{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T00:42:03Z","timestamp":1775090523479,"version":"3.50.1"},"reference-count":41,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T00:00:00Z","timestamp":1739750400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Humanities and Social Sciences Fund of the Ministry of Education","award":["20YJCZH225"],"award-info":[{"award-number":["20YJCZH225"]}]},{"name":"Humanities and Social Sciences Fund of the Ministry of Education","award":["23YJC630109"],"award-info":[{"award-number":["23YJC630109"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>Emergency logistics is essential for rapid and efficient disaster response, ensuring the timely availability and deployment of resources to affected areas. In the process of rescue work, the dynamic changes in rescue point information greatly increase the difficulty of rescue. This paper establishes a combined neural network model considering soft time-window penalty and applies deep reinforcement learning (DRL) to address the dynamic routing problem in emergency logistics. This method utilizes the actor\u2013critic framework, combined with attention mechanisms, pointer networks, and long short-term memory neural networks, to determine effective disaster relief path, and it compares the obtained scheduling scheme with the results obtained from the DRL algorithm based on the single-network model and ant colony optimization (ACO) algorithm. Simulation experiments show that the proposed method reduces the solution accuracy by nearly 10% compared to the ACO algorithm, but it saves nearly 80% in solution time. Additionally, it slightly increases solution times but improves accuracy by nearly 20% over traditional DRL approaches, demonstrating a promising balance between performance efficiency and computational resource utilization in emergency logistics.<\/jats:p>","DOI":"10.3390\/systems13020127","type":"journal-article","created":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T07:48:22Z","timestamp":1739778502000},"page":"127","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Advancing Dynamic Emergency Route Optimization with a Composite Network Deep Reinforcement Learning Model"],"prefix":"10.3390","volume":"13","author":[{"given":"Jin","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Transport & Communications, Shanghai Maritime University, Shanghai 201306, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Transport & Communications, Shanghai Maritime University, Shanghai 201306, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ding","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Transport & Communications, Shanghai Maritime University, Shanghai 201306, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Transportation Engineering, Tongji University, Shanghai 200092, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,2,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1111\/j.1467-7717.1984.tb00853.x","article-title":"Lessons in logistics from Somalia","volume":"08","author":"Stephenson","year":"1984","journal-title":"Disasters"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kundu, T., Sheu, J., and Kuo, H. (2022). Emergency logistics management\u2014Review and propositions for future research. Transp. Res. Part E Logist. Transp. Rev., 164.","DOI":"10.1016\/j.tre.2022.102789"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Bola\u00f1os, C., Rojas, B., Salazar-Cabrera, R., Ram\u00edrez-Gonz\u00e1lez, G., de la Cruz, \u00c1.P., and Molina, J.M.M. (2022). Fleet management and control system for developing countries implemented with Intelligent Transportation Systems (ITS) services. Transp. Res. Interdiscip. Perspect., 16.","DOI":"10.1016\/j.trip.2022.100694"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.rcim.2012.04.012","article-title":"A bottleneck Steiner tree based multi-objective location model and intelligent optimization of emergency logistics systems","volume":"29","author":"Zhang","year":"2013","journal-title":"Robot. Comput. -Integr. Manuf."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ju, X., Su, S., Xu, C., and Wang, H. (2023). Computation offloading and tasks scheduling for the internet of vehicles in edge computing: A deep reinforcement learning-based pointer network approach. Comput. Netw., 223.","DOI":"10.1016\/j.comnet.2023.109572"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Chung, S.H. (2021). Applications of smart technologies in logistics and transport: A review. Transp. Res. Part E Logist. Transp. Rev., 153.","DOI":"10.1016\/j.tre.2021.102455"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1016\/j.asoc.2018.07.050","article-title":"Routing optimization of emergency grain distribution vehicles using the immune ant colony optimization algorithm","volume":"71","author":"Zhang","year":"2018","journal-title":"Appl. Soft Comput."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Peng, W., Wang, D., Yin, Y., and Cheng, T.C.E. (2025). Multi-agent deep reinforcement learning-based truck-drone collaborative routing with dynamic emergency response. Transp. Res. Part E Logist. Transp. Rev., 195.","DOI":"10.1016\/j.tre.2025.103974"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.cie.2015.12.007","article-title":"The vehicle routing problem: State of the art classification and review","volume":"99","author":"Braekers","year":"2016","journal-title":"Comput. Ind. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.tre.2009.07.005","article-title":"Dynamic relief-demand management for emergency logistics operations under large-scale disasters","volume":"46","author":"Sheu","year":"2010","journal-title":"Transp. Res. Part E Logist. Transp. Rev."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ejor.2012.08.015","article-title":"A review of dynamic vehicle routing problems","volume":"225","author":"Pillac","year":"2013","journal-title":"Eur. J. Oper. Res."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Miller, R.E., and Thatcher, J.W. (1972). Reducibility among combinatorial problems. Complexity of Computer Computations, Plenum Press.","DOI":"10.1007\/978-1-4684-2001-2"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1002\/net.3230110211","article-title":"Complexity of vehicle routing and scheduling problems","volume":"11","author":"Lenstra","year":"1981","journal-title":"Networks"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1287\/mnsc.6.1.80","article-title":"The truck dispatching problem","volume":"6","author":"Dantzig","year":"1959","journal-title":"Manag. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1287\/opre.12.2.300","article-title":"On an Integer Program for a Delivery Problem","volume":"12","author":"Balinski","year":"1964","journal-title":"Oper. Res."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhang, X., Hao, Y., Zhao, X., and Yuan, X. (2023). A novel vehicle path planning method for freight enterprises considering environmental regulation. J. Clean. Prod., 423.","DOI":"10.1016\/j.jclepro.2023.138839"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, Z., and Wen, P. (2020). Optimization of a Low-Carbon Two-Echelon Heterogeneous-Fleet Vehicle Routing for Cold Chain Logistics under Mixed Time Window. Sustainability, 12.","DOI":"10.3390\/su12051967"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Amiri, A., Amin, S.H., and Zolfagharinia, H. (2023). A bi-objective green vehicle routing problem with a mixed fleet of conventional and electric trucks: Considering charging power and density of stations. Expert Syst. Appl., 213.","DOI":"10.1016\/j.eswa.2022.119228"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Hu, W., Gu, W., Yu, Y., and Xu, M. (2025). A multi-mode hybrid electric vehicle routing problem with time windows. Transp. Res. Part E Logist. Transp. Rev., 195.","DOI":"10.1016\/j.tre.2025.103976"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Jie, K.W., Liu, S.Y., and Sun, X.J. (2022). A hybrid algorithm for time-dependent vehicle routing problem with soft time windows and stochastic factors. Eng. Appl. Artif. Intell., 109.","DOI":"10.1016\/j.engappai.2021.104606"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wang, W., Li, Y., Yan, H., Zhao, W., Zhao, Q., and Luo, K. (2025). A two-phase algorithm for the dynamic time-dependent green vehicle routing problem in decoration waste collection. Expert Syst. Appl., 262.","DOI":"10.1016\/j.eswa.2024.125570"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wang, Y., Gou, M., Luo, S., Fan, J., and Wang, H. (2025). The multi-depot pickup and delivery vehicle routing problem with time windows and dynamic demands. Eng. Appl. Artif. Intell., 139.","DOI":"10.1016\/j.engappai.2024.109700"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/s00291-012-0317-0","article-title":"A dynamic dispatching and routing model to plan\/replan logistics activities in response to an earthquake","volume":"36","author":"Najafi","year":"2014","journal-title":"Oper. Res. Spektrum"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1002\/net.21584","article-title":"Vehicle routing problems with different service constraints: A branch\u2043and cut-and-price algorithm","volume":"64","author":"Ceselli","year":"2014","journal-title":"Networks"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1287\/trsc.2014.0582","article-title":"An Exact Algorithm for the Elementary Shortest Path Problem with Resource Constraints","volume":"50","author":"Lozano","year":"2016","journal-title":"Transp. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Elshaer, R., and Awad, H. (2020). A taxonomic review of metaheuristic algorithms for solving the vehicle routing problem and its variants. Comput. Ind. Eng., 140.","DOI":"10.1016\/j.cie.2019.106242"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Li, J.K., Li, J.Q., and Xu, Y. (2024). An improved multiobjective evolutionary algorithm for time-dependent vehicle routing problem with time windows. Egypt. Inform. J., 28.","DOI":"10.1016\/j.eij.2024.100574"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4626","DOI":"10.1007\/s12205-017-0880-7","article-title":"Robust periodic vehicle routing problem with time windows under uncertainty: An efficient algorithm","volume":"22","author":"Alinaghian","year":"2018","journal-title":"KSCE J. Civ. Eng."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1016\/j.jclepro.2019.03.185","article-title":"An improved ant colony optimization algorithm for the multi-depot green vehicle routing problem with multiple objectives","volume":"227","author":"Li","year":"2019","journal-title":"J. Clean. Prod."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wu, H., and Gao, Y. (2023). An ant colony optimization based on local search for the vehicle routing problem with simultaneous pickup\u2013delivery and time window. Appl. Soft Comput., 139.","DOI":"10.1016\/j.asoc.2023.110203"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Teng, Y., Chen, J., Zhang, S., Wang, J., and Zhang, Z. (2024). Solving dynamic vehicle routing problem with time windows by ant colony system with bipartite graph matching. Egypt. Inform. J., 25.","DOI":"10.1016\/j.eij.2023.100421"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chen, M., Chen, Y., Du, Y., Wei, L., and Chen, Y. (2020). Heuristic algorithms based on deep reinforcement learning for quadratic unconstrained binary optimization. Knowl. -Based Syst., 207.","DOI":"10.1016\/j.knosys.2020.106366"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tang, M., Zhuang, W., Li, B., Liu, H., Song, Z., and Yin, G. (2023). Energy-optimal routing for electric vehicles using deep reinforcement learning with transformer. Appl. Energy, 350.","DOI":"10.1016\/j.apenergy.2023.121711"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"4861","DOI":"10.1109\/TII.2020.3031409","article-title":"Step-wise deep learning models for solving routing problems","volume":"17","author":"Xin","year":"2020","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wang, Y., Hong, X., Wang, Y., Zhao, J., Sun, G., and Qin, B. (2024). Token-based deep reinforcement learning for Heterogeneous VRP with Service Time Constraints. Knowl. -Based Syst., 300.","DOI":"10.1016\/j.knosys.2024.112173"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhang, K., He, F., Zhang, Z., Lin, X., and Li, M. (2020). Multi-vehicle routing problems with soft time windows: A multi-agent reinforcement learning approach. Transp. Res. Part C Emerg. Technol., 121.","DOI":"10.1016\/j.trc.2020.102861"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1016\/S0305-0548(99)00146-X","article-title":"Comparing neuro-dynamic programming algorithms for the vehicle routing problem with sto chastic demands","volume":"27","author":"Secomandi","year":"2000","journal-title":"Comput. Oper. Res."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhou, C., Ma, J., Douge, L., Chew, E.P.P., and Lee, L.H. (2023). Reinforcement learning-based approach for dynamic vehicle routing problem with stochastic demand. Comput. Ind. Eng., 182.","DOI":"10.1016\/j.cie.2023.109443"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Kamrani, M., Srinivasan, A.R., Chakraborty, S., and Khattak, A.J. (2020). Applying Markov decision process to understand driving decisions using basic safety messages data. Transp. Res. Part C Emerg. Technol., 115.","DOI":"10.1016\/j.trc.2020.102642"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Wang, J., Liu, K., and Li, H. (2024). LSTM-based graph attention network for vehicle trajectory prediction. Comput. Netw., 248.","DOI":"10.1016\/j.comnet.2024.110477"}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/2\/127\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:36:12Z","timestamp":1760027772000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/2\/127"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,17]]},"references-count":41,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["systems13020127"],"URL":"https:\/\/doi.org\/10.3390\/systems13020127","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,17]]}}}