GLAS: Global-to-Local Safe Autonomy Synthesis for Multi-Robot Motion Planning With End-to-End Learning

We present GLAS: G lobal-to- L ocal A utonomy S ynthesis, a provably-safe, automated distributed policy generation for multi-robot motion planning. Our approach combines the advantage of centralized planning of avoiding local minima with the advantage of decentralized controllers of scalability and...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE robotics and automation letters Vol. 5; no. 3; pp. 4249 - 4256
Main Authors:	Riviere, Benjamin, Honig, Wolfgang, Yue, Yisong, Chung, Soon-Jo
Format:	Journal Article
Language:	English
Published:	Piscataway IEEE 01.07.2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Collision avoidance Distributed robot systems imitation learning Learning Measurement Microcontrollers Motion planning Multiple robots Optimal control path planning for multiple mobile robots or agents Planning Policies Robot dynamics Robots Safety State (computer science) Trajectory
ISSN:	2377-3766, 2377-3766
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	We present GLAS: G lobal-to- L ocal A utonomy S ynthesis, a provably-safe, automated distributed policy generation for multi-robot motion planning. Our approach combines the advantage of centralized planning of avoiding local minima with the advantage of decentralized controllers of scalability and distributed computation. In particular, our synthesized policies only require relative state information of nearby neighbors and obstacles, and compute a provably-safe action. Our approach has three major components: i) we generate demonstration trajectories using a global planner and extract local observations from them, ii) we use deep imitation learning to learn a decentralized policy that can run efficiently online, and iii) we introduce a novel differentiable safety module to ensure collision-free operation, thereby allowing for end-to-end policy training. Our numerical experiments demonstrate that our policies have a 20% higher success rate than optimal reciprocal collision avoidance, ORCA, across a wide range of robot and obstacle densities. We demonstrate our method on an aerial swarm, executing the policy on low-end microcontrollers in real-time.
AbstractList	We present GLAS: G lobal-to- L ocal A utonomy S ynthesis, a provably-safe, automated distributed policy generation for multi-robot motion planning. Our approach combines the advantage of centralized planning of avoiding local minima with the advantage of decentralized controllers of scalability and distributed computation. In particular, our synthesized policies only require relative state information of nearby neighbors and obstacles, and compute a provably-safe action. Our approach has three major components: i) we generate demonstration trajectories using a global planner and extract local observations from them, ii) we use deep imitation learning to learn a decentralized policy that can run efficiently online, and iii) we introduce a novel differentiable safety module to ensure collision-free operation, thereby allowing for end-to-end policy training. Our numerical experiments demonstrate that our policies have a 20% higher success rate than optimal reciprocal collision avoidance, ORCA, across a wide range of robot and obstacle densities. We demonstrate our method on an aerial swarm, executing the policy on low-end microcontrollers in real-time.
Author	Honig, Wolfgang Yue, Yisong Riviere, Benjamin Chung, Soon-Jo
Author_xml	– sequence: 1 givenname: Benjamin orcidid: 0000-0003-4189-4090 surname: Riviere fullname: Riviere, Benjamin email: briviere@caltech.edu organization: California Institute of Technology, Pasadena, CA, USA – sequence: 2 givenname: Wolfgang orcidid: 0000-0002-0773-028X surname: Honig fullname: Honig, Wolfgang email: whoenig@caltech.edu organization: California Institute of Technology, Pasadena, CA, USA – sequence: 3 givenname: Yisong surname: Yue fullname: Yue, Yisong email: yyue@caltech.edu organization: California Institute of Technology, Pasadena, CA, USA – sequence: 4 givenname: Soon-Jo orcidid: 0000-0002-6657-3907 surname: Chung fullname: Chung, Soon-Jo email: sjchung@caltech.edu organization: California Institute of Technology, Pasadena, CA, USA
BookMark	eNp9UEFLwzAYDaLgnLsLXgKeO78kTbt4G2NOoUPZBh5L2iYuo0tmmh72723ZEPHg6X3wvfe-970bdGmdVQjdERgTAuIxW03HFCiMqRAxMH6BBpSlacTSJLn8NV-jUdPsAIBwmjLBB0gvsun6CS9qV8g6Ci7KXClrvJZa4WkbnHX7I14fbdiqxjRYO4-XbR1MtHKFC3jpgnEWv9fSWmM_8YcJWzy3Ve_UAc6U9P3iFl1pWTdqdMYh2jzPN7OXKHtbvM6mWVRSQULEBWG6kqzU8YTwgseiggJiJipZVMWk0jzRHCaSyrSABHgiKAgCpWKMxBVjQ_Rwsj1499WqJuQ713rbXcxpDCmwRBDSsZITq_SuabzSeWmC7B8JXpo6J5D3reZdq3nfan5utRPCH-HBm730x_8k9yeJUUr90EWXukvMvgENX4Jg
CODEN	IRALC6
CitedBy_id	crossref_primary_10_1016_j_arcontrol_2021_10_001 crossref_primary_10_1109_TRO_2024_3509015 crossref_primary_10_2514_1_G007671 crossref_primary_10_1109_TNNLS_2023_3303502 crossref_primary_10_1007_s40031_024_01097_w crossref_primary_10_1007_s10846_021_01378_2 crossref_primary_10_1007_s11432_022_3666_2 crossref_primary_10_1007_s10514_023_10104_w crossref_primary_10_1016_j_paerosci_2021_100696 crossref_primary_10_1109_TCST_2022_3172872 crossref_primary_10_1109_TRO_2022_3181055 crossref_primary_10_1109_TRO_2023_3297010 crossref_primary_10_1109_LRA_2021_3096758 crossref_primary_10_3390_electronics12183946 crossref_primary_10_1109_TITS_2021_3097297 crossref_primary_10_3389_fnbot_2024_1464572 crossref_primary_10_1109_LRA_2020_3026638 crossref_primary_10_1109_ACCESS_2024_3392305 crossref_primary_10_1007_s10462_024_10739_w crossref_primary_10_7717_peerj_cs_1056 crossref_primary_10_3390_app11199055 crossref_primary_10_1109_ACCESS_2024_3416111 crossref_primary_10_1126_scirobotics_ado1010 crossref_primary_10_1134_S1064562422060229 crossref_primary_10_1109_TRO_2023_3344034 crossref_primary_10_1109_LRA_2024_3426374 crossref_primary_10_3390_s23042036 crossref_primary_10_1109_TRO_2021_3098436 crossref_primary_10_1109_ACCESS_2024_3402564 crossref_primary_10_1109_LRA_2021_3091019 crossref_primary_10_1109_TNSM_2024_3406350 crossref_primary_10_1038_s41467_021_27015_y crossref_primary_10_1051_itmconf_20257801015 crossref_primary_10_1109_TNNLS_2022_3172168 crossref_primary_10_1109_LRA_2023_3337700 crossref_primary_10_1109_LRA_2021_3061073 crossref_primary_10_3390_app14103960 crossref_primary_10_1109_TCE_2023_3340327 crossref_primary_10_1109_TIV_2024_3422172 crossref_primary_10_1108_RIA_01_2024_0011 crossref_primary_10_1109_LRA_2021_3139145 crossref_primary_10_1016_j_knosys_2023_111121 crossref_primary_10_1109_ACCESS_2021_3129474
Cites_doi	10.1109/ICRA.2017.7989376 10.15607/RSS.2018.XIV.056 10.1109/TRO.2017.2659727 10.1007/978-3-642-19457-3_1 10.1109/LRA.2019.2903261 10.1109/70.163777 10.1109/IROS40897.2019.8968483 10.1109/LRA.2018.2890572 10.15607/RSS.2005.I.007 10.15607/RSS.2018.XIV.001 10.1109/TRO.2017.2705044 10.1177/0278364916632065 10.1109/TNN.2008.2005605 10.1109/TRO.2018.2853613
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/LRA.2020.2994035
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2377-3766
EndPage	4256
ExternalDocumentID	10_1109_LRA_2020_2994035 9091314
Genre	orig-research
GrantInformation_xml	– fundername: Raytheon Company and Caltech/NASA Jet Propulsion Laboratory
GroupedDBID	0R~ 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFS AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF KQ8 M43 M~E O9- OCL RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c291t-5913fda3cf4815b549d0b0439dabdb8df56f508a2a7b06056920910ce3314d33
IEDL.DBID	RIE
ISICitedReferencesCount	69
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000541736400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2377-3766
IngestDate	Sun Nov 30 04:55:30 EST 2025 Sat Nov 29 06:03:07 EST 2025 Tue Nov 18 22:23:56 EST 2025 Wed Aug 27 02:37:41 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	3
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c291t-5913fda3cf4815b549d0b0439dabdb8df56f508a2a7b06056920910ce3314d33
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-6657-3907 0000-0003-4189-4090 0000-0002-0773-028X
PQID	2407036911
PQPubID	4437225
PageCount	8
ParticipantIDs	proquest_journals_2407036911 crossref_citationtrail_10_1109_LRA_2020_2994035 ieee_primary_9091314 crossref_primary_10_1109_LRA_2020_2994035
PublicationCentury	2000
PublicationDate	2020-07-01
PublicationDateYYYYMMDD	2020-07-01
PublicationDate_xml	– month: 07 year: 2020 text: 2020-07-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE robotics and automation letters
PublicationTitleAbbrev	LRA
PublicationYear	2020
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref12 ref15 li (ref13) 2019 ref11 ref10 ross (ref24) 0; 15 berg (ref1) 0; 70 ref2 zaheer (ref17) 0 ref19 khalil (ref21) 2002 shi (ref18) 0 cheng (ref7) 0; 97 khatib (ref3) 1990 ref23 paszke (ref22) 0 ref25 boyd (ref20) 2014 raju (ref16) 2019 ref8 ref9 ref4 ref6 ref5 khan (ref14) 2019
References_xml	– year: 2002 ident: ref21 publication-title: Nonlinear Systems – ident: ref23 doi: 10.1109/ICRA.2017.7989376 – ident: ref19 doi: 10.15607/RSS.2018.XIV.056 – ident: ref6 doi: 10.1109/TRO.2017.2659727 – volume: 15 start-page: 627 year: 0 ident: ref24 article-title: A reduction of imitation learning and structured prediction to no-regret online learning publication-title: Proc Int Conf Artif Intell Statist – volume: 70 start-page: 3 year: 0 ident: ref1 article-title: Reciprocal n-body collision avoidance publication-title: Proc Int Symp Robot Res doi: 10.1007/978-3-642-19457-3_1 – ident: ref12 doi: 10.1109/LRA.2019.2903261 – year: 0 ident: ref18 article-title: Neural-swarm: Decentralized close-proximity multirotor control using learned interactions publication-title: Proc IEEE Int Conf Robot Autom – start-page: 396 year: 1990 ident: ref3 article-title: Real-time obstacle avoidance for manipulators and mobile robots publication-title: Autonomous Robot Vehicles – ident: ref4 doi: 10.1109/70.163777 – year: 2019 ident: ref13 article-title: Graph neural networks for decentralized multi-robot path planning – ident: ref15 doi: 10.1109/IROS40897.2019.8968483 – ident: ref11 doi: 10.1109/LRA.2018.2890572 – start-page: 8024 year: 0 ident: ref22 article-title: Pytorch: An imperative style, high-performance deep learning library publication-title: Proc Adv Neural Inf Process Syst – year: 2014 ident: ref20 publication-title: Convex optimization – ident: ref5 doi: 10.15607/RSS.2005.I.007 – ident: ref8 doi: 10.15607/RSS.2018.XIV.001 – start-page: 3391 year: 0 ident: ref17 article-title: Deep sets publication-title: Proc Adv Neural Inf Process Syst – year: 2019 ident: ref16 article-title: Decentralized runtime synthesis of shields for multi-agent systems – ident: ref2 doi: 10.1109/TRO.2017.2705044 – ident: ref9 doi: 10.1177/0278364916632065 – ident: ref25 doi: 10.1109/TNN.2008.2005605 – ident: ref10 doi: 10.1109/TRO.2018.2853613 – year: 2019 ident: ref14 article-title: Graph policy gradients for large scale unlabeled motion planning with constraints – volume: 97 start-page: 1141 year: 0 ident: ref7 article-title: Control regularization for reduced variance reinforcement learning publication-title: Proc Int Conf Mach Learn
SSID	ssj0001527395
Score	2.488578
Snippet	We present GLAS: G lobal-to- L ocal A utonomy S ynthesis, a provably-safe, automated distributed policy generation for multi-robot motion planning. Our...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	4249
SubjectTerms	Collision avoidance Distributed robot systems imitation learning Learning Measurement Microcontrollers Motion planning Multiple robots Optimal control path planning for multiple mobile robots or agents Planning Policies Robot dynamics Robots Safety State (computer science) Trajectory
Title	GLAS: Global-to-Local Safe Autonomy Synthesis for Multi-Robot Motion Planning With End-to-End Learning
URI	https://ieeexplore.ieee.org/document/9091314 https://www.proquest.com/docview/2407036911
Volume	5
WOSCitedRecordID	wos000541736400001&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
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2377-3766 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001527395 issn: 2377-3766 databaseCode: RIE dateStart: 20160101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2377-3766 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001527395 issn: 2377-3766 databaseCode: M~E dateStart: 20160101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFH5M8aAHf01xOiUHL4LZ6tourbchUw9TxA3crTS_dCCtuE7w4t_ue2k3BUXw1B6SkOZr8t5L8r4P4FiYiO6H4_wW1udBN1RcBtbwwBdaBMq3oXKJwgNxexuNx_FdDU4XuTDGGHf5zLTo1Z3l61zNaKusHROJJalWLwkhylytr_0UYhKLw_lJpBe3B_c9jP86XgtX3MBzem5flsdJqfxYf51Rudz4X3c2Yb1yHlmvRHsLaibbhrVvlIJ1sFeD3vCclVT-vMj5gIwVG6bWsN6scCkMbPieod83nUwZuqzM5eDy-1zmBbtxoj5sLmXEHibFE-tnmlrCB6voWB93YHTZH11c80pLgatOfFbwELtqdeorS-wsEqNC7UlKi9Wp1DLSNuxa9NXSTiqkhyFON-6QJ6GMj1-ofX8XlrM8M3vAZCCUH0VUFWPrKEhJ4w_9Dhlg4dSYBrTnw5yoimec5C6eExdveHGCwCQETFIB04CTRY2XkmPjj7J1AmJRrsKgAc05kkk1CacJBatooHE53_-91gGsUtvl7dsmLBevM3MIK-qtmExfj2Dp5qN_5P6yT0QIzeA
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT9swFH5CMGnsANsKWgcMH3aZNNOQOE3CrULtipZWU1tpvUXxL6iEEkRTpP33vOek7aShSZySg53Y-WK_92y_7wP4GpmYzofj-I5swEU3VFwKa7gIIh0JFdhQuUThNBqP4_k8-bUD3ze5MMYYd_jMXNCt28vXpVrRUlknIRJLUq3eC4XwL-tsre2KCnGJJeF6L9JLOumkhxGg713gnCs8p-i2tT1OTOWfGdiZlcHh6xr0Hg4a95H1arw_wI4pPsK7v0gFW2B_pL3pFavJ_HlV8pTMFZvm1rDeqnJJDGz6p0DPb7lYMnRamcvC5ZNSlhUbOVkfthYzYr8X1R3rF5qehBfWELLeHsFs0J9dD3mjpsCVn1xWPMSmWp0HyhI_i8S4UHuSEmN1LrWMtQ27Fr213M8j6WGQ00188iWUCbCHOgiOYbcoC_MJmBSRCuKYqmJ0HYucVP7Q85ACC-fGtKGz_syZapjGSfDiPnMRh5dkCExGwGQNMG34tqnxULNs_Kdsi4DYlGswaMPpGsmsGYbLjMJVNNE4oX9-udY5vB3ORmmW3ox_nsA-vac-i3sKu9XjypzBG_VULZaPX9y_9gxDTs_2
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%3Ajournal&rft.genre=article&rft.atitle=GLAS%3A+Global-to-Local+Safe+Autonomy+Synthesis+for+Multi-Robot+Motion+Planning+With+End-to-End+Learning&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Riviere%2C+Benjamin&rft.au=Honig%2C+Wolfgang&rft.au=Yue%2C+Yisong&rft.au=Chung%2C+Soon-Jo&rft.date=2020-07-01&rft.issn=2377-3766&rft.eissn=2377-3766&rft.volume=5&rft.issue=3&rft.spage=4249&rft.epage=4256&rft_id=info:doi/10.1109%2FLRA.2020.2994035&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LRA_2020_2994035
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2377-3766&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2377-3766&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2377-3766&client=summon