{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:26:18Z","timestamp":1774121178341,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"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":["91748114"],"award-info":[{"award-number":["91748114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51535004"],"award-info":[{"award-number":["51535004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Group Program of Hubei Province","award":["2017CFA003"],"award-info":[{"award-number":["2017CFA003"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Intell Robot Appl"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s41315-020-00138-z","type":"journal-article","created":{"date-parts":[[2020,6,2]],"date-time":"2020-06-02T20:10:59Z","timestamp":1591128659000},"page":"202-216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Model accelerated reinforcement learning for high precision robotic assembly"],"prefix":"10.1007","volume":"4","author":[{"given":"Xin","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1589-5375","authenticated-orcid":false,"given":"Huan","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Pengfei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Han","family":"Ding","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,6,2]]},"reference":[{"key":"138_CR1","doi-asserted-by":"crossref","unstructured":"Billard, A., Calinon, S., Dillmann, R., Schaal, S.: Robot programming by demonstration. Springer handbook of robotics, 1371\u20131394 (2008)","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"138_CR2","unstructured":"Chhatpar, S.R., Branicky, M.S.: Search strategies for peg-in-hole assemblies with position uncertainty. Proceedings 2001 IEEE\/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180), 20011465\u20131470. (2001)"},{"key":"138_CR3","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. Paper presented at the Proceedings of the 35th International Conference on Machine Learning (2018)"},{"key":"138_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2019\/5262859","volume":"2019","author":"X Gao","year":"2019","unstructured":"Gao, X., Ling, J., Xiao, X., Li, M.: Learning force-relevant skills from human demonstration. Complexity 2019, 1\u201311 (2019). https:\/\/doi.org\/10.1155\/2019\/5262859","journal-title":"Complexity"},{"key":"138_CR5","unstructured":"Haarnoja, T., Tang, H., Abbeel, P., Levine, S.: Reinforcement learning with deep energy-based policiesProceedings of the 34th International Conference on Machine Learning Volume 70, Sydney, NSW, Australia, 2017. JMLR.org, p 1352\u20131361. (2017)"},{"key":"138_CR6","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, Proceedings of Machine Learning Research, 2018. PMLR, p 1861\u20131870. (2018)"},{"issue":"5","key":"138_CR7","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1177\/027836499101000508","volume":"10","author":"B Hannaford","year":"1991","unstructured":"Hannaford, B., Lee, P.: Hidden markov model analysis of force\/torque information in telemanipulation. Int. J. Robot. Res. 10(5), 528\u2013539 (1991). https:\/\/doi.org\/10.1177\/027836499101000508","journal-title":"Int. J. Robot. Res."},{"key":"138_CR8","doi-asserted-by":"crossref","unstructured":"Inoue, T., De Magistris, G., Munawar, A., Yokoya, T., Tachibana, R.: Deep reinforcement learning for high precision assembly tasks. Paper presented at the 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2018)","DOI":"10.1109\/IROS.2017.8202244"},{"issue":"1","key":"138_CR9","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1007\/s00170-011-3501-5","volume":"59","author":"Z Jakovljevic","year":"2012","unstructured":"Jakovljevic, Z., Petrovic, P.B., Hodolic, J.: Contact states recognition in robotic part mating based on support vector machines. Int. J. Adv. Manuf. Technol. 59(1), 377\u2013395 (2012). https:\/\/doi.org\/10.1007\/s00170-011-3501-5","journal-title":"Int. J. Adv. Manuf. Technol."},{"issue":"3","key":"138_CR10","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1007\/s10845-012-0706-x","volume":"25","author":"Z Jakovljevic","year":"2014","unstructured":"Jakovljevic, Z., Petrovic, P.B., Mikovic, V.D., Pajic, M.: Fuzzy inference mechanism for recognition of contact states in intelligent robotic assembly. J Intell Manuf 25(3), 571\u2013587 (2014). https:\/\/doi.org\/10.1007\/s10845-012-0706-x","journal-title":"J Intell Manuf"},{"issue":"8","key":"138_CR11","doi-asserted-by":"publisher","first-page":"1448","DOI":"10.1177\/0954405415598945","volume":"231","author":"IF Jasim","year":"2017","unstructured":"Jasim, I.F., Plapper, P.W., Voos, H.: Contact-state modelling in force-controlled robotic peg-in-hole assembly processes of flexible objects using optimised Gaussian mixtures. Proc. Inst. Mech. Eng. Part B J. Eng. Manuf. 231(8), 1448\u20131463 (2017). https:\/\/doi.org\/10.1177\/0954405415598945","journal-title":"Proc. Inst. Mech. Eng. Part B J. Eng. Manuf."},{"key":"138_CR12","unstructured":"Kim, I., Lim, D., Kim, K.: Active peg-in-hole of chamferless parts using force\/moment sensor. Paper presented at the 1999 IEEE\/RSJ International Conference on Intelligent Robots and Systems., 1999"},{"key":"138_CR13","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.robot.2017.09.019","volume":"98","author":"A Kramberger","year":"2017","unstructured":"Kramberger, A., Gams, A., Nemec, B., Chrysostomou, D., Madsen, O., Ude, A.: Generalization of orientation trajectories and force-torque profiles for robotic assembly. Robot Auton Syst 98, 333\u2013346 (2017). https:\/\/doi.org\/10.1016\/j.robot.2017.09.019","journal-title":"Robot Auton Syst"},{"key":"138_CR14","unstructured":"Kronander, K.J.A.: Control and learning of compliant manipulation skills. doctoral, EPFL (2015)"},{"key":"138_CR15","unstructured":"Kronander, K., Burdet, E., Billard, A.: Task transfer via collaborative manipulation for insertion assembly. Paper presented at the 2014 Workshop on human-robot interaction for industrial manufacturing, robotics, science and systems (2014)"},{"key":"138_CR16","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. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"138_CR17","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.neucom.2019.01.087","volume":"345","author":"F Li","year":"2019","unstructured":"Li, F., Jiang, Q., Zhang, S., Wei, M., Song, R.: Robot skill acquisition in assembly process using deep reinforcement learning. Neurocomputing 345, 92\u2013102 (2019). https:\/\/doi.org\/10.1016\/j.neucom.2019.01.087","journal-title":"Neurocomputing"},{"key":"138_CR18","doi-asserted-by":"crossref","unstructured":"Luo, J., Solowjow, E., Wen, C., Ojea, J.A., Agogino, A.M.: Deep reinforcement learning for robotic assembly of mixed deformable and rigid objects. Paper presented at the 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","DOI":"10.1109\/IROS.2018.8594353"},{"issue":"2","key":"138_CR19","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). https:\/\/doi.org\/10.1007\/s10846-017-0468-y","journal-title":"J Intell Robot Syst"},{"key":"138_CR20","doi-asserted-by":"publisher","DOI":"10.1115\/1.4041331","author":"T Ren","year":"2018","unstructured":"Ren, T., Dong, Y., Wu, D., Chen, K.: Learning-based variable compliance control for robotic assembly. J. Mech. Robot. (2018). https:\/\/doi.org\/10.1115\/1.4041331","journal-title":"J. Mech. Robot."},{"key":"138_CR21","doi-asserted-by":"crossref","unstructured":"Siciliano, B., Sciavicco, L., Villani, L., Oriolo, G.: Robotics: modelling, planning and control. Springer Science & Business Media. (2010)","DOI":"10.1007\/978-1-84628-642-1"},{"issue":"7587","key":"138_CR22","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M.: Others: mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484 (2016)","journal-title":"Nature"},{"key":"138_CR23","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. MIT Press, Cambridge (2018)"},{"key":"138_CR24","unstructured":"Tang, T.: Skill learning for industrial robot manipulators., UC Berkeley (2018)"},{"key":"138_CR25","doi-asserted-by":"crossref","unstructured":"Tang, T., Lin, H.C., Zhao, Y., Fan, Y., Chen, W., Tomizuka, M.: Teach industrial robots peg-hole-insertion by human demonstration. Paper presented at the 2016 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics, AIM, 2016\u201301\u201301 (2016)","DOI":"10.1109\/AIM.2016.7576815"},{"key":"138_CR26","doi-asserted-by":"crossref","unstructured":"Thomas, G., Chien, M., Tamar, A., Ojea, J.A., Abbeel, P.: Learning robotic assembly from CAD. Paper presented at the 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018\u201301\u201301","DOI":"10.1109\/ICRA.2018.8460696"},{"issue":"1","key":"138_CR27","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1115\/1.3149634","volume":"104","author":"DE Whitney","year":"1982","unstructured":"Whitney, D.E.: Quasi-static assembly of compliantly supported rigid parts. J. Dyn. Syst. Meas. Control. Trans. ASME 104(1), 65\u201377 (1982). https:\/\/doi.org\/10.1115\/1.3149634","journal-title":"J. Dyn. Syst. Meas. Control. Trans. ASME"},{"key":"138_CR28","volume-title":"Gaussian processes for machine learning","author":"CK Williams","year":"2006","unstructured":"Williams, C.K., Rasmussen, C.E.: Gaussian processes for machine learning, vol. 2. MIT press, Cambridge (2006)"},{"issue":"1\u20132","key":"138_CR29","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1007\/s00170-005-0047-4","volume":"30","author":"Y Xia","year":"2006","unstructured":"Xia, Y., Yin, Y., Chen, Z.: Dynamic analysis for peg-in-hole assembly with contact deformation. Int. J. Adv. Manuf. Technol. 30(1\u20132), 118\u2013128 (2006). https:\/\/doi.org\/10.1007\/s00170-005-0047-4","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"138_CR30","unstructured":"Xu, J., Hou, Z., Liu, Z., Qiao, H.: Compare contact model-based control and contact model-free learning: a survey of robotic peg-in-hole assembly strategies. arXiv preprint arXiv:1904.05240 (2019a)"},{"issue":"3","key":"138_CR31","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1109\/TII.2018.2868859","volume":"15","author":"J Xu","year":"2019","unstructured":"Xu, J., Hou, Z., Wang, W., Xu, B., Zhang, K., Chen, K.: Feedback deep deterministic policy gradient with fuzzy reward for robotic multiple peg-in-hole assembly tasks. IEEE T Ind Inform 15(3), 1658\u20131667 (2019b). https:\/\/doi.org\/10.1109\/TII.2018.2868859","journal-title":"IEEE T Ind Inform"}],"container-title":["International Journal of Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41315-020-00138-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41315-020-00138-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41315-020-00138-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,2]],"date-time":"2021-06-02T00:10:41Z","timestamp":1622592641000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41315-020-00138-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["138"],"URL":"https:\/\/doi.org\/10.1007\/s41315-020-00138-z","relation":{},"ISSN":["2366-5971","2366-598X"],"issn-type":[{"value":"2366-5971","type":"print"},{"value":"2366-598X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6]]},"assertion":[{"value":"28 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}