Paper:
Aircraft Autopilot Composed of Scenario Classifier and Flight Controllers Based on CNNs for Landing Flights
Issei Tanaka and Satoshi Hoshino
Department of Mechanical and Intelligent Engineering, Utsunomiya University
7-1-2 Yoto, Utsunomiya, Tochigi 321-8585, Japan
This paper is dedicated to the realization of an aircraft autopilot. Therefore, the authors focus on landing flights, which are considered the most difficult due to the physical contact between the aircraft and the runway. During landing, the aircraft descends toward the runway and momentarily maintains a constant altitude just before touchdown to mitigate the impact. The former scenario is referred to as “descending,” while the latter is known as the “landing flare.” The pilot performs different maneuvers for the aircraft, lowering the nose in the descending scenario and raising it in the flaring scenario. In this paper, therefore, we propose an autopilot specifically for unmanned landing flights. The autopilot is composed of a scenario classifier and two flight controllers, selected based on the classified flight scenario. This enables the aircraft to perform appropriate maneuvers autonomously depending on the scenario. Since only images from the cockpit are used as inputs, both the scenario classifier and the flight controllers are developed using convolutional neural networks. In the experiments, the proposed autopilot is applied to an aircraft in a flight simulator, and its effectiveness for landing flights is evaluated based on the results.
Flight instructions through a simulator
- [1] K. Hancock, “The Airline Pilot Shortage: A Result of Age Discrimination or Excessive Training Requirements?,” J. of Air Law and Commerce, Vol.88, Issue 2, pp. 535-572, 2023. https://doi.org/10.25172/jalc.88.2.5
- [2] M. Bojarski et al., “End to End Learning for Self-Driving Cars,” arXiv preprint, arXiv:1604.07316v1, 2016. https://doi.org/10.48550/arXiv.1604.07316
- [3] H. M. Eraqi et al., “End-to-End Deep Learning for Steering Autonomous Vehicles Considering Temporal Dependencies,” 31st Conf. on Neural Information Processing Systems (NIPS 2017), 2017.
- [4] L. Li et al., “Humanlike Driving: Empirical Decision-Making System for Autonomous Vehicles,” IEEE Trans. on Vehicular Technology, Vol.67, Issue 8, pp. 6814-6823, 2018. https://doi.org/10.1109/TVT.2018.2822762
- [5] B. D. Argall et al., “A Survey of Robot Learning from Demonstration,” Robotics and Autonomous Systems, Vol.57, Issue 5, pp. 469-483, 2009. https://doi.org/10.1016/j.robot.2008.10.024
- [6] K. Ujiie et al., “Behavior Cloning for Aircraft Autopilot in Approaching and Flaring Scenarios,” SICE Conf. on System Integration, pp. 3248-3252, 2022 (in Japanese).
- [7] Y. Lecun et al., “Gradient-Based Learning Applied to Document Recognition,” Proc. of the IEEE, Vol.86, Issue 11, pp. 2278-2324, 1998. https://doi.org/10.1109/5.726791
- [8] A. O. Ly and M. Akhloufi, “Learning to Drive by Imitation: An Overview of Deep Behavior Cloning Methods,” IEEE Trans. on Intelligent Vehicles, Vol.6, Issue 2, pp. 195-209, 2021. https://doi.org/10.1109/TIV.2020.3002505
- [9] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, Vol.9, Issue 8, pp. 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
- [10] M. V. Cook, “Flight Dynamics Principles: A Linear Systems Approach to Aircraft Stability and Control,” Butterworth-Heinemann, 1997. https://doi.org/10.1016/C2010-0-65889-5
- [11] T. Akiba et al., “Optuna: A Next-generation Hyperparameter Optimization Framework,” Proc. of the 25th ACM SIGKDD Int. Conf. on Knowledge Discovery & Data Mining (KDD ’19), pp. 2623-2631, 2019. https://doi.org/10.1145/3292500.3330701
- [12] X. Glorot and Y. Bengio, “Understanding the Difficulty of Training Deep Feedforward Neural Networks,” Proc. of 13th Int. Conf. on Artificial Intelligence and Statistics, Vol.9, pp. 249-256, 2010.
- [13] Z. N. D. Liu and A. C. Hansen, “Do Stable Neural Networks Exist for Classification Problems? – A New View on Stability in AI,” arXiv preprint, arXiv:2401.07874, 2024. https://doi.org/10.48550/arXiv.2401.07874
- [14] D. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Int. Conf. on Learning Representations (ICLR), 2015.
- [15] L. R. Ribeiro and N. M. F. Oliveira, “UAV Autopilot Controllers Test Platform Using Matlab/Simulink and X-Plane,” IEEE Frontiers in Education Conf. (FIE), pp. S2H-1-S2H-6, 2010. https://doi.org/10.1109/FIE.2010.5673378
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.