM065088), a PEO scholarship, and by a Department of Education (GAANN) Fellowship. Thomas supported in part by an NSF Graduate Research Fellowship, a PEO scholarship, a Dept. of Education Graduate Fellowship (GAANN), and an IBM TJ Watson PhD Fellowship.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.titleAn unsupervised adaptive strategy for constructing probabilistic roadmapsen
dc.typeConference Paperen
dc.identifier.journal2009 IEEE International Conference on Robotics and Automationen
dc.contributor.institutionTexas A and M University, College Station, United Statesen
kaust.grant.numberKUS-C1-016-04en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.