{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T12:41:13Z","timestamp":1776775273880,"version":"3.51.2"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.neucom.2026.133469","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:39:14Z","timestamp":1774543154000},"page":"133469","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A deep Q-learning framework for multi-robot anti-congestion navigation using RFID-based coordination"],"prefix":"10.1016","volume":"683","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1568-6933","authenticated-orcid":false,"given":"Ning","family":"Wang","sequence":"first","affiliation":[]},{"given":"Hamid R.","family":"Parsaei","sequence":"additional","affiliation":[]},{"given":"Yali","family":"Ren","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133469_bib0005","series-title":"Proc. IEEE Int. Conf. Robot","first-page":"9667","article-title":"Voluntary retreat for decentralized interference reduction in robot swarms","author":"Mayya","year":"2019"},{"issue":"6","key":"10.1016\/j.neucom.2026.133469_bib0010","doi-asserted-by":"crossref","first-page":"2062","DOI":"10.3390\/s21062062","article-title":"Swarm robotics: a perspective on the latest reviewed concepts and applications","volume":"21","author":"Dias","year":"2021","journal-title":"Sensors."},{"key":"10.1016\/j.neucom.2026.133469_bib0015","doi-asserted-by":"crossref","first-page":"36","DOI":"10.3389\/frobt.2020.00036","article-title":"Swarm robotic behaviors and current applications","volume":"7","author":"Schranz","year":"2020","journal-title":"Front. Robot. AI."},{"issue":"7","key":"10.1016\/j.neucom.2026.133469_bib0020","doi-asserted-by":"crossref","first-page":"1152","DOI":"10.1109\/JPROC.2021.3072740","article-title":"Swarm robotics: past, present, and future","volume":"109","author":"Dorigo","year":"2021","journal-title":"Proc. IEEE"},{"issue":"4","key":"10.1016\/j.neucom.2026.133469_bib0025","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1287\/trsc.2018.0873","article-title":"Robotized and automated warehouse systems: review and recent developments","volume":"53","author":"Azadeh","year":"2019","journal-title":"Transp. Sci."},{"issue":"4","key":"10.1016\/j.neucom.2026.133469_bib0030","first-page":"2159","article-title":"Collaborative mapping with IoE-based heterogeneous vehicles for enhanced situational awareness","volume":"20","author":"Queralta","year":"2020","journal-title":"IEEE Sens. J."},{"issue":"4","key":"10.1016\/j.neucom.2026.133469_bib0035","first-page":"1273","article-title":"Aerial robotic systems for environmental monitoring","volume":"21","author":"Hernandez","year":"2021","journal-title":"Sensors."},{"issue":"7","key":"10.1016\/j.neucom.2026.133469_bib0040","first-page":"3110","article-title":"Adaptive control barrier functions","volume":"65","author":"Wang","year":"2020","journal-title":"IEEE Trans. Automat. Control."},{"issue":"2","key":"10.1016\/j.neucom.2026.133469_bib0045","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.1109\/LRA.2017.2656241","article-title":"Fast, on-line collision avoidance for dynamic vehicles using buffered voronoi cells","volume":"6","author":"Zhou","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"3","key":"10.1016\/j.neucom.2026.133469_bib0050","first-page":"1036","article-title":"The impact of diversity on optimal control policies for heterogeneous robot swarms","volume":"37","author":"Prorok","year":"2021","journal-title":"IEEE Trans. Robot."},{"issue":"4","key":"10.1016\/j.neucom.2026.133469_bib0055","first-page":"1600","article-title":"Path planning for robotic mobile fulfillment systems","volume":"16","author":"Merschformann","year":"2019","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.neucom.2026.133469_bib0060","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1007\/s10514-016-9577-x","article-title":"Avoiding target congestion on the navigation of robotic swarms","volume":"41","author":"Marcolino","year":"2017","journal-title":"Auton. Robot."},{"issue":"4","key":"10.1016\/j.neucom.2026.133469_bib0065","doi-asserted-by":"crossref","first-page":"1298","DOI":"10.1109\/TASE.2015.2461213","article-title":"Planning paths for package delivery in heterogeneous multirobot teams","volume":"12","author":"Mathew","year":"2020","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.neucom.2026.133469_bib0070","series-title":"Proc. Symp. Combinat. Search","first-page":"151","article-title":"Multi-agent pathfinding: definitions, variants, and benchmarks","author":"Stern","year":"2019"},{"issue":"1","key":"10.1016\/j.neucom.2026.133469_bib0075","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1109\/TRO.2021.3071618","article-title":"Congestion-aware policy synthesis for multirobot systems","volume":"38","author":"Street","year":"2021","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.neucom.2026.133469_bib0080","first-page":"1543","article-title":"ALAN: adaptive learning for multi-agent navigation, auton","volume":"42","author":"Godoy","year":"2018","journal-title":"Robot."},{"key":"10.1016\/j.neucom.2026.133469_bib0085","series-title":"IEEE Int. Conf. Robot. Autom","first-page":"6252","article-title":"Towards optimally decentralized multi-robot collision avoidance via deep reinforcement learning, in: proc","author":"Long","year":"2020"},{"issue":"3","key":"10.1016\/j.neucom.2026.133469_bib0090","doi-asserted-by":"crossref","first-page":"2378","DOI":"10.1109\/LRA.2019.2903261","article-title":"PRIMAL: pathfinding via reinforcement and imitation multi-agent learning","volume":"4","author":"Sartoretti","year":"2019","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.133469_bib0095","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1007\/s10514-015-9429-0","article-title":"Collision avoidance for aerial vehicles in multi-agent scenarios","volume":"39","author":"Alonso-Mora","year":"2015","journal-title":"Auton. Robots."},{"issue":"2","key":"10.1016\/j.neucom.2026.133469_bib0100","doi-asserted-by":"crossref","first-page":"3368","DOI":"10.1109\/LRA.2020.2975956","article-title":"Scalable cooperative transport of cable-suspended loads with UAVs using distributed trajectory optimization","volume":"5","author":"Walker","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.133469_bib0105","series-title":"Proc. Int. Conf. Automat. Plan","first-page":"279","article-title":"Disjoint splitting for multi-agent path finding with conflict-based search","author":"Li","year":"2019"},{"issue":"4","key":"10.1016\/j.neucom.2026.133469_bib0110","doi-asserted-by":"crossref","first-page":"3529","DOI":"10.1109\/LRA.2019.2927938","article-title":"Robust and efficient quadrotor trajectory generation for fast autonomous flight","volume":"4","author":"Zhou","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.133469_bib0115","series-title":"Proc. IEEE Int. Conf. Robot. Autom","first-page":"2141","article-title":"Reactive collision avoidance of multiple moving agents by cooperation and conflict propagation","author":"Krishna","year":"2004"},{"key":"10.1016\/j.neucom.2026.133469_bib0120","series-title":"Robotics Research: the 14th International Symposium ISRR, Springer Tracts in Advanced Robotics","first-page":"3","article-title":"Reciprocal n-body collision avoidance","volume":"vol. 70","author":"van den Berg","year":"2011"},{"issue":"3","key":"10.1016\/j.neucom.2026.133469_bib0125","article-title":"DMVC-tracker: distributed multi-agent trajectory planning for target tracking using dynamic buffered voronoi and inter-visibility cells","volume":"10","author":"Lee","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"3","key":"10.1016\/j.neucom.2026.133469_bib0130","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1109\/TRO.2017.2659727","article-title":"Safety barrier certificates for collisions-free multirobot systems","volume":"33","author":"Wang","year":"2021","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.neucom.2026.133469_bib0135","doi-asserted-by":"crossref","first-page":"10357","DOI":"10.1109\/ACCESS.2021.3050338","article-title":"Collision avoidance in pedestrian-rich environments with deep reinforcement learning","volume":"9","author":"Everett","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.neucom.2026.133469_bib0140","article-title":"Decentralized multi-robot encirclement of a 3D target with guaranteed collision avoidance","volume":"39","author":"Franchi","year":"2015","journal-title":"Auton Robots."},{"key":"10.1016\/j.neucom.2026.133469_bib0145","series-title":"Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst","first-page":"3235","article-title":"Using minimal communication to improve decentralized conflict resolution for nonholonomic vehicles","author":"Krontiris","year":"2011"},{"issue":"2","key":"10.1016\/j.neucom.2026.133469_bib0150","doi-asserted-by":"crossref","first-page":"2666","DOI":"10.1109\/LRA.2021.3062803","article-title":"Primal2: pathfinding via reinforcement and imitation multi-agent learning \u2013 lifelong","volume":"6","author":"Damani","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.133469_bib0155","series-title":"Proc. Int. Conf. Learn. Represent","article-title":"QPLEX: duplex dueling multi-agent Q-learning","author":"Peng","year":"2021"},{"key":"10.1016\/j.neucom.2026.133469_bib0160","series-title":"Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst","first-page":"11785","article-title":"Graph neural networks for decentralized multi-robot path planning","author":"Li","year":"2020"},{"key":"10.1016\/j.neucom.2026.133469_bib0165","series-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"issue":"3\u20134","key":"10.1016\/j.neucom.2026.133469_bib0170","first-page":"279","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"issue":"3","key":"10.1016\/j.neucom.2026.133469_bib0175","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1023\/A:1022689125041","article-title":"Asynchronous stochastic approximation and Q-learning","volume":"16","author":"Tsitsiklis","year":"1994","journal-title":"Machine Learning"},{"key":"10.1016\/j.neucom.2026.133469_bib0180","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature."},{"key":"10.1016\/j.neucom.2026.133469_bib0185","series-title":"Reinforcement Learning: an Introduction","author":"Sutton","year":"2018"},{"issue":"7","key":"10.1016\/j.neucom.2026.133469_bib0190","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1109\/TPAMI.2005.147","article-title":"Probabilistic finite-state machines \u2013 part i","volume":"27","author":"Vidal","year":"2005","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.neucom.2026.133469_bib0195","article-title":"AI-driven Automation of aviation equipment inspection: insights from a complex adaptive systems perspective","volume":"7","author":"Wu","year":"2026","journal-title":"The Innov."},{"key":"10.1016\/j.neucom.2026.133469_bib0200","first-page":"1","article-title":"DLA-Net: a dynamically learnable attention network for intelligent surface visual inspection of aero-engine blades","volume":"74","author":"Chen","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"3","key":"10.1016\/j.neucom.2026.133469_bib0205","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1111\/1468-0262.00429","article-title":"Deterministic approximation of stochastic evolution in games","volume":"71","author":"Benaim","year":"2003","journal-title":"Econometrica"},{"key":"10.1016\/j.neucom.2026.133469_bib0210","series-title":"Proc. Eur. Conf. Mach. Learn","first-page":"317","article-title":"Neural fitted Q iteration \u2013 first experiences with a data efficient neural reinforcement learning method","author":"Riedmiller","year":"2005"},{"issue":"178","key":"10.1016\/j.neucom.2026.133469_bib0215","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.133469_bib0220","series-title":"Proc. AAAI Conf. Artif. Intell","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","author":"Foerster","year":"2018"},{"issue":"5","key":"10.1016\/j.neucom.2026.133469_bib0225","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw."},{"issue":"4","key":"10.1016\/j.neucom.2026.133469_bib0230","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/BF02551274","article-title":"Approximation by superpositions of a sigmoidal function","volume":"2","author":"Cybenko","year":"1989","journal-title":"Math. Control Signals Syst."},{"key":"10.1016\/j.neucom.2026.133469_bib0235","series-title":"Proceedings of 1995 34th IEEE Conference on Decision and Control, New Orleans, LA, USA","first-page":"560","article-title":"Neuro-dynamic programming: an overview","volume":"vol. 1","author":"Bertsekas","year":"1995"},{"key":"10.1016\/j.neucom.2026.133469_bib0240","series-title":"AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents (AAAI-SDMIA)","article-title":"Deep recurrent Q-network for partially observable MDPs","author":"Hausknecht","year":"2015"},{"key":"10.1016\/j.neucom.2026.133469_bib0245","series-title":"Proceedings of the 16th International Conference on Machine Learning (ICML)","first-page":"278","article-title":"Policy invariance under reward transformations: theory and application to reward shaping","author":"Ng","year":"1999"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226008660?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226008660?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T11:46:57Z","timestamp":1776772017000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226008660"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":49,"alternative-id":["S0925231226008660"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133469","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A deep Q-learning framework for multi-robot anti-congestion navigation using RFID-based coordination","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133469","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133469"}}