{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T12:47:38Z","timestamp":1785761258562,"version":"3.56.0"},"reference-count":27,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"System of Systems and Artificial Intelligence Key Laboratory of Sichuan Province pioneer fund","award":["SSAI202508"],"award-info":[{"award-number":["SSAI202508"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Autonomous flight planners consume sensor-derived estimated states rather than simulator ground truth. Learned dynamics surrogates are queried over a planning horizon through architecture-native multi-step interfaces, so strong short-horizon accuracy can still yield unreliable long-horizon trajectory scores. We address this with a JSBSim sensor-interface evaluation protocol that assesses surrogate predictions from onboard sensing and lightweight estimation\u2014inertial measurement unit (IMU), global navigation satellite system (GNSS)\/air-data, barometric, and vertical-speed channels with delay, dropout, asynchronous refresh, and estimator filtering\u2014and guides surrogate selection by a planning task. This paper contributes an evaluation-and-selection methodology for learned flight-dynamics surrogates used by autonomous planners; it is not a new flight-dynamics, guidance, or control method, and it does not propose a new neural architecture. The contribution is a transparent and auditable sensor-interface and estimator-conditioned protocol, instantiated on five surrogate families over a 20 s prediction horizon. We emphasize at the outset that under strict native-unit physical tolerances, all evaluated surrogates diverge on 90\u2013100% of validation windows and none is field-ready; all results are comparative JSBSim stress-test evidence, not field-readiness evidence. Results reveal criterion-dependent ordering: long short-term memory (LSTM) networks are strongest on root-mean-square error (RMSE@1s\/RMSE@20s), shared-threshold failure, and absolute fidelity, whereas the Transformer is favored under self-scaled divergence and capped-risk criteria. These aggregate scores combine heterogeneous simulator-coordinate units and are benchmark diagnostics rather than physical safety margins. Because different threshold families select different winners, our central conclusion is not that one surrogate is best, but that the choice of metric and threshold family is itself part of the benchmark assessment. In separately generated JSBSim candidate-screening episodes, Transformer has approximately 8% lower mean cost under abstract sensing corruption, whereas estimator-loop screening shifts toward LSTM; feedback-rich tracking remains exploratory at 40 episodes per scenario and has mixed cost and success endpoints. Cross-aircraft transfer degrades substantially. Surrogates should be assessed using sensing-aware, estimator-conditioned, task-specific long-horizon criteria, not short-horizon accuracy alone.<\/jats:p>","DOI":"10.3390\/s26154888","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T11:50:21Z","timestamp":1785757821000},"page":"4888","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A JSBSim Sensor-Interface Protocol for Selecting Learned Fixed-Wing Flight-Dynamics Surrogates"],"prefix":"10.3390","volume":"26","author":[{"given":"Yihao","family":"Feng","sequence":"first","affiliation":[{"name":"School of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[{"name":"System of Systems and Artificial Intelligence Key Laboratory of Sichuan Province, Chengdu 610091, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Yang","sequence":"additional","affiliation":[{"name":"AVIC Chengdu Aircraft Design and Research Institute, Chengdu 610091, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3116-5759","authenticated-orcid":false,"given":"Yulong","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Berndt, J.S. (2004, January 16\u201319). JSBSim: An Open Source Flight Dynamics Model in C++. Proceedings of the AIAA Modeling and Simulation Technologies Conference and Exhibit, Providence, RI, USA. AIAA Paper 2004-4923.","DOI":"10.2514\/6.2004-4923"},{"key":"ref_2","first-page":"4754","article-title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","volume":"Volume 31","author":"Bengio","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_3","first-page":"12519","article-title":"When to Trust Your Model: Model-Based Policy Optimization","volume":"Volume 32","author":"Janner","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_4","unstructured":"Hafner, D., Lillicrap, T., Ba, J., and Norouzi, M. (2020, January 25\u201330). Dream to Control: Learning Behaviors by Latent Imagination. Proceedings of the International Conference on Learning Representations (ICLR), Virtual Conference, Available online: https:\/\/openreview.net\/forum?id=S1lOTC4tDS."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Nagabandi, A., Kahn, G., Fearing, R.S., and Levine, S. (2018, January 21\u201325). Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning. Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, QLD, Australia.","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref_6","first-page":"14129","article-title":"MOPO: Model-based Offline Policy Optimization","volume":"Volume 33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_7","first-page":"21810","article-title":"MOReL: Model-Based Offline Reinforcement Learning","volume":"Volume 33","author":"Kidambi","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_8","unstructured":"Talvitie, E. (2014). Model Regularization for Stable Sample Rollouts. Proceedings of the Thirtieth Conference on Uncertainty in Artificial Intelligence (UAI), Quebec City, QC, Canada, 23\u201327 July 2014, AUAI Press."},{"key":"ref_9","first-page":"2597","article-title":"Self-Correcting Models for Model-Based Reinforcement Learning","volume":"Volume 31","author":"Singh","year":"2017","journal-title":"Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), San Francisco, CA, USA, 4\u20139 February 2017"},{"key":"ref_10","first-page":"3024","article-title":"Improving Multi-Step Prediction of Learned Time Series Models","volume":"Volume 29","author":"Bonet","year":"2015","journal-title":"Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, TX, USA, 25\u201330 January 2015"},{"key":"ref_11","unstructured":"Jategaonkar, R.V. (2006). Flight Vehicle System Identification: A Time Domain Methodology, American Institute of Aeronautics and Astronautics. [1st ed.]. Progress in Astronautics and Aeronautics."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yu, Y., Yao, H., and Liu, Y. (2018). Physics-based Learning for Aircraft Dynamics Simulation. Annu. Conf. PHM Soc., 10.","DOI":"10.36001\/phmconf.2018.v10i1.513"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/s40323-022-00227-7","article-title":"A physics-based neural network for flight dynamics modelling and simulation","volume":"9","author":"Stachiw","year":"2022","journal-title":"Adv. Model. Simul. Eng. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"108157","DOI":"10.1016\/j.ast.2023.108157","article-title":"Sparse Online Gaussian Process Adaptation for Incremental Backstepping Flight Control","volume":"136","author":"Ignatyev","year":"2023","journal-title":"Aerosp. Sci. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Qiu, X., Liu, C., and Li, J. (2026). Sparse Neural Dynamics Modeling for NMPC-Based UAV Trajectory Tracking. Aerospace, 13.","DOI":"10.3390\/aerospace13030229"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Song, Y., Nuske, S., and Scherer, S. (2017). A Multi-Sensor Fusion MAV State Estimation from Long-Range Stereo, IMU, GPS and Barometric Sensors. Sensors, 17.","DOI":"10.3390\/s17010011"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bod\u00f3, Z., and Lantos, B. (2017, January 14\u201316). State Estimation for UAVs Using Sensor Fusion. Proceedings of the 2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY), Subotica, Serbia.","DOI":"10.1109\/SISY.2017.8080535"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Reitbauer, E., and Wieser, M. (2019, January 9\u201312). Integrated Multi-Sensor State Estimation Using GNSS and Redundant IMUs for UAVs Beyond Visual Line of Sight. Proceedings of the 2019 European Navigation Conference (ENC), Warsaw, Poland.","DOI":"10.1109\/EURONAV.2019.8714130"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sun, X., Zhang, C., Zou, L., and Li, S. (2023). Real-Time Optimal States Estimation with Inertial and Delayed Visual Measurements for Unmanned Aerial Vehicles. Sensors, 23.","DOI":"10.3390\/s23229074"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Negru, S.A., Geragersian, P., Petrunin, I., and Guo, W. (2024). Resilient Multi-Sensor UAV Navigation with a Hybrid Federated Fusion Architecture. Sensors, 24.","DOI":"10.3390\/s24030981"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"20188","DOI":"10.1109\/JSEN.2024.3395009","article-title":"Error Compensation Method of GNSS\/INS Integrated Navigation System Based on AT-LSTM During GNSS Outages","volume":"24","author":"Chen","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"9430096","DOI":"10.1155\/ijae\/9430096","article-title":"Autonomous Landing of a Fixed-Wing UAV with RTK GNSS and MEMS IMU","volume":"2025","author":"Xia","year":"2025","journal-title":"Int. J. Aerosp. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Abbas, N., Abbas, Z., Zafar, S., Ahmad, N., Liu, X., Khan, S.S., Foster, E.D., and Larkin, S. (2024). Survey of Advanced Nonlinear Control Strategies for UAVs: Integration of Sensors and Hybrid Techniques. Sensors, 24.","DOI":"10.3390\/s24113286"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1433","DOI":"10.1109\/LCSYS.2024.3410152","article-title":"Active Sensing for Data Quality Improvement in Model Learning","volume":"8","author":"Napolitano","year":"2024","journal-title":"IEEE Control Syst. Lett."},{"key":"ref_25","unstructured":"Bai, S., Kolter, J.Z., and Koltun, V. (2018). An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv."},{"key":"ref_26","first-page":"5998","article-title":"Attention Is All You Need","volume":"Volume 30","author":"Guyon","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_27","first-page":"11106","article-title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","volume":"Volume 35","author":"Zhou","year":"2021","journal-title":"Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), Virtual Event, 2\u20139 February 2021"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/15\/4888\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T11:55:20Z","timestamp":1785758120000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/15\/4888"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"references-count":27,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26154888"],"URL":"https:\/\/doi.org\/10.3390\/s26154888","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]}}}