{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T21:15:10Z","timestamp":1762377310112,"version":"3.37.3"},"reference-count":32,"publisher":"American Institute of Aeronautics and Astronautics (AIAA)","issue":"4","funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/R009953\/1"],"award-info":[{"award-number":["EP\/R009953\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["arc.aiaa.org"],"crossmark-restriction":true},"short-container-title":["Journal of Aerospace Information Systems"],"published-print":{"date-parts":[[2023,4]]},"abstract":"<jats:p> Existing variants of vehicle routing problems have limited capabilities in describing real-world drone delivery scenarios in terms of drone physical restrictions, mission constraints, and stochastic operating environments. To that end, this paper proposes a specific drone delivery problem with recharging (DDP-R) characterized by directional edges and stochastic edge costs subject to wind conditions. To address it, the DDP-R is cast into a Markov decision process over a graph, with the next node chosen according to a stochastic policy based on the evolving observation. An edge-enhanced attention model (AM-E) is then suggested to map the optimal policy via the deep reinforcement learning (DRL) approach. The AM-E comprises a succession of edge-enhanced dot-product attention layers and is designed with the aim of capturing the heterogeneous node relationship for DDP-Rs by incorporating adjacent edge information. Simulations show that edge enhancement facilitates the training process, achieving superior performance with less trainable parameters and simpler architecture in comparison with other deep learning models. Furthermore, a stochastic drone energy cost model in consideration of winds is incorporated into validation simulations, which provides a practical insight into drone delivery problems. In terms of both nonwind and windy cases, extensive simulations demonstrate that the proposed DRL method outperforms state-of-the-art heuristics for solving DDP-Rs, especially at large sizes. <\/jats:p>","DOI":"10.2514\/1.i011171","type":"journal-article","created":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T06:06:15Z","timestamp":1675231575000},"page":"216-228","update-policy":"https:\/\/doi.org\/10.2514\/aiaa_crossmarkpolicy","source":"Crossref","is-referenced-by-count":4,"title":["Edge-Enhanced Attentions for Drone Delivery in Presence of Winds and Recharging Stations"],"prefix":"10.2514","volume":"20","author":[{"given":"Ruifan","family":"Liu","sequence":"first","affiliation":[{"name":"Cranfield University, Bedfordshire, England MK43 0AL, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9938-0370","authenticated-orcid":false,"given":"Hyo-Sang","family":"Shin","sequence":"additional","affiliation":[{"name":"Cranfield University, Bedfordshire, England MK43 0AL, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3966-7633","authenticated-orcid":false,"given":"Antonios","family":"Tsourdos","sequence":"additional","affiliation":[{"name":"Cranfield University, Bedfordshire, England MK43 0AL, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1387","reference":[{"key":"r1","first-page":"1","volume":"9","author":"Toth P.","year":"2002","journal-title":"An Overview of Vehicle Routing Problem"},{"key":"r2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2582745"},{"key":"r3","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.02.017"},{"key":"r5","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2016.02.007"},{"key":"r6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2909530"},{"key":"r7","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/5075671"},{"key":"r9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2909109"},{"key":"r10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01559-5"},{"key":"r11","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2020.102126"},{"key":"r12","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2016.1535"},{"key":"r13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2021.107650"},{"key":"r14","doi-asserted-by":"publisher","DOI":"10.1016\/S0898-1221(97)00090-4"},{"key":"r15","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.1090.0272"},{"key":"r16","doi-asserted-by":"publisher","DOI":"10.1007\/BF02601637"},{"key":"r17","doi-asserted-by":"publisher","DOI":"10.1080\/03155986.1999.11732386"},{"key":"r18","doi-asserted-by":"publisher","DOI":"10.1016\/j.endm.2018.01.008"},{"key":"r19","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-021-04320-9"},{"key":"r20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2016.01.018"},{"key":"r21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2019.05.010"},{"key":"r22","unstructured":"VinyalsO.FortunatoM.JaitlyN. \u201cPointer Networks,\u201d 2015, pp.\u00a01\u20139. 10.48550\/ARXIV.1506.03134"},{"key":"r24","first-page":"9839","volume":"2018","author":"Nazari M.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"r25","first-page":"1","volume":"27","author":"Bono G.","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"r27","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3113995"},{"key":"r30","unstructured":"BonoG. \u201cDeep Multi-Agent Reinforcement Learning for Dynamic and Stochastic Vehicle Routing Problems To Cite this Version : HAL Id : tel-03098433 Deep Multi-Agent Reinforcement Learning for Dynamic and Stochastic Vehicle Routing Problems,\u201d Universit'e de Lyon, 2020."},{"key":"r31","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2020.12.007"},{"key":"r32","doi-asserted-by":"publisher","DOI":"10.1177\/0020294019847688"},{"key":"r33","doi-asserted-by":"publisher","DOI":"10.1016\/j.trd.2020.102668"},{"key":"r34","doi-asserted-by":"publisher","DOI":"10.1016\/j.trd.2019.102209"},{"key":"r36","unstructured":"KimonP.ValavanisG. J. V., Handbook of Unmanned Aerial Vehicles, Vol.\u00a01, Springer, 2015, pp.\u00a0307\u2013329. 10.1007\/978-90-481-9707-1_47"},{"volume-title":"Wind Energy Systems","year":"1985","author":"Johnson G. L.","key":"r37"},{"key":"r38","unstructured":"MoorhouseD. J.WoodcockR. J. \u201cBackground Information and User Guide for MIL-F-8785B, Military Specification\u2014Flying Qualities of Piloted Airplanes,\u201d Mil-F-8785C, Air Force Wright Aeronautical Labs, Wright-Patterson AFB OH, 1982, p.\u00a0255, http:\/\/www.dept.aoe.vt.edu\/~durham\/AOE5214\/MILSPEC8785C.pdf."},{"volume-title":"Attention Is All You Need","year":"2017","author":"Vaswani A.","key":"r40"}],"container-title":["Journal of Aerospace Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/arc.aiaa.org\/doi\/pdf\/10.2514\/1.I011171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T13:35:19Z","timestamp":1680096919000},"score":1,"resource":{"primary":{"URL":"https:\/\/arc.aiaa.org\/doi\/10.2514\/1.I011171"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["10.2514\/1.I011171"],"URL":"https:\/\/doi.org\/10.2514\/1.i011171","relation":{},"ISSN":["1940-3151","2327-3097"],"issn-type":[{"type":"print","value":"1940-3151"},{"type":"electronic","value":"2327-3097"}],"subject":[],"published":{"date-parts":[[2023,4]]},"assertion":[{"value":"2022-07-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-18","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-11-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}