A Deep Reinforcement Learning Based Collision Avoidance Algorithm for USV in Narrow Channel
The utilization of deep reinforcement learning (DRL) algorithms presents a viable approach to addressing the collision avoidance problem for unmanned surface vehicles (USVs) in complex environments. However, DRL-based algorithms are subject to certain limitations, which including difficulties in con...
Uložené v:
| Vydané v: | International Symposium on Autonomous Systems (Online) s. 1 - 6 |
|---|---|
| Hlavní autori: | , , |
| Médium: | Konferenčný príspevok.. |
| Jazyk: | English |
| Vydavateľské údaje: |
IEEE
23.05.2025
|
| Predmet: | |
| ISSN: | 2996-3850 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | The utilization of deep reinforcement learning (DRL) algorithms presents a viable approach to addressing the collision avoidance problem for unmanned surface vehicles (USVs) in complex environments. However, DRL-based algorithms are subject to certain limitations, which including difficulties in concurrently managing obstacle avoidance and channel edge tasks due to insufficient exploration of environmental information, thus reduced the availability of generated path. This study proposes a Soft Actor-Critic (SAC) based dynamic obstacle avoidance algorithm that optimizes the path-planning strategy of a USVs model using the DRL algorithm, thereby achieving efficient two-dimensional position control. The proposed approach integrates the basic SAC algorithm with the artificial potential field method, thus facilitates the generation of a faster and smoother obstacle avoidance path, which mitigating the limitations of traditional DRL-based algorithms. Simulation results demonstrate that the proposed algorithm effectively avoids obstacles in narrow channel environments, thereby enhancing the autonomous navigation capability and safety of the USVs model. |
|---|---|
| AbstractList | The utilization of deep reinforcement learning (DRL) algorithms presents a viable approach to addressing the collision avoidance problem for unmanned surface vehicles (USVs) in complex environments. However, DRL-based algorithms are subject to certain limitations, which including difficulties in concurrently managing obstacle avoidance and channel edge tasks due to insufficient exploration of environmental information, thus reduced the availability of generated path. This study proposes a Soft Actor-Critic (SAC) based dynamic obstacle avoidance algorithm that optimizes the path-planning strategy of a USVs model using the DRL algorithm, thereby achieving efficient two-dimensional position control. The proposed approach integrates the basic SAC algorithm with the artificial potential field method, thus facilitates the generation of a faster and smoother obstacle avoidance path, which mitigating the limitations of traditional DRL-based algorithms. Simulation results demonstrate that the proposed algorithm effectively avoids obstacles in narrow channel environments, thereby enhancing the autonomous navigation capability and safety of the USVs model. |
| Author | Qu, Dong Lin, Yuchang Song, Rui |
| Author_xml | – sequence: 1 givenname: Yuchang surname: Lin fullname: Lin, Yuchang email: lyc22724998@shu.edu.cn organization: Shanghai University,School of Future Technology,Shanghai,China – sequence: 2 givenname: Rui surname: Song fullname: Song, Rui email: song_rui@shu.edu.cn organization: Shanghai University,School of Future Technology,Shanghai,China – sequence: 3 givenname: Dong surname: Qu fullname: Qu, Dong email: dongqu@shu.edu.cn organization: Shanghai University,School of Future Technology,Shanghai,China |
| BookMark | eNo1kE1LAzEYhKMoWGv_gYccvG59s_loclzXqoWi4FYvHkp2900b2SYluyj-eyvqaRiGZ2DmnJyEGJCQKwZTxsBcL8piUS2qolJCaD7NIZc_gWRayiMyMTOjOWdSiBmoYzLKjVEZ1xLOyKTv3wGAM20M5CPyVtBbxD19Rh9cTA3uMAx0iTYFHzb0xvbY0jJ2ne99DLT4iL61oUFadJuY_LDd0QNGX6pX6gN9tCnFT1pubQjYXZBTZ7seJ386Jqu7-ap8yJZP94cFy8wbPmSKCclVLbVyzoJu0IHltZSmbW3jag7O2rwRTGmj4GCYVdygQGCmlq00fEwuf2s9Iq73ye9s-lr_38G_AfP8V8M |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/ICAISISAS64483.2025.11051855 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Xplore POP ALL IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISBN | 9798331544706 |
| EISSN | 2996-3850 |
| EndPage | 6 |
| ExternalDocumentID | 11051855 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IF 6IL 6IN AAJGR ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK OCL RIE RIL |
| ID | FETCH-LOGICAL-i93t-614536b586ffa08cef0a3b559ddacfb30faa2c41689600fa1a639e4e019b5d593 |
| IEDL.DBID | RIE |
| IngestDate | Thu Jul 10 06:34:09 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i93t-614536b586ffa08cef0a3b559ddacfb30faa2c41689600fa1a639e4e019b5d593 |
| PageCount | 6 |
| ParticipantIDs | ieee_primary_11051855 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-May-23 |
| PublicationDateYYYYMMDD | 2025-05-23 |
| PublicationDate_xml | – month: 05 year: 2025 text: 2025-May-23 day: 23 |
| PublicationDecade | 2020 |
| PublicationTitle | International Symposium on Autonomous Systems (Online) |
| PublicationTitleAbbrev | ICAIS & ISAS |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0003189902 |
| Score | 1.90972 |
| Snippet | The utilization of deep reinforcement learning (DRL) algorithms presents a viable approach to addressing the collision avoidance problem for unmanned surface... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Autonomous vehicles Collision avoidance Deep reinforcement learning Heuristic algorithms Narrow environment Navigation Position control Safety Simulation Soft-Actor Critics Training Unmanned surface vehicle Vehicle dynamics |
| Title | A Deep Reinforcement Learning Based Collision Avoidance Algorithm for USV in Narrow Channel |
| URI | https://ieeexplore.ieee.org/document/11051855 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG6EGONJjRh_pweug7Gu-3GcKJELIQ4NiQeytq-4BDeCg7_f1zIwHjx425ZuWd5r-r3vtd97hLSZL8DzFDg6DrWDeJw5Mce53PMluEqLQOhts4lwNIqm03hci9WtFgYA7OEz6JhLu5evSrk2qbIuQhVHfOEN0gjDcCvW2idUcHLiyuodkXZdR7M77CfDdJgmqeEgDLmgxzu7T_xqpmKxZHDyz784Ja0fVR4d7_HmjBxAcU7eE_oIsKQvYEugSpvto3XV1Dl9QJBS1GQHrIacJpsyV8bRNFnMy1VefXxSfI2-pm80L-jIlmSkRnJQwKJFJoOnSf_ZqRsmOHnMKmSBPmeB4FGgdeZGErSbMYGUQalMasFcnWWexAgsQtqCN70MwxPwAaM8wRWP2QVpFmUBl4TiIKWiHnpSaz-SLAoUjgyEELEvpQivSMsYZrbclsSY7Wxy_cfzG3JszG-23T12S5rVag135FBuqvxrdW8d-Q3WTp81 |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4UjXpSI8bf9sB1_FjXsR0nalhEQgQNiQeytq-4BAfBwd_vaxkYDx68bUu3LH3Nvve97vseIRXmCXBdBY4Om9pBPE6ckONabngS6koLX-hVs4lmtxsMh2GvEKtbLQwA2J_PoGoO7V6-msqFKZXVEKo44gvfJjvc89zGSq61Kang8sRvq7tHKoWTZi1uRXE_7kd9w0IYskGXV9cP-dVOxaLJ4-E_3-OIlH90ebS3QZxjsgXZCXmP6D3AjL6ANUGVtt5HC9_UMb1DmFLU1AesipxGy2mqTKhpNBlP52n-8UnxNvraf6NpRrvWlJEa0UEGkzIZPD4MWm2naJngpCHLkQd6nPmCB77WST2QoOsJE0galEqkFqyuk8SVmIMFSFzwpJFgggIeYJ4nuOIhOyWlbJrBGaE4SKmggbHU2gskC3yFI30hROhJKZrnpGwmZjRbmWKM1nNy8cf1W7LfHjx3Rp24-3RJDkwozCa8y65IKZ8v4JrsymWefs1vbFC_AU50onw |
| 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%3Abook&rft.genre=proceeding&rft.title=International+Symposium+on+Autonomous+Systems+%28Online%29&rft.atitle=A+Deep+Reinforcement+Learning+Based+Collision+Avoidance+Algorithm+for+USV+in+Narrow+Channel&rft.au=Lin%2C+Yuchang&rft.au=Song%2C+Rui&rft.au=Qu%2C+Dong&rft.date=2025-05-23&rft.pub=IEEE&rft.eissn=2996-3850&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FICAISISAS64483.2025.11051855&rft.externalDocID=11051855 |