{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T01:10:02Z","timestamp":1773018602836,"version":"3.50.1"},"reference-count":38,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T00:00:00Z","timestamp":1772064000000},"content-version":"vor","delay-in-days":56,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72271039"],"award-info":[{"award-number":["72271039"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72293563"],"award-info":[{"award-number":["72293563"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12435014"],"award-info":[{"award-number":["12435014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>\n                    The online\u2010to\u2010offline (O2O) business model has facilitated millions of daily transactions on popular online food ordering platforms. Online food delivery route planning presents a complex multidepot vehicle routing problem (VRP) with capacity limits, pickup\u2013delivery, and time\u2010window constraints. However, the vast volume of transactions and computational complexities of delivery routes pose significant challenges. This paper proposes a novel feature fusion attention\u2010based deep reinforcement learning model to address such constrained routing problems. The innovative encoding and masking scheme with a self\u2010attention\u2010guided order relocation operator efficiently handles multidepot and multiconstraint scenarios. Additionally, incorporating self\u2010attention with a graph neural network (GNN) framework extends existing research from static unit square environments to dynamic real road networks. Computational experiments demonstrate that our proposed route solver outperforms state\u2010of\u2010the\u2010art heuristics and reinforcement learning methods regarding solution quality and computation time across unit square environments and real road networks. Exploratory analysis using real\u2010world delivery data\n                    <jats:sup>a<\/jats:sup>\n                    illustrates the applicability of our approach to practical online ordering platforms.\n                  <\/jats:p>","DOI":"10.1155\/int\/3716055","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:15:16Z","timestamp":1773015316000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Feature Fusion Attention\u2010Based Deep Reinforcement Learning for Multidepot O2O Food Delivery Route Optimization"],"prefix":"10.1155","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1890-6874","authenticated-orcid":false,"given":"Guangyu","family":"Zou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Levent","family":"Yilmaz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,2,26]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2021.3089179"},{"key":"e_1_2_9_2_2","doi-asserted-by":"crossref","unstructured":"MaY. LiJ. CaoZ.et al. Efficient Neural Neighborhood Search for Pickup and Delivery Problems Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence 2022 4776\u20134784.","DOI":"10.24963\/ijcai.2022\/662"},{"key":"e_1_2_9_3_2","article-title":"Multi-Type Attention for Solving Multi-Depot Vehicle Routing Problems","volume":"25","author":"Li J.","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-022-04788-z"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1080\/23270012.2023.2229842"},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124514"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3193852"},{"key":"e_1_2_9_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3056120"},{"key":"e_1_2_9_9_2","first-page":"21188","article-title":"Pomo: Policy Optimization With Multiple Optima for Reinforcement Learning","volume":"33","author":"Kwon Y. D.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128660"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2025.126314"},{"key":"e_1_2_9_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2019.106242"},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.12206"},{"key":"e_1_2_9_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.09.022"},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107403"},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2020.101866"},{"key":"e_1_2_9_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.05.041"},{"key":"e_1_2_9_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3152062"},{"key":"e_1_2_9_19_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10243147"},{"key":"e_1_2_9_20_2","article-title":"Pointer Networks","volume":"28","author":"Vinyals O.","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_21_2","article-title":"Neural Combinatorial Optimization With Reinforcement Learning","author":"Bello I.","year":"2016","journal-title":"arXiv preprint arXiv:161109940"},{"key":"e_1_2_9_22_2","article-title":"Reinforcement Learning for Solving the Vehicle Routing Problem","volume":"31","author":"Nazari M.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_23_2","article-title":"Attention, Learn to Solve Routing Problems","author":"Kool W.","year":"2018","journal-title":"arxiv Preprint arXiv:180308475"},{"key":"e_1_2_9_24_2","first-page":"48485","article-title":"Winner Takes it all: Training Performant RL Populations for Combinatorial Optimization","volume":"36","author":"Grinsztajn N.","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_25_2","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.52202\/068431-0141","article-title":"Sym-Nco: Leveraging Symmetricity for Neural Combinatorial Optimization","volume":"35","author":"Kim M.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_26_2","unstructured":"GaoC. ShangH. XueK. LiD. andQianC. LarsonK. Towards Generalizable Neural Solvers for Vehicle Routing Problems via Ensemble With Transferrable Local Policy Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence 2024 Jeju South Korea IJCAI-24 International Joint Conferences on Artificial Intelligence Organization 6914\u20136922."},{"key":"e_1_2_9_27_2","unstructured":"FangH. SongZ. WengP. andBanY. Invit: A Generalizable Routing Problem Solver With Invariant Nested View Transformer Forty-first International Conference on Machine Learning 2024 Vienna Austria."},{"key":"e_1_2_9_28_2","unstructured":"HottungA. KwonY. D. andTierneyK. Efficient Active Search for Combinatorial Optimization Problems International Conference on Learning Representations 2021 Vienna Austria."},{"key":"e_1_2_9_29_2","first-page":"8845","article-title":"Neural Combinatorial Optimization With Heavy Decoder: Toward Large Scale Generalization","volume":"36","author":"Luo F.","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_30_2","article-title":"PARCO: Learning Parallel Autoregressive Policies for Efficient Multi-Agent Combinatorial Optimization","author":"Berto F.","year":"2024","journal-title":"arXiv preprint arXiv:240903811"},{"key":"e_1_2_9_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2019.2909109"},{"key":"e_1_2_9_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2023.121711"},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"HottungA.andTierneyK. Neural Large Neighborhood Search for the Capacitated Vehicle Routing Problem arXiv preprint arXiv:191109539 2019.","DOI":"10.3233\/FAIA200124"},{"key":"e_1_2_9_34_2","unstructured":"LuH. ZhangX. andYangS. A Learning-Based Iterative Method for Solving Vehicle Routing Problems International Conference on Learning Representations 2019 New Orleans."},{"key":"e_1_2_9_35_2","first-page":"11096","article-title":"Learning to Iteratively Solve Routing Problems With Dual-Aspect Collaborative Transformer","volume":"34","author":"Ma Y.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3068828"},{"key":"e_1_2_9_37_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21236"},{"key":"e_1_2_9_38_2","doi-asserted-by":"publisher","DOI":"10.1080\/17477778.2021.2007808"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/3716055","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/3716055","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/3716055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:15:18Z","timestamp":1773015318000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/3716055"}},"subtitle":[],"editor":[{"given":"Richard","family":"Murray","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/int\/3716055"],"URL":"https:\/\/doi.org\/10.1155\/int\/3716055","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-10-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3716055"}}