{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T13:05:23Z","timestamp":1759496723344,"version":"3.37.3"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3115711","type":"journal-article","created":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T20:50:05Z","timestamp":1632516605000},"page":"132491-132507","source":"Crossref","is-referenced-by-count":11,"title":["Implementation of Decentralized Reinforcement Learning-Based Multi-Quadrotor Flocking"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3572-4458","authenticated-orcid":false,"given":"Pramod","family":"Abichandani","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Newark College of Engineering (NCE), Robotics and Data Laboratory (RADLab), New Jersey Institute of Technology, Newark, NJ, USA"}]},{"given":"Christian","family":"Speck","sequence":"additional","affiliation":[{"name":"Lockheed Martin Advanced Technology Laboratories, Cherry Hill, NJ, USA"}]},{"given":"Donald","family":"Bucci","sequence":"additional","affiliation":[{"name":"Lockheed Martin Advanced Technology Laboratories, Cherry Hill, NJ, USA"}]},{"given":"William","family":"Mcintyre","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Newark College of Engineering (NCE), Robotics and Data Laboratory (RADLab), New Jersey Institute of Technology, Newark, NJ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7434-8013","authenticated-orcid":false,"given":"Deepan","family":"Lobo","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Newark College of Engineering (NCE), Robotics and Data Laboratory (RADLab), New Jersey Institute of Technology, Newark, NJ, USA"}]}],"member":"263","reference":[{"key":"ref73","first-page":"656","article-title":"Q-decomposition for reinforcement learning agents","author":"russell","year":"2003","journal-title":"Proc 20th Int Conf Mach Learn (ICML)"},{"key":"ref72","first-page":"1445","article-title":"Multiple-goal reinforcement learning with modular Sarsa(O)","author":"sprague","year":"2003","journal-title":"Proc 18th Int Joint Conf Artif Intell"},{"key":"ref71","first-page":"592","article-title":"Flocking control of UAV swarms with deep reinforcement leaming approach","author":"yan","year":"2020","journal-title":"Proc 3rd Int Conf Unmanned Syst (ICUS)"},{"journal-title":"Python Implementation of Dryden Turbulence Model","year":"2021","author":"abichandani","key":"ref70"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref77","first-page":"1061","article-title":"Object focused q-learning for autonomous agents","author":"cobo","year":"2013","journal-title":"Proc 2013 Int Conf Auto Agents Multi-agent Syst"},{"key":"ref74","first-page":"260","article-title":"Rlboa: A modular reinforcement learning framework for autonomous negotiating agents","author":"bakker","year":"2019","journal-title":"Proc 18th Int Conf Auto Agents Multiagent Syst"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEAM.2019.8742915"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971780"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646428"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2016.2599486"},{"key":"ref33","first-page":"595","article-title":"Mathematical modeling for flocking flight of autonomous multi-UAV system, including environmental factors","volume":"14","author":"kwon","year":"2020","journal-title":"KSII Trans Internet Inf Syst"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/978-3-319-17518-8_24","article-title":"Flocking algorithm for fixed-wing unmanned aerial vehicles","author":"kownacki","year":"2015","journal-title":"Advances in Aerospace Guidance Navigation and Control"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aat3536"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3374587.3374599"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2019.8865184"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2019.01.016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93818-9_10"},{"key":"ref60","first-page":"64","article-title":"A continuous actor-critic reinforcement learning approach to flocking with fixed-wing uavs","author":"wang","year":"2019","journal-title":"Proc Asian Conf Mach Learn"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631082"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2206474"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1005\/1\/012017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095129"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.2514\/6.2009-1983"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2994466"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.2514\/6.2010-7935"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.2514\/1.52532"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2944892"},{"article-title":"Mil-HDBK-1797 flying qualities of piloted aircraft","year":"1997","author":"mitchell","key":"ref67"},{"article-title":"Background information and user guide for MIL-F-8785C, military specification-flying qualities of piloted airplanes","year":"1982","author":"moorhouse","key":"ref68"},{"article-title":"Experimental characterization and simulation of a tethered aerostat with controllable tail fins","year":"2008","author":"howard","key":"ref69"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2009.932530"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23778-7_38"},{"key":"ref20","first-page":"105","article-title":"A novel path planning algorithm based on Q-learning and adaptive exploration strategy","volume":"3","author":"li","year":"2019","journal-title":"Electr Eng Comput Sci"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICISC44355.2019.9036354"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/00051144.2019.1570630"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app9040669"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2514\/6.2019-0391"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/70.736776"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430773"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2922849"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.06.061"},{"key":"ref59","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv 1603 04467"},{"journal-title":"Keras","year":"2015","author":"chollet","key":"ref58"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6377(86)90073-8"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/UEMCON47517.2019.8992966"},{"key":"ref55","article-title":"Visual exploration and energy-aware path planning via reinforcement learning","author":"niaraki","year":"2019","journal-title":"arXiv 1909 12217"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WiMOB.2019.8923410"},{"key":"ref53","article-title":"UAV aided search and rescue operation using reinforcement learning","author":"kulkarni","year":"2020","journal-title":"arXiv 2002 08415"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2941229"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225141"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989375"},{"journal-title":"DJI Matrice M100 Quadcopter for Developers","year":"2021","key":"ref40"},{"key":"ref12","article-title":"Towards search-based motion planning for micro aerial vehicles","author":"liu","year":"2018","journal-title":"arXiv 1810 03071"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794246"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97586-3_4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37406"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.75.1226"},{"key":"ref81","article-title":"Visual exploration and energy-aware path planning via reinforcement learning","author":"niaraki","year":"2019","journal-title":"arXiv 1909 12217"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1006\/jtbi.2002.3065"},{"key":"ref84","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2977693"},{"key":"ref83","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS48674.2020.9213837"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2017.09.027"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT.2015.7125609"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2010.2054080"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2794608"},{"key":"ref5","first-page":"1","article-title":"Decentralized multi-target tracking in urban environments: Overview and challenges","author":"bucci","year":"2019","journal-title":"Proc 22nd Int Conf Inf Fusion (Fusion)"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980409"},{"key":"ref86","article-title":"Implementation matters in deep policy gradients: A case study on PPO and TRPO","author":"engstrom","year":"2020","journal-title":"arXiv 2005 12729"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2430519"},{"key":"ref49","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017","journal-title":"arXiv 1707 02286"},{"key":"ref87","article-title":"Flightmare: A flexible quadrotor simulator","author":"song","year":"2020","journal-title":"arXiv 2009 00563"},{"key":"ref88","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0192987"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2017.07.005"},{"key":"ref48","article-title":"Grid path planning with deep reinforcement learning: Preliminary results","author":"panov","year":"2017","journal-title":"Biologically Inspired Cognitive Architectures"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727894"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05816-6_3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2021.03.004"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1561\/2300000025"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008815304810"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09548090.pdf?arnumber=9548090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T10:26:44Z","timestamp":1699525604000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9548090\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3115711","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}