요격 정확도 향상을 위한 유전 알고리즘 기반 반응속도 최적화 기법 연구

김현승¹^{, *} ; 현철² ; 이성균² ; 고진용² ; 김창환²

1LIG넥스원 해양연구소 선임연구원
2LIG넥스원 해양연구소 수석연구원

Research on Genetic Algorithm-based Optimization of Response Time for Improved Interception Accuracy

Hyunseung Kim¹^{, *} ; Chul Hyun² ; Sungkyun Lee² ; Jinyong Go² ; Changhwan Kim²

1Research engineer, Marine R&D Center, LIG Nex1
2Chief research engineer, Marine R&D Center, LIG Nex1

Correspondence to: ^*Hyunseung Kim Marine R&D Center, LIG Nex1 333 Pangyo-ro, Bundang-gu, Seongnam-si, Gyeonggi-do, 13488, Republic of Korea Tel: +82-31-5179-7272 Fax: +82-31-5179-7086 E-mail: hyunseung.kim2@lignex1.com

초록

본 논문에서는 등속 운동 표적을 요격하기 위한 기하 기반 예상 요격 지점 산출과 반응 지연 보정 기법을 제안하였다. 요격체 지연 특성 모델과 유전 알고리즘을 통한 최적 반응속도 계수 산출을 통합 설계하였다. 다양한 교전 상황에서 최적 반응속도 계수를 적용한 결과가 고정 계수를 적용한 결과 대비 요격 오차가 유의미하게 감소되는 것을 확인하였다. 본 논문에서 제시하는 프레임워크는 실시간 유도 전략 수립에 활용할 수 있을 것으로 기대된다.

Abstract

In this paper, a geometry-based method for predicting interception points and a delay compensation technique are proposed to intercept constant-velocity maneuvering target. An integrated model is designed combining the interceptor’s delay characteristic model and optimization of the reaction rate coefficient via a genetic algorithm. Applying the optimizing reaction rate coefficient in various engagement scenarios to showed a significant reduction in interception error compared to using a fixed coefficient. The proposed method is expected to use for establishing real-time guidance strategies.

Keywords:

Predicted Intercept Point, Genetic Algorithm, Geometric Modeling, Reaction Rate Coefficient, Autonomous Guidance Control

키워드:

예상 요격 지점, 유전 알고리즘, 기하 모델, 반응속도 계수, 자율 유도 제어

References

C. Qu, J. He, J. Li, C. Fang and Y. Mo, “Moving Target Interception Considering Dynamic Environment,” 2022 American Control Conference, pp. 1194-1199, Jun. 2022. [https://doi.org/10.23919/ACC53348.2022.9867177]
K. Ding, X. Cui, Z. Wang, Z. Qiu, Y. Hu and H. Zhang, “Research on Interception Model of Surface-to-air Missile Anti-cruise Missile Weapon System,” Journal of Physics: Conference Series 2890, pp. 1-14, Aug. 2024. [https://doi.org/10.1088/1742-6596/2890/1/012006]
A. Dastider, H. Fang and M. Lin, “Unified Control Framework for Real-Time Interception and Obstacle Avoidance of Fast-Moving Objects with Diffusion Variational Auto-encoder,” International Conference on Intelligent Robots and Systems, pp. 14-18, Oct. 2024. [https://doi.org/10.1109/IROS58592.2024.10802535]
A. Stair, U. Demir, G. Sever and N. Ure, “Nonlinear Model Based Guidance with Deep Learning Based Target Trajectory Prediction Against Aerial Agile Attack Patterns,” 2021 American Control Conference, pp. 2607-2612, May. 2021. [https://doi.org/10.23919/ACC50511.2021.9483038]
Y. Zhang, X. Gao, J. Zong, Z. Leng and Z. Hou, “Real-Time Trajectory Planning and Effectiveness Analysis of Intercepting Large-scale Invading UAV Swarms Based on Motion Primitives,” Journal of the MDPI Drones, Vol. 8, No. 10, pp. 1-25, Oct. 2024. [https://doi.org/10.3390/drones8100588]
Z. Gyenes, L. Boloni and E. Kardoss, “Can Genetic Algorithms Be Used for Real-time Obstacle Avoidance for LiDAR-Equipped Mobile Robots?,” Journal of the MDPI Sensors, Vol. 23, No. 6, pp. 1-17, Mar. 2023. [https://doi.org/10.3390/s23063039]