DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles
This article proposes a novel learning-based control policy with strong generalizability to new environments that enables a mobile robot to navigate autonomously through spaces filled with both static obstacles and dense crowds of pedestrians. The policy uses a unique combination of input data to ge...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on robotics Jg. 39; H. 4; S. 2700 - 2719 |
|---|---|
| Hauptverfasser: | , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
New York
IEEE
01.08.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Schlagworte: | |
| ISSN: | 1552-3098, 1941-0468 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | This article proposes a novel learning-based control policy with strong generalizability to new environments that enables a mobile robot to navigate autonomously through spaces filled with both static obstacles and dense crowds of pedestrians. The policy uses a unique combination of input data to generate the desired steering angle and forward velocity: a short history of lidar data, kinematic data about nearby pedestrians, and a subgoal point. The policy is trained in a reinforcement learning setting using a reward function that contains a novel term based on velocity obstacles to guide the robot to actively avoid pedestrians and move toward the goal. Through a series of 3-D simulated experiments with up to 55 pedestrians, this control policy is able to achieve a better balance between collision avoidance and speed (i.e., higher success rate and faster average speed) than state-of-the-art model-based and learning-based policies, and it also generalizes better to different crowd sizes and unseen environments. An extensive series of hardware experiments demonstrate the ability of this policy to directly work in different real-world environments with different crowd sizes with zero retraining. Furthermore, a series of simulated and hardware experiments show that the control policy also works in highly constrained static environments on a different robot platform without any additional training. Lastly, several important lessons that can be applied to other robot learning systems are summarized. |
|---|---|
| AbstractList | This article proposes a novel learning-based control policy with strong generalizability to new environments that enables a mobile robot to navigate autonomously through spaces filled with both static obstacles and dense crowds of pedestrians. The policy uses a unique combination of input data to generate the desired steering angle and forward velocity: a short history of lidar data, kinematic data about nearby pedestrians, and a subgoal point. The policy is trained in a reinforcement learning setting using a reward function that contains a novel term based on velocity obstacles to guide the robot to actively avoid pedestrians and move toward the goal. Through a series of 3-D simulated experiments with up to 55 pedestrians, this control policy is able to achieve a better balance between collision avoidance and speed (i.e., higher success rate and faster average speed) than state-of-the-art model-based and learning-based policies, and it also generalizes better to different crowd sizes and unseen environments. An extensive series of hardware experiments demonstrate the ability of this policy to directly work in different real-world environments with different crowd sizes with zero retraining. Furthermore, a series of simulated and hardware experiments show that the control policy also works in highly constrained static environments on a different robot platform without any additional training. Lastly, several important lessons that can be applied to other robot learning systems are summarized. |
| Author | Xie, Zhanteng Dames, Philip |
| Author_xml | – sequence: 1 givenname: Zhanteng orcidid: 0000-0002-5442-1252 surname: Xie fullname: Xie, Zhanteng email: zhanteng.xie@temple.edu organization: Department of Mechanical Engineering, Temple University, Philadelphia, PA, USA – sequence: 2 givenname: Philip orcidid: 0000-0002-7257-0075 surname: Dames fullname: Dames, Philip email: pdames@temple.edu organization: Department of Mechanical Engineering, Temple University, Philadelphia, PA, USA |
| BookMark | eNp9kD1PwzAQhi1UJEphZ2CwxJziryQ2G2r5kiIilbRr5DiXNlUaFzsF9d-Tqh0QA9Pd8D736p5LNGhtCwjdUDKmlKj7bJaOGWF8zFkYh0KdoSFVggZERHLQ72HIAk6UvECX3q8JYUIRPkTZdJYEi_QBJ6BdW7dL3Fn8rr_qpe4AZytnd8sVnjj7XUKJp_tWb2qDPwy04PHcH4AFNNbU3R6nhe-0acBfofNKNx6uT3OE5s9P2eQ1SNKXt8ljEhimWBdQ4EKDKJmIqoIzE8sqNMBLqSkrC6NjSaOKybCICi21LEFSKqEqTVwUQgHwEbo73t06-7kD3-Vru3NtX5kzKWIViZhHfYocU8ZZ7x1U-dbVG-32OSX5wV3eu8sP7vKTux6J_iD9g7qrbds5XTf_gbdHsAaAXz1EKqoi_gM4V34r |
| CODEN | ITREAE |
| CitedBy_id | crossref_primary_10_1016_j_eswa_2024_124388 crossref_primary_10_1111_exsy_13718 crossref_primary_10_1145_3719019 crossref_primary_10_1109_TIE_2024_3419242 crossref_primary_10_1109_TIV_2024_3444854 crossref_primary_10_1109_LRA_2024_3502060 crossref_primary_10_1109_LRA_2025_3598567 crossref_primary_10_1109_LRA_2024_3482190 crossref_primary_10_1109_TASE_2025_3582522 crossref_primary_10_1109_TASE_2025_3578326 crossref_primary_10_1109_TASE_2025_3579573 crossref_primary_10_3390_s24092794 crossref_primary_10_1016_j_compeleceng_2025_110430 crossref_primary_10_1016_j_robot_2025_105020 crossref_primary_10_1109_LRA_2025_3553050 crossref_primary_10_1007_s10489_024_05679_5 crossref_primary_10_1016_j_eswa_2025_129706 crossref_primary_10_1109_LRA_2024_3396057 crossref_primary_10_1007_s10586_025_05475_x crossref_primary_10_1109_LRA_2025_3544927 crossref_primary_10_1049_csy2_70012 crossref_primary_10_1016_j_isatra_2024_10_026 crossref_primary_10_1109_TRO_2024_3522187 crossref_primary_10_1109_ACCESS_2025_3597330 crossref_primary_10_1109_LRA_2025_3568320 crossref_primary_10_1109_TIV_2024_3405330 crossref_primary_10_3390_drones8090497 crossref_primary_10_1080_01691864_2025_2506091 crossref_primary_10_1109_LRA_2023_3331621 crossref_primary_10_1109_LRA_2025_3547306 crossref_primary_10_3390_s23249732 crossref_primary_10_1111_risa_17599 |
| Cites_doi | 10.1109/ICRA48506.2021.9561417 10.1109/IROS51168.2021.9636613 10.1177/0278364920916531 10.1109/ICRA.2018.8461113 10.1109/IROS45743.2020.9341783 10.1109/LRA.2019.2929976 10.1109/IROS51168.2021.9636463 10.1109/LRA.2018.2795643 10.1109/IROS.2016.7759428 10.1109/TCST.2017.2654063 10.1109/ICRA48506.2021.9561595 10.1098/rspb.2009.0405 10.1109/ICRA40945.2020.9197379 10.1109/ICRA48506.2021.9561462 10.1007/978-3-642-19457-3_1 10.1103/PhysRevE.51.4282 10.1109/LRA.2021.3057023 10.1109/100.580977 10.1109/IROS45743.2020.9340705 10.1109/LRA.2022.3161699 10.1109/IROS.2013.6696576 10.1109/IROS.2017.8202312 10.1109/LRA.2018.2869644 10.1109/ICRA.2019.8794134 10.1287/ijoc.1080.0305 10.1109/ICRA.2017.7989182 10.1109/IROS51168.2021.9636618 10.1109/ICRA.2019.8794062 10.1109/IROS.2009.5354175 10.1109/TITS.2020.2972974 10.1109/CVPR.2016.90 10.1109/IROS.2004.1389727 10.1109/ROMAN.2017.8172334 10.1007/978-3-030-58526-6_42 10.1109/IROS.2018.8593871 10.1109/ICRA48506.2021.9560893 10.1109/SSRR50563.2020.9292572 10.1109/ICRA48506.2021.9560951 10.1109/LRA.2021.3064461 10.1109/MRA.2022.3213466 10.1109/ACCESS.2019.2933492 10.1109/IROS51168.2021.9636102 10.1109/LRA.2020.2976302 10.1177/027836499801700706 10.1049/iet-ipr.2017.1244 10.1109/IROS45743.2020.9341540 10.1109/LRA.2020.2972868 10.1109/ACCESS.2021.3050338 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D |
| DOI | 10.1109/TRO.2023.3257549 |
| 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 Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering 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 Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database 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 | 1941-0468 |
| EndPage | 2719 |
| ExternalDocumentID | 10_1109_TRO_2023_3257549 10089196 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Science Foundation grantid: IIS-1830419; 1625061 funderid: 10.13039/501100008982 – fundername: Temple University funderid: 10.13039/100010842 – fundername: Army Research Laboratory grantid: W911NF-16-2-0189 funderid: 10.13039/100006754 |
| GroupedDBID | .DC 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO 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 MS~ O9- OCL P2P PQQKQ RIA RIE RNS VJK AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c292t-1e34ae4d246fb32c78f5ce3d8a12dbca7816f285b6ba8a8de8118efdc7bb49ee3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 51 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000967530400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1552-3098 |
| IngestDate | Sun Jun 29 15:33:31 EDT 2025 Tue Nov 18 22:05:37 EST 2025 Sat Nov 29 01:47:31 EST 2025 Wed Aug 27 02:46:23 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| 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-c292t-1e34ae4d246fb32c78f5ce3d8a12dbca7816f285b6ba8a8de8118efdc7bb49ee3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-7257-0075 0000-0002-5442-1252 |
| PQID | 2847964736 |
| PQPubID | 27625 |
| PageCount | 20 |
| ParticipantIDs | proquest_journals_2847964736 ieee_primary_10089196 crossref_citationtrail_10_1109_TRO_2023_3257549 crossref_primary_10_1109_TRO_2023_3257549 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-Aug. 2023-8-00 20230801 |
| PublicationDateYYYYMMDD | 2023-08-01 |
| PublicationDate_xml | – month: 08 year: 2023 text: 2023-Aug. |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on robotics |
| PublicationTitleAbbrev | TRO |
| PublicationYear | 2023 |
| 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 ref12 ref56 ref15 ref14 ref58 ref11 ref10 marr (ref3) 2020 ref17 ref16 schulman (ref25) 2017 ref19 ref18 kingma (ref55) 2014 ref51 makoviychuk (ref62) 2021 mnih (ref52) 0 ref46 ref45 ref48 ref42 gloor (ref57) 2016 ref41 ref44 ref43 quigley (ref8) 0; 3 blyler (ref2) 2020 ref49 raffin (ref59) 2019 ref7 ref9 ref4 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref31 schulman (ref53) 0 ref30 ref33 ref32 coulter (ref50) 1992 ref39 ref38 kim (ref1) 2021 redmon (ref47) 2018 ref24 ref23 ref26 ref20 ref22 ref21 wang (ref54) 2016 ref28 ref27 ref29 ref60 ref61 |
| References_xml | – year: 2017 ident: ref25 article-title: Proximal policy optimization algorithms – ident: ref15 doi: 10.1109/ICRA48506.2021.9561417 – ident: ref9 doi: 10.1109/IROS51168.2021.9636613 – year: 2020 ident: ref3 article-title: Demand for these autonomous delivery robots is skyrocketing during this pandemic – ident: ref27 doi: 10.1177/0278364920916531 – ident: ref26 doi: 10.1109/ICRA.2018.8461113 – start-page: 1889 year: 0 ident: ref53 article-title: Trust region policy optimization publication-title: Proc Int Conf Mach Learn – ident: ref6 doi: 10.1109/IROS45743.2020.9341783 – year: 2016 ident: ref57 article-title: PEDSIM: Pedestrian crowd simulation – ident: ref14 doi: 10.1109/LRA.2019.2929976 – ident: ref40 doi: 10.1109/IROS51168.2021.9636463 – ident: ref22 doi: 10.1109/LRA.2018.2795643 – ident: ref21 doi: 10.1109/IROS.2016.7759428 – ident: ref60 doi: 10.1109/TCST.2017.2654063 – ident: ref36 doi: 10.1109/ICRA48506.2021.9561595 – ident: ref58 doi: 10.1098/rspb.2009.0405 – ident: ref38 doi: 10.1109/ICRA40945.2020.9197379 – year: 2019 ident: ref59 article-title: Stable baselines3 – ident: ref41 doi: 10.1109/ICRA48506.2021.9561462 – ident: ref12 doi: 10.1007/978-3-642-19457-3_1 – ident: ref16 doi: 10.1103/PhysRevE.51.4282 – ident: ref23 doi: 10.1109/LRA.2021.3057023 – ident: ref4 doi: 10.1109/100.580977 – ident: ref34 doi: 10.1109/IROS45743.2020.9340705 – ident: ref42 doi: 10.1109/LRA.2022.3161699 – ident: ref17 doi: 10.1109/IROS.2013.6696576 – ident: ref30 doi: 10.1109/IROS.2017.8202312 – ident: ref49 doi: 10.1109/LRA.2018.2869644 – volume: 3 year: 0 ident: ref8 article-title: ROS: An open-source robot operating system publication-title: Proc ICRA Workshop Open Source Softw – ident: ref33 doi: 10.1109/ICRA.2019.8794134 – ident: ref45 doi: 10.1287/ijoc.1080.0305 – year: 2014 ident: ref55 article-title: Adam: A method for stochastic optimization – ident: ref20 doi: 10.1109/ICRA.2017.7989182 – ident: ref13 doi: 10.1109/IROS51168.2021.9636618 – ident: ref24 doi: 10.1109/ICRA.2019.8794062 – ident: ref11 doi: 10.1109/IROS.2009.5354175 – year: 2016 ident: ref54 article-title: Sample efficient actor-critic with experience replay – ident: ref51 doi: 10.1109/TITS.2020.2972974 – ident: ref44 doi: 10.1109/CVPR.2016.90 – year: 2020 ident: ref2 article-title: One big 2020 robot trend that's hard to miss – ident: ref56 doi: 10.1109/IROS.2004.1389727 – ident: ref18 doi: 10.1109/ROMAN.2017.8172334 – ident: ref46 doi: 10.1007/978-3-030-58526-6_42 – ident: ref31 doi: 10.1109/IROS.2018.8593871 – year: 2018 ident: ref47 article-title: YOLOv3: An incremental improvement – ident: ref28 doi: 10.1109/ICRA48506.2021.9560893 – ident: ref61 doi: 10.1109/SSRR50563.2020.9292572 – ident: ref39 doi: 10.1109/ICRA48506.2021.9560951 – ident: ref29 doi: 10.1109/LRA.2021.3064461 – year: 1992 ident: ref50 article-title: Implementation of the pure pursuit path tracking algorithm – ident: ref7 doi: 10.1109/MRA.2022.3213466 – ident: ref43 doi: 10.1109/ACCESS.2019.2933492 – start-page: 1928 year: 0 ident: ref52 article-title: Asynchronous methods for deep reinforcement learning publication-title: Proc Int Conf Mach Learn – year: 2021 ident: ref62 article-title: ISAAC gym: High performance GPU-based physics simulation for robot learning – ident: ref5 doi: 10.1109/IROS51168.2021.9636102 – ident: ref19 doi: 10.1109/LRA.2020.2976302 – ident: ref10 doi: 10.1177/027836499801700706 – year: 2021 ident: ref1 article-title: Keimyung hospital demonstrates smart autonomous mobile robot – ident: ref48 doi: 10.1049/iet-ipr.2017.1244 – ident: ref37 doi: 10.1109/IROS45743.2020.9341540 – ident: ref35 doi: 10.1109/LRA.2020.2972868 – ident: ref32 doi: 10.1109/ACCESS.2021.3050338 |
| SSID | ssj0024903 |
| Score | 2.6338358 |
| Snippet | This article proposes a novel learning-based control policy with strong generalizability to new environments that enables a mobile robot to navigate... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 2700 |
| SubjectTerms | Autonomous navigation Barriers Collision avoidance Data models deep learning in robotics and automation field robotics Hardware Kinematics Laser radar Navigation Pedestrians reactive and sensor-based planning Robot kinematics Robot sensing systems Robots Steering Velocity |
| Title | DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles |
| URI | https://ieeexplore.ieee.org/document/10089196 https://www.proquest.com/docview/2847964736 |
| Volume | 39 |
| WOSCitedRecordID | wos000967530400001&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: 1941-0468 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0024903 issn: 1552-3098 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI5g4gAHnkOMl3LgwiHb2mRNwg0xEAe0IRiIW5WHi5DQhvb6_cRpB5MQSNx6SKrWdmO7tr-PkDPlJBceDEuMsEzoQjItrWe2COGzdCaVmY1kE7LXUy8v-r4aVo-zMAAQm8-giZexlu9Hboa_yloIRKODyaySVSllOaz1DaynIw0yQoox3tZqUZNs69bgod9EmvAmDwbaQdjMJR8USVV-nMTRvdxs_fPBtslmFUfSy1LxO2QFhrtkYwldcI8Mug937Ll_QSsM1Vc6HdGemSOoBtBBSdBDr0Ie7sHTbklNTx8dnn40thLQZwi-LsTptG9DFIkNdHXydHM9uLplFYkCc6lOpywBLgwIn4qssDx1UhUdB9wrk6TeOiNVkhWp6tjMGmWUBxVSDii8k9YKDcD3SW04GsIBocbarC0zSGwhhDPhfV1S8NRj8RrjogZpLcSauwphHIku3vOYabR1HhSRoyLyShENcv6146NE1_hjbR0Fv7SulHmDHC9Ul1ff3yRHp4sztjw7_GXbEVnHu5e9fMekNh3P4ISsufn0bTI-jab1CT1yy8A |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VFgl66AOKun2AD71w8O7G9sY2N9RSFbHdRSVUvUV-TBAS2kXttr-_HicLKyGQuOVgK8nMxDOTmfk-gBMTtFQRHS-c8lzZRnOrfeS-SeGzDk7o0meyCT2ZmJsb-7kbVs-zMIiYm8-wT5e5lh_n4Z5-lQ0IiMYmk3kCGyOlRNGOa_2G1rOZCJlAxbgcWrOsSg7toLqa9okovC-TiY4IOHPFC2ValT_O4uxgzrf_89F2YKuLJNn7VvW7sIazF7C5gi_4EqqzqzG_nr5jHYrqN7aYs4l7IFgNZFVL0cNOUyYeMbKzlpyefQl0_rHcTMCuMXm7FKmzqU9xJLXQ7cHX8w_V6QXvaBR4EFYseIFSOVRRqLLxUgRtmlFAGY0rRPTBaVOUjTAjX3pnnIloUtKBTQzae2UR5StYn81nuA_MeV8OdYmFb5QKLr1vKBopIpWvKTLqwWAp1jp0GONEdfGjzrnG0NZJETUpou4U0YO3v3b8bPE1_rF2jwS_sq6VeQ-Olqqruy_wria3S1O2sjz4y7Y38OyiuhzX44-TT4fwnO7UdvYdwfri9h6P4Wl4WHy_u32dzewRAYTPBw |
| 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=DRL-VO%3A+Learning+to+Navigate+Through+Crowded+Dynamic+Scenes+Using+Velocity+Obstacles&rft.jtitle=IEEE+transactions+on+robotics&rft.au=Xie%2C+Zhanteng&rft.au=Dames%2C+Philip&rft.date=2023-08-01&rft.pub=IEEE&rft.issn=1552-3098&rft.volume=39&rft.issue=4&rft.spage=2700&rft.epage=2719&rft_id=info:doi/10.1109%2FTRO.2023.3257549&rft.externalDocID=10089196 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1552-3098&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1552-3098&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1552-3098&client=summon |