{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T16:56:52Z","timestamp":1778691412867,"version":"3.51.4"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T00:00:00Z","timestamp":1679875200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T00:00:00Z","timestamp":1679875200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the National Key R&D Program of China","award":["2018YFB1307400"],"award-info":[{"award-number":["2018YFB1307400"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Robot Syst"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s10846-023-01822-5","type":"journal-article","created":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T14:02:51Z","timestamp":1679925771000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["An Efficiently Convergent Deep Reinforcement Learning-Based Trajectory Planning Method for Manipulators in Dynamic Environments"],"prefix":"10.1007","volume":"107","author":[{"given":"Li","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YaHao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Run","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaolei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4062-9730","authenticated-orcid":false,"given":"Erbao","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,27]]},"reference":[{"key":"1822_CR1","doi-asserted-by":"crossref","unstructured":"Brog\u00e5ardh, T.: Present and future robot control development\u2014an industrial perspective. Annu. Rev. Control. 31(1), 69\u201379 (2007)","DOI":"10.1016\/j.arcontrol.2007.01.002"},{"key":"1822_CR2","doi-asserted-by":"publisher","first-page":"148","DOI":"10.3389\/frobt.2021.550644","volume":"8","author":"M Wonsick","year":"2021","unstructured":"Wonsick, M., Long, P., \u00d6nol, A.\u00d6., Wang, M., Pad\u0131r, T.: A holistic approach to human-supervised humanoid robot operations in extreme environments. Front. Robot. and AI 8, 148 (2021)","journal-title":"Front. Robot. and AI"},{"issue":"12","key":"1822_CR3","doi-asserted-by":"publisher","first-page":"408","DOI":"10.5772\/56791","volume":"10","author":"JCM Carvalho","year":"2013","unstructured":"Gon\u00e7alves R.S., Carvalho, J.C.M.: Review and latest trends in mobile robots used on power transmission lines. Int. J. Adv. Robot. Syst. 10(12), 408 (2013)","journal-title":"Int. J. Adv. Robot. Syst."},{"issue":"2","key":"1822_CR4","first-page":"91","volume":"4","author":"E Mgbemena","year":"2020","unstructured":"Mgbemena, E.: Man-machine systems : a review of current trends and applications. FUPRE J. Sci Ind. Res. (FJSIR) 4(2), 91\u2013117 (2020)","journal-title":"FUPRE J. Sci Ind. Res. (FJSIR)"},{"key":"1822_CR5","doi-asserted-by":"publisher","first-page":"26754","DOI":"10.1109\/ACCESS.2017.2773127","volume":"5","author":"S Robla-Gomez\u0301","year":"2017","unstructured":"Robla-Gomez\u0301, S., Becerra, V.M., Llata, J.R., Gonzalez-Sarabia, E., Torre-Ferrero, C., Perez-Oria, J.: Working together : a review on safe human-robot collaboration in industrial environments. IEEE Access 5, 26754\u201326773 (2017)","journal-title":"IEEE Access"},{"issue":"1","key":"1822_CR6","first-page":"32","volume":"2","author":"AA Ata","year":"2007","unstructured":"Ata, A.A.: Optimal trajectory planning of manipulators : a review. J. Eng. Sci. Technol. 2(1), 32\u201354 (2007)","journal-title":"J. Eng. Sci. Technol."},{"key":"1822_CR7","doi-asserted-by":"crossref","unstructured":"Wang, T., Wang, W., Wei, F.: An overview of control strategy and trajectory planning of visual servoing. In: Recent Featured Applications of Artificial Intelligence Methods. LSMS 2020 and ICSEE 2020 Workshops, pp. 358\u2013370. Springer (2020)","DOI":"10.1007\/978-981-33-6378-6_27"},{"key":"1822_CR8","doi-asserted-by":"crossref","unstructured":"Gasparetto, A., Boscariol, P., Lanzutti, A., Vidoni, R.: Path planning and trajectory planning algorithms: a general overview. Motion Oper. Plan. Robot. Syst. 3\u201327 (2015)","DOI":"10.1007\/978-3-319-14705-5_1"},{"key":"1822_CR9","doi-asserted-by":"crossref","unstructured":"Guan, Y., Yokoi, K., Stasse, O., Kheddar, A.: On robotic trajectory planning using polynomial interpolations. In: 2005 IEEE International Conference on Robotics and Biomimetics-ROBIO, pp. 111\u2013116. IEEE (2005)","DOI":"10.1109\/ROBIO.2005.246411"},{"key":"1822_CR10","doi-asserted-by":"crossref","unstructured":"Fang, S., Ma, X., Zhao, Y., Zhang, Q., Li, Y.: Trajectory planning for seven-dof robotic arm based on quintic polynormial. In: 2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), vol. 2, pp. 198\u2013201. IEEE (2019)","DOI":"10.1109\/IHMSC.2019.10142"},{"key":"1822_CR11","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1016\/j.mechmachtheory.2019.05.002","volume":"139","author":"H Wang","year":"2019","unstructured":"Wang, H., Wang, H., Huang, J., Zhao, B., Quan, L.: Smooth point-to-point trajectory planning for industrial robots with kinematical constraints based on high-order polynomial curve. Mech. Mach. Theory 139, 284\u2013293 (2019)","journal-title":"Mech. Mach. Theory"},{"key":"1822_CR12","doi-asserted-by":"crossref","unstructured":"Guldner, J.R., Utkin, V.I., Hashimoto H.: Robot obstacle avoidance in n-dimensional space using planar harmonic artificial potential fields (1997)","DOI":"10.1115\/1.2801228"},{"key":"1822_CR13","doi-asserted-by":"crossref","unstructured":"Guernane, R., Belhocine, M.: A smoothing strategy for prm paths application to six-axes motoman sv3x manipulator. In: 2005 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 4155\u20134160. IEEE (2005)","DOI":"10.1109\/IROS.2005.1545308"},{"issue":"5","key":"1822_CR14","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1109\/TCST.2008.2012116","volume":"17","author":"Y Kuwata","year":"2009","unstructured":"Kuwata, Y., Teo, J., Fiore, G., Karaman, S., Frazzoli, E., How, J. P.: Real-time motion planning with applications to autonomous urban driving. IEEE Trans. Control Syst. Technol. 17(5), 1105\u20131118 (2009)","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"1822_CR15","doi-asserted-by":"publisher","first-page":"26059","DOI":"10.1109\/ACCESS.2021.3056397","volume":"9","author":"A Sepehri","year":"2021","unstructured":"Sepehri, A., Moghaddam, A.M.: A motion planning algorithm for redundant manipulators using rapidly exploring randomized trees and artificial potential fields. IEEE Access 9, 26059\u201326070 (2021)","journal-title":"IEEE Access"},{"key":"1822_CR16","doi-asserted-by":"crossref","unstructured":"Qureshi, A.H., Nakamura, Y., Yoshikawa, Y., Ishiguro, H.: Robot gains social intelligence through multimodal deep reinforcement learning. In: 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), pp. 745\u2013751. IEEE (2016)","DOI":"10.1109\/HUMANOIDS.2016.7803357"},{"key":"1822_CR17","doi-asserted-by":"crossref","unstructured":"Kahn, G., Villaflor, A., Ding, B., Abbeel, P., Levine, S.: Self-supervised deep reinforcement learning with generalized computation graphs for robot navigation. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 5129\u20135136. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"1822_CR18","doi-asserted-by":"crossref","unstructured":"Tai, L., Paolo, G., Liu, M.: Virtual-to-real deep reinforcement learning : Continuous control of mobile robots for mapless navigation. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 31\u201336. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202134"},{"key":"1822_CR19","doi-asserted-by":"crossref","unstructured":"Chen, X., Ghadirzadeh, A., Folkesson, J., Bj\u00f6rkman, M., Jensfelt, P.: Deep reinforcement learning to acquire navigation skills for wheel-legged robots in complex environments. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3110\u20133116. IEEE (2018)","DOI":"10.1109\/IROS.2018.8593702"},{"issue":"1","key":"1822_CR20","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/TCDS.2018.2868921","volume":"12","author":"T Zhao","year":"2018","unstructured":"Zhao, T., Deng, M., Li, Z., Hu, Y.: Cooperative manipulation for a mobile dual-arm robot using sequences of dynamic movement primitives. IEEE Trans. Cogn. Dev. Syst. 12(1), 18\u201329 (2018)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"issue":"1","key":"1822_CR21","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s13246-019-00828-4","volume":"43","author":"FN Rahatabad","year":"2020","unstructured":"Rahatabad, F.N., Rangraz, P.: Combination of reinforcement learning and bee algorithm for controlling two-link arm with six muscle: simplified human arm model in the horizontal plane. Phys. Eng. Sci. Med. 43(1), 135\u2013142 (2020)","journal-title":"Phys. Eng. Sci. Med."},{"issue":"12","key":"1822_CR22","doi-asserted-by":"publisher","first-page":"3515","DOI":"10.3390\/s20123515","volume":"20","author":"C Liu","year":"2020","unstructured":"Liu, C., Gao, J., Bi, Y., Shi, X., Tian, D.: A multitasking-oriented robot arm motion planning scheme based on deep reinforcement learning and twin synchro-control. Sensors 20(12), 3515 (2020)","journal-title":"Sensors"},{"key":"1822_CR23","doi-asserted-by":"publisher","first-page":"105657","DOI":"10.1016\/j.ast.2019.105657","volume":"98","author":"Y-H Wu","year":"2020","unstructured":"Wu, Y.-H., Yu, Z.-C., Li, C.-Y., He, M.-J., Hua, B., Chen, Z.-M.: Reinforcement learning in dual-arm trajectory planning for a free-floating space robot. Aerosp. Sci. Technol. 98, 105657 (2020)","journal-title":"Aerosp. Sci. Technol."},{"key":"1822_CR24","doi-asserted-by":"crossref","unstructured":"Chen, S., Yan, D., Zhang, Y., Tan, Y., Wang, W.: Live working manipulator control model based on dppo-dqn combined algorithm. In: 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), vol. 1, pp. 2620\u20132624. IEEE (2019)","DOI":"10.1109\/IAEAC47372.2019.8997839"},{"key":"1822_CR25","doi-asserted-by":"crossref","unstructured":"Rohmer, E., Singh, S.P., Freese, M.: V-rep : a versatile and scalable robot simulation framework. In: 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1321\u20131326. IEEE (2013)","DOI":"10.1109\/IROS.2013.6696520"},{"key":"1822_CR26","doi-asserted-by":"crossref","unstructured":"Freese, M., Singh, S., Ozaki, F., Matsuhira, N.: Virtual robot experimentation platform v-rep : a versatile 3d robot simulator. In: International Conference on Simulation, Modeling, and Programming for Autonomous Robots, pp. 51\u201362. Springer (2010)","DOI":"10.1007\/978-3-642-17319-6_8"},{"key":"1822_CR27","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:1509.02971 (2015)"},{"issue":"7540","key":"1822_CR28","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, A. A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"1822_CR29","doi-asserted-by":"crossref","unstructured":"Hessel, M., Modayil, J., Van Hasselt, H., Schaul, T., Ostrovski, G., Dabney, W., Horgan, D., Piot, B., Azar, M., Silver, D.: Rainbow: combining improvements in deep reinforcement learning. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"1822_CR30","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)"},{"key":"1822_CR31","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"}],"container-title":["Journal of Intelligent &amp; Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-023-01822-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10846-023-01822-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-023-01822-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T03:34:43Z","timestamp":1729136083000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10846-023-01822-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,27]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["1822"],"URL":"https:\/\/doi.org\/10.1007\/s10846-023-01822-5","relation":{},"ISSN":["0921-0296","1573-0409"],"issn-type":[{"value":"0921-0296","type":"print"},{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,27]]},"assertion":[{"value":"2 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Ethics approval"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Consent to participate"}},{"value":"The authors affirm that human research participants provided informed consent for publication of the images in Fig. 1.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Consent for Publication"}},{"value":"All authors disclosed no relevant financial or nonfinancial interests to disclose.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Competing interests"}}],"article-number":"50"}}