Predictive Obstacle Avoidance Algorithm for Under‐Actuated Unmanned Surface Vehicle Under Disturbances via Reinforcement Learning
ABSTRACT Due to the growing complexity of diverse maritime tasks, underactuated unmanned surface vehicle (USV) has become a research hotspot. The rapid development of deep reinforcement learning (DRL) technology has brought forth a novel approach for the USV autonomous control, rendering unnecessary...
Uloženo v:
| Vydáno v: | Journal of field robotics Ročník 42; číslo 7; s. 3482 - 3499 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Hoboken
Wiley Subscription Services, Inc
01.10.2025
|
| Témata: | |
| ISSN: | 1556-4959, 1556-4967 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | ABSTRACT
Due to the growing complexity of diverse maritime tasks, underactuated unmanned surface vehicle (USV) has become a research hotspot. The rapid development of deep reinforcement learning (DRL) technology has brought forth a novel approach for the USV autonomous control, rendering unnecessary the dynamical modeling of the target USV. To further improve the USV collision avoidance performance against maritime disturbances, this paper presents a predictive reinforcement learning method for USV obstacle avoidance control. A prediction module is designed to generate latent features that depict environmental states. After that, the prediction feature is provided for a DRL‐based policy module to produce an action distribution for the underactuated unmanned surface vehicle. The proposed method in this paper can enable the USV avoid obstacle and reach the destination solely based on its local observational information, without relying on prior global information. Simulation and physical experiments have demonstrated that, compared to general DRL methods, the proposed method exhibits stronger robustness to environmental disturbances, enabling the USV to reach the destination while avoid the obstacle. |
|---|---|
| AbstractList | ABSTRACT
Due to the growing complexity of diverse maritime tasks, underactuated unmanned surface vehicle (USV) has become a research hotspot. The rapid development of deep reinforcement learning (DRL) technology has brought forth a novel approach for the USV autonomous control, rendering unnecessary the dynamical modeling of the target USV. To further improve the USV collision avoidance performance against maritime disturbances, this paper presents a predictive reinforcement learning method for USV obstacle avoidance control. A prediction module is designed to generate latent features that depict environmental states. After that, the prediction feature is provided for a DRL‐based policy module to produce an action distribution for the underactuated unmanned surface vehicle. The proposed method in this paper can enable the USV avoid obstacle and reach the destination solely based on its local observational information, without relying on prior global information. Simulation and physical experiments have demonstrated that, compared to general DRL methods, the proposed method exhibits stronger robustness to environmental disturbances, enabling the USV to reach the destination while avoid the obstacle. Due to the growing complexity of diverse maritime tasks, underactuated unmanned surface vehicle (USV) has become a research hotspot. The rapid development of deep reinforcement learning (DRL) technology has brought forth a novel approach for the USV autonomous control, rendering unnecessary the dynamical modeling of the target USV. To further improve the USV collision avoidance performance against maritime disturbances, this paper presents a predictive reinforcement learning method for USV obstacle avoidance control. A prediction module is designed to generate latent features that depict environmental states. After that, the prediction feature is provided for a DRL‐based policy module to produce an action distribution for the underactuated unmanned surface vehicle. The proposed method in this paper can enable the USV avoid obstacle and reach the destination solely based on its local observational information, without relying on prior global information. Simulation and physical experiments have demonstrated that, compared to general DRL methods, the proposed method exhibits stronger robustness to environmental disturbances, enabling the USV to reach the destination while avoid the obstacle. |
| Author | Liu, Zhe Wang, Jian Jin, Kefan |
| Author_xml | – sequence: 1 givenname: Kefan orcidid: 0000-0001-7457-2392 surname: Jin fullname: Jin, Kefan organization: Shanghai Jiao Tong University – sequence: 2 givenname: Zhe surname: Liu fullname: Liu, Zhe email: liuzhesjtu@sjtu.edu.cn organization: Shanghai Jiao Tong University – sequence: 3 givenname: Jian surname: Wang fullname: Wang, Jian organization: Ministry of Education |
| BookMark | eNp1kM1KAzEUhYNU0FYXvsGAKxe1mZlkfpa1_kKhotbtkEnutCnTpCaZijvBF_AZfRIzbXEhurrnhu-cS04XdZRWgNBJiM9DjKOB0eV5FFFK9tBhSGnSJ3mSdn40zQ9Q19oFxiTOcnqIPu4NCMmdXEMwKa1jvIZguNZSMMW9qmfaSDdfBpU2wVQJMF_vn0PuGuZA-IclU8qLx8ZUzPPPMJdtwoYMLqV1jSnbJBusJQseQCofxGEJygVjYEZJNTtC-xWrLRzvZg9Nr6-eRrf98eTmbjQc93mU56TPIBaY4hSI4GVU0YyXiSCYEppDFkNEGW6XKkt4RUTI4yolkMTgf54yLNK4h063uSujXxqwrljoxih_sogjGmc4S0hLDbYUN9paA1XBpWNOauUMk3UR4qJtuvBNF5umvePsl2Nl5JKZtz_ZXfqrrOHtf7B4mFxsHd_OAJJ5 |
| CitedBy_id | crossref_primary_10_1016_j_apor_2025_104778 |
| Cites_doi | 10.1109/TIV.2024.3397651 10.1109/TNNLS.2021.3056444 10.1109/TNNLS.2020.3009214 10.1109/TIV.2023.3245612 10.1109/TVT.2024.3410183 10.1109/TIE.2024.3384617 10.1109/TPAMI.2023.3314762 10.1109/TSMC.2024.3460370 10.1002/rob.22068 10.1016/j.oceaneng.2024.120059 10.1016/j.neucom.2017.06.066 10.1016/j.oceaneng.2023.115467 10.1109/TII.2022.3142323 10.1109/TNNLS.2023.3313312 10.1016/j.oceaneng.2023.115958 10.1109/TTE.2024.3518553 10.1016/j.oceaneng.2024.117501 10.1109/TVT.2024.3490760 10.1038/nature14236 10.1109/TIE.2023.3274869 10.1002/rob.22456 10.1002/rob.22225 10.1109/TCST.2024.3377876 10.1109/TIV.2023.3331905 10.1002/rob.22262 10.1109/TSMC.2023.3321119 10.1016/j.oceaneng.2022.112226 10.1109/TIE.2023.3342290 10.1109/TITS.2024.3419585 10.1109/TMECH.2022.3188834 10.1109/TNNLS.2022.3223666 10.1109/TII.2023.3274229 10.1109/TITS.2024.3478319 10.1109/TITS.2024.3374796 10.1109/TIV.2023.3339852 10.1109/TII.2024.3424573 10.1109/TASE.2024.3492174 |
| ContentType | Journal Article |
| Copyright | 2025 Wiley Periodicals LLC. |
| Copyright_xml | – notice: 2025 Wiley Periodicals LLC. |
| DBID | AAYXX CITATION 7SC 7SP 7TB 8FD F28 FR3 JQ2 L7M L~C L~D |
| DOI | 10.1002/rob.22554 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database ANTE: Abstracts in New Technology & Engineering 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 ANTE: Abstracts in New Technology & Engineering Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Technology Research Database CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1556-4967 |
| EndPage | 3499 |
| ExternalDocumentID | 10_1002_rob_22554 ROB22554 |
| Genre | researchArticle |
| GrantInformation_xml | – fundername: This study was supported the National Natural Science Foundation of China under Grant 62303307. |
| GroupedDBID | .3N .4S .DC .GA .Y3 05W 0R~ 10A 1L6 1OB 1OC 31~ 33P 3SF 3WU 4.4 4ZD 50Y 50Z 51W 51X 52M 52N 52O 52P 52S 52T 52U 52W 52X 5GY 5VS 66C 6TJ 702 7PT 8-0 8-1 8-3 8-4 8-5 85S 8UM 930 A03 AAESR AAEVG AAHQN AAMMB AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCQN ABCUV ABEML ABIJN ABJNI ABPVW ACAHQ ACBWZ ACCZN ACFBH ACGFS ACIWK ACPOU ACRPL ACSCC ACXBN ACXQS ACYXJ ADBBV ADEOM ADIYS ADIZJ ADKYN ADMGS ADMLS ADNMO ADOZA ADXAS ADZMN AEFGJ AEIGN AEIMD AENEX AEUYR AFBPY AFFPM AFGKR AFWVQ AFZJQ AGHNM AGQPQ AGXDD AGYGG AHBTC AIDQK AIDYY AITYG AIURR AJXKR ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ARCSS ASPBG ATUGU AUFTA AVWKF AZBYB AZFZN AZVAB BAFTC BDRZF BHBCM BMNLL BMXJE BNHUX BROTX BRXPI BY8 CS3 D-E D-F DCZOG DPXWK DR2 DRFUL DRSTM DU5 EBS EDO EJD F00 F01 F04 FEDTE G-S GNP GODZA H.T H.X HBH HF~ HGLYW HVGLF HZ~ I-F IX1 J0M JPC LATKE LAW LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES MEWTI MK4 MK~ MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM N04 N05 N9A NF~ NNB O66 O9- OIG P2W P2X P4D PQQKQ Q.N Q11 QB0 QRW R.K RNS ROL RX1 SUPJJ TUS UB1 V2E W8V W99 WBKPD WIH WIK WLBEL WOHZO WQJ WXSBR WYISQ XG1 XV2 ~02 ~IA ~WT AAYXX CITATION O8X 7SC 7SP 7TB 8FD F28 FR3 JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c2994-ae3d0507e4dcb2f58cb6d405459e83e25a00545f86cf4d1c3f74e63e5567a0d73 |
| IEDL.DBID | DRFUL |
| ISICitedReferencesCount | 2 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001489847300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1556-4959 |
| IngestDate | Thu Nov 06 15:42:23 EST 2025 Tue Nov 18 21:33:48 EST 2025 Thu Nov 27 01:09:04 EST 2025 Thu Sep 25 09:40:30 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 7 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c2994-ae3d0507e4dcb2f58cb6d405459e83e25a00545f86cf4d1c3f74e63e5567a0d73 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-7457-2392 |
| PQID | 3253808647 |
| PQPubID | 1006410 |
| PageCount | 18 |
| ParticipantIDs | proquest_journals_3253808647 crossref_citationtrail_10_1002_rob_22554 crossref_primary_10_1002_rob_22554 wiley_primary_10_1002_rob_22554_ROB22554 |
| PublicationCentury | 2000 |
| PublicationDate | October 2025 2025-10-00 20251001 |
| PublicationDateYYYYMMDD | 2025-10-01 |
| PublicationDate_xml | – month: 10 year: 2025 text: October 2025 |
| PublicationDecade | 2020 |
| PublicationPlace | Hoboken |
| PublicationPlace_xml | – name: Hoboken |
| PublicationTitle | Journal of field robotics |
| PublicationYear | 2025 |
| Publisher | Wiley Subscription Services, Inc |
| Publisher_xml | – name: Wiley Subscription Services, Inc |
| References | 2023; 54 2023; 35 2023; 285 2023; 59 2023; 8 2023; 9 2023; 288 2024; 73 2024; 74 2024; 32 2024; 55 2024; 11 2024; 301 2024 2020; 32 2022; 27 2025; 317 2023; 20 2023; 40 2021; 32 2022; 262 2018; 272 2023; 45 2024; 71 2022; 35 2018 2024; 41 2015; 518 2024; 20 2017 2016 2024; 22 2024; 25 2023; 71 2023; 72 2022; 39 2022; 18 2014; 32 Ma B. (e_1_2_13_22_1) 2023; 72 e_1_2_13_25_1 e_1_2_13_24_1 e_1_2_13_27_1 e_1_2_13_46_1 e_1_2_13_26_1 e_1_2_13_47_1 e_1_2_13_21_1 e_1_2_13_20_1 e_1_2_13_45_1 e_1_2_13_23_1 e_1_2_13_42_1 e_1_2_13_43_1 e_1_2_13_9_1 e_1_2_13_40_1 e_1_2_13_8_1 e_1_2_13_41_1 e_1_2_13_7_1 e_1_2_13_6_1 Zhang J. (e_1_2_13_44_1) 2023; 59 e_1_2_13_17_1 e_1_2_13_18_1 e_1_2_13_39_1 e_1_2_13_19_1 e_1_2_13_13_1 e_1_2_13_36_1 e_1_2_13_14_1 e_1_2_13_35_1 e_1_2_13_15_1 e_1_2_13_38_1 e_1_2_13_16_1 e_1_2_13_37_1 e_1_2_13_32_1 e_1_2_13_10_1 e_1_2_13_31_1 e_1_2_13_11_1 e_1_2_13_34_1 e_1_2_13_12_1 e_1_2_13_33_1 e_1_2_13_30_1 e_1_2_13_5_1 e_1_2_13_4_1 e_1_2_13_3_1 e_1_2_13_2_1 Silver D. (e_1_2_13_28_1) 2014; 32 e_1_2_13_29_1 |
| References_xml | – volume: 73 start-page: 14510 issue: 10 year: 2024 end-page: 14524 article-title: A Potential Field‐Based Model Predictive Target Following Controller for Underactuated Unmanned Surface Vehicles publication-title: IEEE Transactions on Vehicular Technology – volume: 22 start-page: 8898 year: 2024 end-page: 8911 article-title: Estimating Lyapunov Region of Attraction for Robust Model‐Based Reinforcement Learning Usv publication-title: IEEE Transactions on Automation Science and Engineering – volume: 71 start-page: 4089 issue: 4 year: 2023 end-page: 4097 article-title: Policy Learning for Nonlinear Model Predictive Control With Application to Usvs publication-title: IEEE Transactions on Industrial Electronics – volume: 8 start-page: 2088 issue: 3 year: 2023 end-page: 2096 article-title: Predictor‐Based Fixed‐Time Los Path Following Control of Underactuated Usv With Unknown Disturbances publication-title: IEEE Transactions on Intelligent Vehicles – volume: 55 start-page: 63 issue: 1 year: 2024 end-page: 72 article-title: Fuzzy Trajectory Tracking Control of Under‐Actuated Unmanned Surface Vehicles With Ocean Current and Input Quantization publication-title: IEEE Transactions on Systems, Man, and Cybernetics: Systems – year: 2024 article-title: Model‐Based Reinforcement Learning for Trajectory Tracking Control of Autonomous Surface Ship – volume: 32 start-page: 5456 issue: 12 year: 2021 end-page: 5467 article-title: Data‐Driven Performance‐Prescribed Reinforcement Learning Control of an Unmanned Surface Vehicle publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 25 start-page: 21404 issue: 12 year: 2024 end-page: 21415 article-title: A Balanced Collision Avoidance Algorithm for Usvs in Complex Environment: A Deep Reinforcement Learning Approach publication-title: IEEE Transactions on Intelligent Transportation Systems – volume: 9 start-page: 3127 issue: 2 year: 2023 end-page: 3139 article-title: Event‐Triggered Based Trajectory Tracking Control of Under‐Actuated Unmanned Surface Vehicle With State and Input Quantization publication-title: IEEE Transactions on Intelligent Vehicles – volume: 39 start-page: 631 issue: 5 year: 2022 end-page: 649 article-title: Hijacking of Unmanned Surface Vehicles: A Demonstration of Attacks and Countermeasures in the Field publication-title: Journal of Field Robotics – year: 2024 article-title: Robust Collision Avoidance and Path‐Following of Usvs With Reduced Conservativeness: A Control Barrier Function‐Based Approach publication-title: Journal of Field Robotics – volume: 74 start-page: 3885 issue: 3 year: 2024 end-page: 3900 article-title: Collision Avoidance and Path Point Tracking Control for Underactuated Unmanned Surface Vehicles With Unknown Model Nonlinearity publication-title: IEEE Transactions on Vehicular Technology – volume: 18 start-page: 6950 issue: 10 year: 2022 end-page: 6961 article-title: Filtered Probabilistic Model Predictive Control‐Based Reinforcement Learning for Unmanned Surface Vehicles publication-title: IEEE Transactions on Industrial Informatics – start-page: 1861 year: 2018 end-page: 1870 article-title: Soft Actor‐Critic: Off‐policy Maximum Entropy Deep Reinforcement Learning With a Stochastic Actor – volume: 518 start-page: 529 issue: 7540 year: 2015 end-page: 533 article-title: Human‐Level Control Through Deep Reinforcement Learning publication-title: Nature – year: 2016 – volume: 11 start-page: 6875 issue: 2 year: 2024 end-page: 6886 article-title: Los Guidance for Fuzzy Adaptive Fault‐Tolerant Path Following Control of Usv With Side‐Slip Compensation and Actuator Fault publication-title: IEEE Transactions on Transportation Electrification – volume: 288 year: 2023 article-title: Demrl: Dynamic Estimation Meta Reinforcement Learning for Path Following on Unseen Unmanned Surface Vehicle publication-title: Ocean Engineering – volume: 20 start-page: 12837 issue: 11 year: 2024 end-page: 12847 article-title: Event‐Triggered Optimal Tracking Control for Underactuated Surface Vessels via Neural Reinforcement Learning publication-title: IEEE Transactions on Industrial Informatics – year: 2018 article-title: Reinforcement learning: An introduction – year: 2024 article-title: Trajectory Tracking Control of an Intelligent Ship Based on Deep Reinforcement Learning – year: 2024 article-title: Adaptive Backstepping Control for Underactuated 6‐dof Usv With Uncertain Dynamics publication-title: IEEE Transactions on Intelligent Vehicles – volume: 40 start-page: 1887 issue: 8 year: 2023 end-page: 1905 article-title: Field Demonstration of Advanced Autonomous Navigation Technique for a Fully Unmanned Surface Vehicle in Complex Coastal Traffic Areas publication-title: Journal of Field Robotics – volume: 35 start-page: 8026 issue: 6 year: 2022 end-page: 8039 article-title: Neural Network Control of Underactuated Surface Vehicles With Prescribed Trajectory Tracking Performance publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 54 start-page: 787 issue: 2 year: 2023 end-page: 799 article-title: Distributed Robust Learning Control for Multiple Unmanned Surface Vessels With Fixed‐Time Prescribed Performance publication-title: IEEE Transactions on Systems, Man, and Cybernetics: Systems – volume: 59 start-page: 7252 issue: 5 year: 2023 end-page: 7268 article-title: Dynamic Path Planning Algorithm for Unmanned Surface Vehicle Under Island‐Reef Environment publication-title: IEEE Transactions on Aerospace and Electronic Systems – volume: 25 start-page: 11522 issue: 9 year: 2024 end-page: 11533 article-title: Hybrid Physics‐Learning Model Based Predictive Control for Trajectory Tracking of Unmanned Surface Vehicles publication-title: IEEE Transactions on Intelligent Transportation Systems – volume: 32 start-page: 1904 issue: 5 year: 2024 end-page: 1919 article-title: Path‐Following Control of Unmanned Underwater Vehicle Based on an Improved td3 Deep Reinforcement Learning publication-title: IEEE Transactions on Control Systems Technology – volume: 41 start-page: 470 issue: 2 year: 2024 end-page: 489 article-title: Field Experiment of Autonomous Ship Navigation in Canal and Surrounding Nearshore Environments publication-title: Journal of Field Robotics – volume: 32 start-page: 3034 issue: 7 year: 2020 end-page: 3045 article-title: Reinforcement Learning‐Based Optimal Tracking Control of an Unknown Unmanned Surface Vehicle publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 20 start-page: 1283 issue: 2 year: 2023 end-page: 1293 article-title: Probabilistic Model‐Based Reinforcement Learning Unmanned Surface Vehicles Using Local Update Sparse Spectrum Approximation publication-title: IEEE Transactions on Industrial Informatics – volume: 27 start-page: 5736 issue: 6 year: 2022 end-page: 5747 article-title: Network‐Based Multiple Operating Points Cooperative Dynamic Positioning of Unmanned Surface Vehicles publication-title: IEEE/ASME Transactions on Mechatronics – volume: 32 start-page: 387 issue: 1 year: 2014 end-page: 395 article-title: Deterministic Policy Gradient Algorithms publication-title: International Conference on Machine Learning, 2014 Proceedings of Machine Learning Research (PMLR) – volume: 317 year: 2025 article-title: Target Tracking Control for Unmanned Surface Vehicles: An End‐To‐End Deep Reinforcement Learning Approach publication-title: Ocean Engineering – volume: 35 start-page: 18237 issue: 12 year: 2023 end-page: 18250 article-title: Path Following Control for Unmanned Surface Vehicles: A Reinforcement Learning‐Based Method With Experimental Validation publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 9 start-page: 3293 issue: 2 year: 2023 end-page: 3304 article-title: Adaptive Neural Network‐Quantized Tracking Control of Uncertain Unmanned Surface Vehicles With Output Constraints publication-title: IEEE Transactions on Intelligent Vehicles – volume: 301 year: 2024 article-title: Based on Deep Reinforcement Learning to Path Planning in Uncertain Ocean Currents for Underwater Gliders publication-title: Ocean Engineering – volume: 45 start-page: 14745 issue: 12 year: 2023 end-page: 14759 article-title: Human‐Guided Reinforcement Learning With Sim‐To‐Real Transfer for Autonomous Navigation publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – year: 2017 – volume: 72 start-page: 1 year: 2023 end-page: 13 article-title: Deep Reinforcement Learning of Uav Tracking Control Under Wind Disturbances Environments publication-title: IEEE Transactions on Instrumentation and Measurement – volume: 25 start-page: 17810 issue: 11 year: 2024 end-page: 17820 article-title: Integrated Intelligent Guidance and Motion Control of Usvs With Anticipatory Collision Avoidance Decision‐Making publication-title: IEEE Transactions on Intelligent Transportation Systems – volume: 285 year: 2023 article-title: Flexible Unmanned Surface Vehicles Control Using Probabilistic Model‐Based Reinforcement Learning With Hierarchical Gaussian Distribution publication-title: Ocean Engineering – volume: 71 start-page: 11272 issue: 9 year: 2023 end-page: 11282 article-title: A Stochastic Event‐Triggered Robust Unscented Kalman Filter‐Based Usv Parameter Estimation publication-title: IEEE Transactions on Industrial Electronics – volume: 262 year: 2022 article-title: Path Planning for Underwater Gliders in Time‐Varying Ocean Current Using Deep Reinforcement Learning publication-title: Ocean Engineering – volume: 272 start-page: 63 year: 2018 end-page: 73 article-title: Concise Deep Reinforcement Learning Obstacle Avoidance for Underactuated Unmanned Marine Vessels publication-title: Neurocomputing – volume: 71 start-page: 16388 issue: 12 year: 2024 end-page: 16397 article-title: Gaussian Process‐Based Learning Model Predictive Control With Application to Usv publication-title: IEEE Transactions on Industrial Electronics – volume: 32 start-page: 387 issue: 1 year: 2014 ident: e_1_2_13_28_1 article-title: Deterministic Policy Gradient Algorithms publication-title: International Conference on Machine Learning, 2014 Proceedings of Machine Learning Research (PMLR) – ident: e_1_2_13_43_1 doi: 10.1109/TIV.2024.3397651 – ident: e_1_2_13_33_1 doi: 10.1109/TNNLS.2021.3056444 – volume: 59 start-page: 7252 issue: 5 year: 2023 ident: e_1_2_13_44_1 article-title: Dynamic Path Planning Algorithm for Unmanned Surface Vehicle Under Island‐Reef Environment publication-title: IEEE Transactions on Aerospace and Electronic Systems – ident: e_1_2_13_34_1 doi: 10.1109/TNNLS.2020.3009214 – ident: e_1_2_13_36_1 doi: 10.1109/TIV.2023.3245612 – ident: e_1_2_13_11_1 doi: 10.1109/TVT.2024.3410183 – ident: e_1_2_13_16_1 doi: 10.1109/TIE.2024.3384617 – ident: e_1_2_13_40_1 doi: 10.1109/TPAMI.2023.3314762 – ident: e_1_2_13_32_1 – ident: e_1_2_13_25_1 doi: 10.1109/TSMC.2024.3460370 – ident: e_1_2_13_29_1 doi: 10.1002/rob.22068 – ident: e_1_2_13_18_1 – ident: e_1_2_13_38_1 doi: 10.1016/j.oceaneng.2024.120059 – ident: e_1_2_13_2_1 doi: 10.1016/j.neucom.2017.06.066 – ident: e_1_2_13_5_1 doi: 10.1016/j.oceaneng.2023.115467 – ident: e_1_2_13_26_1 – ident: e_1_2_13_3_1 doi: 10.1109/TII.2022.3142323 – ident: e_1_2_13_37_1 doi: 10.1109/TNNLS.2023.3313312 – ident: e_1_2_13_12_1 doi: 10.1016/j.oceaneng.2023.115958 – ident: e_1_2_13_42_1 doi: 10.1109/TTE.2024.3518553 – ident: e_1_2_13_15_1 doi: 10.1016/j.oceaneng.2024.117501 – ident: e_1_2_13_47_1 doi: 10.1109/TVT.2024.3490760 – ident: e_1_2_13_23_1 doi: 10.1038/nature14236 – ident: e_1_2_13_9_1 – ident: e_1_2_13_35_1 doi: 10.1109/TIE.2023.3274869 – ident: e_1_2_13_39_1 doi: 10.1002/rob.22456 – ident: e_1_2_13_10_1 doi: 10.1002/rob.22225 – ident: e_1_2_13_17_1 – ident: e_1_2_13_8_1 doi: 10.1109/TCST.2024.3377876 – ident: e_1_2_13_6_1 doi: 10.1109/TIV.2023.3331905 – ident: e_1_2_13_13_1 doi: 10.1002/rob.22262 – ident: e_1_2_13_7_1 doi: 10.1109/TSMC.2023.3321119 – ident: e_1_2_13_14_1 doi: 10.1016/j.oceaneng.2022.112226 – ident: e_1_2_13_27_1 doi: 10.1109/TIE.2023.3342290 – ident: e_1_2_13_31_1 doi: 10.1109/TITS.2024.3419585 – ident: e_1_2_13_20_1 doi: 10.1109/TMECH.2022.3188834 – ident: e_1_2_13_45_1 doi: 10.1109/TNNLS.2022.3223666 – ident: e_1_2_13_4_1 doi: 10.1109/TII.2023.3274229 – ident: e_1_2_13_21_1 doi: 10.1109/TITS.2024.3478319 – ident: e_1_2_13_30_1 – ident: e_1_2_13_46_1 doi: 10.1109/TITS.2024.3374796 – ident: e_1_2_13_24_1 doi: 10.1109/TIV.2023.3339852 – ident: e_1_2_13_19_1 doi: 10.1109/TII.2024.3424573 – volume: 72 start-page: 1 year: 2023 ident: e_1_2_13_22_1 article-title: Deep Reinforcement Learning of Uav Tracking Control Under Wind Disturbances Environments publication-title: IEEE Transactions on Instrumentation and Measurement – ident: e_1_2_13_41_1 doi: 10.1109/TASE.2024.3492174 |
| SSID | ssj0043895 |
| Score | 2.4445171 |
| Snippet | ABSTRACT
Due to the growing complexity of diverse maritime tasks, underactuated unmanned surface vehicle (USV) has become a research hotspot. The rapid... Due to the growing complexity of diverse maritime tasks, underactuated unmanned surface vehicle (USV) has become a research hotspot. The rapid development of... |
| SourceID | proquest crossref wiley |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 3482 |
| SubjectTerms | Collision avoidance Deep learning deep reinforcement learning (DRL) Disturbances Dynamic models Modules Obstacle avoidance Predictions state prediction Surface vehicles Task complexity unmanned surface vehicle (USV) control Unmanned vehicles |
| Title | Predictive Obstacle Avoidance Algorithm for Under‐Actuated Unmanned Surface Vehicle Under Disturbances via Reinforcement Learning |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1002%2Frob.22554 https://www.proquest.com/docview/3253808647 |
| Volume | 42 |
| WOSCitedRecordID | wos001489847300001&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: PRVWIB databaseName: Wiley Online Library customDbUrl: eissn: 1556-4967 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0043895 issn: 1556-4959 databaseCode: DRFUL dateStart: 20060101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1JS8QwFH7ojAc9uIs7QTx4qXbStE3xNC6DB9FhXPBWkjTVAZ2RznIW_AP-Rn-JL2k7M4KC4K2U16S89UvafA9gn0Yp5ZIHDmXKdVjgpY6IXO0wLC8CF0U1V3LbbCK8uuIPD1FzCo7LszA5P8Row81Ehs3XJsCF7B2NSUOzrjxEZ_TZNFQp-i2rQPWs1bi7LBOx6evtW7pUP3BwHRCVxEIuPRo9_L0cjTHmJFK1paax8K-XXIT5AmGSeu4SSzClO8swN8E7uALvzcx8nzGZjlxLxIcoSOrDbjsxPkDqz4_drN1_eiGIaIntjPT59lE3R00Qn-KNF2GyM7kZZKlA-Xv9ZKbKJckZOs4gk2akHhm2BWlpy86q7EYkKQhdH1fhrnF-e3rhFN0YHEUNf7DQXuIietQsUZKmPlcySBDuMT_S3NPUFwb--SkPVMqSmvLSkOnA06j9ULhJ6K1BpdPt6HUgfiiSINARFUIzRPcR14wx5dGkFmnB5QYclEaJVUFVbjpmPMc5yTKNUa-x1esG7I1EX3N-jp-EtkvLxkWI9mKPYq7HBR0LcTprw98HiFvXJ_Zi8--iWzBLTa9g--PfNlT62UDvwIwa9tu9bLfw1S9FgO7d |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1dT9swFL0qBWnsYcAGGgOGNfGwl0Dq2Ikj8VJgFYiurUo79S1yHAcqQTulH8-T9gf2G_dLdu0kbScNaRJvUXRiR9fX18c38bkAJzRMqYiF71CmXIf5XurI0NUOw-VF4qao5sbCFpsIWi0xGISdCpyXZ2FyfYhFws3MDBuvzQQ3CemzpWpoNo5P0Rs5W4N17ETwKqxfdRv9ZhmJTWFvbvVSue_gRiAslYVcerZ4-O_1aEkyV6mqXWsaWy97y214U3BMUs-dYgcqevQWXq8oD76Dn53MfKExsY60Y2SICCT1-XiYGC8g9cf7cTacPjwR5LTE1kb6_eNX3Rw2QYaKN56kic_kbpalEvHf9IPpKkeSK3SdWRabliZkPpSkq60-q7KpSFJIut7vQr_xpXd57RT1GBxFjYKw1F7iIn_ULFExTblQsZ8g4WM81MLTlEtDAHkqfJWypKa8NGDa9zSaP5BuEnh7UB2NR_o9EB7IxPd1SKXUDPl9KDRjTHk0qYVaingfPpejEqlCrNzUzHiMcpllGqFdI2vXffi0gH7PFTr-BToshzYqJukk8ihGe9zSsQC7s4P4fANRt31hLz78P_QYXl33vjaj5k3r9gA2qakcbH8DPITqNJvpI9hQ8-lwkn0sHPcPjMDyzQ |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT9wwEB5RqCp6gD5A5dVaVQ-9pGQdx3EkLgvLqlXRstqWilvk2BNYCXZR9nFG4g_wG_tLOnaShUqtVKm3KJrY0Tw_O_E3AB94WnCVKxlwYcJAyKgIdBpiIKi8aFoUtcJc-WYTSa-nzs_T_hIcNGdhKn6IxYabiwyfr12A440t9h9YQ8tx_om8MRZPYEXEqaSwXOkMumcnTSZ2jb1jz5cay4AWAmnDLBTy_cXDv9ejB5D5GKr6WtNd_7-3fAFrNcZk7copXsISjl7B80fMg6_hrl-6LzQu17HTnBAiCbL2fDy0zgtY--piXA6nl9eMMC3zvZF-3t633WETQqh041q7_My-zcpCk_wPvHRTVZKsQ64zK3M30oTNh5oN0POzGr8VyWpK14sNOOsefz_6HNT9GALDHYOwxsiGhB9RWJPzIlYml5YAHykfVYQ81g4AxoWSphC2ZaIiESgjJPUnOrRJtAnLo_EI3wCLE22lxJRrjYLwfapQCGEiblspapVvwcfGKpmpycpdz4yrrKJZ5hnpNfN63YL3C9GbiqHjT0K7jWmzOkgnWcQp29OSTiQ0nTfi3wfIBqeH_mL730XfwbN-p5udfOl93YFV7hoH-78Ad2F5Ws5wD56a-XQ4Kd_WfvsLLBrySA |
| 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=Predictive+Obstacle+Avoidance+Algorithm+for+Under%E2%80%90Actuated+Unmanned+Surface+Vehicle+Under+Disturbances+via+Reinforcement+Learning&rft.jtitle=Journal+of+field+robotics&rft.au=Jin%2C+Kefan&rft.au=Liu%2C+Zhe&rft.au=Wang%2C+Jian&rft.date=2025-10-01&rft.pub=Wiley+Subscription+Services%2C+Inc&rft.issn=1556-4959&rft.eissn=1556-4967&rft.volume=42&rft.issue=7&rft.spage=3482&rft.epage=3499&rft_id=info:doi/10.1002%2Frob.22554&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1556-4959&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1556-4959&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1556-4959&client=summon |