Fast Estimation of Initial Costate for Time-Optimal Trajectory Based on Surrogate Model
Publication: Journal of Aerospace Engineering
Volume 36, Issue 6
Abstract
This study investigated the time-optimal low-thrust interplanetary transfer problem, and proposes a fast estimation method for guessing the initial costate and optimal transfer time based on a surrogate model, and applied it to the problem of the 11th Global Trajectory Optimization Competition (GTOC 11). Two core methods are proposed in this paper: (1) a fast generation method called the neighbor point iteration algorithm (NPIA) is presented for rapidly generating low-thrust databases with high efficiency and accuracy; and (2) deep neural networks (DNNs) are adopted to learn the state–costate pairs of low-thrust databases, and the surrogate network can quickly estimate the initial costate and optimal transfer time of the low-thrust interplanetary problem. Experiments verified the proposed method and investigated the influence of network structure, learning rate, and loss function on the accuracy of network estimation. The effects of database generation and network estimation were compared based on three transfer scenarios: coplanar, non-coplanar, and arbitrary orbital transfer. In addition, the application case study showed that the proposed method can quickly obtain the time-optimal low-thrust solution to GTOC 11’s interplanetary transfer, which achieves high precision and meets the terminal constraints.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or codes that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This work was supported by the Scientific Research Project of National University of Defense Technology (No. ZK22-02), and the Postgraduate Scientific Research Innovation Project of Hunan Province (CX20200026).
References
Arora, L., and A. Dutta. 2020. “Reinforcement learning for sequential low-thrust orbit raising problem.” In AIAA Scitech 2020 forum. Orlando, FL: American Institute of Aeronautics and Astronautics.
Bang, J., and J. Ahn. 2019. “Multitarget rendezvous for active debris removal using multiple spacecraft.” J. Spacecr. Rockets 56 (4): 1237–1247. https://doi.org/10.2514/1.A34344.
Benkhoff, J., J. van Casteren, H. Hayakawa, M. Fujimoto, H. Laakso, M. Novara, P. Ferri, H. R. Middleton, and R. Ziethe. 2010. “BepiColombo—Comprehensive exploration of mercury: Mission overview and science goals.” Planet. Space Sci. 58 (1–2): 2–20. https://doi.org/10.1016/j.pss.2009.09.020.
Betts, J. T. 1998. “Survey of numerical methods for trajectory optimization.” J. Guidance Control Dyn. 21 (2): 193–207. https://doi.org/10.2514/2.4231.
Betts, T. J. 2010. “Practical methods for optimal control and estimation using nonlinear programming.” Appl. Mech. Rev. 55 (4): B68. https://doi.org/10.1115/1.1483351.
Böttcher, L., N. Antulov-Fantulin, and T. Asikis. 2022. “AI Pontryagin or how artificial neural networks learn to control dynamical systems.” Nat. Commun. 13 (1): 333. https://doi.org/10.1038/s41467-021-27590-0.
Broucke, R. A., and P. J. Cefola. 1972. “On the equinoctial orbit elements.” Celest. Mech. 5 (3): 303–310. https://doi.org/10.1007/BF01228432.
Chen, Q., G. Giambene, L. Yang, C. Fan, and X. Chen. 2021. “Analysis of inter-satellite link paths for LEO mega-constellation networks.” IEEE Trans. Veh. Technol. 70 (3): 2743–2755. https://doi.org/10.1109/TVT.2021.3058126.
Cheng, L., Z. Wang, F. Jiang, and C. Zhou. 2019. “Real-time optimal control for spacecraft orbit transfer via multiscale deep neural networks.” IEEE Trans. Aerosp. Electron. Syst. 55 (5): 2436–2450. https://doi.org/10.1109/TAES.2018.2889571.
Dyson, F. J. 1960. “Search for artificial stellar sources of infrared radiation.” Science 131 (3414): 1667–1668. https://doi.org/10.1126/science.131.3414.1667.
El-Sabaa, F. M., T. S. Amer, A. A. Sallam, and I. M. Abady. 2022a. “Modeling a semi-optimal deceleration of a rigid body rotational motion in a resisting medium.” Sci. Rep. 12 (1): 18916. https://doi.org/10.1038/s41598-022-22063-w.
El-Sabaa, F. M., T. S. Amer, A. A. Sallam, and I. M. Abady. 2022b. “Modeling of the optimal deceleration for the rotatory motion of asymmetric rigid body.” Math. Comput. Simul. 198 (Aug): 407–425. https://doi.org/10.1016/j.matcom.2022.03.002.
Gao, Y., and C. Kluever. 2004. “Low-thrust interplanetary orbit transfers using hybrid trajectory optimization method with multiple shooting.” In Proc., AIAA/AAS Astrodynamics Specialist Conf. and Exhibit. Providence, RI: American Institute of Aeronautics and Astronautics.
Izzo, D., M. Märtens, and B. Pan. 2019a. “A survey on artificial intelligence trends in spacecraft guidance dynamics and control.” Astrodynamics 3 (Dec): 287–299. https://doi.org/10.1007/s42064-018-0053-6.
Izzo, D., and E. Öztürk. 2021. “Real-time guidance for low-thrust transfers using deep neural networks.” J. Guidance Control Dyn. 44 (2): 315–327. https://doi.org/10.2514/1.G005254.
Izzo, D., C. I. Sprague, and D. V. Tailor. 2019b. “Machine learning and evolutionary techniques in interplanetary trajectory design.” In Modeling and optimization in space engineering, Springer optimization and its applications, edited by G. Fasano and J. D. Pintér, 191–210. Cham, Switzerland: Springer International Publishing.
Jiang, F., H. Baoyin, and J. Li. 2012. “Practical techniques for low-thrust trajectory optimization with homotopic approach.” J. Guidance Control Dyn. 35 (1): 245–258. https://doi.org/10.2514/1.52476.
Kechichian, J. A. 1996. “Optimal low-thrust rendezvous using equinoctial orbit elements.” Acta Astronaut. 38 (1): 1–14. https://doi.org/10.1016/0094-5765(95)00121-2.
Kechichian, J. A. 1997. “Mechanics of trajectory optimization using nonsingular variational equations in polar coordinates.” J. Guidance Control Dyn. 20 (4): 812–818. https://doi.org/10.2514/2.4117.
La Mantia, M., and L. Casalino. 2006. “Indirect optimization of low-thrust capture trajectories.” J. Guidance Control Dyn. 29 (4): 1011–1014. https://doi.org/10.2514/1.18986.
Lee, D., and H. Bang. 2009. “Efficient initial costates estimation for optimal spiral orbit transfer trajectories design.” J. Guidance Control Dyn. 32 (6): 1943–1947. https://doi.org/10.2514/1.44550.
Lee, D., H. Bang, and H.-D. Kim. 2012. “Optimal earth-moon trajectory design using new initial costate estimation method.” J. Guidance Control Dyn. 35 (5): 1671–1676. https://doi.org/10.2514/1.55863.
Li, H., S. Chen, D. Izzo, and H. Baoyin. 2020. “Deep networks as approximators of optimal low-thrust and multi-impulse cost in multitarget missions.” Acta Astronaut. 166 (Jan): 469–481. https://doi.org/10.1016/j.actaastro.2019.09.023.
Li, H., F. Topputo, and H. Baoyin. 2019. “Autonomous time-optimal many-revolution orbit raising for electric propulsion GEO satellites via neural networks.” Preprint, submitted September 19, 2019. https://arxiv.org/abs/1909.08768.
Li, S., X. Huang, and B. Yang. 2018. “Review of optimization methodologies in global and China trajectory optimization competitions.” Prog. Aerosp. Sci. 102 (Oct): 60–75. https://doi.org/10.1016/j.paerosci.2018.07.004.
Luo, Y.-Z., Y.-H. Zhu, P. Shu, B. Yan, J.-C. Zhang, H.-X. Shen, A.-Y. Huang, and T.-J. Zhang. 2021. “The problem of the 11th global trajectory optimization competition.” Accessed October 16, 2021. https://gtoc11.nudt.edu.cn/GTOC?page=home.
Martell, C. A., and J. A. Lawton. 1995. “Adjoint variable solutions via an auxiliary optimization problem.” J. Guidance Control Dyn. 18 (6): 1267–1272. https://doi.org/10.2514/3.21540.
Märtens, M., D. Izzo, E. Blazquez, M. von Looz, P. Gómez, A. Mergy, G. Acciarini, C. H. Yam, J. Hernando-Ayuso, and Y. Shimane. 2022. “The fellowship of the Dyson ring: ACT&Friends’ results and methods for GTOC 11.” Acta Astronaut. 202 (Jan): 807–818. https://doi.org/10.1016/j.actaastro.2022.06.025.
Miller, D., and R. Linares. 2019. “Low-thrust optimal control via reinforcement learning.” In Vol. 168 of Proc., 29th AAS/AIAA Space Flight Mechanics Meeting 2019, 1817–1834. Ka’anapali, HI: American Astronautical Society.
O’Brien, D. P., and M. V. Sykes. 2011. “The origin and evolution of the asteroid belt—Implications for Vesta and Ceres.” Space Sci. Rev. 163 (1–4): 41–61. https://doi.org/10.1007/s11214-011-9808-6.
Prockter, L., S. Murchie, A. Cheng, S. Krimigis, R. Farquhar, A. Santo, and J. Trombka. 2002. “The NEAR shoemaker mission to asteroid 433 eros.” Acta Astronaut. 51 (1–9): 491–500. https://doi.org/10.1016/S0094-5765(02)00098-X.
Ranieri, C. L., and C. A. Ocampo. 2006. “Indirect optimization of spiral trajectories.” J. Guidance Control Dyn. 29 (6): 1360–1366. https://doi.org/10.2514/1.19539.
Rayman, M. D., P. A. Chadbourne, J. S. Culwell, and S. N. Williams. 1999. “Mission design for deep space 1: A low-thrust technology validation mission.” Acta Astronaut. 45 (4–9): 381–388. https://doi.org/10.1016/S0094-5765(99)00157-5.
Russell, R. P. 2007. “Primer vector theory applied to global low-thrust trade studies.” J. Guidance Control Dyn. 30 (2): 460–472. https://doi.org/10.2514/1.22984.
Sánchez-Sánchez, C., and D. Izzo. 2018. “Real-time optimal control via deep neural networks: Study on landing problems.” J. Guidance Control Dyn. 41 (5): 1122–1135. https://doi.org/10.2514/1.G002357.
Schiassi, E., A. D’Ambrosio, K. Drozd, F. Curti, and R. Furfaro. 2022. “Physics-informed neural networks for optimal planar orbit transfers.” J. Spacecr. Rockets 59 (3): 834–849. https://doi.org/10.2514/1.A35138.
Seywald, H., and R. R. Kumar. 1996. “Method for automatic costate calculation.” J. Guidance Control Dyn. 19 (6): 1252–1261. https://doi.org/10.2514/3.21780.
Shen, H.-X., L. Casalino, and H.-Y. Li. 2015. “Adjoints estimation methods for impulsive Moon-to-Earth trajectories in the restricted three-body problem.” Optim. Control Appl. Methods 36 (4): 463–474. https://doi.org/10.1002/oca.2120.
Skamangas, E. E., J. A. Lawton, and J. T. Black. 2021. “Analytic costate initialization from rough state-trajectory estimates.” J. Guidance Control Dyn. 44 (12): 2318–2326. https://doi.org/10.2514/1.G005224.
Sullivan, C. J., and N. Bosanac. 2020. “Using reinforcement learning to design a low-thrust approach into a periodic orbit in a multi-body system.” In AIAA Scitech 2020 Forum. Orlando, FL: American Institute of Aeronautics and Astronautics.
Thorne, J. D., and C. D. Hall. 1996. “Approximate initial Lagrange costates for continuous-thrust spacecraft.” J. Guidance Control Dyn. 19 (2): 283–288. https://doi.org/10.2514/3.21616.
Yan, H., and H. Wu. 1999. “Initial adjoint-variable guess technique and its application in optimal orbital transfer.” J. Guidance Control Dyn. 22 (3): 490–492. https://doi.org/10.2514/2.7631.
Yin, S., J. Li, and L. Cheng. 2020. “Low-thrust spacecraft trajectory optimization via a DNN-based method.” Adv. Space Res. 66 (7): 1635–1646. https://doi.org/10.1016/j.asr.2020.05.046.
Zhu, Y., and Y.-Z. Luo. 2019. “Fast evaluation of low-thrust transfers via multilayer perceptions.” J. Guidance Control Dyn. 42 (12): 2627–2637. https://doi.org/10.2514/1.G004080.
Information & Authors
Information
Published In
Journal of Aerospace Engineering
Volume 36 • Issue 6 • November 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Sep 20, 2022
Accepted: Apr 28, 2023
Published online: Aug 28, 2023
Published in print: Nov 1, 2023
Discussion open until: Jan 28, 2024
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.