{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:44:56Z","timestamp":1782848696243,"version":"3.54.5"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100015401","name":"Key Research and Development Projects of Shaanxi Province","doi-asserted-by":"publisher","award":["No.2023-ZDLNY-48"],"award-info":[{"award-number":["No.2023-ZDLNY-48"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Intel Serv Robotics"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s11370-025-00620-2","type":"journal-article","created":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T13:07:42Z","timestamp":1749560862000},"page":"857-874","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Path planning in dynamic structured environments using transformer-enabled twin delayed deep deterministic policy gradient for mobile robots in simulation"],"prefix":"10.1007","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5497-9701","authenticated-orcid":false,"given":"Jianghong","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yumei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6358-1840","authenticated-orcid":false,"given":"Qieshi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,10]]},"reference":[{"issue":"9","key":"620_CR1","doi-asserted-by":"publisher","first-page":"1695","DOI":"10.1007\/s12541-023-00876-7","volume":"24","author":"N Sharma","year":"2023","unstructured":"Sharma N, Pandey JK, Mondal S (2023) A review of mobile robots: applications and future prospect. Int J Precis Eng Manuf 24(9):1695\u20131706","journal-title":"Int J Precis Eng Manuf"},{"key":"620_CR2","doi-asserted-by":"crossref","unstructured":"Wang H, Shi Z, Li C, Wang F (2023) Comparison and implementation of ROS-based SLAM and path planning methods. In: International Conference on Artificial Intelligence Logic and Applications. Springer. pp 162\u2013175.","DOI":"10.1007\/978-981-99-7869-4_13"},{"key":"620_CR3","first-page":"5983","volume":"70","author":"B Ma","year":"2023","unstructured":"Ma B, Liu Z, Dang Q, Zhao W, Wang J, Cheng Y, Yuan Z (2023) Deep reinforcement learning of UAV tracking control under wind disturbances environments. IEEE Trans Instrum Meas 70:5983\u20136000","journal-title":"IEEE Trans Instrum Meas"},{"key":"620_CR4","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, Graves A et al (2015) Human-level control through deep reinforcement learning. Nature 518:529\u2013533","journal-title":"Nature"},{"key":"620_CR5","unstructured":"Hasselt H. van, Guez A, Silver D (2015) Deep reinforcement learning with double Q-learning. arXiv preprint arXiv:1509.06461."},{"key":"620_CR6","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 preprint arXiv:1509.02971."},{"key":"620_CR7","unstructured":"Fujimoto S, Hoof H. van, Meger D (2018) Addressing function approximation error in actor-critic methods. In: Proceedings of the 35th International Conference on Machine Learning, PMLR, pp 1587\u20131596."},{"issue":"12","key":"620_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/s23125622","volume":"23","author":"H Han","year":"2023","unstructured":"Han H, Wang J, Kuang L, Han X, Xue H (2023) Improved robot path planning method based on deep reinforcement learning. Sensors 23(12):1\u201323","journal-title":"Sensors"},{"issue":"3","key":"620_CR9","doi-asserted-by":"publisher","first-page":"6932","DOI":"10.1109\/LRA.2020.3026638","volume":"5","author":"B Wang","year":"2020","unstructured":"Wang B, Liu Z, Li Q, Prorok A (2020) Mobile robot path planning in dynamic environments through globally guided reinforcement learning. IEEE Robot Automation Lett 5(3):6932\u20136939","journal-title":"IEEE Robot Automation Lett"},{"issue":"11","key":"620_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.heliyon.2024.e32167","volume":"10","author":"P Li","year":"2024","unstructured":"Li P, Chen D, Wang Y, Zhang L, Zhao S (2024) Path planning of mobile robot based on improved TD3 algorithm in dynamic environment. Heliyon 10(11):1\u201321","journal-title":"Heliyon"},{"issue":"3","key":"620_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/electronics9030411","volume":"9","author":"R Cimurs","year":"2020","unstructured":"Cimurs R, Lee JH, Suh IH (2020) Goal-Oriented obstacle avoidance with deep reinforcement learning in continuous action space. Electronics 9(3):1\u201316","journal-title":"Electronics"},{"issue":"4","key":"620_CR12","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/JAS.2019.1911732","volume":"7","author":"L Jiang","year":"2019","unstructured":"Jiang L, Huang H, Ding Z (2019) Path planning for intelligent robots based on deep Q-learning with experience replay and heuristic knowledge. IEEE\/CAA J Automatica Sinica 7(4):1179\u20131189","journal-title":"IEEE\/CAA J Automatica Sinica"},{"key":"620_CR13","unstructured":"Dulac-Arnold G, Mankowitz DJ, Hester T (2019) Challenges of real-world reinforcement learning: definitions, benchmarks and analysis. In: Proceedings of the 36th International Conference on Machine Learning, pp 1\u201316."},{"key":"620_CR14","doi-asserted-by":"crossref","unstructured":"Jiayao J, Xing X, Chang DE (2022) GRU-Attention based TD3 network for mobile robot navigation. In: The 22nd International Conference on Control, Automation and Systems.","DOI":"10.23919\/ICCAS55662.2022.10003950"},{"issue":"9","key":"620_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/s22093579","volume":"22","author":"H Gong","year":"2022","unstructured":"Gong H, Wang P, Ni C, Cheng N (2022) Efficient path planning for mobile robot based on deep deterministic policy gradient. Sensors 22(9):1\u201320","journal-title":"Sensors"},{"key":"620_CR16","unstructured":"Parisotto E, Song F, Rae J, Pascanu R, Gulcehre C et al (2020) Stabilizing transformers for reinforcement learning. In: Proceedings of the 37th International Conference on Machine Learning, pp 7487\u20137498."},{"key":"620_CR17","unstructured":"Li W, Luo H, Lin Z, Zhang C, Lu Z, Ye D (2023) A survey on transformers in reinforcement learning. arXiv preprint arXiv:2301.03044."},{"key":"620_CR18","doi-asserted-by":"crossref","unstructured":"Tai L, Paolo G, Liu M (2017) Virtual-to-real deep reinforcement learning: continuous control of mobile robots for mapless navigation. In: Proceedings of the 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp 6140\u20136147.","DOI":"10.1109\/IROS.2017.8202134"},{"issue":"2","key":"620_CR19","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1109\/LRA.2021.3133591","volume":"7","author":"R Cimurs","year":"2022","unstructured":"Cimurs R, Suh IH, Lee JH (2022) Goal-driven autonomous exploration through deep reinforcement learning. IEEE Robot Automation Lett 7(2):730\u2013737","journal-title":"IEEE Robot Automation Lett"},{"key":"620_CR20","doi-asserted-by":"crossref","unstructured":"Gao Y, Ellis CA, Calhoun VD, Miller RL (2023) Improving age prediction: Utilizing LSTM-based dynamic forecasting for data augmentation in multivariate time series analysis. arXiv preprint arXiv:2312.08383.","DOI":"10.1109\/SSIAI59505.2024.10508611"},{"key":"620_CR21","doi-asserted-by":"crossref","unstructured":"Meng L, Gorbet R, Kuli\u0107 D (2021) Memory-based deep reinforcement learning for POMDPs. In: Proceedings of the 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems. pp 5619\u20135626.","DOI":"10.1109\/IROS51168.2021.9636140"},{"issue":"18","key":"620_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/app131810056","volume":"13","author":"H Hu","year":"2023","unstructured":"Hu H, Wang Y, Tong W, Zhao J, Gu Y (2023) Path planning for autonomous vehicles in unknown dynamic environment based on deep reinforcement learning. Appl Sci 13(18):1\u201321","journal-title":"Appl Sci"},{"key":"620_CR23","first-page":"1","volume":"2021","author":"N Guo","year":"2021","unstructured":"Guo N, Li C, Gao T, Liu G, Li Y, Wang D (2021) A fusion method of local path planning for mobile robots based on LSTM neural network and reinforcement learning. Math Probl Eng 2021:1\u201321","journal-title":"Math Probl Eng"},{"key":"620_CR24","doi-asserted-by":"publisher","first-page":"15140","DOI":"10.1109\/ACCESS.2019.2894626","volume":"7","author":"J Yuan","year":"2019","unstructured":"Yuan J, Wang H, Lin C, Liu D, Yu D (2019) A novel GRU-RNN network model for dynamic path planning of mobile robot. IEEE Access 7:15140\u201315151","journal-title":"IEEE Access"},{"issue":"2","key":"620_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/s24020700","volume":"24","author":"Q Gao","year":"2024","unstructured":"Gao Q, Chang F, Yang J, Tao Y, Ma L, Su H (2024) Deep reinforcement learning for autonomous driving with an auxiliary actor discriminator. Sensors 24(2):1\u201317","journal-title":"Sensors"},{"key":"620_CR26","unstructured":"Esslinger K, Platt R, Amato C (2022) Deep transformer Q-networks for partially observable reinforcement learning, arXiv preprint arXiv:2206.01078."},{"key":"620_CR27","unstructured":"Janner M, Li Q, Levine S (2021) Offline reinforcement learning as one big sequence modeling problem. In: Advances in Neural Information Processing Systems 34."},{"key":"620_CR28","unstructured":"Chen L, Lu K, Rajeswaran A, Lee K, Grover A, Laskin M, Abbeel P, Srinivas A, Mordatch I (2021) Decision transformer: reinforcement learning via sequence modeling. In: Advances in Neural Information Processing Systems 34."},{"key":"620_CR29","unstructured":"Chebotar Y, Vuong Q, Hausman K et al. (2023) Q-transformer: scalable offline reinforcement learning via autoregressive Q-functions. In: Proceedings of the 7th Conference on Robot Learning, pp 3909\u20133928."},{"key":"620_CR30","unstructured":"Wang K, Zhao H, Luo X, Ren K, Zhang W, Li D (2022) Bootstrapped transformer for offline reinforcement learning. In: Advances in Neural Information Processing Systems 35."},{"issue":"2","key":"620_CR31","first-page":"1100","volume":"25","author":"W Huang","year":"2023","unstructured":"Huang W, Zhou Y, He X, Lv C (2023) Goal-guided transformer-enabled reinforcement learning for efficient autonomous navigation. IEEE Trans Intell Transp Syst 25(2):1100\u20131119","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"620_CR32","doi-asserted-by":"crossref","unstructured":"Xu Y, Chen L, Fang M (2020) Deep reinforcement learning with transformers for text adventure games. In: 2020 IEEE Conference on Games, pp 65\u201372.","DOI":"10.1109\/CoG47356.2020.9231622"},{"key":"620_CR33","doi-asserted-by":"crossref","unstructured":"Lei X, Zhang Z, Dong P (2018) Dynamic path planning of unknown environment based on deep reinforcement learning. J Robot. pp 1\u201310.","DOI":"10.1155\/2018\/5781591"},{"issue":"9","key":"620_CR34","first-page":"1310","volume":"26","author":"X Lei","year":"2011","unstructured":"Lei X, Liu M, Yan M, Li W (2011) Tabu search based autonomous navigation algorithm for mobile robot. Control Decis 26(9):1310\u20131314","journal-title":"Control Decis"},{"key":"620_CR35","unstructured":"Zhang X, Yan M, Liu Y, Ju Y (2010) Autonomous navigation for mobile robot based on Tabu search in unknown environment. In: Proceedings of the 29th Chinese Control Conference, pp 3625:3630."}],"container-title":["Intelligent Service Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-025-00620-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11370-025-00620-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-025-00620-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T19:06:28Z","timestamp":1757185588000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11370-025-00620-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,10]]},"references-count":35,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["620"],"URL":"https:\/\/doi.org\/10.1007\/s11370-025-00620-2","relation":{},"ISSN":["1861-2776","1861-2784"],"issn-type":[{"value":"1861-2776","type":"print"},{"value":"1861-2784","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,10]]},"assertion":[{"value":"27 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}