JMLIS/
Articles/
2609005126
  • Open Access
  • Article

Phy-Ture: A Physics-Guided Fusion and FeaTure Processing Framework for Unmanned Helicopter Dynamics Modeling

  • Bohan Zhang,   
  • Chao Chen,   
  • Jianglan Fu,   
  • Haiwei Chen,   
  • Yiyang Ye,   
  • Beichen Shao,   
  • Mingyan Li,   
  • Quanwang Wu,   
  • Hongyu Huang *

Received: 07 Jun 2026 | Revised: 05 Sep 2026 | Accepted: 09 Sep 2026 | Published: 15 Sep 2026

Abstract

Accurate dynamics modeling for unmanned helicopters remains challenging because rotor aerodynamics, structural vibrations, and actuator dynamics are strongly coupled, nonlinear, and rapidly time varying during flight. To address this challenge, we propose a physics-guided fusion and feature processing framework for unmanned helicopter dynamics modeling (Phy-Ture). In this framework, the sequential dynamics estimates from the first-principles based model are fused with raw state-control input sequences to implement physics-guided feature augmentation. Subsequently, a multiscale temporal feature enhancement module is incorporated to reinforce the framework’s representational capability for both the short-term transient behaviors and long-term evolutionary trends of the unmanned helicopter. Furthermore, a timeseries decomposition and prediction module is introduced to explicitly decouple and model dynamic components across distinct time scales, enabling the precise prediction and compensation of dynamic residuals. Experiments on the Stanford Autonomous Helicopter Project dataset show that Phy-Ture reduces the mean RMSE by approximately 48% relative to the best-performing compared baseline under the benchmark protocol and by approximately 56% on held-out maneuver classes under the maneuver-class-based 10-fold evaluation. These results support the effectiveness of combining a structured physical baseline with adaptive temporal feature learning within the evaluated dataset and maneuver classes.

References 

  • 1.

    Xian, B.; Zhang, X.; Zhang, H.; et al. Robust Adaptive Control for a Small Unmanned Helicopter Using Reinforcement Learning. IEEE Trans. Neural Netw. Learn. Syst. 2022, 33, 7589–7597. https://doi.org/10.1109/tnnls.2021.3085767.

  • 2.

    Zhao, Z.; Wu, J.; Mu, C.; et al. Neural-Network-Based Adaptive Fixed-Time Control for a 2-DOF Helicopter System With Input Quantization and Output Constraints. IEEE Trans. Neural Netw. Learn. Syst. 2025, 36, 7065–7076. https://doi.org/10.1109/tnnls.2024.3403145.

  • 3.

    Zhao, Z.; Zhang, J.; Liu, Z.; et al. Adaptive Neural Network Control of an Uncertain 2-DOF Helicopter With Unknown Backlash-Like Hysteresis and Output Constraints. IEEE Trans. Neural Netw. Learn. Syst. 2023, 34, 10018–10027. https://doi.org/10.1109/tnnls.2022.3163572.

  • 4.

    Yan, C.; Wang, C.; Xiang, X.; et al. Collision-Avoiding Flocking With Multiple Fixed-Wing UAVs in Obstacle-Cluttered Environments: A Task-Specific Curriculum-Based MADRL Approach. IEEE Trans. Neural Netw. Learn. Syst. 2024, 35, 10894–10908. https://doi.org/10.1109/tnnls.2023.3245124.

  • 5.

    Singh, R.; Bhushan, B. Evolving Intelligent System for Trajectory Tracking of Unmanned Aerial Vehicles. IEEE Trans. Autom. Sci. Eng. 2022, 19, 1971–1984. https://doi.org/10.1109/tase.2021.3072339.

  • 6.

    Wei, Z.; Shi, J.; Wang, Y.; et al. Fixed-Time Attitude Control of Flying-Wing Unmanned Aerial Vehicles Based on Plasma Control Surface. Aerosp. Sci. Technol. 2025, 159, 110016. https://doi.org/10.1016/j.ast.2025.110016.

  • 7.

    Dong, L.; Jiang, F.; Wang, M.; et al. Deep Progressive Reinforcement Learning-Based Flexible Resource Scheduling Framework for IRS and UAV-Assisted MEC System. IEEE Trans. Neural Netw. Learn. Syst. 2025, 36, 2314–2326. https://doi.org/10.1109/tnnls.2023.3341067.

  • 8.

    Xi, Y.Z.; Liao, G.X.; Lu, N.; et al. Study on the Aeromagnetic System between Fixed-Wing UAV and Unmanned Helicopter. Minerals 2023, 13, 700. https://doi.org/10.3390/min13050700.

  • 9.

    Hua, H.; Fang, Y. A Novel Learning-Based Trajectory Generation Strategy for a Quadrotor. IEEE Trans. Neural Netw. Learn. Syst. 2024, 35, 9068–9079. https://doi.org/10.1109/tnnls.2022.3217814.

  • 10.

    Dai, J.; Nie, H.; Ying, J.; et al. Modeling and Tracking Control of Unmanned Helicopter. In Proceedings of the 2020 IEEE 6th International Conference on Control Science and Systems Engineering (ICCSSE), Beijing, China, 17–19 July 2020; pp. 149–155. https://doi.org/10.1109/iccsse50399.2020.9171959.

  • 11.

    Gu, X.; Xian, B.; Wang, Y. Geometry-Based Adaptive Tracking Control for an Underactuated Small-Size Unmanned Helicopter. IEEE Trans. Syst. Man Cybern. Syst. 2023, 53, 7489–7500. https://doi.org/10.1109/tsmc.2023.3298034.

  • 12.

    He, Z.; He, X.; Javaid, U. Attitude Control of Unmanned Tandem Helicopter with Active Disturbance Rejection Capability. In Proceedings of the 2024 IEEE International Conference on Robotics and Biomimetics (ROBIO), Bangkok, Thailand, 10–14 December 2024; pp. 2105–2110. https://doi.org/10.1109/robio64047.2024.10907376.

  • 13.

    Wang, G.; Ye, X.; Zhao, B. A Novel Remote Sensing Image Encryption Scheme Based on Block Period Arnold Scrambling. Nonlinear Dyn. 2024, 112, 17477–17507. https://doi.org/10.1007/s11071-024-09953-6.

  • 14.

    Kim, S.K.; Tilbury, D.M. Mathematical Modeling and Experimental Identification of an Unmanned Helicopter Robot with Flybar Dynamics. J. Robot. Syst. 2004, 21, 95–116. https://doi.org/10.1002/rob.20002.

  • 15.

    Han, S.; Wang, G.; Yan, Y. Dynamic Analysis and Model Identification of an Unmanned Helicopter. In Proceedings of the 2nd Asian/Australian Rotorcraft Forum and the 4th International Basic Research Conference on Rotorcraft Technology, Tianjin, China, 8–11 September 2013.

  • 16.

    Fang, X.; Wu, A.; Shang, Y.; et al. A Novel Sliding Mode Controller for Small-Scale Unmanned Helicopters with Mismatched Disturbance. Nonlinear Dyn. 2016, 83, 1053–1068. https://doi.org/10.1007/s11071-015-2387-4.

  • 17.

    Pan, Y.; Song, P.; Li, K.; et al. Attitude Dynamics Modeling of a Small-Scale Unmanned Helicopter. In Proceedings of the 2012 IEEE International Conference on Intelligent Control, Automatic Detection and High-End Equipment (ICADE), Beijing, China, 27–29 July 2012; pp. 84–88. https://doi.org/10.1109/icade.2012.6330104.

  • 18.

    Khadeeja Nusrath, T.K.; Lulu, V.P.; Singh, J. System Identification of Flybar-Less Rotorcraft UAV. Aircr. Eng. Aerosp. Technol. 2020, 92, 1483–1493. https://doi.org/10.1108/aeat-05-2019-0100.

  • 19.

    Liu, S.Y.; Zhou, J.; Shi, J.Y.; et al. Small Unmanned Helicopter System Identification Based on the Weighted Least Square Method and Improved Grey Wolf Optimisation Algorithm. Aeronaut. J. 2025, 129, 1886–1902. https://doi.org/10.1017/aer.2024.159.

  • 20.

    Tischler, M.B.; Cauffman, M.G. Frequency-Response Method for Rotorcraft System Identification: Flight Applications to BO 105 Coupled Rotor/Fuselage Dynamics. J. Am. Helicopter Soc. 1992, 37, 3–17. https://doi.org/10.4050/jahs.37.3.

  • 21.

    La Civita, M.; Messner, W.C.; Kanade, T. Modeling of small-scale helicopters with integrated first-principles and systemidentification techniques. In Proceedings of the AHS International, 58th Annual Forum Proceedings, Montreal, QC, Canada, 11–13 June 2002; pp. 2505–2516. https://doi.org/10.4050/vfs-f58-00109.

  • 22.

    Chaturvedi, N.A.; Sanyal, A.K.; Chellappa, M.; et al. Adaptive tracking of angular velocity for a planar rigid body with unknown models for inertia and input nonlinearity. IEEE Trans. Control Syst. Technol. 2006, 14, 613–627. https://doi.org/10.1109/tcst.2006.876628.

  • 23.

    Tang, S.; Zheng, Z.; Qian, S.; et al. Nonlinear system identification of a small-scale unmanned helicopter. Control Eng. Pract. 2014, 25, 1–15. https://doi.org/10.1016/j.conengprac.2013.12.004.

  • 24.

    Huang, L.; Pei, H.; Cheng, Z. System Identification and Improved Internal Model Control for Yaw of Unmanned Helicopter. Asian J. Control 2023, 25, 1619–1638. https://doi.org/10.1002/asjc.2963.

  • 25.

    Pasquali, C.; Serafini, J.; Gennaretti, M.; et al. Reduced-Order Helicopter Model Identification from Closed-Loop Data. Aerosp. Sci. Technol. 2024, 153, 109419. https://doi.org/10.1016/j.ast.2024.109419.

  • 26.

    Zhou, J.; Liu, S.; Lu, J.; et al. An Improved Dynamic Model Identification Method for Small Unmanned Helicopter. Aircr. Eng. Aerosp. Technol. 2024, 96, 175–183. https://doi.org/10.1108/aeat-05-2023-0145.

  • 27.

    Mazzeo, F.; Pavel, M.D.; Fattizzo, D.; et al. Numerical Modeling, Trim, and Linearization of a Side-by-Side Helicopter in Hovering Conditions. Aerospace 2024, 11, 927. https://doi.org/10.3390/aerospace11110927.

  • 28.

    Mazzeo, F.; Pavel, M.D.; Fattizzo, D.; et al. Flight Dynamic Modeling and Stability of a Small-Scale Side-by-Side Helicopter for Urban Air Mobility. Aerosp. Sci. Technol. 2024, 148, 109117. https://doi.org/10.1016/j.ast.2024.109117.

  • 29.

    Wang, M.; Lou, X.; Wu, W.; et al. Koopman-Based MPC With Learned Dynamics: Hierarchical Neural Network Approach. IEEE Trans. Neural Netw. Learn. Syst. 2024, 35, 3630–3639. https://doi.org/10.1109/tnnls.2022.3194958.

  • 30.

    Huang, X.; Zhang, H.T.; Wang, J. A Data-Driven Bayesian Koopman Learning Method for Modeling Hysteresis Dynamics. IEEE Trans. Neural Netw. Learn. Syst. 2024, 35, 15615–15623. https://doi.org/10.1109/tnnls.2023.3288752.

  • 31.

    Mohammadzahri, M.; Khaleghifar, A.; Ghodsi, M.; et al. A Discrete Approach to Feedback Linearization, Yaw Control of an Unmanned Helicopter. Unmanned Syst. 2023, 11, 57–66. https://doi.org/10.1142/s2301385023500012.

  • 32.

    Zhu, Y.; Li, C.; Zeng, R. A Survey of Learning in Optimal Control and Differential Game. J. Mach. Learn. Inf. Secur. 2026, 2, 4. https://doi.org/10.53941/jmlis.2026.100004.

  • 33.

    Hou, Y.; Ye, X.; Zhang, X.; et al. Generating Multi-Scroll Hidden Attractors via Sigmoid Function. Chaos Solitons Fractals 2026, 212, 119023. https://doi.org/10.1016/j.chaos.2026.119023.

  • 34.

    Zhang, X.; Hou, Y.; Wang, G.; et al. An Improved Sprott-E Chaotic System with Coexisting Attractors for Regional DNA Image Encryption. Nonlinear Dyn. 2026, 114, 1105. https://doi.org/10.1007/s11071-026-13012-7.

  • 35.

    Mercorelli, P. A Wavelet Based Algorithm without a Priori Knowledge of Noise Level for Gross Errors Detection. In Proceedings of the 2013 International Conference on Advances in Intelligent Systems in Bioinformatics, Jakarta, Indonesia, 11 October 2013; pp. 7–12.

  • 36.

    Peng, Z.; Wang, D.; Wang, J. Data-Driven Adaptive Disturbance Observers for Model-Free Trajectory Tracking Control of Maritime Autonomous Surface Ships. IEEE Trans. Neural Netw. Learn. Syst. 2021, 32, 5584–5594. https://doi.org/10.1109/tnnls.2021.3093330.

  • 37.

    Xiong, S.; Hou, Z. Data-Driven Formation Control for Unknown MIMO Nonlinear Discrete-Time Multi-Agent Systems With Sensor Fault. IEEE Trans. Neural Netw. Learn. Syst. 2022, 33, 7728–7742. https://doi.org/10.1109/tnnls.2021.3087481.

  • 38.

    Wang, C.; Huo, X.;Ma, K.; et al. PID-Like Model Free Adaptive Control With Discrete Extended State Observer and Its Application on an Unmanned Helicopter. IEEE Trans. Ind. Inform. 2023, 19, 11265–11274. https://doi.org/10.1109/tii.2023.3245223.

  • 39.

    Punjani, A.; Abbeel, P. Deep Learning Helicopter Dynamics Models. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA, 26–30 May 2015; pp. 3223–3230. https://doi.org/10.1109/icra.2015.7139643.

  • 40.

    Chen, S.; Cao, Y.; Kang, Y.; et al. Deep CNN Identifier for Dynamic Modelling of Unmanned Helicopter. In Proceedings of the Neural Information Processing (ICONIP), Guangzhou, China, 14–18 November 2017; pp. 51–60. https://doi.org/10.1007/978-3-319-70136-3_6.

  • 41.

    Liu, Y.; Zhou, Y.; Li, X. Attitude Estimation of Unmanned Aerial Vehicle Based on LSTM Neural Network. In Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil, 8–13 July 2018; pp. 1–6. https://doi.org/10.1109/ijcnn.2018.8489118.

  • 42.

    Amiruddin, B.P.; Iskandar, E.; Fatoni, A.; et al. Deep Learning Based System Identification of Quadcopter Unmanned Aerial Vehicle. In Proceedings of the 2020 3rd International Conference on Information and Communications Technology (ICOIACT), Yogyakarta, Indonesia, 24–25 November 2020; pp. 165–169. https://doi.org/10.1109/icoiact50329.2020.9332059.

  • 43.

    Candon, M.; Hale, E.; Balajewicz, M.; et al. Parameterization of nonlinear aeroelastic reduced order models via direct interpolation of Taylor partial derivatives. Nonlinear Dyn. 2024, 112, 17649–17670. https://doi.org/10.1007/s11071-024-09976-z.

  • 44.

    Doring, F.A.; Wartmann, J.; Seher-Weiß, S. Data-Driven Approach for Fixed-Frame Rotorcraft Mast-Moment Estimation. J. Guid. Control Dyn. 2024, 47, 2301–2315. https://doi.org/10.2514/1.g007399.

  • 45.

    Bejani, M.M.; Ghatee, M. A Systematic Review on Overfitting Control in Shallow and Deep Neural Networks. Artif. Intell. Rev. 2021, 54, 6391–6438. https://doi.org/10.1007/s10462-021-09975-1.

  • 46.

    Hirtopanu, T.; Wang, Z.; Serrano, A.; et al. Uncertainty-Gated Mixture Modeling for Anomaly Detection in Human-in-the-Loop Vehicle Systems. J. Mach. Learn. Inf. Secur. 2026, 2, 10. https://doi.org/10.53941/jmlis.2026.100010.

  • 47.

    Saviolo, A.; Li, G.; Loianno, G. Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking. IEEE Robot. Autom. Lett. 2022, 7, 10256–10263. https://doi.org/10.1109/lra.2022.3192609.

  • 48.

    Yu, R.; Wang, R. Learning Dynamical Systems From Data: An Introduction to Physics-Guided Deep Learning. Proc. Natl. Acad. Sci. USA 2024, 121, e2311808121. https://doi.org/10.1073/pnas.2311808121.

  • 49.

    Ma, J.; Zhu, Q.; Xue, T.; et al. Aircraft Dynamics Modeling at High Angles of Attack Incorporating Residual Transformer Autoencoder and Physical Mechanisms. Aerosp. Sci. Technol. 2025, 160, 110045. https://doi.org/10.1016/j.ast.2025.110045.

  • 50.

    Kang, Y.; Chen, S.;Wang, X.; et al. Deep Convolutional Identifier for Dynamic Modeling and Adaptive Control of Unmanned Helicopter. IEEE Trans. Neural Netw. Learn. Syst. 2019, 30, 524–538. https://doi.org/10.1109/tnnls.2018.2844173.

  • 51.

    Zhang, H.; Liu, J. A Novel Residual Hybrid Dynamic Model for Unmanned Helicopters: Combining Both Physical and Deep Learning Models. Nonlinear Dyn. 2024, 112, 12235–12252. https://doi.org/10.1007/s11071-024-09689-3.

  • 52.

    Mohajerin, N.; Waslander, S.L. Multistep Prediction of Dynamic Systems With Recurrent Neural Networks. IEEE Trans. Neural Netw. Learn. Syst. 2019, 30, 3370–3383. https://doi.org/10.1109/tnnls.2019.2891257.

  • 53.

    Xia, H. Modeling and Control Strategy of Small Unmanned Helicopter Rotation Based on Deep Learning. Syst. Soft Comput. 2024, 6, 200146. https://doi.org/10.1016/j.sasc.2024.200146.

  • 54.

    Innocenti, M. Helicopter Flight Dynamics: The Theory and Application of Flying Qualities and Simulation Modeling. J. Guid. Control Dyn. 1999, 22, 383–384. https://doi.org/10.2514/2.4396.

  • 55.

    Vaswani, A.; Shazeer, N.; Parmar, N.; et al. Attention Is All You Need. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS), Long Beach, CA, USA, 4–9 December 2017; pp. 6000–6010.

  • 56.

    Liu,M.; Zeng, A.; Chen,M.; et al. SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction. In Proceedings of the Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA, 28 November–9 December 2022.

  • 57.

    Abbeel, P.; Coates, A.; Ng, A.Y. Autonomous Helicopter Aerobatics through Apprenticeship Learning. Int. J. Robot. Res. 2010, 29, 1608–1639. https://doi.org/10.1177/0278364910371999.

  • 58.

    Chen, S.; Kang, Y.; Di, J.; et al. Convex Temporal Convolutional Network–Based Distributed Cooperative Learning Control for Multiagent Systems. IEEE Trans. Neural Netw. Learn. Syst. 2023, 34, 5234–5243. https://doi.org/10.1109/tnnls.2022.3216327.

  • 59.

    Wu, H.; Hu, T.; Liu, Y.; et al. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. In Proceedings of the International Conference on Learning Representations (ICLR), Kigali, Rwanda, 1–5 May 2023. https://arxiv.org/abs/2210.02186.

  • 60.

    Wang, S.; Wu, H.; Shi, X.; et al. TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting. In Proceedings of the International Conference on Learning Representations (ICLR), Vienna, Austria, 7–11 May 2024. https://arxiv.org/abs/2405.14616.

  • 61.

    Zeng, A.; Chen, M.; Zhang, L.; et al. Are Transformers Effective for Time Series Forecasting? In Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA, 7–14 February 2023. https://doi.org/10.1609/aaai.v37i9.26317.

  • 62.

    Wang, Y.; Dou, Y.; Peng, C.; et al. Multi Step Prediction Method of Ship Pitch Based on Conv-Informer Model. In Proceedings of the OCEANS 2023—Limerick, Limerick, Ireland, 5–8 June 2023; pp. 1–6. https://doi.org/10.1109/oceanslimerick52467.2023.10244592.

Share this article:
Download PDF
DOI
10.53941/jmlis.2026.100019
Issue
Volume 2, Issue 3
How to Cite
Zhang, B.; Chen, C.; Fu, J.; Chen, H.; Ye, Y.; Shao, B.; Li, M.; Wu, Q.; Huang, H. Phy-Ture: A Physics-Guided Fusion and FeaTure Processing Framework for Unmanned Helicopter Dynamics Modeling. Journal of Machine Learning and Information Security 2026, 2 (3), 19. https://doi.org/10.53941/jmlis.2026.100019.
RIS
BibTex
Copyright & License
article copyright Image
Copyright (c) 2026 by the authors.
Article Metrics
13
Article Views
0
Citations