Learning-based interfered fluid avoidance guidance for hypersonic reentry vehicles with multiple constraints

Tiancai Wu; Honglun Wang; Yiheng Liu; Tianren Li; Yue Yu

doi:10.1016/j.isatra.2023.04.004

Learning-based interfered fluid avoidance guidance for hypersonic reentry vehicles with multiple constraints

ISA Trans. 2023 Aug:139:291-307. doi: 10.1016/j.isatra.2023.04.004. Epub 2023 Apr 10.

Authors

Tiancai Wu¹, Honglun Wang², Yiheng Liu¹, Tianren Li³, Yue Yu⁴

Affiliations

¹ School of Automation Science and Electrical Engineering, Beihang University, 100191, Beijing, China; Shenyuan Honors College of Beihang University, 100191, Beijing, China; The Science and Technology on Aircraft Control Laboratory, Beihang University, 100191, Beijing, China.
² School of Automation Science and Electrical Engineering, Beihang University, 100191, Beijing, China; The Science and Technology on Aircraft Control Laboratory, Beihang University, 100191, Beijing, China. Electronic address: wang_hl_12@126.com.
³ R & D Center, China Academy of Launch Vehicle Technology, Beijing 100071, China.
⁴ Beijing Aerospace Automatic Control Institute, Beijing 100854, China.

PMID: 37076373
DOI: 10.1016/j.isatra.2023.04.004

Abstract

To address the problem of no-fly zone avoidance for hypersonic reentry vehicles in the multiple constraints gliding phase, a learning-based avoidance guidance framework is proposed. First, the reference heading angle determination problem is solved efficiently and skillfully by introducing a nature-inspired methodology based on the concept of the interfered fluid dynamic system (IFDS), in which the distance and relative position relationships of all no-fly zones can be comprehensively considered, and additional rules are no longer needed. Then, by incorporating the predictor-corrector method, the heading angle corridor, and bank angle reversal logic, a fundamental interfered fluid avoidance guidance algorithm is proposed to steer the vehicle toward the target zone while avoiding no-fly zones. In addition, a learning-based online optimization mechanism is used to optimize the IFDS parameters in real time to improve the avoidance guidance performance of the proposed algorithm in the entire gliding phase. Finally, the adaptability and robustness of the proposed guidance algorithm are verified via comparative and Monte Carlo simulations.

Keywords: Deep reinforcement learning; Hypersonic reentry vehicle; Interfered fluid dynamic system (IFDS); No-fly zone; Predictor–corrector guidance; Reentry avoidance guidance.