{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:44:38Z","timestamp":1766580278322,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T00:00:00Z","timestamp":1704499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T00:00:00Z","timestamp":1704499200000},"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":["62173224"],"award-info":[{"award-number":["62173224"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61833012"],"award-info":[{"award-number":["61833012"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s00034-023-02581-2","type":"journal-article","created":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T19:02:05Z","timestamp":1704567725000},"page":"2585-2607","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Dual-Layer Network Deep Reinforcement Learning Algorithm for Multi-objective Signal Temporal Logic Tasks"],"prefix":"10.1007","volume":"43","author":[{"given":"Yixiao","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiange","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8995-020X","authenticated-orcid":false,"given":"Yuanyuan","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaru","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,6]]},"reference":[{"key":"2581_CR1","doi-asserted-by":"publisher","unstructured":"D.\u00a0Aksaray, A.\u00a0Jones, Z.\u00a0Kong, M.\u00a0Schwager, C.\u00a0Belta, Q-learning for robust satisfaction of signal temporal logic specifications, in 2016 55th IEEE Conference on Decision and Control (2016), pp.\u00a06565\u20136570. https:\/\/doi.org\/10.1109\/CDC.2016.7799279","DOI":"10.1109\/CDC.2016.7799279"},{"issue":"6","key":"2581_CR2","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","volume":"34","author":"K Arulkumaran","year":"2017","unstructured":"K. Arulkumaran, M.P. Deisenroth, M. Brundage, A.A. Bharath, Deep reinforcement learning: a brief survey. IEEE Signal Process. Mag. 34(6), 26\u201338 (2017). https:\/\/doi.org\/10.1109\/MSP.2017.2743240","journal-title":"IEEE Signal Process. Mag."},{"key":"2581_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-023-02366-7","author":"A Bali","year":"2023","unstructured":"A. Bali, S.S. Chouhan, G. Kumar, R. Kumar, U.P. Singh, Adaptive fault-tolerant control for pure-feedback stochastic nonlinear systems with sensor and actuator faults. Circuits Syst. Signal Process. (2023). https:\/\/doi.org\/10.1007\/s00034-023-02366-7","journal-title":"Circuits Syst. Signal Process."},{"key":"2581_CR4","doi-asserted-by":"publisher","unstructured":"C.\u00a0Belta, Formal methods for dynamical systems, in 2014 21st International Symposium on Temporal Representation and Reasoning (2014), pp. 3\u20133. https:\/\/doi.org\/10.1109\/TIME.2014.16","DOI":"10.1109\/TIME.2014.16"},{"issue":"2","key":"2581_CR5","first-page":"63","volume":"36","author":"R Carelli","year":"2006","unstructured":"R. Carelli, C. De la Cruz, F. Roberti, Centralized formation control of non-holonomic mobile robots. Lat. Am. Appl. Res. 36(2), 63\u201369 (2006)","journal-title":"Lat. Am. Appl. Res."},{"key":"2581_CR6","doi-asserted-by":"publisher","unstructured":"W.\u00a0Chun-Fu, W.\u00a0Xiao-Long, C.\u00a0Qing-Xie, C.\u00a0Xiao-Wei, L.\u00a0Guo-Dong, Research on visual navigation algorithm of AGV used in the small agile warehouse, in 2017 Chinese Automation Congress (CAC)(2017), pp. 217\u2013222. https:\/\/doi.org\/10.1109\/CAC.2017.8242766","DOI":"10.1109\/CAC.2017.8242766"},{"key":"2581_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2021.110477","volume":"246","author":"B Du","year":"2022","unstructured":"B. Du, B. Lin, C. Zhang, B. Dong, W. Zhang, Safe deep reinforcement learning-based adaptive control for USV interception mission. Ocean Eng. 246, 110477 (2022). https:\/\/doi.org\/10.1016\/j.oceaneng.2021.110477","journal-title":"Ocean Eng."},{"issue":"3","key":"2581_CR8","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/0034-4877(71)90002-4","volume":"2","author":"S Guia\u015fu","year":"1971","unstructured":"S. Guia\u015fu, Weighted entropy. Rep. Math. Phys. 2(3), 165\u2013179 (1971). https:\/\/doi.org\/10.1016\/0034-4877(71)90002-4","journal-title":"Rep. Math. Phys."},{"issue":"2","key":"2581_CR9","doi-asserted-by":"publisher","first-page":"3687","DOI":"10.1109\/LRA.2021.3064220","volume":"6","author":"D Gundana","year":"2021","unstructured":"D. Gundana, H. Kress-Gazit, Event-based signal temporal logic synthesis for single and multi-robot tasks. IEEE Robot. Autom. Lett. 6(2), 3687\u20133694 (2021). https:\/\/doi.org\/10.1109\/LRA.2021.3064220","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"2","key":"2581_CR10","doi-asserted-by":"publisher","first-page":"5246","DOI":"10.1109\/LRA.2022.3155197","volume":"7","author":"W Hashimoto","year":"2022","unstructured":"W. Hashimoto, K. Hashimoto, S. Takai, Stl2vec: signal temporal logic embeddings for control synthesis with recurrent neural networks. IEEE Robot. Autom. Lett. 7(2), 5246\u20135253 (2022). https:\/\/doi.org\/10.1109\/LRA.2022.3155197","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2581_CR11","doi-asserted-by":"publisher","first-page":"114814","DOI":"10.1109\/ACCESS.2022.3218216","volume":"10","author":"J Ikemoto","year":"2022","unstructured":"J. Ikemoto, T. Ushio, Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxation. IEEE Access 10, 114814\u2013114828 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3218216","journal-title":"IEEE Access"},{"key":"2581_CR12","unstructured":"P. Khanan, Advancements in reinforcement learning: from theory to real-world applications. Int. J. Sustain. Dev. Comput. Sci. 5(1) (2023)"},{"issue":"4","key":"2581_CR13","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/BF01995674","volume":"2","author":"R Koymans","year":"1990","unstructured":"R. Koymans, Specifying real-time properties with metric temporal logic. Real-Time Syst. 2(4), 255\u2013299 (1990). https:\/\/doi.org\/10.1007\/BF01995674","journal-title":"Real-Time Syst."},{"key":"2581_CR14","doi-asserted-by":"publisher","first-page":"2635","DOI":"10.1109\/LCSYS.2022.3172857","volume":"6","author":"V Kurtz","year":"2022","unstructured":"V. Kurtz, H. Lin, Mixed-integer programming for signal temporal logic with fewer binary variables. IEEE Control Syst. Lett. 6, 2635\u20132640 (2022). https:\/\/doi.org\/10.1109\/LCSYS.2022.3172857","journal-title":"IEEE Control Syst. Lett."},{"key":"2581_CR15","volume":"20","author":"M Li","year":"2023","unstructured":"M. Li, H. Liu, M. Yan, J. Wu, L. Jin, H. He, Data-driven bi-level predictive energy management strategy for fuel cell buses with algorithmics fusion. Energy Convers. Manage: X 20, 100414 (2023)","journal-title":"Energy Convers. Manage: X"},{"issue":"3","key":"2581_CR16","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1109\/LCSYS.2019.2917975","volume":"3","author":"L Lindemann","year":"2019","unstructured":"L. Lindemann, D.V. Dimarogonas, Control barrier functions for multi-agent systems under conflicting local signal temporal logic tasks. IEEE Control Syst. Lett. 3(3), 757\u2013762 (2019). https:\/\/doi.org\/10.1109\/LCSYS.2019.2917975","journal-title":"IEEE Control Syst. Lett."},{"key":"2581_CR17","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1109\/LCSYS.2021.3049917","volume":"6","author":"W Liu","year":"2022","unstructured":"W. Liu, N. Mehdipour, C. Belta, Recurrent neural network controllers for signal temporal logic specifications subject to safety constraints. IEEE Control Syst. Lett. 6, 91\u201396 (2022). https:\/\/doi.org\/10.1109\/LCSYS.2021.3049917","journal-title":"IEEE Control Syst. Lett."},{"key":"2581_CR18","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1007\/s00034-021-01802-w","volume":"41","author":"Y Liu","year":"2022","unstructured":"Y. Liu, Q. Zhu, Event-triggered adaptive fuzzy tracking control for uncertain nonlinear systems with time-delay and state constraints. Circuits Syst. Signal Process. 41, 636\u2013660 (2022). https:\/\/doi.org\/10.1007\/s00034-021-01802-w","journal-title":"Circuits Syst. Signal Process."},{"key":"2581_CR19","doi-asserted-by":"publisher","unstructured":"O.\u00a0Maler, D.\u00a0Nickovic, Monitoring temporal properties of continuous signals, in Formal Techniques, Modelling and Analysis of Timed and Fault-Tolerant Systems(2004), pp. 152\u2013166. https:\/\/doi.org\/10.1007\/978-3-540-30206-3_12","DOI":"10.1007\/978-3-540-30206-3_12"},{"issue":"2","key":"2581_CR20","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1109\/LRA.2019.2891991","volume":"4","author":"F Niroui","year":"2019","unstructured":"F. Niroui, K. Zhang, Z. Kashino, G. Nejat, Deep reinforcement learning robot for search and rescue applications: exploration in unknown cluttered environments. IEEE Robot. Autom. Lett. 4(2), 610\u2013617 (2019). https:\/\/doi.org\/10.1109\/LRA.2019.2891991","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"8","key":"2581_CR21","doi-asserted-by":"publisher","first-page":"3406","DOI":"10.1007\/s00034-019-01157-3","volume":"38","author":"T Ogunfunmi","year":"2019","unstructured":"T. Ogunfunmi, R.P. Ramachandran, R. Togneri, Y. Zhao, X. Xia, A primer on deep learning architectures and applications in speech processing. Circuits Syst. Signal Process. 38(8), 3406\u20133432 (2019). https:\/\/doi.org\/10.1007\/s00034-019-01157-3","journal-title":"Circuits Syst. Signal Process."},{"key":"2581_CR22","unstructured":"A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., Pytorch: An imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"2581_CR23","doi-asserted-by":"publisher","unstructured":"A.\u00a0Pnueli, The temporal logic of programs, in 1977 18th Annual Symposium on Foundations of Computer Science (1977), pp. 46\u201357. https:\/\/doi.org\/10.1109\/SFCS.1977.32","DOI":"10.1109\/SFCS.1977.32"},{"issue":"6","key":"2581_CR24","doi-asserted-by":"publisher","first-page":"3340","DOI":"10.1109\/TRO.2022.3173711","volume":"38","author":"A Romero","year":"2022","unstructured":"A. Romero, S. Sun, P. Foehn, D. Scaramuzza, Model predictive contouring control for time-optimal quadrotor flight. IEEE Trans. Rob. 38(6), 3340\u20133356 (2022). https:\/\/doi.org\/10.1109\/TRO.2022.3173711","journal-title":"IEEE Trans. Rob."},{"issue":"1","key":"2581_CR25","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/s10458-022-09586-2","volume":"37","author":"BJ Smith","year":"2023","unstructured":"B.J. Smith, R. Klassert, R. Pihlakas, Using soft maximin for risk averse multi-objective decision-making. Auton. Agent. Multi-agent Syst. 37(1), 11 (2023). https:\/\/doi.org\/10.1007\/s10458-022-09586-2","journal-title":"Auton. Agent. Multi-agent Syst."},{"key":"2581_CR26","unstructured":"H.\u00a0Venkataraman, D.\u00a0Aksaray, P.\u00a0Seiler, Tractable reinforcement learning of signal temporal logic objectives, in Learning for Dynamics and Control (2020), pp. 308\u2013317"},{"issue":"1","key":"2581_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-021-10118-9","volume":"55","author":"D Wang","year":"2022","unstructured":"D. Wang, M. Ha, M. Zhao, The intelligent critic framework for advanced optimal control. Artif. Intell. Rev. 55(1), 1\u201322 (2022). https:\/\/doi.org\/10.1007\/s10462-021-10118-9","journal-title":"Artif. Intell. Rev."},{"issue":"3","key":"2581_CR28","doi-asserted-by":"publisher","first-page":"2330","DOI":"10.1109\/JIOT.2021.3094465","volume":"9","author":"B Zhao","year":"2021","unstructured":"B. Zhao, X. Zhao, Deep reinforcement learning resource allocation in wireless sensor networks with energy harvesting and relay. IEEE Internet Things J. 9(3), 2330\u20132345 (2021)","journal-title":"IEEE Internet Things J."},{"issue":"5","key":"2581_CR29","doi-asserted-by":"publisher","first-page":"674","DOI":"10.26599\/TST.2021.9010012","volume":"26","author":"K Zhu","year":"2021","unstructured":"K. Zhu, T. Zhang, Deep reinforcement learning based mobile robot navigation: a review. Tsinghua Sci. Technol. 26(5), 674\u2013691 (2021). https:\/\/doi.org\/10.26599\/TST.2021.9010012","journal-title":"Tsinghua Sci. Technol."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-023-02581-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-023-02581-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-023-02581-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,27]],"date-time":"2024-02-27T12:16:49Z","timestamp":1709036209000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-023-02581-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,6]]},"references-count":29,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["2581"],"URL":"https:\/\/doi.org\/10.1007\/s00034-023-02581-2","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2024,1,6]]},"assertion":[{"value":"13 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2024","order":4,"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 that there is no conflict of interest or competing interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}