{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T19:03:06Z","timestamp":1772823786386,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T00:00:00Z","timestamp":1651190400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T00:00:00Z","timestamp":1651190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836003"],"award-info":[{"award-number":["61836003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation for Universities of Jiangsu Province","award":["20KJB520008"],"award-info":[{"award-number":["20KJB520008"]}]},{"name":"Natural Science Founation for Universities of Jiangsu Province","award":["21KJB120009"],"award-info":[{"award-number":["21KJB120009"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1007\/s10489-022-03219-7","type":"journal-article","created":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T01:03:02Z","timestamp":1651194182000},"page":"1417-1434","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Hierarchical dynamic movement primitive for the smooth movement of robots based on deep reinforcement learning"],"prefix":"10.1007","volume":"53","author":[{"given":"Yinlong","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhu Liang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Hua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohu","family":"Sang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,4,29]]},"reference":[{"issue":"1","key":"3219_CR1","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. J Artif Intell Res 4(1):237\u2013285","journal-title":"J Artif Intell Res"},{"issue":"7553","key":"3219_CR2","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"3219_CR3","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85\u2013117","journal-title":"Neural Netw"},{"key":"3219_CR4","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv:1509.02971"},{"key":"3219_CR5","unstructured":"Andrychowicz M, Wolski F, Ray A, Schneider J, Fong R, Welinder P, Mcgrew B, Tobin J, Abbeel P, Zaremba W (2017) Hindsight experience replay. arXiv:1707.01495v3"},{"key":"3219_CR6","unstructured":"Schulman J, Levine S, Moritz P, Jordan MI, Abbeel P (2015) Trust region policy optimization. In: International conference on machine learning, pp 1889\u20131897"},{"key":"3219_CR7","unstructured":"Heess N, Dhruva TB, Sriram S, Lemmon J, Merel J, Wayne G, Tassa Y, Erez T, Wang Z, Eslami SMA (2017) Emergence of locomotion behaviours in rich environments. arXiv:1707.02286v2"},{"key":"3219_CR8","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv:1707.06347v2"},{"key":"3219_CR9","doi-asserted-by":"crossref","unstructured":"Rajeswaran A, Kumar V, Gupta A, Vezzani G, Schulman J, Todorov E, Levine S (2017) Learning complex dexterous manipulation with deep reinforcement learning and demonstrations. arXiv:1709.10087","DOI":"10.15607\/RSS.2018.XIV.049"},{"issue":"3","key":"3219_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/1729881419857534","volume":"16","author":"X Li","year":"2019","unstructured":"Li X, Wu L (2019) Impact motion control of a flexible dual-arm space robot for capturing a spinning object. Int J Adv Robot Syst 16(3):1\u20137","journal-title":"Int J Adv Robot Syst"},{"key":"3219_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.automatica.2019.06.037","volume":"108","author":"M Bagheri","year":"2019","unstructured":"Bagheri M, Naseradinmousavi P, Krsti\u0107 M. (2019) Feedback linearization based predictor for time delay control of a high-dof robot manipulator. Automatica 108:1\u20138","journal-title":"Automatica"},{"key":"3219_CR12","first-page":"1","volume":"49","author":"J Duan","year":"2017","unstructured":"Duan J, Ou Y, Hu J, Wang Z, Jin S, Xu C (2017) Fast and stable learning of dynamical systems based on extreme learning machine. IEEE Trans Syst Man Cybern Syst 49:1\u201311","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"3219_CR13","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.mechmachtheory.2018.09.015","volume":"131","author":"Z Liu","year":"2019","unstructured":"Liu Z, Wu J, Wang D (2019) An engineering-oriented motion accuracy fluctuation suppression method of a hybrid spray-painting robot considering dynamics. Mech Mach Theory 131:62\u201374","journal-title":"Mech Mach Theory"},{"key":"3219_CR14","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.neucom.2019.10.020","volume":"377","author":"H Xiong","year":"2020","unstructured":"Xiong H, Ma T, Zhang L, Diao X (2020) Comparison of end-to-end and hybrid deep reinforcement learning strategies for controlling cable-driven parallel robots. Neurocomputing 377:73\u201384","journal-title":"Neurocomputing"},{"issue":"4","key":"3219_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201397","volume":"37","author":"W Yu","year":"2018","unstructured":"Yu W, Turk G, Liu CK (2018) Learning symmetric and low-energy locomotion. ACM Trans Graph 37(4):1\u201312","journal-title":"ACM Trans Graph"},{"issue":"3","key":"3219_CR16","doi-asserted-by":"publisher","first-page":"4616","DOI":"10.1109\/LRA.2021.3068662","volume":"6","author":"B Brito","year":"2021","unstructured":"Brito B, Everett M, How JP, Alonso-Mora J (2021) Where to go next: learning a subgoal recommendation policy for navigation in dynamic environments. IEEE Robot Autom Lett 6(3):4616\u20134623","journal-title":"IEEE Robot Autom Lett"},{"issue":"12","key":"3219_CR17","doi-asserted-by":"publisher","first-page":"101360","DOI":"10.1016\/j.aei.2021.101360","volume":"49","author":"Q Liu","year":"2021","unstructured":"Liu Q, Liu Z, Xiong B, Xu W, Y. L. (2021) Deep reinforcement learning-based safe interaction for industrial human-robot collaboration using intrinsic reward function. Adv Eng Inform 49(12):101360","journal-title":"Adv Eng Inform"},{"key":"3219_CR18","doi-asserted-by":"publisher","first-page":"29064","DOI":"10.1109\/ACCESS.2020.2971780","volume":"8","author":"B Li","year":"2020","unstructured":"Li B, Wu Y (2020) Path planning for uav ground target tracking via deep reinforcement learning. IEEE Access 8:29064\u201329074","journal-title":"IEEE Access"},{"issue":"10","key":"3219_CR19","doi-asserted-by":"publisher","first-page":"7788","DOI":"10.1109\/TIE.2018.2884240","volume":"66","author":"Y Hu","year":"2018","unstructured":"Hu Y, Wu X, Geng P, Li Z (2018) Evolution strategies learning with variable impedance control for grasping under uncertainty. IEEE Trans Ind Electron 66(10):7788\u20137799","journal-title":"IEEE Trans Ind Electron"},{"key":"3219_CR20","unstructured":"Ijspeert A (2002) Learning attractor landscapes for learning motor primitives. In: Advances in neural information processing systems, pp 1523\u20131530"},{"key":"3219_CR21","doi-asserted-by":"crossref","unstructured":"Kober J, Oztop E, Peters J (2011) Reinforcement learning to adjust robot movements to new situations. In: IEEE\/RSJ international joint conference on artificial intelligence, pp 2650\u20132655","DOI":"10.15607\/RSS.2010.VI.005"},{"key":"3219_CR22","doi-asserted-by":"crossref","unstructured":"Kober J, Mulling K, KroMer O, Lampert CH (2014) Movement templates for learning of hitting and batting. In: IEEE international conference on robotics and automation, pp. 853\u2013858","DOI":"10.1007\/978-3-319-03194-1_3"},{"issue":"5","key":"3219_CR23","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1109\/TRO.2011.2159412","volume":"27","author":"SM Khansari-Zadeh","year":"2011","unstructured":"Khansari-Zadeh SM, Billard A (2011) Learning stable nonlinear dynamical systems with gaussian mixture models. IEEE Trans Robot 27(5):943\u2013957","journal-title":"IEEE Trans Robot"},{"key":"3219_CR24","doi-asserted-by":"crossref","unstructured":"Muelling K, Kober J, Peters J (2010) Learning table tennis with a mixture of motor primitives. In: IEEE international conference on humanoid robots, pp 411\u2013416","DOI":"10.1109\/ICHR.2010.5686298"},{"issue":"4","key":"3219_CR25","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s10514-012-9290-3","volume":"33","author":"J Kober","year":"2012","unstructured":"Kober J, Wilhelm A, Oztop E, Peters J (2012) Reinforcement learning to adjust parametrized motor primitives to new situations. Auton Robot 33(4):361\u2013379","journal-title":"Auton Robot"},{"key":"3219_CR26","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 MP, Peters J, Loh AP, Vadakkepat P, Neumann G (2017) Model-based contextual policy search for data-efficient generalization of robot skills. Artif Intell 247:415\u2013439","journal-title":"Artif Intell"},{"key":"3219_CR27","doi-asserted-by":"crossref","unstructured":"Rueckert E, Mundo J, Paraschos A, Peters J, Neumann G (2015) Extracting low-dimensional control variables for movement primitives. In: IEEE international conference on robotics & automation, pp 1511\u20131518","DOI":"10.1109\/ICRA.2015.7139390"},{"issue":"1","key":"3219_CR28","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TMECH.2017.2717461","volume":"23","author":"Z Li","year":"2017","unstructured":"Li Z, Zhao T, Chen F, Hu C, Yingbai Su, Fukuda T (2017) Reinforcement learning of manipulation and grasping using dynamical movement primitives for a humanoid-like mobile manipulator. IEEE\/ASME Trans Mech 23(1):121\u2013131","journal-title":"IEEE\/ASME Trans Mech"},{"issue":"5","key":"3219_CR29","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1177\/1059712311419378","volume":"19","author":"K Mulling","year":"2010","unstructured":"Mulling K, Kober J, Peters J (2010) A biomimetic approach to robot table tennis. Adapt Behav 19(5):359\u2013376","journal-title":"Adapt Behav"},{"issue":"3","key":"3219_CR30","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1177\/0278364912472380","volume":"32","author":"K Lling","year":"2013","unstructured":"Lling K, Kober J, Kroemer O, Peters J (2013) Learning to select and generalize striking movements in robot table tennis. Int J Robot Res 32(3):263\u2013279","journal-title":"Int J Robot Res"},{"issue":"3","key":"3219_CR31","doi-asserted-by":"publisher","first-page":"122","DOI":"10.3390\/robotics2030122","volume":"2","author":"P Kormushev","year":"2013","unstructured":"Kormushev P, Calinon S, Caldwell DG (2013) Reinforcement learning in robotics: applications and real-world challenges. Robot 2(3):122\u2013148","journal-title":"Robot"},{"key":"3219_CR32","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.robot.2018.08.008","volume":"109","author":"MS Qureshi","year":"2018","unstructured":"Qureshi MS, Swarnkar P, Gupta S (2018) A supervisory on-line tuned fuzzy logic based sliding mode control for robotics: An application to surgical robots. Robot Auton Syst 109:68\u201385","journal-title":"Robot Auton Syst"},{"key":"3219_CR33","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. arXiv:1312.5602"},{"issue":"7540","key":"3219_CR34","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland A, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"3219_CR35","doi-asserted-by":"crossref","unstructured":"Ijspeert AJ, Nakanishi J, Schaal S (2001) Trajectory formation for imitation with nonlinear dynamical systems. In: IEEE international conference on intelligent robots and systems, pp 752\u2013757","DOI":"10.1109\/IROS.2001.976259"},{"key":"3219_CR36","unstructured":"Swaminathan A, Joachims T (2015) The self-normalized estimator for counterfactual learning. In: Annual conference on neural information processing systems, pp 3231\u20133239"},{"issue":"10","key":"3219_CR37","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1016\/j.neunet.2009.01.002","volume":"22","author":"H Hachiya","year":"2009","unstructured":"Hachiya H, Akiyama T, Sugiayma M, Peters J (2009) Adaptive importance sampling for value function approximation in off-policy reinforcement learning. Neural Netw 22(10):1399\u20131410","journal-title":"Neural Netw"},{"key":"3219_CR38","doi-asserted-by":"crossref","unstructured":"Ali W, Abdelkarim S, Zahran M, Zidan M, Sallab AE (2018) Yolo3d: End-to-end real-time 3d oriented object bounding box detection from lidar point cloud. arXiv: Computer Vision and Pattern Recognition","DOI":"10.1007\/978-3-030-11015-4_54"},{"key":"3219_CR39","doi-asserted-by":"crossref","unstructured":"Hersch M, Guenter F, Calinon S, Billard AG (2006) Learning dynamical system modulation for constrained reaching tasks. In: 6th IEEE-RAS international conference on humanoid robots, pp 444\u2013449","DOI":"10.1109\/ICHR.2006.321310"},{"issue":"5","key":"3219_CR40","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"BD Argall","year":"2009","unstructured":"Argall BD, Chernova S, Veloso MM, Browning B (2009) A survey of robot learning from demonstration. Robot Auton Syst 57(5):469\u2013483","journal-title":"Robot Auton Syst"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03219-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03219-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03219-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T04:36:54Z","timestamp":1672807014000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03219-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,29]]},"references-count":40,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["3219"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03219-7","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,29]]},"assertion":[{"value":"6 January 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}