{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T16:12:42Z","timestamp":1784563962123,"version":"3.55.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51379198"],"award-info":[{"award-number":["51379198"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2018QF003"],"award-info":[{"award-number":["ZR2018QF003"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["201961005"],"award-info":[{"award-number":["201961005"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the National Key Research and Development Program of China","award":["2016YFC0301400"],"award-info":[{"award-number":["2016YFC0301400"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Robot Syst"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10846-021-01504-0","type":"journal-article","created":{"date-parts":[[2022,3,4]],"date-time":"2022-03-04T17:12:04Z","timestamp":1646413924000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["A Modified ALOS Method of Path Tracking for AUVs with Reinforcement Learning Accelerated by Dynamic Data-Driven AUV Model"],"prefix":"10.1007","volume":"104","author":[{"given":"Dianrui","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangliang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanzhong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,3,4]]},"reference":[{"issue":"8","key":"1504_CR1","doi-asserted-by":"publisher","first-page":"1021","DOI":"10.1016\/j.mechatronics.2014.08.001","volume":"24","author":"BD A","year":"2014","unstructured":"A, B.D., B, M.L., A, G.P., B, I.G., B, R.B.: Comparison of model-free and model-based methods for time optimal hit control of a badminton robot. Mechatronics 24(8), 1021\u20131030 (2014)","journal-title":"Mechatronics"},{"issue":"1","key":"1504_CR2","doi-asserted-by":"publisher","first-page":"2290","DOI":"10.1016\/j.ifacol.2017.08.228","volume":"50","author":"B Abdurahman","year":"2017","unstructured":"Abdurahman, B., Savvaris, A., Tsourdos, A.: A switching los guidance with relative kinematics for path-following of underactuated underwater vehicles. Ifac Papersonline 50(1), 2290\u20132295 (2017)","journal-title":"Ifac Papersonline"},{"issue":"JUN.15","key":"1504_CR3","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1016\/j.oceaneng.2019.04.021","volume":"182","author":"B Abdurahman","year":"2019","unstructured":"Abdurahman, B., Savvaris, A., Tsourdos, A.: Switching los guidance with speed allocation and vertical course control for path-following of unmanned underwater vehicles under ocean current disturbances. Ocean Eng. 182(JUN.15), 412\u2013426 (2019)","journal-title":"Ocean Eng."},{"issue":"4","key":"1504_CR4","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1109\/TSMC.1972.4309169","volume":"93","author":"BDO Anderson","year":"1972","unstructured":"Anderson, B.D.O., Moore, J.B., Molinari, B.P.: Linear optimal control. IEEE Trans. Syst. Man Cybern. 93(4), 559\u2013559 (1972)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"1504_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1002\/rob.20370","volume":"27","author":"MR Benjamin","year":"2010","unstructured":"Benjamin, M.R., Schmidt, H., Newman, P., Leonard, J.: Nested autonomy for unmanned marine vehicles with moos-ivp. J. Field Robot. 27, 834\u2013875 (2010)","journal-title":"J. Field Robot."},{"issue":"2","key":"1504_CR6","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1109\/JOE.2018.2792278","volume":"43","author":"M Carreras","year":"2018","unstructured":"Carreras, M., Hernndez, J.D., Vidal, E., Palomeras, N., Ribas, D., Ridao, P.: Sparus ii auv-a hovering vehicle for seabed inspection. IEEE J. Ocean. Eng. 43(2), 344\u2013355 (2018)","journal-title":"IEEE J. Ocean. Eng."},{"key":"1504_CR7","unstructured":"Filonov, P., Lavrentyev, A., Vorontsov, A.: Multivariate industrial time series with cyber-attack simulation: Fault detection using an lstm-based predictive data model. arXiv:1612.06676 (2016)"},{"issue":"4","key":"1504_CR8","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1002\/acs.2550","volume":"31","author":"TI Fossen","year":"2017","unstructured":"Fossen, T.I., Lekkas, A.M.: Direct and indirect adaptive integral line-of-sight path-following controllers for marine craft exposed to ocean currents. Int. J. Adapt. Control Signal Proc. 31(4), 445\u2013463 (2017)","journal-title":"Int. J. Adapt. Control Signal Proc."},{"issue":"11","key":"1504_CR9","doi-asserted-by":"publisher","first-page":"2912","DOI":"10.1016\/j.automatica.2014.10.018","volume":"50","author":"TI Fossen","year":"2014","unstructured":"Fossen, T.I., Pettersen, K.Y.: On uniform semiglobal exponential stability (usges) of proportional line-of-sight guidance laws. Automatica 50(11), 2912\u20132917 (2014)","journal-title":"Automatica"},{"key":"1504_CR10","first-page":"115","volume":"3","author":"FA Gers","year":"2003","unstructured":"Gers, F.A., Schraudolph, N.N.: Learning precise timing with lstm recurrent networks. J. Mach. Learn. Res. 3, 115\u2013143 (2003)","journal-title":"J. Mach. Learn. Res."},{"issue":"1-2","key":"1504_CR11","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1007\/s11071-013-0840-9","volume":"73","author":"N Khaled","year":"2013","unstructured":"Khaled, N., Chalhoub, N.G.: A self-tuning guidance and control system for marine surface vessels. Nonlinear Dyn. 73(1-2), 897\u2013906 (2013)","journal-title":"Nonlinear Dyn."},{"key":"1504_CR12","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.artint.2014.11.005","volume":"247","author":"A Kupcsik","year":"2017","unstructured":"Kupcsik, A., Deisenroth, M.P., Peters, J., Loh, A.P., Vadakkepat, P., Neumann, G.: Model-based contextual policy search for data-efficient generalization of robot skills. Artif. Intell. 247, 415\u2013439 (2017)","journal-title":"Artif. Intell."},{"issue":"3","key":"1504_CR13","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1016\/j.automatica.2006.09.017","volume":"43","author":"S Laghrouche","year":"2007","unstructured":"Laghrouche, S., Plestan, F., Glumineau, A.: Higher order sliding mode control based on integral sliding mode. Automatica 43(3), 531\u2013537 (2007)","journal-title":"Automatica"},{"issue":"6","key":"1504_CR14","doi-asserted-by":"publisher","first-page":"2287","DOI":"10.1109\/TCST.2014.2306774","volume":"22","author":"A Lekkas","year":"2014","unstructured":"Lekkas, A., Fossen, T.: Integral los path following for curved paths based on a monotone cubic hermite spline parametrization. IEEE Trans. Control Syst. Technol. 22(6), 2287\u20132301 (2014)","journal-title":"IEEE Trans. Control Syst. Technol."},{"issue":"27","key":"1504_CR15","doi-asserted-by":"crossref","first-page":"398","DOI":"10.3182\/20120919-3-IT-2046.00068","volume":"45","author":"AM Lekkas","year":"2012","unstructured":"Lekkas, A.M., Fossen, T.I.: A time-varying lookahead distance guidance law for path following. Ifac Proc. 45(27), 398\u2013403 (2012)","journal-title":"Ifac Proc."},{"key":"1504_CR16","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1007\/s10846-013-9873-z","volume":"74","author":"AM Lekkas","year":"2014","unstructured":"Lekkas, A.M., Fossen, T.I.: Uav path following in windy urban environments. J. Intell. Robot. Syst. 74, 1013\u20131028 (2014)","journal-title":"J. Intell. Robot. Syst."},{"issue":"6","key":"1504_CR17","first-page":"1","volume":"8","author":"TP Lillicrap","year":"2015","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. Comput. Sci. 8(6), 1\u201314 (2015)","journal-title":"Comput. Sci."},{"key":"1504_CR18","unstructured":"Lin, C., Chiang, H., Lee, T.: A practical fuzzy controller with q-learning approach for the path tracking of a walking-aid robot. In: The SICE Annual Conference 2013, pp. 888\u2013893 (2013)"},{"key":"1504_CR19","doi-asserted-by":"publisher","first-page":"102443","DOI":"10.1016\/j.mechatronics.2020.102443","volume":"72","author":"P Liu","year":"2020","unstructured":"Liu, P., Huda, M.N., Sun, L., Yu, H.: A survey on underactuated robotic systems: Bio-inspiration, trajectory planning and control. Mechatronics 72, 102443 (2020)","journal-title":"Mechatronics"},{"key":"1504_CR20","doi-asserted-by":"publisher","first-page":"1447","DOI":"10.1007\/s11071-019-05170-8","volume":"98","author":"P Liu","year":"2019","unstructured":"Liu, P., Yu, H., Cang, S.: Adaptive neural network tracking control for underactuated systems with matched and mismatched disturbances. Nonlinear Dyn. 98, 1447\u20131464 (2019)","journal-title":"Nonlinear Dyn."},{"key":"1504_CR21","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1007\/s11071-018-4458-9","volume":"94","author":"P Liu","year":"2018","unstructured":"Liu, P., Yu, H., Shuang, C.: Optimized adaptive tracking control for an underactuated vibro-driven capsule system. Nonlinear Dyn. 94, 1803\u20131817 (2018)","journal-title":"Nonlinear Dyn."},{"issue":"2","key":"1504_CR22","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1109\/JOE.2016.2569218","volume":"42","author":"L Lu","year":"2017","unstructured":"Lu, L., Dan, W., Peng, Z.: Eso-based line-of-sight guidance law for path following of underactuated marine surface vehicles with exact sideslip compensation. IEEE J. Ocean. Eng. 42(2), 477\u2013487 (2017)","journal-title":"IEEE J. Ocean. Eng."},{"key":"1504_CR23","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1016\/j.cirp.2020.04.001","volume":"69","author":"A Malus","year":"2020","unstructured":"Malus, A., Kozjek, D., Vrabic, R.: Real-time order dispatching for a fleet of autonomous mobile robots using multi-agent reinforcement learning. CIRP Ann. 69, 397\u2013400 (2020)","journal-title":"CIRP Ann."},{"key":"1504_CR24","doi-asserted-by":"crossref","unstructured":"Mandel, J., Beezley, J.D., Bennethum, L.S., Chakraborty, S., Vodacek, A.: A dynamic data driven wildland fire model. In: Computational Science - ICCS 2007, 7th International Conference Beijing, China, May 27-30 2007 Proceedings, Part I (2007)","DOI":"10.1007\/978-3-540-72584-8_137"},{"key":"1504_CR25","first-page":"1","volume":"2018","author":"D Mu","year":"2018","unstructured":"Mu, D., Wang, G., Fan, Y., Bai, Y., Zhao, Y.: Fuzzy-based optimal adaptive line-of-sight path following for underactuated unmanned surface vehicle with uncertainties and time-varying disturbances. Math. Probl. Eng. 2018, 1\u201312 (2018)","journal-title":"Math. Probl. Eng."},{"issue":"2","key":"1504_CR26","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s11071-017-3611-1","volume":"92","author":"NM Nouri","year":"2018","unstructured":"Nouri, N.M., Valadi, M., Asgharian, J.: Optimal input design for hydrodynamic derivatives estimation of nonlinear dynamic model of auv. Nonlinear Dyn. 92(2), 139\u2013151 (2018)","journal-title":"Nonlinear Dyn."},{"issue":"2","key":"1504_CR27","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s10846-017-0468-y","volume":"86","author":"AS Polydoros","year":"2017","unstructured":"Polydoros, A.S., Nalpantidis, L.: Survey of model-based reinforcement learning: Applications on robotics. J. Intell. Robot. Syst. 86(2), 153\u2013173 (2017)","journal-title":"J. Intell. Robot. Syst."},{"key":"1504_CR28","unstructured":"Pong, V., Gu, S., Dalal, M., Levine, S.: Temporal difference models: Model-free deep RL for model-based control. 1\u201314 arXiv:1802.09081 (2018)"},{"key":"1504_CR29","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/s10846-020-01191-3","volume":"100","author":"T Praczyk","year":"2020","unstructured":"Praczyk, T.: Using neurocevolutionary techniques to tune odometric navigational system of small biomimetic autonomous underwater vehicle c preliminary report. J. Intell. Robot. Syst. 100, 363\u2013376 (2020)","journal-title":"J. Intell. Robot. Syst."},{"issue":"2","key":"1504_CR30","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1109\/JOE.2018.2809018","volume":"44","author":"L Qiao","year":"2019","unstructured":"Qiao, L., Zhang, W.: Adaptive second-order fast nonsingular terminal sliding mode tracking control for fully actuated autonomous underwater vehicles. IEEE J. Ocean. Eng. 44(2), 363\u2013385 (2019)","journal-title":"IEEE J. Ocean. Eng."},{"issue":"1","key":"1504_CR31","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s10846-014-0151-5","volume":"78","author":"M Sadeghzadeh","year":"2015","unstructured":"Sadeghzadeh, M., Calvert, D., Abdullah, H.A.: Self-learning visual servoing of robot manipulator using explanation-based fuzzy neural networks and q-learning. J. Intell. Robot. Syst. 78(1), 83\u2013104 (2015)","journal-title":"J. Intell. Robot. Syst."},{"key":"1504_CR32","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1016\/j.ins.2018.01.032","volume":"436-437","author":"H Shi","year":"2018","unstructured":"Shi, H., Lin, Z., Zhang, S., Li, X., Hwang, K.S.: An adaptive decision-making method with fuzzy bayesian reinforcement learning for robot soccer. Inform. Sci. 436-437, 268\u2013281 (2018)","journal-title":"Inform. Sci."},{"key":"1504_CR33","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: 31st International Conference on Machine Learning, ICML, 2014, pp 387\u2013395 (2014)"},{"key":"1504_CR34","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1007\/s10846-019-01004-2","volume":"96","author":"Y Sun","year":"2019","unstructured":"Sun, Y., Cheng, J., Zhang, G., Xu, H.: Mapless motion planning system for an autonomous underwater vehicle using policy gradient-based deep reinforcement learning. J. Intell. Robot. Syst. 96, 591\u2013601 (2019)","journal-title":"J. Intell. Robot. Syst."},{"key":"1504_CR35","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction (1998)","DOI":"10.1109\/TNN.1998.712192"},{"issue":"5","key":"1504_CR36","doi-asserted-by":"publisher","first-page":"2409","DOI":"10.1109\/TMAG.2013.2240666","volume":"49","author":"A Wang","year":"2013","unstructured":"Wang, A., Jia, X., Dong, S.: A new exponential reaching law of sliding mode control to improve performance of permanent magnet synchronous motor. IEEE Trans. Magnet. 49(5), 2409\u20132412 (2013)","journal-title":"IEEE Trans. Magnet."},{"issue":"3","key":"1504_CR37","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1007\/s10846-019-01146-3","volume":"99","author":"X Wang","year":"2020","unstructured":"Wang, X., Yao, X., Zhang, L.: Path planning under constraints and path following control of autonomous underwater vehicle with dynamical uncertainties and wave disturbances. J. Intell. Robot. Syst. 99(3), 891\u2013908 (2020)","journal-title":"J. Intell. Robot. Syst."},{"issue":"1","key":"1504_CR38","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.oceaneng.2019.04.099","volume":"183","author":"J Woo","year":"2019","unstructured":"Woo, J.: Y.C..K.N.: Deep reinforcement learning-based controller for path following of an unmanned surface vehicle. Ocean Eng. 183(1), 155\u2013166 (2019)","journal-title":"Ocean Eng."},{"issue":"10","key":"1504_CR39","doi-asserted-by":"publisher","first-page":"2920","DOI":"10.1109\/TCYB.2017.2752458","volume":"48","author":"C Yuan","year":"2018","unstructured":"Yuan, C., Licht, S., He, H.: Formation learning control of multiple autonomous underwater vehicles with heterogeneous nonlinear uncertain dynamics. IEEE Trans. Cybern. 48(10), 2920\u20132934 (2018)","journal-title":"IEEE Trans. Cybern."},{"issue":"3","key":"1504_CR40","first-page":"298","volume":"27","author":"Z Yue","year":"2012","unstructured":"Yue, Z., Zhu, D.: A bio-inspired neurodynamics based back stepping path-following control of an auv with ocean current. Int. J. Robot. Autom 27(3), 298\u2013307 (2012)","journal-title":"Int. J. Robot. Autom"}],"container-title":["Journal of Intelligent &amp; Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-021-01504-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10846-021-01504-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-021-01504-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T11:22:26Z","timestamp":1674904946000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10846-021-01504-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":40,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["1504"],"URL":"https:\/\/doi.org\/10.1007\/s10846-021-01504-0","relation":{},"ISSN":["0921-0296","1573-0409"],"issn-type":[{"value":"0921-0296","type":"print"},{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3]]},"assertion":[{"value":"19 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Consent for publication was obtained from all participants.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Consent for Publication"}},{"value":"The authors declare that they have no competing financial interests","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Competing interests"}}],"article-number":"49"}}