Using Load Balancing to Scalably Parallelize Sampling-Based Motion Planning Algorithms

Handle URI:
http://hdl.handle.net/10754/600151
Title:
Using Load Balancing to Scalably Parallelize Sampling-Based Motion Planning Algorithms
Authors:
Fidel, Adam; Jacobs, Sam Ade; Sharma, Shishir; Amato, Nancy M.; Rauchwerger, Lawrence
Abstract:
Motion planning, which is the problem of computing feasible paths in an environment for a movable object, has applications in many domains ranging from robotics, to intelligent CAD, to protein folding. The best methods for solving this PSPACE-hard problem are so-called sampling-based planners. Recent work introduced uniform spatial subdivision techniques for parallelizing sampling-based motion planning algorithms that scaled well. However, such methods are prone to load imbalance, as planning time depends on region characteristics and, for most problems, the heterogeneity of the sub problems increases as the number of processors increases. In this work, we introduce two techniques to address load imbalance in the parallelization of sampling-based motion planning algorithms: an adaptive work stealing approach and bulk-synchronous redistribution. We show that applying these techniques to representatives of the two major classes of parallel sampling-based motion planning algorithms, probabilistic roadmaps and rapidly-exploring random trees, results in a more scalable and load-balanced computation on more than 3,000 cores. © 2014 IEEE.
Citation:
Fidel A, Jacobs SA, Sharma S, Amato NM, Rauchwerger L (2014) Using Load Balancing to Scalably Parallelize Sampling-Based Motion Planning Algorithms. 2014 IEEE 28th International Parallel and Distributed Processing Symposium. Available: http://dx.doi.org/10.1109/IPDPS.2014.66.
Publisher:
Institute of Electrical & Electronics Engineers (IEEE)
Journal:
2014 IEEE 28th International Parallel and Distributed Processing Symposium
KAUST Grant Number:
KUS-C1-016-04
Issue Date:
May-2014
DOI:
10.1109/IPDPS.2014.66
Type:
Conference Paper
Sponsors:
This research supported in part by NSF awards CNS-0551685, CCF-0833199, CCF-0830753, IIS-0916053, IIS-0917266, EFRI-1240483, RI-1217991, by NIH NCI R25 CA090301-11, by DOE awards DE-AC02-06CH11357, B575363, by Samsung, Chevron, IBM, Intel, Oracle/Sun andby Award KUS-C1-016-04, made by King Abdullah University of Scienceand Technology (KAUST). This research used resources of the NationalEnergy Research Scientific Computing Center, which is supported by theOffice of Science of the U.S. Department of Energy under Contract No.DE-AC02-05CH11231.
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorFidel, Adamen
dc.contributor.authorJacobs, Sam Adeen
dc.contributor.authorSharma, Shishiren
dc.contributor.authorAmato, Nancy M.en
dc.contributor.authorRauchwerger, Lawrenceen
dc.date.accessioned2016-02-28T06:43:48Zen
dc.date.available2016-02-28T06:43:48Zen
dc.date.issued2014-05en
dc.identifier.citationFidel A, Jacobs SA, Sharma S, Amato NM, Rauchwerger L (2014) Using Load Balancing to Scalably Parallelize Sampling-Based Motion Planning Algorithms. 2014 IEEE 28th International Parallel and Distributed Processing Symposium. Available: http://dx.doi.org/10.1109/IPDPS.2014.66.en
dc.identifier.doi10.1109/IPDPS.2014.66en
dc.identifier.urihttp://hdl.handle.net/10754/600151en
dc.description.abstractMotion planning, which is the problem of computing feasible paths in an environment for a movable object, has applications in many domains ranging from robotics, to intelligent CAD, to protein folding. The best methods for solving this PSPACE-hard problem are so-called sampling-based planners. Recent work introduced uniform spatial subdivision techniques for parallelizing sampling-based motion planning algorithms that scaled well. However, such methods are prone to load imbalance, as planning time depends on region characteristics and, for most problems, the heterogeneity of the sub problems increases as the number of processors increases. In this work, we introduce two techniques to address load imbalance in the parallelization of sampling-based motion planning algorithms: an adaptive work stealing approach and bulk-synchronous redistribution. We show that applying these techniques to representatives of the two major classes of parallel sampling-based motion planning algorithms, probabilistic roadmaps and rapidly-exploring random trees, results in a more scalable and load-balanced computation on more than 3,000 cores. © 2014 IEEE.en
dc.description.sponsorshipThis research supported in part by NSF awards CNS-0551685, CCF-0833199, CCF-0830753, IIS-0916053, IIS-0917266, EFRI-1240483, RI-1217991, by NIH NCI R25 CA090301-11, by DOE awards DE-AC02-06CH11357, B575363, by Samsung, Chevron, IBM, Intel, Oracle/Sun andby Award KUS-C1-016-04, made by King Abdullah University of Scienceand Technology (KAUST). This research used resources of the NationalEnergy Research Scientific Computing Center, which is supported by theOffice of Science of the U.S. Department of Energy under Contract No.DE-AC02-05CH11231.en
dc.publisherInstitute of Electrical & Electronics Engineers (IEEE)en
dc.titleUsing Load Balancing to Scalably Parallelize Sampling-Based Motion Planning Algorithmsen
dc.typeConference Paperen
dc.identifier.journal2014 IEEE 28th International Parallel and Distributed Processing Symposiumen
dc.contributor.institutionTexas A and M University, College Station, United Statesen
dc.contributor.institutionABB USA, Norwalk, United Statesen
dc.contributor.institutionMicrosoft, Redmond, United Statesen
kaust.grant.numberKUS-C1-016-04en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.