{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:55:44Z","timestamp":1755798944550,"version":"3.44.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032014856"},{"type":"electronic","value":"9783032014863"}],"license":[{"start":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T00:00:00Z","timestamp":1755043200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T00:00:00Z","timestamp":1755043200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-01486-3_29","type":"book-chapter","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T15:46:49Z","timestamp":1755618409000},"page":"381-394","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparative Evaluation of\u00a0Reinforcement Learning and\u00a0Model Predictive Control for\u00a06DoF Position Control of\u00a0an\u00a0Autonomous Underwater Vehicle"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7143-7406","authenticated-orcid":false,"given":"S\u00fcmer","family":"Tun\u00e7ay","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4688-1304","authenticated-orcid":false,"given":"Alain","family":"Andres","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6262-480X","authenticated-orcid":false,"given":"Ignacio","family":"Carlucho","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,13]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Coates, A., Quigley, M., Ng, A.: An application of reinforcement learning to aerobatic helicopter flight. In: Sch\u00f6lkopf, B., Platt, J., Hoffman, T. (eds.) Advances in Neural Information Processing Systems. vol.\u00a019. MIT Press (2006)","DOI":"10.7551\/mitpress\/7503.003.0006"},{"issue":"4","key":"29_CR2","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1109\/TCST.2005.847331","volume":"13","author":"KH Ang","year":"2005","unstructured":"Ang, K.H., Chong, G., Li, Y.: PID control system analysis, design, and technology. IEEE Trans. Control Syst. Technol. 13(4), 559\u2013576 (2005). https:\/\/doi.org\/10.1109\/TCST.2005.847331","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"29_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.05.016","author":"I Carlucho","year":"2018","unstructured":"Carlucho, I., De Paula, M., Wang, S., Petillot, Y., Acosta, G.G.: Adaptive low-level control of autonomous underwater vehicles using deep reinforcement learning. Robot. Auton. Syst. (2018). https:\/\/doi.org\/10.1016\/j.robot.2018.05.016","journal-title":"Robot. Auton. Syst."},{"key":"29_CR4","unstructured":"Chen, X., Hu, J., Jin, C., Li, L., Wang, L.: Understanding domain randomization for sim-to-real transfer. ArXiv abs\/2110.03239 (2021)"},{"key":"29_CR5","unstructured":"Chen, X., Wang, C., Zhou, Z., Ross, K.W.: Randomized ensembled double q-learning: Learning fast without a model. ArXiv abs\/2101.05982 (2021)"},{"key":"29_CR6","doi-asserted-by":"publisher","unstructured":"Cie\u015blak, P.: Stonefish: an advanced open-source simulation tool designed for marine robotics, with a ROS interface. In: OCEANS 2019 - Marseille. pp.\u00a01\u20136 (2019). https:\/\/doi.org\/10.1109\/OCEANSE.2019.8867434","DOI":"10.1109\/OCEANSE.2019.8867434"},{"key":"29_CR7","unstructured":"Diamond, S., Boyd, S.P.: Cvxpy: A python-embedded modeling language for convex optimization. J. Mach. Learn. Res. JMLR 17 (2016)"},{"key":"29_CR8","unstructured":"Fossen, T.: Guidance and Control of Ocean Vehicles. Wiley (1994)"},{"key":"29_CR9","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning. pp. 1582\u20131591 (2018)"},{"key":"29_CR10","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. ArXiv abs\/1801.01290 (2018)"},{"key":"29_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2022.103326","volume":"129","author":"B Hadi","year":"2022","unstructured":"Hadi, B., Khosravi, A., Sarhadi, P.: Deep reinforcement learning for adaptive path planning and control of an autonomous underwater vehicle. Appl. Ocean Res. 129, 103326 (2022). https:\/\/doi.org\/10.1016\/j.apor.2022.103326","journal-title":"Appl. Ocean Res."},{"key":"29_CR12","unstructured":"Hiraoka, T., Imagawa, T., Hashimoto, T., Onishi, T., Tsuruoka, Y.: Dropout q-functions for doubly efficient reinforcement learning. In: International Conference on Learning Representations (2022)"},{"issue":"7976","key":"29_CR13","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1038\/s41586-023-06419-4","volume":"620","author":"E Kaufmann","year":"2023","unstructured":"Kaufmann, E.: Champion-level drone racing using deep reinforcement learning. Nature 620(7976), 982\u2013987 (2023). https:\/\/doi.org\/10.1038\/s41586-023-06419-4","journal-title":"Nature"},{"key":"29_CR14","unstructured":"Kurniawati, H.: Partially observable Markov decision processes (pomdps) and robotics. CoRR abs\/2107.07599 (2021). https:\/\/arxiv.org\/abs\/2107.07599"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Lambert, N.O., Drew, D.S., Yaconelli, J., Calandra, R., Levine, S., Pister, K.S.J.: Low level control of a quadrotor with deep model-based reinforcement learning (2019)","DOI":"10.1109\/LRA.2019.2930489"},{"key":"29_CR16","unstructured":"Li, H., Xu, Z., Taylor, G., Goldstein, T.: Visualizing the loss landscape of neural nets. ArXiv abs\/1712.09913 (2017)"},{"key":"29_CR17","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning (2013). http:\/\/arxiv.org\/abs\/1312.5602, cite arxiv:1312.5602Comment: NIPS Deep Learning Workshop 2013"},{"key":"29_CR18","doi-asserted-by":"publisher","unstructured":"Molero, A., Dunia, R., Cappelletto, J., Fernandez, G.: Model predictive control of remotely operated underwater vehicles. In: 2011 50th IEEE Conference on Decision and Control and European Control Conference. pp. 2058\u20132063 (2011). https:\/\/doi.org\/10.1109\/CDC.2011.6161447","DOI":"10.1109\/CDC.2011.6161447"},{"key":"29_CR19","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. ArXiv abs\/1912.01703 (2019)"},{"key":"29_CR20","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. ArXiv abs\/1707.06347 (2017)"},{"key":"29_CR21","doi-asserted-by":"publisher","unstructured":"Shen, C., Shi, Y., Buckham, B.: Model predictive control for an AUV with dynamic path planning. In: 2015 54th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE). pp. 475\u2013480 (2015). https:\/\/doi.org\/10.1109\/SICE.2015.7285374","DOI":"10.1109\/SICE.2015.7285374"},{"issue":"7","key":"29_CR22","doi-asserted-by":"publisher","first-page":"5796","DOI":"10.1109\/TIE.2017.2779442","volume":"65","author":"C Shen","year":"2018","unstructured":"Shen, C., Shi, Y., Buckham, B.: Trajectory tracking control of an autonomous underwater vehicle using lyapunov-based model predictive control. IEEE Trans. Industr. Electron. 65(7), 5796\u20135805 (2018). https:\/\/doi.org\/10.1109\/TIE.2017.2779442","journal-title":"IEEE Trans. Industr. Electron."},{"key":"29_CR23","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: an Introduction. 2nd edn. The MIT Press (2018)"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Willners, J.S., et al.: From market-ready ROVs to low-cost AUVs (2021)","DOI":"10.23919\/OCEANS44145.2021.9705798"},{"key":"29_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2020.107884","volume":"217","author":"Z Yan","year":"2020","unstructured":"Yan, Z., Gong, P., Zhang, W., Wu, W.: Model predictive control of autonomous underwater vehicles for trajectory tracking with external disturbances. Ocean Eng. 217, 107884 (2020). https:\/\/doi.org\/10.1016\/j.oceaneng.2020.107884","journal-title":"Ocean Eng."},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Yu, R., Shi, Z., Huang, C., Li, T., Ma, Q.: Deep Reinforcement Learning Based Optimal Trajectory Tracking Control of Autonomous Underwater Vehicle. In: 36th Chinese Control Conference. pp. 4958\u20134965 (2017)","DOI":"10.23919\/ChiCC.2017.8028138"},{"key":"29_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.115021","volume":"283","author":"T Zhang","year":"2023","unstructured":"Zhang, T., Miao, X., Li, Y., Jia, L., Wei, Z., Gong, Q., Wen, T.: AUV 3D docking control using deep reinforcement learning. Ocean Eng. 283, 115021 (2023). https:\/\/doi.org\/10.1016\/j.oceaneng.2023.115021","journal-title":"Ocean Eng."}],"container-title":["Lecture Notes in Computer Science","Towards Autonomous Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-01486-3_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T15:46:53Z","timestamp":1755618413000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-01486-3_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,13]]},"ISBN":["9783032014856","9783032014863"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-01486-3_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,13]]},"assertion":[{"value":"13 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TAROS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Annual Conference Towards Autonomous Robotic Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"York","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"taros2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/taros-conference.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}