{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:32:56Z","timestamp":1773171176580,"version":"3.50.1"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,1,19]],"date-time":"2025-01-19T00:00:00Z","timestamp":1737244800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,19]],"date-time":"2025-01-19T00:00:00Z","timestamp":1737244800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100013061","name":"Jilin Provincial Scientific and Technological Development Program","doi-asserted-by":"publisher","award":["2020040101144GX"],"award-info":[{"award-number":["2020040101144GX"]}],"id":[{"id":"10.13039\/501100013061","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Intell Robot Appl"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s41315-024-00413-3","type":"journal-article","created":{"date-parts":[[2025,1,19]],"date-time":"2025-01-19T15:42:27Z","timestamp":1737301347000},"page":"721-740","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Deep reinforcement learning with hindsight experience replay for dual-arm robot trajectory planning"],"prefix":"10.1007","volume":"9","author":[{"given":"Shoutao","family":"Li","sequence":"first","affiliation":[]},{"given":"Zhanggen","family":"Chu","sequence":"additional","affiliation":[]},{"given":"Zhidong","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Zhenze","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,19]]},"reference":[{"issue":"1","key":"413_CR7","doi-asserted-by":"publisher","first-page":"04022046","DOI":"10.1061\/(ASCE)CP.1943-5487.0001056","volume":"37","author":"J Cai","year":"2023","unstructured":"Cai, J., Du, A., Liang, X., Li, S.: Prediction-based path planning for safe and efficient human-robot collaboration in construction via deep reinforcement learning. J. Comput. Civ. Eng. 37(1), 04022046 (2023)","journal-title":"J. Comput. Civ. Eng."},{"key":"413_CR4","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.neucom.2022.05.006","volume":"497","author":"P Chen","year":"2022","unstructured":"Chen, P., Pei, J., Lu, W., Li, M.: A deep reinforcement learning based method for real-time path planning and dynamic obstacle avoidance. Neurocomputing 497, 64\u201375 (2022)","journal-title":"Neurocomputing"},{"key":"413_CR18","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 (2018). PMLR"},{"issue":"2","key":"413_CR14","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/LRA.2019.2893400","volume":"4","author":"YJ Heo","year":"2019","unstructured":"Heo, Y.J., Kim, D., Lee, W., Kim, H., Park, J., Chung, W.K.: Collision detection for industrial collaborative robots: a deep learning approach. IEEE Robot Automat Lett 4(2), 740\u2013746 (2019)","journal-title":"IEEE Robot Automat Lett"},{"issue":"1","key":"413_CR16","first-page":"5169460","volume":"2021","author":"P Li","year":"2021","unstructured":"Li, P., Ding, X., Sun, H., Zhao, S., Cajo, R.: Research on dynamic path planning of mobile robot based on improved ddpg algorithm. Mob. Inf. Syst. 2021(1), 5169460 (2021)","journal-title":"Mob. Inf. Syst."},{"key":"413_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117191","volume":"199","author":"ES Low","year":"2022","unstructured":"Low, E.S., Ong, P., Low, C.Y., Omar, R.: Modified q-learning with distance metric and virtual target on path planning of mobile robot. Expert Syst. Appl. 199, 117191 (2022)","journal-title":"Expert Syst. Appl."},{"issue":"9","key":"413_CR2","doi-asserted-by":"publisher","first-page":"3826","DOI":"10.1109\/TCYB.2020.2977374","volume":"50","author":"TT Nguyen","year":"2020","unstructured":"Nguyen, T.T., Nguyen, N.D., Nahavandi, S.: Deep reinforcement learning for multiagent systems: a review of challenges, solutions, and applications. IEEE Trans Cybern 50(9), 3826\u20133839 (2020)","journal-title":"IEEE Trans Cybern"},{"issue":"6","key":"413_CR10","doi-asserted-by":"publisher","first-page":"3566","DOI":"10.1109\/TSMC.2022.3228901","volume":"53","author":"G Peng","year":"2022","unstructured":"Peng, G., Yang, J., Li, X., Khyam, M.O.: Deep reinforcement learning with a stage incentive mechanism of dense reward for robotic trajectory planning. IEEE Trans Syst Man Cybern Syst 53(6), 3566\u20133573 (2022)","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"20","key":"413_CR13","doi-asserted-by":"publisher","first-page":"5911","DOI":"10.3390\/s20205911","volume":"20","author":"E Prianto","year":"2020","unstructured":"Prianto, E., Kim, M., Park, J.-H., Bae, J.-H., Kim, J.-S.: Path planning for multi-arm manipulators using deep reinforcement learning: soft actor-critic with hindsight experience replay. Sensors 20(20), 5911 (2020)","journal-title":"Sensors"},{"key":"413_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.robot.2015.02.007","volume":"68","author":"AH Qureshi","year":"2015","unstructured":"Qureshi, A.H., Ayaz, Y.: Intelligent bidirectional rapidly-exploring random trees for optimal motion planning in complex cluttered environments. Robot. Auton. Syst. 68, 1\u201311 (2015)","journal-title":"Robot. Auton. Syst."},{"key":"413_CR8","doi-asserted-by":"crossref","unstructured":"Sangiovanni, B., Rendiniello, A., Incremona, G.P., Ferrara, A., Piastra, M.: Deep reinforcement learning for collision avoidance of robotic manipulators. In: 2018 European Control Conference (ECC), pp. 2063\u20132068 (2018). IEEE","DOI":"10.23919\/ECC.2018.8550363"},{"key":"413_CR12","doi-asserted-by":"crossref","unstructured":"Shahid, A.A., Roveda, L., Piga, D., Braghin, F.: Learning continuous control actions for robotic grasping with reinforcement learning. In: 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 4066\u20134072 (2020). IEEE","DOI":"10.1109\/SMC42975.2020.9282951"},{"issue":"4","key":"413_CR11","doi-asserted-by":"publisher","first-page":"564","DOI":"10.3390\/mi13040564","volume":"13","author":"W Tang","year":"2022","unstructured":"Tang, W., Cheng, C., Ai, H., Chen, L.: Dual-arm robot trajectory planning based on deep reinforcement learning under complex environment. Micromachines 13(4), 564 (2022)","journal-title":"Micromachines"},{"key":"413_CR15","doi-asserted-by":"crossref","unstructured":"Tu, C., Yu, L.: Research on collision detection algorithm based on aabb-obb bounding volume. In: 2009 First International Workshop on Education Technology and Computer Science, 1, 331\u2013333 (2009). IEEE","DOI":"10.1109\/ETCS.2009.82"},{"issue":"3","key":"413_CR19","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1109\/TCYB.2020.2990722","volume":"52","author":"LF Vecchietti","year":"2020","unstructured":"Vecchietti, L.F., Seo, M., Har, D.: Sampling rate decay in hindsight experience replay for robot control. IEEE Trans Cybern 52(3), 1515\u20131526 (2020)","journal-title":"IEEE Trans Cybern"},{"key":"413_CR17","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/j.neucom.2020.05.089","volume":"411","author":"S Xie","year":"2020","unstructured":"Xie, S., Chu, X., Zheng, M., Liu, C.: A composite learning method for multi-ship collision avoidance based on reinforcement learning and inverse control. Neurocomputing 411, 375\u2013392 (2020)","journal-title":"Neurocomputing"},{"issue":"13","key":"413_CR6","doi-asserted-by":"publisher","first-page":"5974","DOI":"10.3390\/s23135974","volume":"23","author":"S Zhang","year":"2023","unstructured":"Zhang, S., Xia, Q., Chen, M., Cheng, S.: Multi-objective optimal trajectory planning for robotic arms using deep reinforcement learning. Sensors 23(13), 5974 (2023)","journal-title":"Sensors"},{"issue":"20","key":"413_CR9","doi-asserted-by":"publisher","first-page":"4392","DOI":"10.3390\/math11204392","volume":"11","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Yang, F., Jin, Q., Lou, P., Hu, J.: Path planning algorithm for dual-arm robot based on depth deterministic gradient strategy algorithm. Mathematics 11(20), 4392 (2023)","journal-title":"Mathematics"},{"key":"413_CR5","unstructured":"Zheng, Q., Peng, Z., Zhu, P., Zhao, Y., Ma, W.: Robotic arm trajectory tracking method based on improved proximal policy optimization. Proceedings of the Romanian Academy, Series A: Mathematics, Physics, Technical Sciences, Information Science 24(3), (2023)"}],"container-title":["International Journal of Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41315-024-00413-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41315-024-00413-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41315-024-00413-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T08:37:25Z","timestamp":1750322245000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41315-024-00413-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,19]]},"references-count":19,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["413"],"URL":"https:\/\/doi.org\/10.1007\/s41315-024-00413-3","relation":{},"ISSN":["2366-5971","2366-598X"],"issn-type":[{"value":"2366-5971","type":"print"},{"value":"2366-598X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,19]]},"assertion":[{"value":"14 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}