{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T10:47:14Z","timestamp":1782730034143,"version":"3.54.5"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":38,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Parafoil systems are increasingly deployed in military and civilian missions that require high-precision trajectory tracking. However, conventional controllers based on linear strategies and limited decision information often fail to cope with task complexity, and existing reinforcement learning studies rarely consider the systematic construction of training task sets, thereby limiting generalization. To address these issues, this paper proposes a Benchmark Task Set Generation (BTSG) algorithm that builds high-quality task sets with diverse and balanced complexity for robust controller training and comprehensive evaluation, formulates the trajectory tracking problem as a Markov decision process with a 46-dimensional observation space and a dense reward structure to enrich decision-support information and improve learning efficiency, and develops a BTSG-SAC framework that integrates BTSG with Soft Actor-Critic (SAC) for controller training. Simulation results show that BTSG-SAC markedly outperforms PID and PPO controllers on the generated benchmark task set, reducing distance deviation by 50.7% and 33.2% under noise-free conditions; under sensor noise, BTSG-SAC attains a 98% success rate, whereas PPO reaches 77% and PID fails to achieve successful tracking. Overall, this paper extends the application of reinforcement learning to parafoil control and offers generalizable methodologies for future autonomous control research.<\/jats:p>","DOI":"10.1038\/s41598-026-54074-2","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T09:04:37Z","timestamp":1779440677000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Trajectory tracking control of parafoil systems via soft actor-critic with benchmark task set generation"],"prefix":"10.1038","volume":"16","author":[{"given":"Yufeng","family":"Fan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lulu","family":"Ning","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caixia","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengju","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongfeng","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"key":"54074_CR1","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/s10846-021-01339-9","volume":"101","author":"Y Guo","year":"2021","unstructured":"Guo, Y., Yan, J., Wu, C., Chen, M. & Xing, X. Autonomous homing design and following for parafoil\/rocket system with high-altitude. J. Intell. Robot. Syst. 101, 73. https:\/\/doi.org\/10.1007\/s10846-021-01339-9 (2021).","journal-title":"J. Intell. Robot. Syst."},{"key":"54074_CR2","unstructured":"Mercurio, A. Design and Modeling of an Autonomous Parafoil for Rover Mars Landing (Turin, Italy, 2021) (Ph.D. thesis)."},{"key":"54074_CR3","unstructured":"Gasparri, M. Non-linear Model Predictive Controller for the Autonomous Descent and Landing of a Parafoil System in Multi-Planetary Applications (Turin, Italy, 2023) (Ph.D. thesis)."},{"key":"54074_CR4","doi-asserted-by":"crossref","unstructured":"Matthies, L., Daftry, S. & Rothrock, B. Terrain relative navigation for guided descent on titan. In Proceedings of the 2020 IEEE Aerospace Conference 1\u201310 (Big Sky, MT, USA, 2020).","DOI":"10.1109\/AERO47225.2020.9172286"},{"key":"54074_CR5","doi-asserted-by":"publisher","first-page":"11205","DOI":"10.1007\/s11071-023-08444-4","volume":"111","author":"Y Zheng","year":"2023","unstructured":"Zheng, Y. et al. Ddpg-based active disturbance rejection 3d path-following control for powered parafoil under wind disturbances. Nonlinear Dyn. 111, 11205\u201311221. https:\/\/doi.org\/10.1007\/s11071-023-08444-4 (2023).","journal-title":"Nonlinear Dyn."},{"key":"54074_CR6","doi-asserted-by":"publisher","first-page":"107406","DOI":"10.1016\/j.ast.2022.107406","volume":"122","author":"Q Sun","year":"2022","unstructured":"Sun, Q. et al. Trajectory tracking control of powered parafoil system based on sliding mode control in a complex environment. Aerosp. Sci. Technol. 122, 107406 (2022).","journal-title":"Aerosp. Sci. Technol."},{"key":"54074_CR7","doi-asserted-by":"crossref","unstructured":"Jann, T. Aerodynamic model identification and gnc design for the parafoil-load system alex. In Proceedings of the 16th AIAA Aerodynamic Decelerator Systems Technology Conference and Seminar (Boston, MA, USA, 2001).","DOI":"10.2514\/6.2001-2015"},{"key":"54074_CR8","doi-asserted-by":"crossref","unstructured":"Prakash, O., Daftary, A. & Ananthkrishnan, N. Trim and stability analysis of parafoil\/payload system using bifurcation methods. In Proceedings of the 18th AIAA Aerodynamic Decelerator Systems Technology Conference and Seminar (Munich, Germany, 2005).","DOI":"10.2514\/6.2005-1666"},{"key":"54074_CR9","doi-asserted-by":"crossref","unstructured":"Mortaloni, P. A., Yakimenko, O. A. & Dobrokhodov, V. N. On the development of a six-degree-of-freedom model of a low-aspect-ratio parafoil delivery system. In Proceedings of the 17th AIAA Aerodynamic Decelerator Systems Technology Conference and Seminar (Monterey, CA, USA, 2003).","DOI":"10.2514\/6.2003-2105"},{"key":"54074_CR10","doi-asserted-by":"publisher","first-page":"791","DOI":"10.2514\/1.25074","volume":"30","author":"C Redelinghuys","year":"2007","unstructured":"Redelinghuys, C. A flight simulation algorithm for a parafoil suspending an air vehicle. J. Guid. Control Dyn. 30, 791\u2013803 (2007).","journal-title":"J. Guid. Control Dyn."},{"key":"54074_CR11","unstructured":"Toglia, C. & Vendittelli, M. Modeling and motion analysis of autonomous paragliders. Technical Reports 2, Department of Computer and System Sciences Antonio Ruberti (2010)."},{"key":"54074_CR12","doi-asserted-by":"crossref","unstructured":"Prakash, O. & Ananthkrishnan, N. Modeling and simulation of 9-dof parafoil-payload system flight dynamics. In Proceedings of the AIAA Atmospheric Flight Mechanics Conference and Exhibit (Keystone, CO, USA, 2006).","DOI":"10.2514\/6.2006-6130"},{"key":"54074_CR13","doi-asserted-by":"publisher","first-page":"8115","DOI":"10.3390\/app13148115","volume":"13","author":"Z Li","year":"2023","unstructured":"Li, Z. & Nan, Y. Optimal path planning and tracking control methods for parafoil. Appl. Sci. 13, 8115. https:\/\/doi.org\/10.3390\/app13148115 (2023).","journal-title":"Appl. Sci."},{"key":"54074_CR14","doi-asserted-by":"publisher","first-page":"151087","DOI":"10.1109\/ACCESS.2020.3016894","volume":"8","author":"Y Li","year":"2020","unstructured":"Li, Y. et al. 6-dof modeling and 3d trajectory tracking control of a powered parafoil system. IEEE Access 8, 151087\u2013151105. https:\/\/doi.org\/10.1109\/ACCESS.2020.3016894 (2020).","journal-title":"IEEE Access"},{"key":"54074_CR15","doi-asserted-by":"publisher","first-page":"42586","DOI":"10.1109\/ACCESS.2019.2905632","volume":"7","author":"J Tao","year":"2019","unstructured":"Tao, J. et al. A generalized predictive control-based path following method for parafoil systems in wind environments. IEEE Access 7, 42586\u201342595 (2019).","journal-title":"IEEE Access"},{"key":"54074_CR16","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Tao, J. & Sun, Q. Intelligent trajectory tracking control of unmanned parafoil system based on sac optimized ladrc. In Proceedings of the 30th International Conference on Neural Information Processing 97\u2013108 (Changsha, China, 2023) (ICONIP 2023).","DOI":"10.1007\/978-981-99-8073-4_8"},{"key":"54074_CR17","doi-asserted-by":"publisher","first-page":"2916","DOI":"10.1109\/TAES.2022.3141033","volume":"58","author":"H Sun","year":"2022","unstructured":"Sun, H. et al. Accurate modeling and homing control for parafoil delivery system based on wind disturbance rejection. IEEE Trans. Aerosp. Electron. Syst. 58, 2916\u20132934 (2022).","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"54074_CR18","doi-asserted-by":"publisher","first-page":"435","DOI":"10.3390\/su15010435","volume":"15","author":"Y Zheng","year":"2023","unstructured":"Zheng, Y. et al. Deep-reinforcement-learning-based active disturbance rejection control for lateral path following of parafoil system. Sustainability 15, 435. https:\/\/doi.org\/10.3390\/su15010435 (2023).","journal-title":"Sustainability"},{"key":"54074_CR19","unstructured":"Cheng, Y., Chou, B. & Yu, L. The effects of maneuver modes on the flare performance of parafoil-payload system. J. Beijing Univ. Aeronaut. Astronaut 48, (2022)."},{"key":"54074_CR20","doi-asserted-by":"publisher","first-page":"13039","DOI":"10.1007\/s11071-023-08570-z","volume":"111","author":"Y Guo","year":"2023","unstructured":"Guo, Y. et al. Adaptive path-following control for parafoil dynamic systems with wind disturbance and rate constraint. Nonlinear Dyn. 111, 13039\u201313051. https:\/\/doi.org\/10.1007\/s11071-023-08570-z (2023).","journal-title":"Nonlinear Dyn."},{"key":"54074_CR21","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1007\/s11071-016-2972-1","volume":"86","author":"J Tao","year":"2016","unstructured":"Tao, J. et al. Active disturbance rejection control (adrc)-based autonomous homing control of powered parafoils. Nonlinear Dyn. 86, 1461\u20131476. https:\/\/doi.org\/10.1007\/s11071-016-2972-1 (2016).","journal-title":"Nonlinear Dyn."},{"key":"54074_CR22","doi-asserted-by":"publisher","first-page":"2736","DOI":"10.1109\/TMECH.2017.2766884","volume":"22","author":"J Tao","year":"2017","unstructured":"Tao, J. et al. Dynamic modeling and trajectory tracking control of parafoil system in wind environments. IEEE\/ASME Trans. Mechatron. 22, 2736\u20132745. https:\/\/doi.org\/10.1109\/TMECH.2017.2766884 (2017).","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"54074_CR23","doi-asserted-by":"crossref","unstructured":"He, W., Zheng, Y. & Wen, J. Path following control of parafoil system based on sglos and improved adrc tuned by msmpa. IEEE Trans. Circuits Syst. II Express Briefs https:\/\/doi.org\/10.1109\/TCSII.2024.3373963 (2024).","DOI":"10.1109\/TCSII.2024.3377010"},{"key":"54074_CR24","first-page":"510","volume":"39","author":"J Tao","year":"2018","unstructured":"Tao, J. et al. Ladrc-based trajectory tracking control for a parafoil system. J. Harbin Eng. Univ. 39, 510\u2013516 (2018).","journal-title":"J. Harbin Eng. Univ."},{"key":"54074_CR25","doi-asserted-by":"publisher","first-page":"23133","DOI":"10.1038\/s41598-025-05192-w","volume":"15","author":"Y Yan","year":"2025","unstructured":"Yan, Y., Li, J. & Zaggia, C. The analysis of deep reinforcement learning for dynamic graphical games under artificial intelligence. Sci. Rep. 15, 23133. https:\/\/doi.org\/10.1038\/s41598-025-05192-w (2025).","journal-title":"Sci. Rep."},{"key":"54074_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2025.106458","volume":"164","author":"P Garg","year":"2025","unstructured":"Garg, P., Silvas, E. & Willems, F. Safe and time-efficient exploration in reinforcement learning-based control of a vehicle thermal systems. Control Eng. Pract. 164, 106458. https:\/\/doi.org\/10.1016\/j.conengprac.2025.106458 (2025).","journal-title":"Control Eng. Pract."},{"key":"54074_CR27","doi-asserted-by":"publisher","first-page":"106519","DOI":"10.1016\/j.conengprac.2025.106519","volume":"164","author":"S Deniz","year":"2025","unstructured":"Deniz, S., Barzegar, A., Sagirli, F. Y., Vasiloff, K. & Wang, Z. Deep reinforcement learning approach to autonomous landing of evtol vehicles for advanced air mobility. Control Eng. Pract. 164, 106519. https:\/\/doi.org\/10.1016\/j.conengprac.2025.106519 (2025).","journal-title":"Control Eng. Pract."},{"key":"54074_CR28","doi-asserted-by":"publisher","first-page":"173","DOI":"10.3390\/drones8050173","volume":"8","author":"F Almahamid","year":"2024","unstructured":"Almahamid, F. & Grolinger, K. Viznav: A modular off-policy deep reinforcement learning framework for vision-based autonomous uav navigation in 3d dynamic environments. Drones 8, 173. https:\/\/doi.org\/10.3390\/drones8050173 (2024).","journal-title":"Drones"},{"key":"54074_CR29","doi-asserted-by":"publisher","first-page":"18043","DOI":"10.1038\/s41598-025-03287-y","volume":"15","author":"F Almahamid","year":"2025","unstructured":"Almahamid, F. & Grolinger, K. Agile dqn: adaptive deep recurrent attention reinforcement learning for autonomous uav obstacle avoidance. Sci. Rep. 15, 18043. https:\/\/doi.org\/10.1038\/s41598-025-03287-y (2025).","journal-title":"Sci. Rep."},{"key":"54074_CR30","doi-asserted-by":"publisher","first-page":"555","DOI":"10.3390\/aerospace9100555","volume":"9","author":"S Liu","year":"2022","unstructured":"Liu, S. et al. Application of deep reinforcement learning in reconfiguration control of aircraft anti-skid braking system. Aerospace 9, 555. https:\/\/doi.org\/10.3390\/aerospace9100555 (2022).","journal-title":"Aerospace"},{"key":"54074_CR31","doi-asserted-by":"publisher","first-page":"127","DOI":"10.2514\/1.i011283","volume":"21","author":"ZC Goddard","year":"2024","unstructured":"Goddard, Z. C. et al. Leveraging machine learning for generating and utilizing motion primitives in adversarial environments. J. Aerosp. Inf. Syst. 21, 127\u2013139. https:\/\/doi.org\/10.2514\/1.i011283 (2024).","journal-title":"J. Aerosp. Inf. Syst."},{"key":"54074_CR32","doi-asserted-by":"publisher","DOI":"10.1002\/acs.4020","author":"E Soleimani","year":"2025","unstructured":"Soleimani, E., Balachandran, B. & Jagannathan, S. Safe optimal control of quadrotor formations using multilayer neural networks and continual learning. Int. J. Adapt. Control Signal Process. https:\/\/doi.org\/10.1002\/acs.4020 (2025).","journal-title":"Int. J. Adapt. Control Signal Process."},{"key":"54074_CR33","doi-asserted-by":"publisher","first-page":"8189","DOI":"10.3390\/app12168189","volume":"12","author":"J Yu","year":"2022","unstructured":"Yu, J., Sun, H. & Sun, J. Improved twin delayed deep deterministic policy gradient algorithm based real-time trajectory planning for parafoil under complicated constraints. Appl. Sci. 12, 8189. https:\/\/doi.org\/10.3390\/app12168189 (2022).","journal-title":"Appl. Sci."},{"key":"54074_CR34","doi-asserted-by":"crossref","unstructured":"Wei, Z. & Shao, Z. Precision landing of autonomous parafoil system via deep reinforcement learning. In Proceedings of the 2024 IEEE Aerospace Conference (Big Sky, MT, USA, 2024).","DOI":"10.1109\/AERO58975.2024.10521056"},{"key":"54074_CR35","doi-asserted-by":"publisher","first-page":"58","DOI":"10.2514\/1.I011281","volume":"21","author":"J Park","year":"2024","unstructured":"Park, J. & Bang, H. Data-driven hazard avoidance landing of parafoil: A deep reinforcement learning approach. J. Aerosp. Inf. Syst. 21, 58\u201374. https:\/\/doi.org\/10.2514\/1.I011281 (2024).","journal-title":"J. Aerosp. Inf. Syst."},{"key":"54074_CR36","doi-asserted-by":"crossref","unstructured":"Park, J., Lee, S. & Kim, Y. Hazard avoidance landing of loaded parafoil using deep reinforcement learning. In Proceedings of the AIAA SciTech Forum (San Diego, CA, USA, 2022).","DOI":"10.2514\/6.2022-2442"},{"key":"54074_CR37","doi-asserted-by":"publisher","first-page":"280","DOI":"10.3390\/act13080280","volume":"13","author":"X He","year":"2024","unstructured":"He, X. et al. Simulation training system for parafoil motion controller based on actor-critic rl approach. Actuators 13, 280. https:\/\/doi.org\/10.3390\/act13080280 (2024).","journal-title":"Actuators"},{"key":"54074_CR38","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P. & Levine, S. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. Proceedings of the 35th International Conference on Machine Learning (ICML 2018) 80, 1861\u20131870 (2018)."},{"key":"54074_CR39","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/s12567-021-00406-z","volume":"15","author":"A Leeman","year":"2023","unstructured":"Leeman, A., Preda, V., Huertas, I. & Bennani, S. Autonomous parafoil precision landing using convex real-time optimized guidance and control. CEAS Space J. 15, 371\u2013384. https:\/\/doi.org\/10.1007\/s12567-021-00406-z (2023).","journal-title":"CEAS Space J."},{"key":"54074_CR40","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/s10291-025-01895-9","volume":"29","author":"A Wn\u0119k","year":"2025","unstructured":"Wn\u0119k, A. & Kudas, D. Application of combination of denoising methods and complementary ensemble empirical mode decomposition in gnss time series analysis. GPS Solut. 29, 141. https:\/\/doi.org\/10.1007\/s10291-025-01895-9 (2025).","journal-title":"GPS Solut."},{"key":"54074_CR41","unstructured":"Berkenkamp, F., Turchetta, M., Schoellig, A.\u00a0P. & Krause, A. Safe model-based reinforcement learning with stability guarantees. In Advances in Neural Information Processing Systems 30 (NeurIPS 2017), 908\u2013918 (2017)."},{"key":"54074_CR42","unstructured":"Chang, Y.-C., Roohi, N. & Gao, S. Neural lyapunov control. In Advances in Neural Information Processing Systems 32 (NeurIPS 2019), 3245\u20133254 (2019)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-54074-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-54074-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-54074-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T10:15:37Z","timestamp":1782728137000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-54074-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["54074"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-54074-2","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]},"assertion":[{"value":"9 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"19762"}}