{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T05:17:46Z","timestamp":1778563066851,"version":"3.51.4"},"reference-count":40,"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"}],"funder":[{"DOI":"10.13039\/501100012334","name":"Graduate Scientific Research and Innovation Foundation of Chongqing","doi-asserted-by":"publisher","award":["CYB240066"],"award-info":[{"award-number":["CYB240066"]}],"id":[{"id":"10.13039\/501100012334","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42474027"],"award-info":[{"award-number":["42474027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403085"],"award-info":[{"award-number":["62403085"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.115920","type":"journal-article","created":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T11:20:16Z","timestamp":1775388016000},"page":"115920","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Policy distillation-based multiagent actor\u2013critic for cooperative UAV path planning in complex environments"],"prefix":"10.1016","volume":"342","author":[{"given":"Huidong","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangshan","family":"Ai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2623-8768","authenticated-orcid":false,"given":"Xianlei","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangwei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuqiang","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115920_b1","article-title":"Research on UAVs reconnaissance task allocation method based on communication preservation","author":"Li","year":"2024","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.knosys.2026.115920_b2","article-title":"TEBChain: A trusted and efficient blockchain-based data sharing scheme in UAV-assisted IoV for disaster rescue","author":"Wang","year":"2024","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"10.1016\/j.knosys.2026.115920_b3","article-title":"Optimal trajectory design for unmanned aerial vehicle cargo pickup and delivery system based on radio map","author":"Chen","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"3","key":"10.1016\/j.knosys.2026.115920_b4","doi-asserted-by":"crossref","first-page":"1816","DOI":"10.1109\/TRO.2023.3236945","article-title":"Racer: Rapid collaborative exploration with a decentralized multi-uav system","volume":"39","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.knosys.2026.115920_b5","article-title":"Extrinsic-and-intrinsic reward-based multi-agent reinforcement learning for multi-UAV cooperative target encirclement","author":"Chen","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"8","key":"10.1016\/j.knosys.2026.115920_b6","doi-asserted-by":"crossref","first-page":"8290","DOI":"10.1109\/TITS.2023.3258482","article-title":"Distributed stochastic algorithm based on enhanced genetic algorithm for path planning of multi-UAV cooperative area search","volume":"24","author":"Zheng","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.knosys.2026.115920_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111604","article-title":"Autonomous obstacle avoidance and target tracking of UAV: Transformer for observation sequence in reinforcement learning","volume":"290","author":"Jiang","year":"2024","journal-title":"Knowl.-Based Syst."},{"issue":"1","key":"10.1016\/j.knosys.2026.115920_b8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3673896","article-title":"A survey of 3D space path-planning methods and algorithms","volume":"57","author":"Mazaheri","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.knosys.2026.115920_b9","article-title":"Comprehensive review of path planning techniques for unmanned aerial vehicles (UAVs)","author":"Kumar","year":"2025","journal-title":"ACM Comput. Surv."},{"issue":"2","key":"10.1016\/j.knosys.2026.115920_b10","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1109\/JAS.2023.123945","article-title":"Multi-UAVs collaborative path planning in the cramped environment","volume":"11","author":"Feng","year":"2024","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.knosys.2026.115920_b11","article-title":"Multi-UAV cooperative motion planning under global spatio-temporal path inspiration in constraint-rich dynamic environments","author":"Mao","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.knosys.2026.115920_b12","doi-asserted-by":"crossref","DOI":"10.1109\/TVT.2025.3560658","article-title":"Multi-goal rapidly exploring random tree with safety and dynamic constraints for UAV cooperative path planning","author":"Khuat","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.knosys.2026.115920_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102354","article-title":"Super eagle optimization algorithm based three-dimensional ball security corridor planning method for fixed-wing UAVs","volume":"59","author":"Hu","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.knosys.2026.115920_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2022.101829","article-title":"A multi-population immune plasma algorithm for path planning of unmanned combat aerial vehicle","volume":"55","author":"Aslan","year":"2023","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.knosys.2026.115920_b15","series-title":"2009 IEEE International Conference on Robotics and Biomimetics","first-page":"877","article-title":"Hybrid multi-robot path planning strategy based on RRT and fuzzy control in wireless sensor network","author":"Song","year":"2009"},{"issue":"2","key":"10.1016\/j.knosys.2026.115920_b16","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1109\/JAS.2021.1004252","article-title":"An adaptive rapidly-exploring random tree","volume":"9","author":"Li","year":"2021","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.knosys.2026.115920_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110797","article-title":"Path planning for dual UAVs cooperative suspension transport based on artificial potential field-A* algorithm","volume":"277","author":"Rao","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115920_b18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10846-021-01490-3","article-title":"A novel hybrid discrete grey wolf optimizer algorithm for multi-UAV path planning","volume":"103","author":"Huang","year":"2021","journal-title":"J. Intell. Robot. Syst."},{"key":"10.1016\/j.knosys.2026.115920_b19","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.comcom.2020.04.050","article-title":"Optimized multi-UAV cooperative path planning under the complex confrontation environment","volume":"162","author":"Xu","year":"2020","journal-title":"Comput. Commun."},{"key":"10.1016\/j.knosys.2026.115920_b20","series-title":"Multi-agent reinforcement learning-based UAV pathfinding for obstacle avoidance in stochastic environment","author":"Wu","year":"2024"},{"key":"10.1016\/j.knosys.2026.115920_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111462","article-title":"Novel task decomposed multi-agent twin delayed deep deterministic policy gradient algorithm for multi-UAV autonomous path planning","volume":"287","author":"Zhou","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115920_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113429","article-title":"Adaptive multi-UAV cooperative path planning based on novel rotation artificial potential fields","volume":"317","author":"Liu","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115920_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103115","article-title":"Collaborative path planning of multi-unmanned surface vehicles via multi-stage constrained multi-objective optimization","volume":"65","author":"Yin","year":"2025","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.knosys.2026.115920_b24","article-title":"An efficient reinforcement learning-based cooperative navigation algorithm for multiple UAVs in complex environments","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.knosys.2026.115920_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2023.110773","article-title":"Q-learning-based unmanned aerial vehicle path planning with dynamic obstacle avoidance","volume":"147","author":"Sonny","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.knosys.2026.115920_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2025.103157","article-title":"A multi-aircraft co-operative trajectory planning model under dynamic thunderstorm cells using decentralized deep reinforcement learning","volume":"65","author":"Pang","year":"2025","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.knosys.2026.115920_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102947","article-title":"UAV formation path planning for mountainous forest terrain utilizing an artificial rabbit optimizer incorporating reinforcement learning and thermal conduction search strategies","volume":"62","author":"Wang","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.knosys.2026.115920_b28","article-title":"NPE-DRL: Enhancing perception constrained obstacle avoidance with non-expert policy guided reinforcement learning","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Artif. Intell."},{"issue":"16","key":"10.1016\/j.knosys.2026.115920_b29","doi-asserted-by":"crossref","first-page":"14014","DOI":"10.1109\/JIOT.2023.3240671","article-title":"Improving sample efficiency of multiagent reinforcement learning with nonexpert policy for flocking control","volume":"10","author":"Qiu","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.knosys.2026.115920_b30","series-title":"A Concise Introduction to Decentralized POMDPs","author":"Oliehoek","year":"2016"},{"issue":"2","key":"10.1016\/j.knosys.2026.115920_b31","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","article-title":"Multi-agent deep reinforcement learning: a survey","volume":"55","author":"Gronauer","year":"2022","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.knosys.2026.115920_b32","series-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"10.1016\/j.knosys.2026.115920_b33","series-title":"Policy distillation","author":"Rusu","year":"2015"},{"key":"10.1016\/j.knosys.2026.115920_b34","series-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","first-page":"31","article-title":"PTDE: Personalized training with distilled execution for multi-agent reinforcement learning","author":"Chen","year":"2024"},{"key":"10.1016\/j.knosys.2026.115920_b35","series-title":"ISIE 2001. 2001 IEEE International Symposium on Industrial Electronics Proceedings (Cat. No. 01TH8570)","first-page":"1530","article-title":"Obstacle avoidance for mobile robots using artificial potential field approach with simulated annealing","volume":"Vol. 3","author":"Park","year":"2001"},{"key":"10.1016\/j.knosys.2026.115920_b36","series-title":"International Conference on Machine Learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"10.1016\/j.knosys.2026.115920_b37","doi-asserted-by":"crossref","DOI":"10.1109\/TCCN.2024.3412073","article-title":"Age of information aware trajectory planning of UAV","author":"Pan","year":"2024","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"issue":"6","key":"10.1016\/j.knosys.2026.115920_b38","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.cja.2024.03.030","article-title":"MADRL-based UAV swarm non-cooperative game under incomplete information","volume":"37","author":"Ershen","year":"2024","journal-title":"Chin. J. Aeronaut."},{"key":"10.1016\/j.knosys.2026.115920_b39","series-title":"2022 IEEE 17th International Conference on Control & Automation","first-page":"249","article-title":"Research on autonomous formation of multi-UAV based on MADDPG algorithm","author":"Zhang","year":"2022"},{"issue":"11","key":"10.1016\/j.knosys.2026.115920_b40","doi-asserted-by":"crossref","first-page":"12088","DOI":"10.1109\/TVT.2022.3189552","article-title":"Resource allocation in UAV-assisted networks: A clustering-aided reinforcement learning approach","volume":"71","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Veh. Technol."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126006465?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126006465?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T05:03:17Z","timestamp":1778562197000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126006465"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":40,"alternative-id":["S0950705126006465"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115920","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Policy distillation-based multiagent actor\u2013critic for cooperative UAV path planning in complex environments","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115920","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":"115920"}}