This paper presents an efficient and stable DNNs-based Radau pseudospectral method for the free-time elliptical orbit pursuit-evasion game based on the equivalent reconstruction of the game model. Firstly, the relative dynamics equations are established by adding the nonlinear terms caused by the eccentricity to the Hill–Clohessy–Wilshire equations. Then the original pursuit-evasion problem is deduced to a 4-dimensional one-sided optimal control problem (OCP) based on the equivalent reconstruction. Secondly, in order to apply the deep neural networks (DNNs) to map the relationship between the OCP and the solution, the normalization of costates is introduced to eliminate the non-uniqueness of solutions when generating samples for training DNNs. Thirdly, the DNNs-based Radau pseudospectral method is proposed where the DNNs output the guesses of solutions to the derived OCP and the Radau pseudospectral method optimizes the histories of controls obtained by the guesses to the convergence. The simulation results demonstrate that the proposed method converges more stably and decreases the calculation time greatly compared with the traditional indirect method.
IsaacsR. Differential games. New York, NY: John Wiley & Sons, Inc., 1965.
2.
AndersonGMGrazierVW. Barrier in pursuit-evasion problems between two low-thrust orbital spacecraft. Am Inst Aeronautics Astronautics1976; 14(2): 158–163.
3.
KelleyHJCliffGLutzeFH. Pursuit-evasion in orbit. J Astronautical Sci1981; 29(3): 277–288.
4.
GutmanSEshMGefenM. Simple linear pursuit-evasion games. Comput Maths Appl1987; 13(1–3): 83–95.
5.
MenonPCaliseA. Guidance laws for spacecraft pursuit-evasion and rendezvous. In: Guidance, navigation and control conference. Minneapolis, MN; 1988.
6.
PontaniMConwayBA. Numerical solution of the three-dimensional orbital pursuit-evasion game. J Guidance Control Dyn2009; 32(2): 474–487.
7.
ZengXZhuYYangLet al.Comparison of two optimal guidance methods for the long-distance orbital pursuit-evasion game. IEEE Trans Aerospace Electron Syst2021; 57(1): 521–539.
8.
StupikJM. Optimal pursuit/evasion spacecraft trajectories in the Hill reference frame. Master’s Thesis, University of lllinos at Urbana-Champaign, 2013.
9.
JagatASinclairAJ. Optimization of spacecraft pursuit-evasion game trajectories in the euler-hill reference frame. In: AIAA/AAS astrodynamics specialist conference. San Diego2014.
10.
SunSZhangQLoxtonRet al.Numerical solution of a pursuit-evasion differential game involving two spacecraft in low earth orbit. J Ind Manage Optimization2015; 11(4): 1127–1147.
11.
HaferWTReedHLTurnerJ, et al.Sensitivity methods applied to orbital pursuit evasion. J Guidance Control Dyn2015; 38: 1118–1126.
12.
WoodburyTDHurtadoJE. Adaptive play via estimation in uncertain nonzero-sum orbital pursuit evasion games. In: AIAA Space and astronautics forum and exposition. Orlando, FL; 2017.
13.
YeDShiMMSunZW. Satellite proximate interception vector guidance based on differential games. Chin J Aeronautics2018; 31(147): 192–201.
14.
LiZYZhuHYangZ, et al.A dimension-reduction solution of free-time differential games for spacecraft pursuit-evasion. Acta Astronautica2019; 163: 201–210.
15.
YeDShiMMSunZW. Satellite proximate pursuit-evasion game with different thrust configurations. Aerospace Sci Technol2020; 99: 105715.
16.
LiZYZhuHLuoYZ. An escape strategy in orbital pursuit-evasion games with incomplete information. Sci China Technol Sci2021; 64(3): 559–570.
17.
ClohessyWWiltshireR. Terminal guidance system for satellite rendezvous. J Aerospace Sci1960; 27(9): 653–658.
18.
PrinceERHessJACobbRG, et al.Elliptical orbit proximity operations differential games. J Guidance Control Dyn2019; 42(7): 1458–1472.
19.
SullivanJGrimbergSD’AmicoS. Comprehensive survey and assessment of spacecraft relative motion dynamics models. J Guidance Control Dyn2017; 40(8): 1837–1859.
20.
MeltonRG. Time-explicit representation of relative motion between elliptical orbits. J Guidance Control Dyn2000; 23(4): 604–610.
21.
LeeSParkS. Approximate analytical solutions to optimal reconfiguration problems in perturbed satellite relative motion. J Guidance Control Dyn2011; 34(4): 1097–1111.
22.
GhoshPConwayB. Near-optimal feedback strategies for optimal control and pursuit-evasion games: a spatial statistical approach. In: AIAA guidance, navigation, and control conference. Minneapolis, MN, 2012.
23.
ShenHCasalinoL. Revisit of the three-dimensional orbital pursuit-evasion game. J Guidance Control Dyn2018; 41(8): 1823–1831.
24.
RaivioT. Capture set computation of an optimally guided missile. J Guidance Control Dyn2001; 24(6): 1167–1175.
25.
CarrRWCobbRGPachterM, et al.Solution of a pursuit-evasion game using a near-optimal strategy. J Guidance Control Dyn2018; 41(4): 841–850.
26.
SunST. Two spacecraft pursuit-evasion strategies on low earth orbit and numerical solution. PhD thesis, Harbin Institute of Technology, 2015.
27.
ChengLWangZBJiangFH, et al.Real-time optimal control for spacecraft orbit transfer via multiscale deep neural networks. IEEE Trans Aerospace Electron Syst2019; 55(5): 2436–2450.
28.
YinSSLiJChengL. Low-thrust spacecraft trajectory optimization via a DNN-based method. Adv Space Res2020; 66(7): 1635–1646.
29.
ChengLWangZBJiangFH, et al.Fast generation of optimal asteroid landing trajectories using deep neural networks. IEEE Trans Aerospace Electron Syst2020; 56(4): 2642–2655.
30.
ChengLWangZBJiangFH, et al.Fast solution continuation of time-optimal asteroid landing trajectories using deep neural networks. Acta Astronautica2020; 167: 63–72.
31.
WuQCLiBLiJ, et al.Solution of infinite time domain spacecraft pursuit strategy based on deep neural network. Aerospace Control2019; 37(14–18): 2436–2450.
32.
JiangFHBao YinHLiJF. Practical techniques for low-thrust trajectory optimization with homotopic approach. J Guidance Control Dyn2012; 35(1): 245–258.
33.
PedregosaFVaroquauxGGramfortA, et al.Scikit-learn: machine learning in Python. J Machine Learn Res2011; 12: 2825–2830.
34.
HorieKBruceCA. Optimal fighter pursuit-evasion maneuvers found via two-sided optimization. J Guidance, Control Dyn2006; 29(1): 105–112.
35.
PattersonMARaoAV. GPOPS-II. ACM Trans Math Softw2014; 41(1): 1–37.
36.
PattersonMAHagerWWRaoAV. A ph mesh refinement method for optimal control. Optimal Control Appl Methods2015; 36(4): 398–421.
37.
GragD. Advances in global pseudospectral methods for optimal control. PhD Thesis, University of Floria, 2011.
