{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:46:00Z","timestamp":1776876360880,"version":"3.51.2"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.asoc.2026.115145","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T15:13:20Z","timestamp":1774883600000},"page":"115145","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Efficient multi-agent deep reinforcement learning algorithm for multi UAV collision avoidance"],"prefix":"10.1016","volume":"197","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8807-0083","authenticated-orcid":false,"given":"Mohammad Reza","family":"Rezaee","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8095-7678","authenticated-orcid":false,"given":"Nor Asilah Wati","family":"Abdul Hamid","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1063-8502","authenticated-orcid":false,"given":"Masnida","family":"Hussin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2408-6956","authenticated-orcid":false,"given":"Zuriati","family":"Ahmad Zukarnain","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115145_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.robot.2023.104489","article-title":"A deep multi-agent reinforcement learning framework for autonomous aerial navigation to grasping points on loads","volume":"167","author":"Chen","year":"2023","journal-title":"Robot. Auton. Syst."},{"key":"10.1016\/j.asoc.2026.115145_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.113816","article-title":"Self-driving cars: a survey","volume":"165","author":"Badue","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2026.115145_bib0015","doi-asserted-by":"crossref","DOI":"10.1038\/d41586-023-00557-5","article-title":"Autonomous ships are on the horizon: here\u2019s what we need to know","volume":"615","author":"Negenborn","year":"2023","journal-title":"Nature"},{"issue":"6","key":"10.1016\/j.asoc.2026.115145_bib0020","doi-asserted-by":"crossref","DOI":"10.3390\/aerospace7060079","article-title":"Review of conflict resolution methods for manned and unmanned aviation","volume":"7","author":"Ribeiro","year":"2020","journal-title":"Aerospace"},{"key":"10.1016\/j.asoc.2026.115145_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112402","article-title":"Two-step dynamic obstacle avoidance","volume":"302","author":"Hart","year":"2024","journal-title":"Knowl.-Based Syst."},{"issue":"4","key":"10.1016\/j.asoc.2026.115145_bib0030","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1109\/6979.898217","article-title":"A review of conflict detection and resolution modeling methods","volume":"1","author":"Kuchar","year":"2000","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"7","key":"10.1016\/j.asoc.2026.115145_bib0035","doi-asserted-by":"crossref","first-page":"6397","DOI":"10.1109\/TITS.2024.3375893","article-title":"Comprehensive review of drones collision avoidance schemes: challenges and open issues","volume":"25","author":"Rezaee","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.asoc.2026.115145_bib0040","article-title":"Online path generation and navigation for swarms of UAVs","author":"Ashraf","year":"2020","journal-title":"Sci. Program."},{"key":"10.1016\/j.asoc.2026.115145_bib0045","doi-asserted-by":"crossref","first-page":"301","DOI":"10.32604\/jai.2024.054314","article-title":"A comprehensive overview and comparative analysis on deep learning models","volume":"6","author":"Mortezapour Shiri","year":"2024","journal-title":"J. Artif. Intell."},{"key":"10.1016\/j.asoc.2026.115145_bib0050","series-title":"Proc. Of 2018 Fourth Int. Conf. On Computing Communication Control and Automation (ICCUBEA)","article-title":"A review of machine learning and deep learning applications","author":"Shinde","year":"2018"},{"key":"10.1016\/j.asoc.2026.115145_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.sftr.2025.101427","article-title":"Examining environmental stress changes in response to climate change and land use dynamics in the Colorado River basin over the past two decades","volume":"10","author":"Heidari","year":"2025","journal-title":"Sustain. Futures"},{"key":"10.1016\/j.asoc.2026.115145_bib0060","doi-asserted-by":"crossref","DOI":"10.3390\/pr10071307","article-title":"Deep reinforcement learning for integrated non-linear control of autonomous UAVs","volume":"10","author":"Ud Din","year":"2022","journal-title":"Processes"},{"issue":"9","key":"10.1016\/j.asoc.2026.115145_bib0065","doi-asserted-by":"crossref","DOI":"10.3390\/electronics10090999","article-title":"Drone deep reinforcement learning: a review","volume":"10","author":"Azar","year":"2021","journal-title":"Electronics"},{"issue":"8","key":"10.1016\/j.asoc.2026.115145_bib0070","doi-asserted-by":"crossref","DOI":"10.3390\/drones7080491","article-title":"Adaptive collision avoidance for multiple UAVs in urban environments","volume":"7","author":"Zhang","year":"2023","journal-title":"Drones"},{"key":"10.1016\/j.asoc.2026.115145_bib0075","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.neunet.2023.02.027","article-title":"Multi-UAV autonomous collision avoidance based on PPO-GIC algorithm with CNN\u2013LSTM fusion network","volume":"162","author":"Liang","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.asoc.2026.115145_bib0080","series-title":"Proc. of 2021 17th Int. Symp. on Wireless Communication Systems (ISWCS)","first-page":"1","article-title":"Attention-based reinforcement learning for real-time UAV semantic communication","author":"Yun","year":"2021"},{"issue":"2","key":"10.1016\/j.asoc.2026.115145_bib0085","doi-asserted-by":"crossref","DOI":"10.3390\/app12020610","article-title":"Multi-UAV conflict resolution with graph convolutional reinforcement learning","volume":"12","author":"Isufaj","year":"2022","journal-title":"Appl. Sci."},{"key":"10.1016\/j.asoc.2026.115145_bib0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121234","article-title":"Deep reinforcement learning in service of AIR traffic controllers to resolve tactical conflicts","volume":"236","author":"Papadopoulos","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2026.115145_bib0095","author":"Huang"},{"key":"10.1016\/j.asoc.2026.115145_bib0100","series-title":"Proc. 2021 5th Chinese Conf. On Swarm Intelligence and Cooperative Control","article-title":"MADDPG: multi-agent deep deterministic policy gradient algorithm for formation elliptical encirclement and collision avoidance","author":"Xu","year":"2023"},{"key":"10.1016\/j.asoc.2026.115145_bib0105","series-title":"Proc. Of IEEE\/RSJ IROS","article-title":"Vision-based distributed multi-UAV collision avoidance via deep reinforcement learning for navigation","author":"Huang","year":"2022"},{"key":"10.1016\/j.asoc.2026.115145_bib0110","doi-asserted-by":"crossref","DOI":"10.3390\/electronics10090999","article-title":"Drone deep reinforcement learning: a review","volume":"10","author":"Azar","year":"2021","journal-title":"Electronics"},{"key":"10.1016\/j.asoc.2026.115145_bib0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.comnet.2021.108439","article-title":"Computation offloading over multi-UAV MEC network: a distributed deep reinforcement learning approach","volume":"199","author":"Wei","year":"2021","journal-title":"Comput. Netw."},{"key":"10.1016\/j.asoc.2026.115145_bib0120","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.105891","article-title":"Multi-UAV trajectory optimizer: a sustainable system for wireless data harvesting with deep reinforcement learning","volume":"120","author":"Seong","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.asoc.2026.115145_bib0125","series-title":"Proc. 2023 IEEE\/AIAA DASC","article-title":"Reinforcement learning-based assistive collision avoidance for fixed-wing unmanned aerial vehicles","author":"D\u2019Apolito","year":"2023"},{"key":"10.1016\/j.asoc.2026.115145_bib0130","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2023.104125","article-title":"General multi-agent reinforcement learning integrating adaptive manoeuvre strategy for real-time multi-aircraft conflict resolution","volume":"151","author":"Chen","year":"2023","journal-title":"Transp. Res. Part C"},{"key":"10.1016\/j.asoc.2026.115145_bib0135","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"10.1016\/j.asoc.2026.115145_bib0140","series-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"10.1016\/j.asoc.2026.115145_bib0145","series-title":"Proceedings of the 7th International Conference on Research in Air Transportation (ICRAT)","first-page":"132","article-title":"Bluesky ATC simulator project: an open data and open source approach","volume":"vol. 131","author":"Hoekstra","year":"2016"},{"issue":"10","key":"10.1016\/j.asoc.2026.115145_bib0150","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1002\/acs.1176","article-title":"BADA: an advanced aircraft performance model","volume":"24","author":"Nuic","year":"2010","journal-title":"Int. J. Adapt. Control Signal Process."},{"issue":"3","key":"10.1016\/j.asoc.2026.115145_bib0155","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1011950","article-title":"Active reinforcement learning versus action bias and hysteresis","volume":"20","author":"Colas","year":"2024","journal-title":"PLOS Comput. Biol."},{"issue":"2","key":"10.1016\/j.asoc.2026.115145_bib0160","first-page":"207","article-title":"Reinforcement learning-based collision avoidance: impact of reward function and knowledge transfer","volume":"34","author":"Liu","year":"2020","journal-title":"AI Eng. Des. Anal. Manuf."},{"key":"10.1016\/j.asoc.2026.115145_bib0165","article-title":"Deep-reinforcement-learning-based collision avoidance of autonomous driving system","volume":"13","author":"Chen","year":"2024","journal-title":"Electronics"},{"key":"10.1016\/j.asoc.2026.115145_bib0170","doi-asserted-by":"crossref","first-page":"4581","DOI":"10.1007\/s00170-023-11405-1","article-title":"Application of graph theory for preventing carriers\u2019 collisions in variable path braiding machines","volume":"126","author":"Assi","year":"2023","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"10.1016\/j.asoc.2026.115145_bib0175","series-title":"17th AIAA Aviation Technology, Integration, and Operations Conference","first-page":"3775","article-title":"Applying graph theory to problems in air traffic management","author":"Farrahi","year":"2017"},{"issue":"21","key":"10.1016\/j.asoc.2026.115145_bib0180","first-page":"44290","article-title":"Multiscale-graph-enhanced reinforcement learning for conflict resolution in dense UAV networks","volume":"12","author":"Li","year":"2025","journal-title":"IEEE Internet Things J."},{"issue":"3","key":"10.1016\/j.asoc.2026.115145_bib0185","doi-asserted-by":"crossref","first-page":"4529","DOI":"10.1109\/TIV.2024.3364652","article-title":"Graph reinforcement learning for multi-aircraft conflict resolution","volume":"9","author":"Li","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.asoc.2026.115145_bib0190","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2024.109166","article-title":"Graph-based multi-agent reinforcement learning for large-scale UAVs swarm system control","volume":"150","author":"Zhao","year":"2024","journal-title":"Aerosp. Sci. Technol."},{"key":"10.1016\/j.asoc.2026.115145_bib0195","article-title":"Graph-based multi-agent reinforcement learning for collaborative search and tracking of multiple UAVs","author":"Zhao","year":"2024","journal-title":"Chin. J. Aeronaut."},{"issue":"2","key":"10.1016\/j.asoc.2026.115145_bib0200","doi-asserted-by":"crossref","first-page":"3098","DOI":"10.1109\/LRA.2020.2974648","article-title":"A two-stage reinforcement learning approach for multi-UAV collision avoidance under imperfect sensing","volume":"5","author":"Wang","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"8","key":"10.1016\/j.asoc.2026.115145_bib0205","doi-asserted-by":"crossref","first-page":"10894","DOI":"10.1109\/TNNLS.2023.3245124","article-title":"Collision-avoiding flocking with multiple Fixed-Wing UAVs in obstacle-cluttered environments: a task-specific curriculum-based MADRL approach","volume":"35","author":"Yan","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.asoc.2026.115145_bib0210","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"13152","article-title":"CoDe: a cooperative and decentralized collision avoidance algorithm for small-scale UAV swarms considering energy efficiency","author":"Huang","year":"2024"},{"issue":"4","key":"10.1016\/j.asoc.2026.115145_bib0215","article-title":"Communication-aided multi-UAV collision detection and avoidance based on two-stage curriculum reinforcement learning","volume":"5","author":"Wang","year":"2025","journal-title":"Biomimetic Intell. Robot."},{"issue":"12","key":"10.1016\/j.asoc.2026.115145_bib0220","doi-asserted-by":"crossref","first-page":"12698","DOI":"10.1109\/TCYB.2021.3086501","article-title":"Learning to optimize: reference vector reinforcement learning adaption to constrained many-objective optimization of industrial copper burdening system","volume":"52","author":"Ma","year":"2022","journal-title":"IEEE Trans. Cybern."},{"issue":"7","key":"10.1016\/j.asoc.2026.115145_bib0225","doi-asserted-by":"crossref","first-page":"6684","DOI":"10.1109\/TCYB.2020.3041212","article-title":"An adaptive localized decision variable analysis approach to large-scale multiobjective and many-objective optimization","volume":"52","author":"Ma","year":"2022","journal-title":"IEEE Trans. Cybern."},{"issue":"12","key":"10.1016\/j.asoc.2026.115145_bib0230","doi-asserted-by":"crossref","first-page":"21350","DOI":"10.1109\/JIOT.2025.3546915","article-title":"Multiagent deep-reinforcement-learning-based cooperative perception and computation in VEC","volume":"12","author":"Zhao","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.asoc.2026.115145_bib0235","first-page":"1","article-title":"Multi-objective genetic programming assisted stochastic deep reinforcement learning for dynamic knowledge integration in transportation networks","author":"Xue","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.asoc.2026.115145_bib0240","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2022.109943","article-title":"Heuristic smoothing ant colony optimization with differential information for the traveling salesman problem","volume":"133","author":"Li","year":"2023","journal-title":"Appl. Soft Comput."},{"issue":"7","key":"10.1016\/j.asoc.2026.115145_bib0245","doi-asserted-by":"crossref","first-page":"9247","DOI":"10.1109\/TVT.2023.3330661","article-title":"Multi-agent deep reinforcement learning-based task scheduling and resource sharing for o-RAN-empowered multi-UAV-assisted wireless sensor networks","volume":"73","author":"Betalo","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"6","key":"10.1016\/j.asoc.2026.115145_bib0250","doi-asserted-by":"crossref","first-page":"6527","DOI":"10.1109\/TNSM.2024.3454217","article-title":"Multi-agent DRL-based energy harvesting for freshness of data in UAV-assisted wireless sensor networks","volume":"21","author":"Betalo","year":"2024","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"issue":"17","key":"10.1016\/j.asoc.2026.115145_bib0255","doi-asserted-by":"crossref","first-page":"35890","DOI":"10.1109\/JIOT.2025.3579780","article-title":"Generative AI-driven multiagent DRL for task allocation in UAV-assisted EMPD within 6g-enabled SAGIN networks","volume":"12","author":"Betalo","year":"2025","journal-title":"IEEE Internet Things J."},{"issue":"7","key":"10.1016\/j.asoc.2026.115145_bib0260","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1109\/JAS.2024.124965","article-title":"Multi-UAV cooperative pursuit strategy with limited visual field in urban airspace: a multi-agent reinforcement learning approach","volume":"12","author":"Peng","year":"2025","journal-title":"IEEE\/CAA J. Autom. Sin."},{"issue":"16","key":"10.1016\/j.asoc.2026.115145_bib0265","doi-asserted-by":"crossref","first-page":"27421","DOI":"10.1109\/JIOT.2024.3397823","article-title":"Graph-attention-based reinforcement learning for trajectory design and resource assignment in multi-UAV-assisted communication","volume":"11","author":"Feng","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.asoc.2026.115145_bib0270","series-title":"2024 IEEE International Conference on Communications Workshops (ICC Workshops)","first-page":"505","article-title":"Transformer-based multi-agent reinforcement learning for multiple unmanned aerial vehicle coordination in air corridors","author":"Yu","year":"2024"},{"issue":"21","key":"10.1016\/j.asoc.2026.115145_bib0275","doi-asserted-by":"crossref","first-page":"34541","DOI":"10.1109\/JIOT.2024.3447774","article-title":"GNN-empowered effective partial observation MARL method for AoI management in multi-UAV network","volume":"11","author":"Pan","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.asoc.2026.115145_bib0280","series-title":"Proceedings of the 26th Annual International Conference on Machine Learning (ICML \u201909)","first-page":"41","article-title":"Curriculum learning","author":"Bengio","year":"2009"},{"issue":"56","key":"10.1016\/j.asoc.2026.115145_bib0285","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: a survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.asoc.2026.115145_bib0290","series-title":"A Concise Introduction to Decentralized POMDPs, SpringerBriefs in Intelligent Systems","author":"Oliehoek","year":"2016"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626005934?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626005934?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:01:42Z","timestamp":1776873702000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626005934"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":58,"alternative-id":["S1568494626005934"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115145","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Efficient multi-agent deep reinforcement learning algorithm for multi UAV collision avoidance","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115145","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"115145"}}