{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T04:03:43Z","timestamp":1784261023884,"version":"3.55.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:00:00Z","timestamp":1778544000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:00:00Z","timestamp":1778544000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Intel Serv Robotics"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s11370-026-00712-7","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T09:23:29Z","timestamp":1778577809000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A modified double DQN for UAV path planning: dynamic reward shaping and heuristic-guided tie-breaking"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8895-4460","authenticated-orcid":false,"given":"Ghulam","family":"Farid","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanyong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ishaq","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Usman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asma","family":"Iqbal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Talha","family":"Younas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,12]]},"reference":[{"issue":"16","key":"712_CR1","doi-asserted-by":"publisher","first-page":"14438","DOI":"10.1109\/JIOT.2023.3268316","volume":"10","author":"N Cheng","year":"2023","unstructured":"Cheng N et al (2023) AI for UAV-assisted IoT applications: a comprehensive review. IEEE Internet Things J 10(16):14438\u201314461","journal-title":"IEEE Internet Things J"},{"issue":"1","key":"712_CR2","doi-asserted-by":"publisher","first-page":"1068","DOI":"10.1109\/TASE.2022.3232025","volume":"21","author":"D Dissanayaka","year":"2024","unstructured":"Dissanayaka D et al (2024) Review of navigation methods for UAV-based parcel delivery. IEEE Trans Autom Sci Eng 21(1):1068\u20131082","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"712_CR3","doi-asserted-by":"crossref","unstructured":"Yuning J et al (2019) An adaptive neural network state estimator for Q-uadrotor unmanned air vehicle. Int J Adv Compute Sci Appl 10(2)","DOI":"10.14569\/IJACSA.2019.0100242"},{"key":"712_CR4","doi-asserted-by":"crossref","unstructured":"Farid G et al (2018) On control law partitioning for nonlinear control of a Q-uadrotor UAV. In: 2018 15th International Bhurban conference on applied sciences and technology (IBCAST)","DOI":"10.1109\/IBCAST.2018.8312233"},{"issue":"5","key":"712_CR5","doi-asserted-by":"publisher","first-page":"376","DOI":"10.3390\/drones9050376","volume":"9","author":"W Meng","year":"2025","unstructured":"Meng W et al (2025) Advances in UAV path planning: a comprehensive review of methods, challenges, and future directions. Drones 9(5):376","journal-title":"Drones"},{"issue":"12","key":"712_CR6","doi-asserted-by":"publisher","DOI":"10.3390\/app12125791","volume":"12","author":"G Farid","year":"2022","unstructured":"Farid G et al (2022) Modified A-Star (A*) approach to plan the motion of a Q-uadrotor UAV in Three-dimensional obstacle-cluttered environment. Appl Sci 12(12):5791","journal-title":"Appl Sci"},{"key":"712_CR7","doi-asserted-by":"publisher","first-page":"135","DOI":"10.4028\/www.scientific.net\/JERA.44.135","volume":"44","author":"SA Dahmane","year":"2019","unstructured":"Dahmane SA et al (2019) Determination of the optimal path of three axes robot using genetic algorithm. Int J Eng Res Afr 44:135\u2013149","journal-title":"Int J Eng Res Afr"},{"issue":"3","key":"712_CR8","doi-asserted-by":"publisher","first-page":"203","DOI":"10.3390\/drones9030203","volume":"9","author":"A Merei","year":"2025","unstructured":"Merei A et al (2025) A survey on obstacle detection and avoidance methods for UAVs. Drones 9(3):203","journal-title":"Drones"},{"key":"712_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2025.103497","author":"Z Cao","year":"2025","unstructured":"Cao Z, Chen G (2025) Enhanced deep reinforcement learning for integrated navigation in multi-UAV systems. Chin J Aeronaut. https:\/\/doi.org\/10.1016\/j.cja.2025.103497","journal-title":"Chin J Aeronaut"},{"issue":"12","key":"712_CR10","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.cja.2020.12.027","volume":"34","author":"Z Hu","year":"2021","unstructured":"Hu Z et al (2021) Relevant experience learning: a deep reinforcement learning method for UAV autonomous motion planning in complex unknown environments. Chin J Aeronaut 34(12):187\u2013204","journal-title":"Chin J Aeronaut"},{"key":"712_CR11","doi-asserted-by":"publisher","first-page":"108194","DOI":"10.1016\/j.asoc.2021.108194","volume":"115","author":"S Zhang","year":"2022","unstructured":"Zhang S, Li Y, Dong Q (2022) Autonomous navigation of UAV in multi-obstacle environments based on a deep reinforcement learning approach. Appl Soft Comput 115:108194","journal-title":"Appl Soft Comput"},{"key":"712_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2025.113836","volume":"184","author":"G Farid","year":"2025","unstructured":"Farid G et al (2025) A multi-goal reinforcement learning framework for motion planning of a Q-uadrotor UAV in 3D cluttered environment with unseen random goals. Appl Soft Comput 184:113836","journal-title":"Appl Soft Comput"},{"issue":"7540","key":"712_CR13","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V et al (2015) Human-level control through deep reinforcement rearning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"712_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-025-00620-2","author":"J Jiang","year":"2025","unstructured":"Jiang J et al (2025) Path planning in dynamic structured environments using transformer-enabled twin delayed deep deterministic policy gradient for mobile robots in simulation. Intel Serv Robot. https:\/\/doi.org\/10.1007\/s11370-025-00620-2","journal-title":"Intel Serv Robot"},{"key":"712_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-025-00622-0","author":"G Farid","year":"2025","unstructured":"Farid G et al (2025) A reinforcement learning approach for multi-goal motion planning of autonomous ground vehicles in cluttered environments. Intel Serv Robot. https:\/\/doi.org\/10.1007\/s11370-025-00622-0","journal-title":"Intel Serv Robot"},{"issue":"7587","key":"712_CR16","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D et al (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529(7587):484\u2013489","journal-title":"Nature"},{"issue":"3","key":"712_CR17","doi-asserted-by":"publisher","first-page":"4685","DOI":"10.32604\/cmc.2023.034892","volume":"74","author":"A Khan","year":"2022","unstructured":"Khan A et al (2022) DQ-N-based proactive trajectory planning of UAVs in multi-access edge computing. Compute Mater Continua 74(3):4685\u20134702","journal-title":"Compute Mater Continua"},{"issue":"3","key":"712_CR18","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/j.cja.2023.09.033","volume":"37","author":"F Wang","year":"2024","unstructured":"Wang F et al (2024) Deep-reinforcement-learning-based UAV autonomous navigation and collision avoidance in unknown environments. Chin J Aeronaut 37(3):237\u2013257","journal-title":"Chin J Aeronaut"},{"issue":"3","key":"712_CR19","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/j.icte.2022.06.004","volume":"9","author":"MH Lee","year":"2023","unstructured":"Lee MH, Moon J (2023) Deep reinforcement learning-based model-free path planning and collision avoidance for UAVs: a soft actor\u2013critic with hindsight experience replay approach. ICT Express 9(3):403\u2013408","journal-title":"ICT Express"},{"issue":"1","key":"712_CR20","doi-asserted-by":"publisher","first-page":"3837615","DOI":"10.1155\/2023\/3837615","volume":"2023","author":"S Zhao","year":"2023","unstructured":"Zhao S et al (2023) Autonomous navigation of the UAV through deep reinforcement learning with sensor perception enhancement. Math Probl Eng 2023(1):3837615","journal-title":"Math Probl Eng"},{"issue":"2","key":"712_CR21","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/j.dt.2020.11.014","volume":"17","author":"B Li","year":"2021","unstructured":"Li B et al (2021) Maneuvering target tracking of UAV based on MN-DDPG and transfer learning. Defence Technol 17(2):457\u2013466","journal-title":"Defence Technol"},{"key":"712_CR22","unstructured":"Q-i C et al (2022) UAV path planning based on the improved PPO algorithm. In: 2022 Asia conference on advanced robotics, automation, and control engineering (ARACE)"},{"issue":"1","key":"712_CR23","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/2804943","volume":"2023","author":"Z Guo","year":"2023","unstructured":"Guo Z, Chen H, Li S (2023) Deep reinforcement learning-based UAV path planning for energy-efficient multitier cooperative computing in wireless sensor networks. J Sensors 2023(1):2804943","journal-title":"J Sensors"},{"issue":"2","key":"712_CR24","doi-asserted-by":"publisher","first-page":"57","DOI":"10.3390\/act12020057","volume":"12","author":"G-T Tu","year":"2023","unstructured":"Tu G-T, Juang J-G (2023) UAV path planning and obstacle avoidance based on reinforcement learning in 3D environments. Actuators 12(2):57","journal-title":"Actuators"},{"key":"712_CR25","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/978-3-031-28715-2_2","volume-title":"Artificial intelligence for robotics and autonomous systems applications","author":"R Dong","year":"2023","unstructured":"Dong R et al (2023) UAV path planning based on deep reinforcement learning. In: Azar AT, Koubaa A (eds) Artificial intelligence for robotics and autonomous systems applications. Springer International Publishing, Cham, pp 27\u201365"},{"key":"712_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-025-00457-z","author":"LGS Rocha","year":"2025","unstructured":"Rocha LGS et al (2025) Dynamic Q-planning for online UAV path planning in unknown and complex environments. Int J Intell Robot Appl. https:\/\/doi.org\/10.1007\/s41315-025-00457-z","journal-title":"Int J Intell Robot Appl"},{"issue":"8","key":"712_CR27","doi-asserted-by":"publisher","first-page":"518","DOI":"10.3390\/drones9080518","volume":"9","author":"G Farid","year":"2025","unstructured":"Farid G et al (2025) An improved deep Q-learning approach for navigation of an autonomous UAV agent in 3D obstacle-cluttered environment. Drones 9(8):518","journal-title":"Drones"},{"key":"712_CR28","unstructured":"Hasselt Hv, Guez A, Silver D (2016) Deep reinforcement learning with double Q-learning. In: Proceedings of the Thirtieth AAAI conference on artificial intelligence. AAAI Press: Phoenix, Arizona,. pp 2094\u20132100"},{"key":"712_CR29","doi-asserted-by":"crossref","unstructured":"van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double Q-learning. In: Proceedings of the AAAI conference on artificial intelligence 30(1)","DOI":"10.1609\/aaai.v30i1.10295"},{"issue":"2","key":"712_CR30","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/s10846-019-01073-3","volume":"98","author":"C Yan","year":"2020","unstructured":"Yan C, Xiang X, Wang C (2020) Towards real-time path planning through deep reinforcement learning for a UAV in dynamic environments. J Intell Robot Syst 98(2):297\u2013309","journal-title":"J Intell Robot Syst"},{"key":"712_CR31","doi-asserted-by":"crossref","unstructured":"Zhang F, Gu C, Yang F (2022) An improved algorithm of robot path planning in complex environment based on double DQ-N. Singapore: Springer Singapore","DOI":"10.1007\/978-981-15-8155-7_25"},{"key":"712_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.112809","volume":"266","author":"Y Xiaofei","year":"2022","unstructured":"Xiaofei Y et al (2022) Global path planning algorithm based on double DQ-N for multi-tasks amphibious unmanned surface vehicle. Ocean Eng 266:112809","journal-title":"Ocean Eng"},{"issue":"2","key":"712_CR33","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s40430-023-04025-z","volume":"45","author":"S-A Dahmane","year":"2023","unstructured":"Dahmane S-A et al (2023) Analysis and compensation of positioning errors of robotic systems by an interactive method. J Braz Soc Mech Sci Eng 45(2):119","journal-title":"J Braz Soc Mech Sci Eng"},{"issue":"2","key":"712_CR34","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/s12008-018-0519-z","volume":"13","author":"S-A Dahmane","year":"2019","unstructured":"Dahmane S-A et al (2019) Q-uantitative and Q-ualitative study of methods for solving the kinematic problem of a planar parallel manipulator based on precision error optimization. Int J Interactive Design Manuf (IJIDeM) 13(2):567\u2013595","journal-title":"Int J Interactive Design Manuf (IJIDeM)"},{"key":"712_CR35","doi-asserted-by":"crossref","unstructured":"Farid G et al (2018) Comprehensive modelling and static feedback linearization-based trajectory tracking control of a Q-uadrotor UAV. Mechatronic Syst Control (Formerly Control and Intelligent Systems) 46(3)","DOI":"10.2316\/Journal.201.2018.3.201-2846"},{"key":"712_CR36","doi-asserted-by":"crossref","unstructured":"Mellinger D, Kumar V (2011) Minimum snap trajectory generation and control for Q-uadrotors. In: 2011 IEEE international conference on robotics and automation","DOI":"10.1109\/ICRA.2011.5980409"},{"issue":"2","key":"712_CR37","first-page":"225","volume":"27","author":"G Farid","year":"2018","unstructured":"Farid G et al (2018) Waypoint-based generation of guided and optimal trajectories for autonomous tracking using a quadrotor UAV. Stud Inform Control 27(2):225\u2013236","journal-title":"Stud Inform Control"}],"container-title":["Intelligent Service Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-026-00712-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11370-026-00712-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-026-00712-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T03:12:21Z","timestamp":1784257941000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11370-026-00712-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,12]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["712"],"URL":"https:\/\/doi.org\/10.1007\/s11370-026-00712-7","relation":{},"ISSN":["1861-2776","1861-2784"],"issn-type":[{"value":"1861-2776","type":"print"},{"value":"1861-2784","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,12]]},"assertion":[{"value":"7 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare they do not have any conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This paper does not contain any studies with human or animal participants.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors agreed to participate in the research.","order":3,"name":"Ethics","label":"Consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"59"}}