{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:16:08Z","timestamp":1783149368345,"version":"3.54.6"},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52402509"],"award-info":[{"award-number":["52402509"]}],"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":["62173016"],"award-info":[{"award-number":["62173016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.engappai.2026.115178","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T16:16:26Z","timestamp":1779812186000},"page":"115178","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Safe reinforcement learning control for adaptive station-keeping of a stratospheric airship in complex environments"],"prefix":"10.1016","volume":"180","author":[{"given":"Zewei","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.engappai.2026.115178_b1","doi-asserted-by":"crossref","first-page":"3861","DOI":"10.1109\/TAC.2016.2638961","article-title":"Control Barrier Function Based Quadratic Programs for Safety Critical Systems","volume":"62","author":"Ames","year":"2017","journal-title":"IEEE Trans. Autom. Control"},{"issue":"1","key":"10.1016\/j.engappai.2026.115178_b2","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1016\/j.asr.2024.09.052","article-title":"Station keeping control method based on deep reinforcement learning for stratospheric aerostat in dynamic wind field","volume":"75","author":"Bai","year":"2025","journal-title":"Adv. Space Res."},{"issue":"7836","key":"10.1016\/j.engappai.2026.115178_b3","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1038\/s41586-020-2939-8","article-title":"Autonomous navigation of stratospheric balloons using reinforcement learning","volume":"588","author":"Bellemare","year":"2020","journal-title":"Nature"},{"issue":"6","key":"10.1016\/j.engappai.2026.115178_b4","doi-asserted-by":"crossref","first-page":"7520","DOI":"10.1109\/TNNLS.2022.3214681","article-title":"Adaptive Optimal Tracking Control of an Underactuated Surface Vessel Using Actor\u2013Critic Reinforcement Learning","volume":"35","author":"Chen","year":"2024","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.engappai.2026.115178_b5","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1016\/j.ymssp.2018.10.003","article-title":"Asymmetric error-constrained path-following control of a stratospheric airship with disturbances and actuator saturation","volume":"119","author":"Chen","year":"2019","journal-title":"Mech. Syst. Signal Process."},{"key":"10.1016\/j.engappai.2026.115178_b6","series-title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","author":"Cheng","year":"2019"},{"key":"10.1016\/j.engappai.2026.115178_b7","series-title":"OCEANS 2019 MTS\/IEEE SEATTLE","first-page":"1","article-title":"Weather Optimal Area Keeping Intermittent Control Based on Reducing Energy Consumption of USV","author":"Deng","year":"2019"},{"key":"10.1016\/j.engappai.2026.115178_b8","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1016\/j.ast.2019.06.035","article-title":"Station-keeping performance analysis for high altitude balloon with altitude control system","volume":"92","author":"Du","year":"2019","journal-title":"Aerosp. Sci. Technol."},{"issue":"5","key":"10.1016\/j.engappai.2026.115178_b9","doi-asserted-by":"crossref","first-page":"7853","DOI":"10.1109\/TIE.2025.3645468","article-title":"Preassigned performance attitude control without singularity and unwinding phenomenon","volume":"73","author":"Feng","year":"2026","journal-title":"IEEE Trans. Ind. Electron."},{"key":"10.1016\/j.engappai.2026.115178_b10","series-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.engappai.2026.115178_b11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIV.2024.3379582","article-title":"Safe Reinforcement Learning for Autonomous Driving by Using Disturbance-Observer-Based Control Barrier Functions","author":"Hou","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"3","key":"10.1016\/j.engappai.2026.115178_b12","doi-asserted-by":"crossref","first-page":"2332","DOI":"10.1109\/TIV.2022.3233592","article-title":"Safe Reinforcement Learning for Model-Reference Trajectory Tracking of Uncertain Autonomous Vehicles With Model-Based Acceleration","volume":"8","author":"Hu","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"5","key":"10.1016\/j.engappai.2026.115178_b13","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1016\/S0005-1098(01)00006-1","article-title":"Nonlinear passive weather optimal positioning control (WOPC) system for ships and rigs: experimental results","volume":"37","author":"I. Fossen","year":"2001","journal-title":"Automatica"},{"key":"10.1016\/j.engappai.2026.115178_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2020.105792","article-title":"Station-keeping control design of double balloon system based on horizontal region constraints","volume":"100","author":"Jiang","year":"2020","journal-title":"Aerosp. Sci. Technol."},{"key":"10.1016\/j.engappai.2026.115178_b15","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1016\/j.renene.2020.04.011","article-title":"Performance evaluation for scientific balloon station-keeping strategies considering energy management strategy","volume":"156","author":"Jiang","year":"2020","journal-title":"Renew. Energy"},{"issue":"3","key":"10.1016\/j.engappai.2026.115178_b16","doi-asserted-by":"crossref","first-page":"2005","DOI":"10.1109\/TMECH.2024.3427372","article-title":"A robust safety\u2013critical control framework for control affine systems with applications to AUVs","volume":"30","author":"Jiang","year":"2025","journal-title":"IEEE\/ASME Trans. Mechatronics"},{"key":"10.1016\/j.engappai.2026.115178_b17","series-title":"Nonlinear Systems","author":"Khalil","year":"2002"},{"issue":"23","key":"10.1016\/j.engappai.2026.115178_b18","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.ifacol.2016.10.348","article-title":"Weather-optimal control of a dynamic positioning vessel using backstepping: Simulation and model experiment","volume":"49","author":"Kim","year":"2016","journal-title":"IFAC-PapersOnLine"},{"issue":"20","key":"10.1016\/j.engappai.2026.115178_b19","doi-asserted-by":"crossref","first-page":"114","DOI":"10.3182\/20100915-3-DE-3008.00018","article-title":"Weather Optimal Positioning Control for Marine Surface Vessels","volume":"43","author":"Kjerstad","year":"2010","journal-title":"IFAC Proc. Vol."},{"key":"10.1016\/j.engappai.2026.115178_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2019.105610","article-title":"Adaptive sliding-mode-backstepping trajectory tracking control of underactuated airships","volume":"97","author":"Liu","year":"2020","journal-title":"Aerosp. Sci. Technol."},{"issue":"6","key":"10.1016\/j.engappai.2026.115178_b21","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1002\/rnc.5132","article-title":"Safe reinforcement learning: A control barrier function optimization approach","volume":"31","author":"Marvi","year":"2021","journal-title":"Internat. J. Robust Nonlinear Control"},{"key":"10.1016\/j.engappai.2026.115178_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2022.110603","article-title":"Nonlinear station keeping control for underactuated unmanned surface vehicles to resist environmental disturbances","volume":"246","author":"Qu","year":"2022","journal-title":"Ocean Eng."},{"issue":"1\u20132","key":"10.1016\/j.engappai.2026.115178_b23","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1007\/s10846-018-0891-8","article-title":"A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Moving Platform","volume":"93","author":"Rodriguez-Ramos","year":"2019","journal-title":"J. Intell. Robot. Syst."},{"key":"10.1016\/j.engappai.2026.115178_b24","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.oceaneng.2016.09.037","article-title":"Station-keeping control of an unmanned surface vehicle exposed to current and wind disturbances","volume":"127","author":"Sarda","year":"2016","journal-title":"Ocean Eng."},{"key":"10.1016\/j.engappai.2026.115178_b25","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/j.actaastro.2023.08.006","article-title":"Prescribed-time error-constrained moving path following control for a stratospheric airship with disturbances","volume":"212","author":"Sun","year":"2023","journal-title":"Acta Astronaut."},{"issue":"10","key":"10.1016\/j.engappai.2026.115178_b26","doi-asserted-by":"crossref","first-page":"3713","DOI":"10.1109\/TSMC.2018.2884725","article-title":"Deterministic Policy Gradient With Integral Compensator for Robust Quadrotor Control","volume":"50","author":"Wang","year":"2020","journal-title":"IEEE Trans. Syst. Man, Cybern.: Syst."},{"key":"10.1016\/j.engappai.2026.115178_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijnaoe.2022.100456","article-title":"Weather Optimal Area-keeping control for underactuated autonomous surface vehicle with input time-delay","volume":"14","author":"Wang","year":"2022","journal-title":"Int. J. Nav. Archit. Ocean. Eng."},{"key":"10.1016\/j.engappai.2026.115178_b28","series-title":"Proceedings of the 7th Annual Learning for Dynamics & Control Conference","first-page":"698","article-title":"Multi-constraint safe reinforcement learning via closed-form solution for log-sum-exp approximation of control barrier functions","volume":"vol. 283","author":"Wang","year":"2025"},{"key":"10.1016\/j.engappai.2026.115178_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2025.110671","article-title":"Stratospheric airship trajectory planning via temporal perception and dual-source learning","volume":"167","author":"Wei","year":"2025","journal-title":"Aerosp. Sci. Technol."},{"key":"10.1016\/j.engappai.2026.115178_b30","first-page":"259","article-title":"Weather Optimal Station Keeping Control for Airship Based on Deep Reinforcement Learning","volume":"vol. 1354","author":"Wen","year":"2025"},{"key":"10.1016\/j.engappai.2026.115178_b31","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.automatica.2017.10.005","article-title":"Constrained control of input\u2013output linearizable systems using control sharing barrier functions","volume":"87","author":"Xu","year":"2018","journal-title":"Automatica"},{"issue":"3","key":"10.1016\/j.engappai.2026.115178_b32","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1016\/j.asr.2022.05.006","article-title":"Station-keeping for high-altitude balloon with reinforcement learning","volume":"70","author":"Xu","year":"2022","journal-title":"Adv. Space Res."},{"issue":"2","key":"10.1016\/j.engappai.2026.115178_b33","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1109\/JSEE.2012.00032","article-title":"Adaptive fuzzy sliding mode control for robotic airship with model uncertainty and external disturbance","volume":"23","author":"Yang","year":"2012","journal-title":"J. Syst. Eng. Electron."},{"key":"10.1016\/j.engappai.2026.115178_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2020.106100","article-title":"Horizontal trajectory control of stratospheric airships in wind field using Q-learning algorithm","volume":"106","author":"Yang","year":"2020","journal-title":"Aerosp. Sci. Technol."},{"key":"10.1016\/j.engappai.2026.115178_b35","series-title":"Multi-Agent Reinforcement Learning for the Low-Level Control of a Quadrotor UAV","author":"Yu","year":"2024"},{"issue":"12","key":"10.1016\/j.engappai.2026.115178_b36","doi-asserted-by":"crossref","first-page":"5435","DOI":"10.1109\/TNNLS.2021.3084685","article-title":"Safe Reinforcement Learning With Stability Guarantee for Motion Planning of Autonomous Vehicles","volume":"32","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.engappai.2026.115178_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2025.110736","article-title":"Collaborative coverage trajectory planning for stratospheric airship via multi-agent reinforcement learning","volume":"168","author":"Zheng","year":"2026","journal-title":"Aerosp. Sci. Technol."},{"key":"10.1016\/j.engappai.2026.115178_b38","first-page":"1","article-title":"Deep reinforcement learning-based path planning method for stratospheric airships in spatiotemporally complex environments","author":"Zheng","year":"2025","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"10.1016\/j.engappai.2026.115178_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2024.109173","article-title":"Path planning of stratospheric airship in dynamic wind field based on deep reinforcement learning","volume":"150","author":"Zheng","year":"2024","journal-title":"Aerosp. Sci. Technol."},{"issue":"3","key":"10.1016\/j.engappai.2026.115178_b40","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1109\/TAES.2018.2873054","article-title":"Three-Dimensional Path-Following Backstepping Control for an Underactuated Stratospheric Airship","volume":"55","author":"Zuo","year":"2019","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"10.1016\/j.engappai.2026.115178_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.conengprac.2021.104979","article-title":"A survey on modelling, control and challenges of stratospheric airships","volume":"119","author":"Zuo","year":"2022","journal-title":"Control Eng. Pract."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626014624?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626014624?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:24:11Z","timestamp":1783146251000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626014624"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":41,"alternative-id":["S0952197626014624"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115178","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Safe reinforcement learning control for adaptive station-keeping of a stratospheric airship in complex environments","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115178","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115178"}}