{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:32:22Z","timestamp":1777501942454,"version":"3.51.4"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031082221","type":"print"},{"value":"9783031082238","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-08223-8_38","type":"book-chapter","created":{"date-parts":[[2022,6,14]],"date-time":"2022-06-14T14:11:04Z","timestamp":1655215864000},"page":"461-474","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Towards Using Reinforcement Learning for\u00a0Autonomous Docking of\u00a0Unmanned Surface Vehicles"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0967-221X","authenticated-orcid":false,"given":"Martin","family":"Holen","sequence":"first","affiliation":[]},{"given":"Else-Line Malene","family":"Ruud","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9954-0431","authenticated-orcid":false,"given":"Narada Dilp","family":"Warakagoda","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6331-702X","authenticated-orcid":false,"given":"Morten","family":"Goodwin","sequence":"additional","affiliation":[]},{"given":"Paal","family":"Engelstad","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4088-1642","authenticated-orcid":false,"given":"Kristian Muri","family":"Knausg\u00e5rd","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,6,10]]},"reference":[{"key":"38_CR1","unstructured":"ml-agents\/gym-unity at main Unity-Technologies\/ml-agents. https:\/\/github.com\/Unity-Technologies\/ml-agents\/tree\/main\/gym-unity"},{"key":"38_CR2","unstructured":"Andrychowicz, M., et al.: What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study, June 2020. http:\/\/arxiv.org\/abs\/2006.05990"},{"key":"38_CR3","doi-asserted-by":"publisher","first-page":"113816","DOI":"10.1016\/J.ESWA.2020.113816","volume":"165","author":"C Badue","year":"2021","unstructured":"Badue, C., et al.: Self-driving cars: a survey. Expert Syst. Appl. 165, 113816 (2021). https:\/\/doi.org\/10.1016\/J.ESWA.2020.113816","journal-title":"Expert Syst. Appl."},{"key":"38_CR4","unstructured":"Bjering Strand, H.: Autonomous docking control system for the otter USV: a machine learning approach (2020). https:\/\/ntnuopen.ntnu.no\/ntnu-xmlui\/handle\/11250\/2780950"},{"key":"38_CR5","unstructured":"Brockman, G., et al.: OpenAI Gym, June 2016. https:\/\/arxiv.org\/abs\/1606.01540v1"},{"key":"38_CR6","unstructured":"Castro, P.S., Moitra, S., Gelada, C., Kumar, S., Bellemare, M.G.: Dopamine: a research framework for deep reinforcement learning, December 2018. https:\/\/arxiv.org\/abs\/1812.06110v1"},{"key":"38_CR7","doi-asserted-by":"publisher","unstructured":"Cui, R., Yang, C., Li, Y., Sharma, S.: Adaptive neural network control of AUVs with control input nonlinearities using reinforcement learning. IEEE Trans. Syst. Man Cybern. Syst. 47(6), 1019\u20131029 (2017). https:\/\/doi.org\/10.1109\/TSMC.2016.2645699","DOI":"10.1109\/TSMC.2016.2645699"},{"issue":"3","key":"38_CR8","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1002\/ROB.21990","volume":"38","author":"Y Cui","year":"2021","unstructured":"Cui, Y., Osaki, S., Matsubara, T.: Autonomous boat driving system using sample-efficient model predictive control-based reinforcement learning approach. J. Field Robot. 38(3), 331\u2013354 (2021). https:\/\/doi.org\/10.1002\/ROB.21990","journal-title":"J. Field Robot."},{"key":"38_CR9","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., L\u00f3pez, A., Koltun, V.: CARLA: an open urban driving simulator. In: Conference on robot learning, pp. 1\u201316 (2017)"},{"key":"38_CR10","unstructured":"Epic Games, I.: The most powerful real-time 3D creation tool - unreal Engine. https:\/\/www.unrealengine.com\/en-US\/"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Fossen, T.I.: Handbook of Marine Craft Hydrodynamics and Motion Control, 2nd Edition. 2nd edn. Wiley, Hoboken, April 2021","DOI":"10.1002\/9781119575016"},{"issue":"7","key":"38_CR12","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.1016\/J.ASR.2019.12.030","volume":"65","author":"B Gaudet","year":"2020","unstructured":"Gaudet, B., Linares, R., Furfaro, R.: Deep reinforcement learning for six degree-of-freedom planetary landing. Adv. Space Res. 65(7), 1723\u20131741 (2020). https:\/\/doi.org\/10.1016\/J.ASR.2019.12.030","journal-title":"Adv. Space Res."},{"key":"38_CR13","unstructured":"Juliani, A., et al.: Unity: a general platform for intelligent agents, September 2018. https:\/\/arxiv.org\/abs\/1809.02627v2"},{"key":"38_CR14","doi-asserted-by":"publisher","unstructured":"Koenig, N., Howard, A.: Design and use paradigms for Gazebo, an open-source multi-robot simulator. In: 2004 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), vol. 3, pp. 2149\u20132154 (2004). https:\/\/doi.org\/10.1109\/IROS.2004.1389727","DOI":"10.1109\/IROS.2004.1389727"},{"key":"38_CR15","doi-asserted-by":"publisher","unstructured":"Kretschmann, L., Burmeister, H.C., Jahn, C.: Analyzing the economic benefit of unmanned autonomous ships: an exploratory cost-comparison between an autonomous and a conventional bulk carrier. Res. Transp. Bus. Manage. 25, 76\u201386 (2017). https:\/\/doi.org\/10.1016\/J.RTBM.2017.06.002","DOI":"10.1016\/J.RTBM.2017.06.002"},{"key":"38_CR16","doi-asserted-by":"publisher","unstructured":"Kyriakidis, M., et al.: A human factors perspective on automated driving. 20(3), 223\u2013249 (2017). https:\/\/doi.org\/10.1080\/1463922X.2017.1293187, https:\/\/www.tandfonline.com\/doi\/abs\/10.1080\/1463922X.2017.1293187","DOI":"10.1080\/1463922X.2017.1293187"},{"key":"38_CR17","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings, September 2015. https:\/\/arxiv.org\/abs\/1509.02971v6"},{"key":"38_CR18","doi-asserted-by":"publisher","unstructured":"Martinsen, A.B., Lekkas, A.M.: Straight-Path following for underactuated marine vessels using deep reinforcement learning. IFAC-PapersOnLine 51(29), 329\u2013334 (2018). https:\/\/doi.org\/10.1016\/J.IFACOL.2018.09.502","DOI":"10.1016\/J.IFACOL.2018.09.502"},{"key":"38_CR19","doi-asserted-by":"publisher","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). https:\/\/doi.org\/10.1038\/nature14236, https:\/\/www.nature.com\/articles\/nature14236","DOI":"10.1038\/nature14236"},{"key":"38_CR20","unstructured":"Moerland, T.M., Broekens, J., Plaat, A., Jonker, C.M.: A0C: alpha zero in continuous action space, May 2018. https:\/\/arxiv.org\/abs\/1805.09613v1"},{"key":"38_CR21","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/J.OCEANENG.2018.04.018","volume":"159","author":"H Mousazadeh","year":"2018","unstructured":"Mousazadeh, H., et al.: Developing a navigation, guidance and obstacle avoidance algorithm for an unmanned surface vehicle (USV) by algorithms fusion. Ocean Eng. 159, 56\u201365 (2018). https:\/\/doi.org\/10.1016\/J.OCEANENG.2018.04.018","journal-title":"Ocean Eng."},{"key":"38_CR22","unstructured":"OpenAI: openai\/baselines: OpenAI Baselines: high-quality implementations of reinforcement learning algorithms. https:\/\/github.com\/openai\/baselines"},{"key":"38_CR23","unstructured":"Pomerleau, D.A.: Alvinn: an autonomous land vehicle in a neural network. Adv. Neural Inf. Process. Syst. (1989). https:\/\/proceedings.neurips.cc\/paper\/1988\/file\/812b4ba287f5ee0bc9d43bbf5bbe87fb-Paper.pdf"},{"key":"38_CR24","unstructured":"Rai, R.: Socket. IO Real-Time Web Application Development - Rohit Rai - Google Books. Packt Publishing Ltd., Birmingham, 1st edn., February 2013. https:\/\/books.google.no\/books?id=YgdbZbkTDkoC&pg=PT37&dq=socket+io&lr=&source=gbs_selected_pages&cad=2#v=onepage&q=socket%20io&f=false"},{"key":"38_CR25","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms, July 2017. https:\/\/arxiv.org\/abs\/1707.06347v2"},{"issue":"9","key":"38_CR26","doi-asserted-by":"publisher","first-page":"4913","DOI":"10.1109\/TII.2019.2912024","volume":"15","author":"G Shao","year":"2019","unstructured":"Shao, G., Ma, Y., Malekian, R., Yan, X., Li, Z.: A novel cooperative platform design for coupled USV-UAV systems. IEEE Trans. Ind. Inf. 15(9), 4913\u20134922 (2019). https:\/\/doi.org\/10.1109\/TII.2019.2912024","journal-title":"IEEE Trans. Ind. Inf."},{"key":"38_CR27","doi-asserted-by":"publisher","first-page":"106514","DOI":"10.1016\/J.OCEANENG.2019.106514","volume":"191","author":"Y Shuai","year":"2019","unstructured":"Shuai, Y., et al.: An efficient neural-network based approach to automatic ship docking. Ocean Eng. 191, 106514 (2019). https:\/\/doi.org\/10.1016\/J.OCEANENG.2019.106514","journal-title":"Ocean Eng."},{"key":"38_CR28","doi-asserted-by":"publisher","unstructured":"Tang, Y., Agrawal, S.: Discretizing continuous action space for on-policy optimization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 5981\u20135988, April 2020. https:\/\/doi.org\/10.1609\/AAAI.V34I04.6059, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/6059","DOI":"10.1609\/AAAI.V34I04.6059"},{"key":"38_CR29","unstructured":"Thor I. Fossen: Lecture Notes: TTK 4190 Guidance, Navigation and Control of vehicles. https:\/\/www.fossen.biz\/wiley\/pdf\/Ch1.pdf"},{"key":"38_CR30","unstructured":"Unity: Unity - Manual: GameObjects. https:\/\/docs.unity3d.com\/Manual\/GameObjects.html"},{"key":"38_CR31","doi-asserted-by":"publisher","unstructured":"Van Hasselt, H., Wiering, M.A.: Reinforcement learning in continuous action spaces. In: Proceedings of the 2007 IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning, ADPRL 2007, pp. 272\u2013279 (2007). https:\/\/doi.org\/10.1109\/ADPRL.2007.368199","DOI":"10.1109\/ADPRL.2007.368199"},{"key":"38_CR32","doi-asserted-by":"publisher","unstructured":"V\u00e1s\u00e1rhelyi, G., Vir\u00e1gh, C., Somorjai, G., Nepusz, T., Eiben, A.E., Vicsek, T.: Optimized flocking of autonomous drones in confined environments. Sci. Robot. 3(20) (2018). https:\/\/doi.org\/10.1126\/SCIROBOTICS.AAT3536\/SUPPL_FILE\/AAT3536_SM.PDF, https:\/\/www.science.org\/doi\/abs\/10.1126\/scirobotics.aat3536","DOI":"10.1126\/SCIROBOTICS.AAT3536\/SUPPL_FILE\/AAT3536_SM.PDF"},{"key":"38_CR33","doi-asserted-by":"publisher","unstructured":"Veelen, M.v., Spreij, P.: Evolution in games with a continuous action space Matthijs van Veelen $$\\cdot $$ Peter Spreij (2008). https:\/\/doi.org\/10.1007\/s00199-008-0338-8","DOI":"10.1007\/s00199-008-0338-8"},{"key":"38_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, P., et al.: Reinforcement learning-based end-to-end parking for automatic parking system. Sensors 19(18), 3996 (2019). https:\/\/doi.org\/10.3390\/S19183996, https:\/\/www.mdpi.com\/1424-8220\/19\/18\/3996\/htm www.mdpi.com\/1424-8220\/19\/18\/3996","DOI":"10.3390\/S19183996"}],"container-title":["Communications in Computer and Information Science","Engineering Applications of Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-08223-8_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,14]],"date-time":"2022-06-14T14:16:10Z","timestamp":1655216170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-08223-8_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031082221","9783031082238"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-08223-8_38","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 June 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Engineering Applications of Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chersonisos, Crete","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eann2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eannconf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}