Abstract
Accurate dynamic modeling is difficult for aerobatic unmanned aerial vehicles flying at their physical limit, due to the model uncertainty caused by unobservable hidden states like airflow and vibrations. Although some progresses have been made, these hidden states are still not properly characterized, rendering system identification problem for aerobatic unmanned aerial vehicle extremely challenging. To address this issue, a novel spectrally normalized adaptive neural identifier is proposed for the dynamic modeling of aerobatic unmanned aerial vehicles. Specifically, to characterize the model uncertainty, we propose a spectrally normalized adaptive neural network (SNANet) to extract deep features representing the hidden states of the system. Particularly, the proposed SNANet adopts a multi-model adaptive structure, quickly and dynamically updating the model online. Furthermore, the spectral normalization constraint is introduced into the training process to ensure the Lipschitz stability of the SNANet. Consequently, a trajectory tracking control scheme including the sliding mode controller and SNANet is presented. The modeling effectiveness of the proposed method is verified on a real flight dataset. The results demonstrate that our method has high modeling accuracy, short training time, and fast model response speed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Gavrilets, V., Martinos, I., Mettler, B., Feron, E.: Control logic for automated aerobatic flight of a miniature helicopter. In: AIAA Guidance, Navigation, and Control Conference and Exhibit, p. 4834 (2002)
Punjani, A., Abbeel, P.: Deep learning helicopter dynamics models. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 3223–3230. IEEE (2015)
Kang, Y., Chen, S., Wang, X., Cao, Y.: Deep convolutional identifier for dynamic modeling and adaptive control of unmanned helicopter. IEEE Trans. Neural Networks Learn. Syst. 30(2), 524–538 (2018)
Bauersfeld, L., Kaufmann, E., Foehn, P., Sun, S., Scaramuzza, D.: NeuroBEM: hybrid aerodynamic quadrotor model. Ar**v Preprint Ar**v:2106.08015 (2021)
Bartlett, P.L., Foster, D.J., Telgarsky, M.J.: Spectrally-normalized margin bounds for neural networks. Adv. Neural Inf. Process. Syst. 30 (2017)
Zhang, L., et al.: State-of-charge estimation of lithium-ion battery pack based on improved RBF neural networks. Complexity 2020 (2020)
Agarap, A.F.: Deep learning using rectified linear units (RELU). Ar**v Preprint Ar**v:1803.08375 (2018)
Heng, Y., et al.: A pan-specific GRU-based recurrent neural network for predicting HLA-I-binding peptides. ACS Omega 5(29), 18321–18330 (2020)
Tian, Z., Zhou, Y.: Adaptive dynamic surface control of UAV based on RBF neural network. In: 2021 40th Chinese Control Conference, pp. 694–699. IEEE (2021)
Acknowledgment
This work was supported by the Key Research and Development Project of China’s Ministry of Science and Technology (2018AAA0100800).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, S., Kang, Y., Zhao, Y., Cao, Y. (2023). Spectrally Normalized Adaptive Neural Identifier for Dynamic Modeling and Trajectory Tracking Control of Unmanned Aerial Vehicle. In: Yan, L., Duan, H., Deng, Y. (eds) Advances in Guidance, Navigation and Control. ICGNC 2022. Lecture Notes in Electrical Engineering, vol 845. Springer, Singapore. https://doi.org/10.1007/978-981-19-6613-2_674
Download citation
DOI: https://doi.org/10.1007/978-981-19-6613-2_674
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-6612-5
Online ISBN: 978-981-19-6613-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)