Peer-Reviewed | Open Access | International Research Journal
CONFORMALLY CALIBRATED RESIDUAL-LEARNING GUIDANCE FOR FIELD-OF-VIEW CONSTRAINED HIGH-SPEED INTERCEPTION
Main Article Content
Abstract
This paper proposes a certifiable residual learning-enhanced guidance law for high-speed interception subject to field-of-view constraints, measurement delay, and actuator dynamics. A residual predictor estimates the target-maneuver component that is not represented by the physics-based model. Its prediction error is calibrated through split conformal prediction and embedded directly into a robust high-order control-barrier-function condition. The final acceleration command is generated by a CLF–HOCBF safety filter that minimally modifies the nominal command when constraint satisfaction is endangered. The predictor is constructed from 87,560 simulated samples and achieves a held-out RMSE of 5.768 m/s² with 94.83% empirical coverage for a nominal 95% marginal target. The resulting conformal radius is 12.194 m/s², which is 51.16% smaller than the fixed comparison bound. Over 220 Monte Carlo trials for each method and parameter set, the proposed method reduces the median and 95th-percentile terminal errors by 32.64% and 35.26%, respectively, under the moderate condition relative to physics-only guidance. Under the severe near-boundary condition, it reduces the 95th-percentile error by 8.60%, operates at a median field-of-view utilization of 96.64%, and produces no observed field-of-view violation within the investigated domain. The results demonstrate improved maneuver compensation together with an auditable, data-calibrated uncertainty margin for safety filtering.
Downloads
Download data is not yet available.
Article Details
Section
Articles
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
CONFORMALLY CALIBRATED RESIDUAL-LEARNING GUIDANCE FOR FIELD-OF-VIEW CONSTRAINED HIGH-SPEED INTERCEPTION. (2026). International Journal of Engineering, Science and Environment (IJESE), 1(2). https://ijese.in/journal/article/view/72
References
[1] X. Tang, J. Yu, X. Dong, and Z. Ren, “Integrated guidance and control with impact angle and general field-of-view constraints,” Aerospace Science and Technology, vol. 144, Art. no. 108809, 2024, doi: 10.1016/j.ast.2023.108809.
[2] B. Gaudet, R. Furfaro, and R. Linares, “Reinforcement learning for angle-only intercept guidance of maneuvering targets,” Aerospace Science and Technology, vol. 99, Art. no. 105746, 2020, doi: 10.1016/j.ast.2020.105746.
[3] X. Gong, W. Chen, and Z. Chen, “All-aspect attack guidance law for agile missiles based on deep reinforcement learning,” Aerospace Science and Technology, vol. 127, Art. no. 107677, 2022, doi: 10.1016/j.ast.2022.107677.
[4] N. Wang, X. Wang, N. Cui, Y. Li, and B. Liu, “Deep reinforcement learning-based impact time control guidance law with constraints on the field-of-view,” Aerospace Science and Technology, vol. 128, Art. no. 107765, 2022, doi: 10.1016/j.ast.2022.107765.
[5] W. Chen, C. Gao, and W. Jing, “Proximal policy optimization guidance algorithm for intercepting near-space maneuvering targets,” Aerospace Science and Technology, vol. 132, Art. no. 108031, 2023, doi: 10.1016/j.ast.2022.108031.
[6] Z. Yang, X. Liu, and H. Liu, “Impact time control guidance law with time-varying velocity based on deep reinforcement learning,” Aerospace Science and Technology, vol. 142, Art. no. 108603, 2023, doi: 10.1016/j.ast.2023.108603.
[7] A. D. Ames, X. Xu, J. W. Grizzle, and P. Tabuada, “Control barrier function based quadratic programs for safety critical systems,” IEEE Transactions on Automatic Control, vol. 62, no. 8, pp. 3861–3876, 2017, doi: 10.1109/TAC.2016.2638961.
[8] W. Xiao and C. Belta, “High-order control barrier functions,” IEEE Transactions on Automatic Control, vol. 67, no. 7, pp. 3655–3662, 2022, doi: 10.1109/TAC.2021.3105491.
[9] A. J. Taylor and A. D. Ames, “Adaptive safety with control barrier functions,” in Proceedings of the American Control Conference, Denver, CO, USA, 2020, pp. 1399–1405, doi: 10.23919/ACC45564.2020.9147463.
[10] R. Cheng, G. Orosz, R. M. Murray, and J. W. Burdick, “End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 1, pp. 3387–3395, 2019, doi: 10.1609/aaai.v33i01.33013387.
[11] Z. Marvi and B. Kiumarsi, “Safe reinforcement learning: A control barrier function optimization approach,” International Journal of Robust and Nonlinear Control, vol. 31, no. 6, pp. 1923–1940, 2021, doi: 10.1002/rnc.5132.
[12] J. Lei, M. G’Sell, A. Rinaldo, R. J. Tibshirani, and L. Wasserman, “Distribution-free predictive inference for regression,” Journal of the American Statistical Association, vol. 113, no. 523, pp. 1094–1111, 2018, doi: 10.1080/01621459.2017.1307116.
[13] A. N. Angelopoulos and S. Bates, “Conformal prediction: A gentle introduction,” Foundations and Trends in Machine Learning, vol. 16, no. 4, pp. 494–591, 2023, doi: 10.1561/2200000101.