Learning-Based Risk-Bounded Path Planning Under Environmental Uncertainty
Building a general and efficient path planning framework in uncertain nonconvex environments is challenging due to the safety constraints and complex configuration. Traditional avenues usually involve convexifying obstacles and presume Gaussian distribution, which are not universal. Meanwhile, the f...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on automation science and engineering Jg. 21; H. 3; S. 4460 - 4470 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
IEEE
01.07.2024
|
| Schlagworte: | |
| ISSN: | 1545-5955, 1558-3783 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Building a general and efficient path planning framework in uncertain nonconvex environments is challenging due to the safety constraints and complex configuration. Traditional avenues usually involve convexifying obstacles and presume Gaussian distribution, which are not universal. Meanwhile, the fast convergence of high-quality solutions is not guaranteed. Therefore, we develop a novel neural risk-bounded path planner to quickly find near-optimal solutions that have an acceptable collision probability in the complex environments. Firstly, we retrieve the nonconvex obstacles with arbitrary probabilistic uncertainties in the form of a deterministic point cloud map. A neural network sampler encodes it into a latent embedding and is trained with sufficient expert demonstrations, predicting states in the potential subspace. We construct a neural cost estimator to select the best informed state from those samples. Then, we recursively use the simple yet effective neural networks to march toward the start and goal bidirectionally. The collision risk of the intermediate connections is verified based on sum-of-squares optimization. Simulation results show that our approach significantly saves time and resources in finding comparable solutions over the state-of-the-art methods in the seen and unseen challenging environments. Note to Practitioners-More and more robots are deployed in unstructured environments, such as forests and subterranean caves. However, uncertainty in the environment situational awareness usually causes accidents. To quickly generate safe paths without over-conservation in uncertain complex environments, we propose a neural risk-bounded sampling-based path planner. Conventional methods consume lots of computation time and resources to generate satisfactory results. Our learning-based risk-bounded path planning framework can efficiently find paths with a guaranteed risk tolerance avoiding uncertain nonconvex static obstacles. It imitates the expert to generate informed states in a subspace that potentially contains the optimal solution. In practice, we need to formulate the observed uncertain obstacle at a grid map into the polynomial containing random variables and determine their probability distributions. |
|---|---|
| AbstractList | Building a general and efficient path planning framework in uncertain nonconvex environments is challenging due to the safety constraints and complex configuration. Traditional avenues usually involve convexifying obstacles and presume Gaussian distribution, which are not universal. Meanwhile, the fast convergence of high-quality solutions is not guaranteed. Therefore, we develop a novel neural risk-bounded path planner to quickly find near-optimal solutions that have an acceptable collision probability in the complex environments. Firstly, we retrieve the nonconvex obstacles with arbitrary probabilistic uncertainties in the form of a deterministic point cloud map. A neural network sampler encodes it into a latent embedding and is trained with sufficient expert demonstrations, predicting states in the potential subspace. We construct a neural cost estimator to select the best informed state from those samples. Then, we recursively use the simple yet effective neural networks to march toward the start and goal bidirectionally. The collision risk of the intermediate connections is verified based on sum-of-squares optimization. Simulation results show that our approach significantly saves time and resources in finding comparable solutions over the state-of-the-art methods in the seen and unseen challenging environments. Note to Practitioners-More and more robots are deployed in unstructured environments, such as forests and subterranean caves. However, uncertainty in the environment situational awareness usually causes accidents. To quickly generate safe paths without over-conservation in uncertain complex environments, we propose a neural risk-bounded sampling-based path planner. Conventional methods consume lots of computation time and resources to generate satisfactory results. Our learning-based risk-bounded path planning framework can efficiently find paths with a guaranteed risk tolerance avoiding uncertain nonconvex static obstacles. It imitates the expert to generate informed states in a subspace that potentially contains the optimal solution. In practice, we need to formulate the observed uncertain obstacle at a grid map into the polynomial containing random variables and determine their probability distributions. |
| Author | Chen, Liangliang Wang, Jiankun Ma, Han Meng, Fei Meng, Max Q.-H. |
| Author_xml | – sequence: 1 givenname: Fei orcidid: 0000-0001-9225-040X surname: Meng fullname: Meng, Fei email: feimeng@link.cuhk.edu.hk organization: Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong – sequence: 2 givenname: Liangliang orcidid: 0000-0002-9594-640X surname: Chen fullname: Chen, Liangliang email: liangliang.chen@gatech.edu organization: School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA – sequence: 3 givenname: Han orcidid: 0000-0003-1960-5432 surname: Ma fullname: Ma, Han email: hanma@link.cuhk.edu.hk organization: Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong – sequence: 4 givenname: Jiankun orcidid: 0000-0001-9139-0291 surname: Wang fullname: Wang, Jiankun email: wangjk@sustech.edu.cn organization: Department of Electronic and Electrical Engineering, Shenzhen Key Laboratory of Robotics Perception and Intelligence, Southern University of Science and Technology, Shenzhen, China – sequence: 5 givenname: Max Q.-H. orcidid: 0000-0002-5255-5898 surname: Meng fullname: Meng, Max Q.-H. email: max.meng@ieee.org organization: Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong |
| BookMark | eNp9kMtOwzAQRS0EEm3hA5BY5AdS_IgTe9lWBSpVooJ2HU38AEPqINsg9e9J1C4QC1Yzc3XPLM4YnfvOG4RuCJ4SguXddvaynFJM2ZRRWZGqPEMjwrnIWSXY-bAXPOeS80s0jvEdY1oIiUdotTYQvPOv-Ryi0dmzix_5vPvyuj82kN6yTQt-KGS7PgvZ0n-70Pm98QnaPlMmJHA-Ha7QhYU2muvTnKDd_XK7eMzXTw-rxWydK1qWKTdCaWYlLzXFRaEIkdRIIWSjtMBGgGRAQHEhiSWFYY2gpdJgpbVaN5g1bIKq418VuhiDsbVyCZLrfArg2prgejBSD0bqwUh9MtKT5A_5GdwewuFf5vbIOGPMrz7FFWaU_QCsWG-O |
| CODEN | ITASC7 |
| CitedBy_id | crossref_primary_10_3390_s24248177 crossref_primary_10_1109_TASE_2024_3363624 crossref_primary_10_1109_ACCESS_2025_3600283 crossref_primary_10_1109_LRA_2024_3463332 |
| Cites_doi | 10.1049/csy2.12020 10.1109/tase.2022.3215562 10.1177/0278364912456319 10.1109/CDC.2018.8618744 10.1109/ICRA.2018.8461096 10.1109/ICRA.2012.6225337 10.1109/TASE.2021.3121408 10.1109/IROS45743.2020.9341193 10.1109/70.508439 10.1177/0278364913501564 10.1016/j.isatra.2020.10.044 10.1109/ICRA40945.2020.9196785 10.1109/IROS.2018.8593893 10.1109/TAC.2020.3008126 10.1109/TRO.2018.2878996 10.1177/0278364918778338 10.1109/TASE.2021.3118737 10.1177/0278364911406761 10.1017/cbo9780511546877 10.15607/RSS.2019.XV.056 10.1109/ICRA46639.2022.9811363 10.1109/LRA.2019.2901898 10.1109/TRO.2018.2830331 10.1109/IROS.2015.7353740 10.1007/s11071-019-04879-w 10.1109/TASE.2020.2976560 10.1109/MED.2018.8442967 10.1109/TIV.2022.3152740 10.1109/MCS.2016.2602087 10.15607/rss.2021.xvii.069 10.2514/6.2010-8160 10.1007/978-3-319-60916-4_20 10.1109/TRO.2020.3006716 10.1016/j.apm.2022.08.009 10.1109/LRA.2022.3156654 10.15607/RSS.2021.XVII.021 10.1109/LRA.2020.2975759 10.1109/ROBOT.2010.5509683 |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION |
| DOI | 10.1109/TASE.2023.3297176 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-3783 |
| EndPage | 4470 |
| ExternalDocumentID | 10_1109_TASE_2023_3297176 10207032 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 62103181 funderid: 10.13039/501100001809 – fundername: Hong Kong Research Grants Council (RGC)’s Collaborative Research Fund (CRF) grantid: C4063-18G – fundername: Shenzhen Outstanding Scientific and Technological Innovation Talents Training Project grantid: RCBS20221008093305007 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION |
| ID | FETCH-LOGICAL-c266t-e8cd3f956d2044c1192e9889bcd80e8a93a1ac5891f14e3b826cdaf9ffddb03b3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 9 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001043270300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1545-5955 |
| IngestDate | Sat Nov 29 04:12:49 EST 2025 Tue Nov 18 19:41:25 EST 2025 Wed Aug 27 02:15:02 EDT 2025 |
| IsPeerReviewed | false |
| 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-c266t-e8cd3f956d2044c1192e9889bcd80e8a93a1ac5891f14e3b826cdaf9ffddb03b3 |
| ORCID | 0000-0002-5255-5898 0000-0001-9225-040X 0000-0002-9594-640X 0000-0003-1960-5432 0000-0001-9139-0291 |
| PageCount | 11 |
| ParticipantIDs | crossref_primary_10_1109_TASE_2023_3297176 ieee_primary_10207032 crossref_citationtrail_10_1109_TASE_2023_3297176 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-07-01 |
| PublicationDateYYYYMMDD | 2024-07-01 |
| PublicationDate_xml | – month: 07 year: 2024 text: 2024-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | IEEE transactions on automation science and engineering |
| PublicationTitleAbbrev | TASE |
| PublicationYear | 2024 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref13 ref35 LaValle (ref10) 1998 ref12 ref15 ref37 ref14 ref31 ref30 ref11 ref33 ref32 ref2 ref1 ref17 ref39 ref16 ref38 ref19 Qi (ref40) ref18 ApS (ref45) 2019; 4 Srivastava (ref42) 2014; 15 Dixit (ref26) 2022 ref24 ref46 ref23 ref25 ref20 ref41 ref22 ref21 ref43 ref28 Tobenkin (ref44) 2013 ref27 ref29 ref8 Flaspohler (ref36); 33 ref7 ref9 ref4 ref3 ref6 ref5 Kingma (ref47) 2014 Ding (ref34) 2022 |
| References_xml | – ident: ref35 doi: 10.1049/csy2.12020 – ident: ref23 doi: 10.1109/tase.2022.3215562 – ident: ref25 doi: 10.1177/0278364912456319 – ident: ref8 doi: 10.1109/CDC.2018.8618744 – ident: ref37 doi: 10.1109/ICRA.2018.8461096 – year: 2013 ident: ref44 article-title: Spotless polynomial and conic optimization – year: 1998 ident: ref10 article-title: Rapidly-exploring random trees: A new tool for path planning – ident: ref41 doi: 10.1109/ICRA.2012.6225337 – ident: ref14 doi: 10.1109/TASE.2021.3121408 – ident: ref17 doi: 10.1109/IROS45743.2020.9341193 – year: 2022 ident: ref34 article-title: Safety-aware optimal control for motion planning with low computing complexity publication-title: arXiv:2204.13380 – ident: ref9 doi: 10.1109/70.508439 – ident: ref19 doi: 10.1177/0278364913501564 – ident: ref6 doi: 10.1016/j.isatra.2020.10.044 – ident: ref24 doi: 10.1109/ICRA40945.2020.9196785 – ident: ref20 doi: 10.1109/IROS.2018.8593893 – volume: 15 start-page: 1929 issue: 56 year: 2014 ident: ref42 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: J. Mach. Learn. Res. – ident: ref29 doi: 10.1109/TAC.2020.3008126 – ident: ref5 doi: 10.1109/TRO.2018.2878996 – ident: ref16 doi: 10.1177/0278364918778338 – ident: ref30 doi: 10.1109/TASE.2021.3118737 – ident: ref46 doi: 10.1177/0278364911406761 – start-page: 652 volume-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. ident: ref40 article-title: PointNet: Deep learning on point sets for 3D classification and segmentation – ident: ref11 doi: 10.1017/cbo9780511546877 – ident: ref21 doi: 10.15607/RSS.2019.XV.056 – ident: ref22 doi: 10.1109/ICRA46639.2022.9811363 – ident: ref38 doi: 10.1109/LRA.2019.2901898 – volume: 33 start-page: 11108 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref36 article-title: Belief-dependent macro-action discovery in POMDPs using the value of information – ident: ref12 doi: 10.1109/TRO.2018.2830331 – ident: ref28 doi: 10.1109/IROS.2015.7353740 – ident: ref27 doi: 10.1007/s11071-019-04879-w – ident: ref39 doi: 10.1109/TASE.2020.2976560 – ident: ref32 doi: 10.1109/MED.2018.8442967 – year: 2014 ident: ref47 article-title: Adam: A method for stochastic optimization publication-title: arXiv:1412.6980 – ident: ref3 doi: 10.1109/TIV.2022.3152740 – ident: ref4 doi: 10.1109/MCS.2016.2602087 – ident: ref15 doi: 10.15607/rss.2021.xvii.069 – ident: ref18 doi: 10.2514/6.2010-8160 – ident: ref7 doi: 10.1007/978-3-319-60916-4_20 – ident: ref13 doi: 10.1109/TRO.2020.3006716 – year: 2022 ident: ref26 article-title: Risk-averse receding horizon motion planning publication-title: arXiv:2204.09596 – ident: ref31 doi: 10.1016/j.apm.2022.08.009 – ident: ref2 doi: 10.1109/LRA.2022.3156654 – ident: ref1 doi: 10.15607/RSS.2021.XVII.021 – ident: ref33 doi: 10.1109/LRA.2020.2975759 – volume: 4 start-page: 1 year: 2019 ident: ref45 article-title: Mosek optimization toolbox for MATLAB publication-title: User’s Guide Reference Manual – ident: ref43 doi: 10.1109/ROBOT.2010.5509683 |
| SSID | ssj0024890 |
| Score | 2.4249449 |
| Snippet | Building a general and efficient path planning framework in uncertain nonconvex environments is challenging due to the safety constraints and complex... |
| SourceID | crossref ieee |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 4460 |
| SubjectTerms | Collision avoidance deep learning methods Environmental factors Path planning Planning Probabilistic logic risk-bounded path planning Robots Sampling-based algorithm Three-dimensional displays Uncertainty |
| Title | Learning-Based Risk-Bounded Path Planning Under Environmental Uncertainty |
| URI | https://ieeexplore.ieee.org/document/10207032 |
| Volume | 21 |
| WOSCitedRecordID | wos001043270300001&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: 1558-3783 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0024890 issn: 1545-5955 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF60eNCDz4r1RQ6ehK2bZLfZPbbSoiClaAu9hX1KUVqxqeC_d3aT2npQ8JaE3RC-TDIzuzPfh9AVpYxlEEnjljUGU6Eo5hJyHu7pAEkqwesHntmHrN_n47EYVM3qoRfGWhuKz2zTH4a9fDPTC79UBl944i0U_ribWdYqm7VWxHo8LKj4kAAzwVi1hRkTcTNsP3WbXie8mSYC8pfWDye0pqoSnEpv75-Ps492q-gxapev-wBt2Okh2lnjFDxC9xVj6jPugIMy0eNk_oI7XjwJTgYQ70VLnaIoaB5F3VWrG9x6BEYQigSKzzoa9brD2ztc6SVgDW62wJZrkzpIeExCKNUxBG9WcC6UNpxYLkUqY6m9jKCLqU0VZBbaSCecM0aRVKXHqDadTe0JihS3VDlPG8ocZdRIHbvEiFgpJojjWQORJYC5rsjEvabFax6SCiJyj3nuMc8rzBvo-nvKW8mk8dfgusd7bWAJ9ekv18_QNkynZR3tOaoV7wt7gbb0RzGZv18GQ_kCjOm6WA |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF6kCurBZ8X6zMGTsHWT7La7x1ZaWqylaAu9hexLitJKH4L_3tlNautBwVsSNkv4MsnM7M58H0I3lDJWhUgaV4zWmApJMU8h5-GODpDEKXh9zzPbqXa7fDgUvbxZ3ffCGGN88Zkpu0O_l68nauGWyuALj5yFwh93k1Eakaxda0Wtx_2SigsKMBOM5ZuYIRF3_dpzo-yUwstxJCCDqfxwQ2u6Kt6tNPf_-UAHaC-PH4Na9sIP0YYZH6HdNVbBY9TOOVNfcB1clA6eRrNXXHfySXDSg4gvWCoVBV71KGismt1g6gGYgS8TmH8W0aDZ6N-3cK6YgBU42jk2XOnYQsqjI0KpCiF8M4JzIZXmxPBUxGmYKickaENqYgm5hdKpFdZqLUks4xNUGE_G5hQFkhsqrSMOZZYyqlMV2kiLUEomiOXVEiJLABOV04k7VYu3xKcVRCQO88RhnuSYl9Dt9y3vGZfGX4OLDu-1gRnUZ79cv0bbrf5jJ-m0uw_naAemollV7QUqzKcLc4m21Md8NJteeaP5AmtqvZ8 |
| 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=Learning-Based+Risk-Bounded+Path+Planning+Under+Environmental+Uncertainty&rft.jtitle=IEEE+transactions+on+automation+science+and+engineering&rft.au=Meng%2C+Fei&rft.au=Chen%2C+Liangliang&rft.au=Ma%2C+Han&rft.au=Wang%2C+Jiankun&rft.date=2024-07-01&rft.pub=IEEE&rft.issn=1545-5955&rft.volume=21&rft.issue=3&rft.spage=4460&rft.epage=4470&rft_id=info:doi/10.1109%2FTASE.2023.3297176&rft.externalDocID=10207032 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-5955&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-5955&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-5955&client=summon |