Machine learning guided exploration for sampling-based motion planning algorithms

We propose a machine learning (ML)-inspired approach to estimate the relevant region of a motion planning problem during the exploration phase of sampling-based path-planners. The algorithm guides the exploration so that it draws more samples from the relevant region as the number of iterations incr...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2015 IEEE RSJ International Conference on Intelligent Robots and Systems (IROS) s. 2646 - 2652
Hlavní autoři: Arslan, Oktay, Tsiotras, Panagiotis
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.09.2015
Témata:
Approximation algorithms
Machine learning algorithms
Planning
Prediction algorithms
Search problems
Training
Yttrium
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We propose a machine learning (ML)-inspired approach to estimate the relevant region of a motion planning problem during the exploration phase of sampling-based path-planners. The algorithm guides the exploration so that it draws more samples from the relevant region as the number of iterations increases. The approach works in two steps: first, it predicts if a given sample is collision-free (classification phase) without calling the collision-checker, and it then estimates if it is a promising sample, i.e., if it has the potential to improve the current best solution (regression phase), without solving the local steering problem. The proposed exploration strategy is integrated to the RRT # algorithm. Numerical simulations demonstrate the efficiency of the proposed approach.
AbstractList We propose a machine learning (ML)-inspired approach to estimate the relevant region of a motion planning problem during the exploration phase of sampling-based path-planners. The algorithm guides the exploration so that it draws more samples from the relevant region as the number of iterations increases. The approach works in two steps: first, it predicts if a given sample is collision-free (classification phase) without calling the collision-checker, and it then estimates if it is a promising sample, i.e., if it has the potential to improve the current best solution (regression phase), without solving the local steering problem. The proposed exploration strategy is integrated to the RRT # algorithm. Numerical simulations demonstrate the efficiency of the proposed approach.
Author Arslan, Oktay
Tsiotras, Panagiotis
Author_xml – sequence: 1
  givenname: Oktay
  surname: Arslan
  fullname: Arslan, Oktay
  email: oktay@gatech.edu
  organization: Inst. for Robot. & Intell. Machines, Georgia Inst. of Technol., Atlanta, GA, USA
– sequence: 2
  givenname: Panagiotis
  surname: Tsiotras
  fullname: Tsiotras, Panagiotis
  email: tsiotras@gatech.edu
  organization: D. Guggenheim Sch. of Aerosp. Eng., Inst. for Robot. & Intell. Machines, Atlanta, GA, USA
BookMark eNotj8tKAzEYhSMoaGsfQNzMC8yYy2SSLKWoLVSKt3X50_xpI5nMkBlB395aezZn8fEdOBNynrqEhNwwWjFGzd3ydf1WccpkpYQUSugzMmG1Mn-pm0syG4ZPSikztZSsviIvz7Ddh4RFRMgppF2x-woOXYHffewyjKFLhe9yMUDbxwMvLQwH3HZH0kdIRwvirsth3LfDNbnwEAecnXpKPh4f3ueLcrV-Ws7vV2XgVI8laItS8C1YzxQq7UBah9xxqT1XwqNykqMzWujGNlSiR2Yck3UNxnIAMSW3_7sBETd9Di3kn83ptfgFogJRrQ
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/IROS.2015.7353738
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 1479999946
9781479999941
EndPage 2652
ExternalDocumentID 7353738
Genre orig-research
GroupedDBID 6IE
6IF
6IG
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ADFMO
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
IEGSK
IERZE
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i208t-a8be532cabf17e78da5bde2d258f273fe7d52ed98386b605efe19d1544a9b2aa3
IEDL.DBID RIE
ISICitedReferencesCount 32
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000371885402122&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:54:46 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i208t-a8be532cabf17e78da5bde2d258f273fe7d52ed98386b605efe19d1544a9b2aa3
PageCount 7
ParticipantIDs ieee_primary_7353738
PublicationCentury 2000
PublicationDate 20150901
PublicationDateYYYYMMDD 2015-09-01
PublicationDate_xml – month: 09
  year: 2015
  text: 20150901
  day: 01
PublicationDecade 2010
PublicationTitle 2015 IEEE RSJ International Conference on Intelligent Robots and Systems (IROS)
PublicationTitleAbbrev IROS
PublicationYear 2015
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001945514
Score 2.2040563
Snippet We propose a machine learning (ML)-inspired approach to estimate the relevant region of a motion planning problem during the exploration phase of...
SourceID ieee
SourceType Publisher
StartPage 2646
SubjectTerms Approximation algorithms
Machine learning algorithms
Planning
Prediction algorithms
Search problems
Training
Yttrium
Title Machine learning guided exploration for sampling-based motion planning algorithms
URI https://ieeexplore.ieee.org/document/7353738
WOSCitedRecordID wos000371885402122&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEA1t8eBJpRW1Kjl4NG03aZrsWSwKWusX9FbyMVkXdFvarb_fJLu0CF68hBBIAhPCm0zezEPoShvjwGpDuJOMDIV1RHHfaOnhMHGCylFMFH4Qk4mczdJpA11vc2EAIJLPoBe68S_fLswmhMr6gvFQiKeJmkKMqlytXTwlHQbwrz8uk0Hav395eg3cLd6r5_0SUIn4MT74386HqLNLxMPTLcQcoQYUbfT8GAmQgGvFhwxnm9yCxdXC0dTY-6J4rQJdvMhIgCqLK8EevKxlirD6zBarvPz4WnfQ-_j27eaO1MoIJKcDWRIlNXBGjdIuESCkVVxboJZy6bw_4kBYTsGmksmR9g8WcJCkNhTeUammSrFj1CoWBZwgHHwOzajlwmh_mT06JYlxdmiM0JoZc4rawRzzZVX8Yl5b4uzv4S7aDxavSFjnqFWuNnCB9sx3ma9Xl_HEfgAxqZt3
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwIxEJ0gmuhJDRi_7cGjC2yX0u7ZSCAComLCjfRjumyiC4HF3-92dwMx8eKlaZq0TaZp3nT6Zh7AvdLaolHaY1YEXpsb60mWNUpkcOhbTkUnTxQe8NFITKfhuAIP21wYRMzJZ9hw3fwv3yz0xoXKmjxgrhDPHuw75awyW2sXUQnbDv7Lr0u_FTb7by_vjr3FGuXMXxIqOYJ0j_-39wnUd6l4ZLwFmVOoYFKD12FOgURSaj5EJNrEBg0pFs6NTTJvlKylI4wnkefAypBCsocsS6EiIj-jxSpO51_rOnx0nyaPPa_URvBi2hKpJ4VCFlAtlfU5cmEkUwapoUzYzCOxyA2jaEIRiI7Knixo0Q-NK70jQ0WlDM6gmiwSPAfivA4VUMO4Vtl1zvDJ97U1ba25UoHWF1Bz5pgti_IXs9ISl38P38FhbzIczAb90fMVHDnrF5Ssa6imqw3ewIH-TuP16jY_vR94_p7A
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2015+IEEE+RSJ+International+Conference+on+Intelligent+Robots+and+Systems+%28IROS%29&rft.atitle=Machine+learning+guided+exploration+for+sampling-based+motion+planning+algorithms&rft.au=Arslan%2C+Oktay&rft.au=Tsiotras%2C+Panagiotis&rft.date=2015-09-01&rft.pub=IEEE&rft.spage=2646&rft.epage=2652&rft_id=info:doi/10.1109%2FIROS.2015.7353738&rft.externalDocID=7353738