{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:54:14Z","timestamp":1791914054528,"version":"4.3.4"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T00:00:00Z","timestamp":1791849600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62506378"],"award-info":[{"award-number":["62506378"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Safety-critical autonomous systems often require multiple agents to detect, assign, and intercept non-cooperative mobile targets using only partial observations. These subtasks are tightly coupled because the same agents must balance spatial exploration for detection with goal-directed motion for interception, while target maneuvers remain uncertain. This study develops and validates an integrated multi-agent coordination framework for jointly optimizing distributed detection, dynamic task allocation, and path planning under partial observability. The problem is formulated as a coupled Dec-POMDP made computationally tractable through factored decentralized policies, parameter sharing, and centralized training with decentralized execution, and a Weighted Coordinated Multi-Agent Proximal Policy Optimization (W-MAPPO) framework is introduced to adaptively coordinate competing subtasks. W-MAPPO combines an observation-conditioned Policy Ratio Predictor, an LSTM-based history-aware processor for temporal modeling of target maneuvers, and a Voronoi-based collaborative detection module for spatial coverage coordination within a centralized-training decentralized-execution paradigm. Comprehensive simulation experiments across increasing target densities compare W-MAPPO with seven representative MARL baselines and two classical methods, supported by statistical testing, ablation studies, sensitivity analysis, and representative case studies. W-MAPPO achieves a 94% success rate in the 5 vs 5 scenario and maintains stable interception performance as the number of targets increases to 10 and 15. These results demonstrate the technical reliability and practical potential of integrated subtask coordination for partially observable multi-agent systems.<\/jats:p>","DOI":"10.1371\/journal.pone.0359071","type":"journal-article","created":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:37:26Z","timestamp":1791913046000},"page":"e0359071","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Joint optimization of detection, task allocation, and path planning for multi-agent cooperative interception under partial observability"],"prefix":"10.1371","volume":"21","author":[{"given":"Qinlong","family":"Huang","sequence":"first","affiliation":[{"name":"Naval University of Engineering","place":["Wuhan, Hubei, P. R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2647-8000","authenticated-orcid":true,"given":"Zhikun","family":"Liu","sequence":"additional","affiliation":[{"name":"Naval University of Engineering","place":["Wuhan, Hubei, P. R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasong","family":"Luo","sequence":"additional","affiliation":[{"name":"Naval University of Engineering","place":["Wuhan, Hubei, P. R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong","family":"Liu","sequence":"additional","affiliation":[{"name":"Naval University of Engineering","place":["Wuhan, Hubei, P. R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingtao","family":"Xia","sequence":"additional","affiliation":[{"name":"Naval University of Engineering","place":["Wuhan, Hubei, P. R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Naval University of Engineering","place":["Wuhan, Hubei, P. R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,13]]},"reference":[{"issue":"11","key":"pone.0359071.ref001","doi-asserted-by":"crossref","first-page":"103934","DOI":"10.1016\/j.cja.2025.103934","article-title":"Reach-avoid differential games technologies for anti-unmanned aerial vehicles","volume":"39","author":"R Liang","year":"2026","journal-title":"Chinese Journal of Aeronautics"},{"issue":"4","key":"pone.0359071.ref002","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1109\/TETCI.2020.2992778","article-title":"A comprehensive review of shepherding as a bio-inspired swarm-robotics guidance approach","volume":"4","author":"NK Long","year":"2020","journal-title":"IEEE Trans Emerg Top Comput Intell"},{"issue":"1","key":"pone.0359071.ref003","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s13677-023-00567-8","article-title":"Context-aware environment online monitoring for safety autonomous vehicle systems: An automata-theoretic approach","volume":"13","author":"Y Zhang","year":"2024","journal-title":"Journal of Cloud Computing: Advances, Systems and Applications"},{"issue":"11","key":"pone.0359071.ref004","article-title":"CFDAgent: A language-guided, zero-shot multi-agent system for complex flow simulation","volume":"37","author":"Z Xu","year":"2025","journal-title":"Physics of Fluids"},{"issue":"7","key":"pone.0359071.ref005","doi-asserted-by":"crossref","first-page":"5539","DOI":"10.1109\/TWC.2025.3547794","article-title":"Dynamic access control in multi-layer satellite remote sensing system using multi-agent deep reinforcement learning","volume":"24","author":"H Hu","year":"2025","journal-title":"IEEE Trans Wireless Commun"},{"key":"pone.0359071.ref006","doi-asserted-by":"crossref","first-page":"103770","DOI":"10.1016\/j.jnca.2023.103770","article-title":"Dynamic resource management in integrated NOMA terrestrial\u2013satellite networks using multi-agent reinforcement learning","volume":"221","author":"A Nauman","year":"2024","journal-title":"Journal of Network and Computer Applications"},{"issue":"2","key":"pone.0359071.ref007","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-025-11439-9","article-title":"Reinforcement learning for single-agent to multi-agent systems: From basic theory to industrial application progress, a survey","volume":"59","author":"D Zhang","year":"2025","journal-title":"Artif Intell Rev"},{"issue":"3","key":"pone.0359071.ref008","doi-asserted-by":"crossref","first-page":"2447","DOI":"10.1109\/TII.2025.3640714","article-title":"Multi-UAV Interception Decision-Making via Meta Reinforcement Learning","volume":"22","author":"C Qi","year":"2026","journal-title":"IEEE Trans Ind Inf"},{"issue":"4","key":"pone.0359071.ref009","doi-asserted-by":"crossref","first-page":"2221","DOI":"10.1109\/LRA.2023.3245412","article-title":"Multi-Agent System for Rogue Drone Interception","volume":"8","author":"N Souli","year":"2023","journal-title":"IEEE Robot Autom Lett"},{"issue":"3","key":"pone.0359071.ref010","doi-asserted-by":"crossref","first-page":"3588","DOI":"10.1109\/TASE.2023.3281577","article-title":"An Efficient distributed task allocation method for maximizing task allocations of multirobot systems","volume":"21","author":"S Wang","year":"2024","journal-title":"IEEE Trans Automat Sci Eng"},{"issue":"7","key":"pone.0359071.ref011","doi-asserted-by":"crossref","first-page":"4562","DOI":"10.1109\/TSMC.2025.3551500","article-title":"Capability-oriented decision-making in multi-UAV deployment and task allocation: A hierarchical game-based framework","volume":"55","author":"X Hai","year":"2025","journal-title":"IEEE Trans Syst Man Cybern, Syst"},{"key":"pone.0359071.ref012","doi-asserted-by":"crossref","first-page":"12730","DOI":"10.1109\/TASE.2025.3544306","article-title":"Distributed output feedback prescribed performance control for high-order nonlinear multi-agent systems","volume":"22","author":"Z Li","year":"2025","journal-title":"IEEE Trans Automat Sci Eng"},{"issue":"3","key":"pone.0359071.ref013","doi-asserted-by":"crossref","first-page":"1669","DOI":"10.1109\/JSYST.2024.3432796","article-title":"Approximate optimal strategy for multiagent system pursuit\u2013evasion game","volume":"18","author":"Z Xu","year":"2024","journal-title":"IEEE Systems Journal"},{"issue":"6","key":"pone.0359071.ref014","doi-asserted-by":"crossref","first-page":"3263","DOI":"10.1109\/TCYB.2025.3650263","article-title":"Distributed capturing strategy in heterogeneous multiagent pursuit-evasion games","volume":"56","author":"R Shi","year":"2026","journal-title":"IEEE Trans Cybern"},{"issue":"4","key":"pone.0359071.ref015","doi-asserted-by":"crossref","first-page":"6085","DOI":"10.1109\/TIE.2025.3626621","article-title":"A constrained stochastic game approach to pursuit-evasion problem: Theory and application to quadruped robots","volume":"73","author":"D Yang","year":"2026","journal-title":"IEEE Transactions on Industrial Electronics"},{"issue":"8","key":"pone.0359071.ref016","doi-asserted-by":"crossref","DOI":"10.1007\/s44443-025-00176-2","article-title":"A weighted Stackelberg strategy approach for three pursuers against a superior evader using reinforcement learning","volume":"37","author":"Z Zhan","year":"2025","journal-title":"J King Saud Univ Comput Inf Sci"},{"key":"pone.0359071.ref017","doi-asserted-by":"crossref","first-page":"108643","DOI":"10.1016\/j.ress.2022.108643","article-title":"Condition-based maintenance strategy for redundant systems with arbitrary structures using improved reinforcement learning","volume":"225","author":"A Yang","year":"2022","journal-title":"Reliability Engineering & System Safety"},{"key":"pone.0359071.ref018","doi-asserted-by":"crossref","first-page":"126800","DOI":"10.1016\/j.eswa.2025.126800","article-title":"Joint optimization of quality control and maintenance policy for a production system with quality-dependent failures","volume":"272","author":"J Wang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"pone.0359071.ref019","doi-asserted-by":"crossref","first-page":"111345","DOI":"10.1016\/j.ress.2025.111345","article-title":"Joint optimization of maintenance policy and two-way stock transshipments policy for balanced systems","volume":"264","author":"J Wang","year":"2025","journal-title":"Reliability Engineering & System Safety"},{"key":"pone.0359071.ref020","doi-asserted-by":"crossref","first-page":"112138","DOI":"10.1016\/j.ress.2025.112138","article-title":"Multi-level adaptive risk control: Synergistic maintenance-termination optimization with online parameter learning","volume":"270","author":"Y Ma","year":"2026","journal-title":"Reliability Engineering & System Safety"},{"issue":"1","key":"pone.0359071.ref021","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1109\/TCNS.2025.3649099","article-title":"IDCAIS: Interdefender Collision-Aware Interception Strategy Against Multiple Attackers","volume":"13","author":"VS Chipade","year":"2026","journal-title":"IEEE Trans Control Netw Syst"},{"key":"pone.0359071.ref022","doi-asserted-by":"crossref","first-page":"126029","DOI":"10.1016\/j.eswa.2024.126029","article-title":"Multi-evader dynamic pursuit strategy based on improved AAPC and auction algorithm amidst static and dynamic obstacles","volume":"266","author":"M Chen","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"pone.0359071.ref023","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.automatica.2017.03.015","article-title":"Sequential pursuit of multiple targets under external disturbances via Zermelo\u2013Voronoi diagrams","volume":"81","author":"W Sun","year":"2017","journal-title":"Automatica"},{"key":"pone.0359071.ref024","doi-asserted-by":"crossref","first-page":"106068","DOI":"10.1016\/j.engappai.2023.106068","article-title":"Optimal non-autonomous area coverage control with adaptive reinforcement learning","volume":"122","author":"F Soleymani","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"2","key":"pone.0359071.ref025","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1109\/TAC.2023.3278794","article-title":"Pursuer coordination against a fast evader via coverage control","volume":"69","author":"P Rivera","year":"2024","journal-title":"IEEE Transactions on Automatic Control"},{"issue":"17","key":"pone.0359071.ref026","doi-asserted-by":"crossref","first-page":"12700","DOI":"10.1016\/j.jfranklin.2020.08.039","article-title":"Distributed coordination of multi-agent systems for neutralizing unknown threats based on a mixed coverage-tracking metric","volume":"357","author":"K Luo","year":"2020","journal-title":"Journal of the Franklin Institute"},{"issue":"12","key":"pone.0359071.ref027","doi-asserted-by":"crossref","first-page":"8877","DOI":"10.1109\/TSMC.2025.3613395","article-title":"Mission-driven trajectory homotopy to explore dynamic coverage of USV\u2013UAV systems","volume":"55","author":"J Fu","year":"2025","journal-title":"IEEE Trans Syst Man Cybern, Syst"},{"key":"pone.0359071.ref028","doi-asserted-by":"crossref","first-page":"117395","DOI":"10.1016\/j.oceaneng.2024.117395","article-title":"Vessel intrusion interception utilising unmanned surface vehicles for offshore wind farm asset protection","volume":"299","author":"Y Gu","year":"2024","journal-title":"Ocean Engineering"},{"issue":"2","key":"pone.0359071.ref029","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1109\/TSMC.2024.3501480","article-title":"Priority-based DREAM approach for highly manoeuvring intruders in a perimeter defense problem","volume":"55","author":"S Velhal","year":"2025","journal-title":"IEEE Trans Syst Man Cybern, Syst"},{"issue":"4","key":"pone.0359071.ref030","first-page":"2149","article-title":"A game theory-based approach for multiple UAVs cooperative target defense","volume":"71","author":"B Tong","year":"2024","journal-title":"IEEE Trans Circuits Syst II"},{"issue":"10","key":"pone.0359071.ref031","doi-asserted-by":"crossref","first-page":"3700","DOI":"10.1109\/TMC.2021.3062225","article-title":"Multi-Agent Coordinated Close-in Jamming for Disabling a Rogue Drone","volume":"21","author":"P Valianti","year":"2022","journal-title":"IEEE Trans on Mobile Comput"},{"key":"pone.0359071.ref032","doi-asserted-by":"crossref","DOI":"10.34133\/space.0086","article-title":"Orbital interception pursuit strategy for random evasion using deep reinforcement learning","volume":"3","author":"R Jiang","year":"2023","journal-title":"Space Sci Technol"},{"issue":"7","key":"pone.0359071.ref033","doi-asserted-by":"crossref","first-page":"3320","DOI":"10.1109\/TCYB.2025.3562263","article-title":"Nash-minmax strategies for multiagent pursuit-evasion games with reinforcement learning","volume":"55","author":"Y Wang","year":"2025","journal-title":"IEEE Trans Cybern"},{"key":"pone.0359071.ref034","doi-asserted-by":"crossref","first-page":"114896","DOI":"10.1016\/j.eswa.2021.114896","article-title":"A deep reinforcement learning-based method applied for solving multi-agent defense and attack problems","volume":"176","author":"L Huang","year":"2021","journal-title":"Expert Systems with Applications"},{"issue":"3","key":"pone.0359071.ref035","doi-asserted-by":"crossref","first-page":"3727","DOI":"10.1007\/s40747-024-01385-4","article-title":"A modified evolutionary reinforcement learning for multi-agent region protection with fewer defenders","volume":"10","author":"S Sun","year":"2024","journal-title":"Complex Intell Syst"},{"key":"pone.0359071.ref036","doi-asserted-by":"crossref","first-page":"129702","DOI":"10.1016\/j.eswa.2025.129702","article-title":"DASF-GRL: Dynamic agent-scaling framework with game-augmented reinforcement learning for defensive counter-air operations","volume":"298","author":"Y Chen","year":"2026","journal-title":"Expert Systems with Applications"},{"issue":"7","key":"pone.0359071.ref037","first-page":"3614","article-title":"Multi-task learning for dense prediction tasks: A Survey","volume":"44","author":"S Vandenhende","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"pone.0359071.ref038","doi-asserted-by":"crossref","first-page":"7254","DOI":"10.1109\/TIT.2025.3581454","article-title":"Theoretical study of conflict-avoidant multi-objective reinforcement learning","volume":"71","author":"Y Wang","year":"2025","journal-title":"IEEE Trans Inform Theory"},{"issue":"6","key":"pone.0359071.ref039","article-title":"Large sequence models for sequential decision-making: A survey","volume":"17","author":"M Wen","year":"2023","journal-title":"Front Comput Sci"},{"key":"pone.0359071.ref040","unstructured":"Schulman J, Moritz P, Levine S, Jordan M, Abbeel P. High-dimensional continuous control using generalized advantage estimation. arXiv preprint. 2016. https:\/\/arxiv.org\/abs\/1506.02438"},{"key":"pone.0359071.ref041","doi-asserted-by":"crossref","unstructured":"Yu C, Velu A, Vinitsky E, Gao J, Wang Y, Bayen A, et al. The surprising effectiveness of PPO in cooperative multi-agent games. In: Advances in Neural Information Processing Systems 35, 2022. 24611\u201324. https:\/\/doi.org\/10.52202\/068431-1787","DOI":"10.52202\/068431-1787"},{"key":"pone.0359071.ref042","unstructured":"de Witt CS, Gupta T, Makoviichuk D, Makoviychuk V, Torr PHS, Sun M, et al. Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge? 2020."},{"key":"pone.0359071.ref043","unstructured":"Lowe R, Wu Y, Tamar A, Harb J, Abbeel P, Mordatch I. Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, Curran Associates, Inc. 2017."},{"key":"pone.0359071.ref044","unstructured":"Wang J, Ren Z, Liu T, Yu Y, Zhang C. QPLEX: Duplex dueling multi-agent Q-learning. In: International Conference on Learning Representations. 2021."},{"key":"pone.0359071.ref045","doi-asserted-by":"crossref","unstructured":"Wen M, Kuba J, Lin R, Zhang W, Wen Y, Wang J, et al. Multi-agent reinforcement learning is a sequence modeling problem. In: Advances in Neural Information Processing Systems 35, 2022. 16509\u201321. https:\/\/doi.org\/10.52202\/068431-1201","DOI":"10.52202\/068431-1201"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:37:35Z","timestamp":1791913055000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359071"}},"subtitle":[],"editor":[{"given":"Qingan","family":"Qiu","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,13]]},"references-count":45,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0359071","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,13]]}}}