MLNav: Learning to Safely Navigate on Martian Terrains
We present MLNav , a learning-enhanced path planning framework for safety-critical and resource-limited systems operating in complex environments, such as rovers navigating on Mars. MLNav makes judicious use of machine learning to enhance the efficiency of path planning while fully respecting safety...
Uloženo v:
| Vydáno v: | IEEE robotics and automation letters Ročník 7; číslo 2; s. 5461 - 5468 |
|---|---|
| Hlavní autoři: | , , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Piscataway
IEEE
01.04.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Témata: | |
| ISSN: | 2377-3766, 2377-3766 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | We present MLNav , a learning-enhanced path planning framework for safety-critical and resource-limited systems operating in complex environments, such as rovers navigating on Mars. MLNav makes judicious use of machine learning to enhance the efficiency of path planning while fully respecting safety constraints. In particular, the dominant computational cost in such safety-critical settings is running a model-based safety checker on the proposed paths. Our learned search heuristic can simultaneously predict the feasibility for all path options in a single run, and the model-based safety checker is only invoked on the top-scoring paths. We validate in high-fidelity simulations using both real Martian terrain data collected by the Perseverance rover, as well as a suite of challenging synthetic terrains. Our experiments show that: (i) compared to the baseline ENav path planner on board the Perserverance rover, MLNav can provide a significant improvement in multiple key metrics, such as a 10x reduction in collision checks when navigating real Martian terrains, despite being trained with synthetic terrains; and (ii) MLNav can successfully navigate highly challenging terrains where the baseline ENav fails to find a feasible path before timing out. |
|---|---|
| AbstractList | We present MLNav , a learning-enhanced path planning framework for safety-critical and resource-limited systems operating in complex environments, such as rovers navigating on Mars. MLNav makes judicious use of machine learning to enhance the efficiency of path planning while fully respecting safety constraints. In particular, the dominant computational cost in such safety-critical settings is running a model-based safety checker on the proposed paths. Our learned search heuristic can simultaneously predict the feasibility for all path options in a single run, and the model-based safety checker is only invoked on the top-scoring paths. We validate in high-fidelity simulations using both real Martian terrain data collected by the Perseverance rover, as well as a suite of challenging synthetic terrains. Our experiments show that: (i) compared to the baseline ENav path planner on board the Perserverance rover, MLNav can provide a significant improvement in multiple key metrics, such as a 10x reduction in collision checks when navigating real Martian terrains, despite being trained with synthetic terrains; and (ii) MLNav can successfully navigate highly challenging terrains where the baseline ENav fails to find a feasible path before timing out. |
| Author | Daftry, Shreyansh Ono, Masahiro Byon, Amos Abcouwer, Neil Venkatraman, Siddarth Igel, Lucas Rosolia, Ugo Song, Jialin Yue, Yisong Sesto, Tyler Del |
| Author_xml | – sequence: 1 givenname: Shreyansh orcidid: 0000-0002-0157-5944 surname: Daftry fullname: Daftry, Shreyansh email: shreyansh.daftry@jpl.nasa.gov organization: Jet Propulsion Laboratory, Institute of Technology, California, USA – sequence: 2 givenname: Neil surname: Abcouwer fullname: Abcouwer, Neil email: neil.abcouwer@jpl.nasa.gov organization: Jet Propulsion Laboratory, Institute of Technology, California, USA – sequence: 3 givenname: Tyler Del surname: Sesto fullname: Sesto, Tyler Del email: tyler.del.sesto@jpl.nasa.gov organization: Jet Propulsion Laboratory, Institute of Technology, California, USA – sequence: 4 givenname: Siddarth orcidid: 0000-0002-3607-2781 surname: Venkatraman fullname: Venkatraman, Siddarth email: siddarthegreat@gmail.com organization: Manipal Institute of Technology, India – sequence: 5 givenname: Jialin surname: Song fullname: Song, Jialin email: jssong@caltech.edu organization: Institute of Technology, California, USA – sequence: 6 givenname: Lucas surname: Igel fullname: Igel, Lucas email: luke.igel@gmail.com organization: Massachusetts Institute of Technology, USA – sequence: 7 givenname: Amos surname: Byon fullname: Byon, Amos email: amos.j.byon@jpl.nasa.gov organization: Jet Propulsion Laboratory, Institute of Technology, California, USA – sequence: 8 givenname: Ugo orcidid: 0000-0002-1682-0551 surname: Rosolia fullname: Rosolia, Ugo email: urosolia@caltech.edu organization: Institute of Technology, California, USA – sequence: 9 givenname: Yisong surname: Yue fullname: Yue, Yisong email: yyue@caltech.edu organization: Institute of Technology, California, USA – sequence: 10 givenname: Masahiro surname: Ono fullname: Ono, Masahiro email: masahiro.ono@jpl.nasa.gov organization: Jet Propulsion Laboratory, Institute of Technology, California, USA |
| BookMark | eNp9kM1LAzEQxYNUsNbeBS8Bz7vmextvpfgFWwWt55DNzpaUmq3ZVOh_75YWEQ-eZhjebx7vnaNBaAMgdElJTinRN-XrNGeEsZxTqZQUJ2jIeFFkvFBq8Gs_Q-OuWxFCqGQF13KI1Lx8tl-3uAQbgw9LnFr8ZhtY73B_90ubALcBz21M3ga8gBitD90FOm3suoPxcY7Q-_3dYvaYlS8PT7NpmTmmacpk7RoLBDQTMKlrNakqRogGSoCyglW6gEpb4JJWztnKCS0cCNUoUFZSUfMRuj783cT2cwtdMqt2G0NvaZgSRHDeR-tV5KByse26CI3ZRP9h485QYvYFmb4gsy_IHAvqEfUHcT7Z5NuQ-oDr_8CrA-gB4MdHF0xLovg3CWRzJw |
| CODEN | IRALC6 |
| CitedBy_id | crossref_primary_10_1038_s41598_025_91107_8 crossref_primary_10_1109_TGRS_2024_3432533 crossref_primary_10_1109_TASE_2023_3297176 crossref_primary_10_3390_aerospace11080692 crossref_primary_10_3390_geosciences12060248 crossref_primary_10_54105_ijdm_A1643_05010525 crossref_primary_10_1109_LRA_2023_3281261 crossref_primary_10_1109_ACCESS_2023_3312021 crossref_primary_10_3390_rs17111924 crossref_primary_10_1016_j_engappai_2025_110690 crossref_primary_10_1016_j_artint_2023_104018 crossref_primary_10_1109_TAC_2022_3210871 crossref_primary_10_1016_j_asr_2025_05_034 crossref_primary_10_1109_LRA_2024_3387042 crossref_primary_10_2514_1_G008791 |
| Cites_doi | 10.1002/rob.21892 10.1109/ICRA.2016.7487116 10.1145/1015330.1015430 10.1109/IROS.2016.7759328 10.15607/RSS.2017.XIII.064 10.1109/ROBOT.1997.619371 10.1109/AERO.2007.352683 10.1007/978-3-030-66723-8_5 10.1109/IROS45743.2020.9341526 10.1109/AERO47225.2020.9172345 10.1002/rob.22011 10.1109/ICRA.2018.8460730 10.1109/ICRA.2018.8461096 10.1109/LRA.2021.3096758 10.1109/ICRA.2017.7989182 10.1029/2002JE002035 10.1109/TRO.2020.3006716 10.1007/978-3-319-50115-4_1 10.1177/0278364918781001 10.1007/978-3-319-24574-4_28 10.1145/3447928.3456653 10.1007/978-3-030-44051-0_4 10.1109/TRO.2020.2974094 10.1109/AERO50100.2021.9438337 10.1007/s10514-022-10039-8 10.1109/ACCESS.2014.2302442 10.1177/0278364917722396 10.1007/978-3-319-27702-8_26 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/LRA.2022.3156654 |
| DatabaseName | IEEE Xplore (IEEE) 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 | 5468 |
| ExternalDocumentID | 10_1109_LRA_2022_3156654 9729506 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Raytheon – fundername: JPL Research and Technology Development |
| 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-5dcfae0e924e8dd68bb2009e10e1272b97eb9ae351bccabc494ce46f6e6a514d3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 18 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000770589900008&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 Jun 29 15:46:16 EDT 2025 Sat Nov 29 06:03:16 EST 2025 Tue Nov 18 21:00:09 EST 2025 Wed Aug 27 02:48:01 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| 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-5dcfae0e924e8dd68bb2009e10e1272b97eb9ae351bccabc494ce46f6e6a514d3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-0157-5944 0000-0002-1682-0551 0000-0002-3607-2781 |
| PQID | 2640433377 |
| PQPubID | 4437225 |
| PageCount | 8 |
| ParticipantIDs | proquest_journals_2640433377 crossref_primary_10_1109_LRA_2022_3156654 ieee_primary_9729506 crossref_citationtrail_10_1109_LRA_2022_3156654 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-04-01 |
| PublicationDateYYYYMMDD | 2022-04-01 |
| PublicationDate_xml | – month: 04 year: 2022 text: 2022-04-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE robotics and automation letters |
| PublicationTitleAbbrev | LRA |
| PublicationYear | 2022 |
| 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 | ref13 Levine (ref14) 2016; 17 ref35 ref12 ref34 ref15 ref31 ref30 ref11 ref33 ref10 ref32 ref2 Dhiman (ref5) 2018 ref17 Gao (ref22) 2017 ref16 ref19 Smith (ref7) 2018 ref24 ref23 ref26 ref25 ref20 ref28 ref27 McHenry (ref1) 2020 ref29 ref8 ref9 ref4 ref3 ref6 Yao (ref21) 2019 Ziebart (ref18) 2008; 8 Doyle (ref36) 2013 |
| References_xml | – ident: ref32 doi: 10.1002/rob.21892 – ident: ref28 doi: 10.1109/ICRA.2016.7487116 – ident: ref17 doi: 10.1145/1015330.1015430 – ident: ref20 doi: 10.1109/IROS.2016.7759328 – volume: 17 start-page: 1334 issue: 1 year: 2016 ident: ref14 article-title: End-to-end training of deep visuomotor policies publication-title: J. Mach. Learn. Res. – start-page: 3003 volume-title: Proc. Meeting Amer. Astronomical Soc. year: 2020 ident: ref1 article-title: Mars 2020 autonomous rover navigation – ident: ref24 doi: 10.15607/RSS.2017.XIII.064 – ident: ref3 doi: 10.1109/ROBOT.1997.619371 – ident: ref31 doi: 10.1109/AERO.2007.352683 – ident: ref29 doi: 10.1007/978-3-030-66723-8_5 – year: 2019 ident: ref21 article-title: Following social groups: Socially compliant autonomous navigation in dense crowds – ident: ref27 doi: 10.1109/IROS45743.2020.9341526 – year: 2018 ident: ref5 article-title: A critical investigation of deep reinforcement learning for navigation – ident: ref34 doi: 10.1109/AERO47225.2020.9172345 – ident: ref2 doi: 10.1002/rob.22011 – ident: ref11 doi: 10.1109/ICRA.2018.8460730 – volume: 8 start-page: 1433 year: 2008 ident: ref18 article-title: Maximum entropy inverse reinforcement learning publication-title: Aaai – ident: ref23 doi: 10.1109/ICRA.2018.8461096 – ident: ref8 doi: 10.1109/LRA.2021.3096758 – ident: ref16 doi: 10.1109/ICRA.2017.7989182 – ident: ref35 doi: 10.1029/2002JE002035 – volume-title: Proc. Conf. Robot Learning. PMLR year: 2017 ident: ref22 article-title: Intention-net: Integrating planning and deep learning for goal-directed autonomous navigation – ident: ref9 doi: 10.1109/TRO.2020.3006716 – ident: ref15 doi: 10.1007/978-3-319-50115-4_1 – ident: ref10 doi: 10.1177/0278364918781001 – ident: ref33 doi: 10.1007/978-3-319-24574-4_28 – volume-title: Proc. Workshop Spacecraft Flight Softw. year: 2013 ident: ref36 article-title: High performance spaceflight computing (HPSC) next-generation space processor (NGSP): A joint investment of NASA and AFRL – ident: ref6 doi: 10.1145/3447928.3456653 – ident: ref25 doi: 10.1007/978-3-030-44051-0_4 – ident: ref26 doi: 10.1109/TRO.2020.2974094 – year: 2018 ident: ref7 article-title: Learning to navigate: Exploiting deep networks to inform sample-based planning during vision-based navigation – ident: ref12 doi: 10.1109/AERO50100.2021.9438337 – ident: ref4 doi: 10.1007/s10514-022-10039-8 – ident: ref13 doi: 10.1109/ACCESS.2014.2302442 – ident: ref19 doi: 10.1177/0278364917722396 – ident: ref30 doi: 10.1007/978-3-319-27702-8_26 |
| SSID | ssj0001527395 |
| Score | 2.343267 |
| Snippet | We present MLNav , a learning-enhanced path planning framework for safety-critical and resource-limited systems operating in complex environments, such as... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 5461 |
| SubjectTerms | Computational modeling Feasibility Integrated planning and learning Machine learning Mars Mars rovers motion and path planning Navigation Path planning Planning Robots Safety Safety critical space robotics and automation |
| Title | MLNav: Learning to Safely Navigate on Martian Terrains |
| URI | https://ieeexplore.ieee.org/document/9729506 https://www.proquest.com/docview/2640433377 |
| Volume | 7 |
| WOSCitedRecordID | wos000770589900008&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/eLvHCXMwlV3PS8MwFH5sw4Me_DXF6Rw5eBGs68808TZkw8M2RCfsVprkVYTRytYNvPi3m7TdVBTBWyhJKN9r897LS74P4IIrxYTiviWoCixfMWUxyTxLSkwcrls8KcUmwvGYTaf8vgZXm7swiFgcPsNr0yxq-SqTS7NV1uU6EgwMv3Y9DGl5V-tzP8UwifFgXYm0eXf40NP5n-vqtDQwGrvfPE8hpfJj_S2cymDvf6-zD7tV8Eh6pbUPoIbpIex8oRRsAh0Nx_HqhlS8qc8kz8hjnODsjejnhk8DSZaSgj0gTskE50YjYnEET4P-5PbOqrQRLOlyJ7cCJZMYbdTpEzKlKBPC1DnQsdFxQ1fwEAWP0QscoW0kpM99iT5NKNJYx0jKO4ZGmqV4AkRoj0QTE_cZph3hC8mVtKW0Q-WomLkt6K5xi2RFHG70K2ZRkUDYPNJIRwbpqEK6BZebEa8lacYffZsG2U2_CtQWtNemiaq_ahHp4M3wrXlhePr7qDPYNnOXJ2va0MjnSzyHLbnKXxbzDtRH7_1O8dl8AFCIv-4 |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwED6GCuqDv6Y4nZoHXwTr-ruNb0McE7siOmFvoUmuIoxWtm7gf2_SdlNRBN9CSUj5rs3d5ZLvAzinUoZcUtfgvvQMV4bSCEXoGEJgalHVomklNhHEcTga0YcGXC7vwiBiefgMr3SzrOXLXMz0VlmHqkjQ0_zaq57r2mZ1W-tzR0VziVFvUYs0aSd67KoM0LZVYuppld1vvqcUU_mxApdupbf9vxfaga06fCTdyt670MBsDza_kAo2wR9EcTK_JjVz6gspcvKUpDh-J-q5ZtRAkmek5A9IMjLEiVaJmO7Dc-92eNM3anUEQ9jUKgxPijRBE1UChaGUfsi5rnSgZaJlBzanAXKaoONZXFmJC5e6Al0_9dFPVJQknQNYyfIMD4Fw5ZP8VEd-mmuHu1xQKUwhzEBaMgntFnQWuDFRU4drBYsxK1MIkzKFNNNIsxrpFlwsR7xVtBl_9G1qZJf9alBb0F6YhtX_1ZSp8E0zrjlBcPT7qDNY7w8HEYvu4vtj2NDzVOds2rBSTGZ4AmtiXrxOJ6flx_MB7MjCBA |
| 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=MLNav%3A+Learning+to+Safely+Navigate+on+Martian+Terrains&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Daftry%2C+Shreyansh&rft.au=Abcouwer%2C+Neil&rft.au=Tyler+Del+Sesto&rft.au=Venkatraman%2C+Siddarth&rft.date=2022-04-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.eissn=2377-3766&rft.volume=7&rft.issue=2&rft.spage=5461&rft_id=info:doi/10.1109%2FLRA.2022.3156654&rft.externalDBID=NO_FULL_TEXT |
| 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 |