Efficient fuel-optimal multi-impulse orbital transfer via contrastive pre-trained reinforcement learning
Multi-impulse transfers between noncoplanar orbits are significant for on-orbit service spacecraft. This paper investigates the complex optimization problem of multi-impulse orbital transfer involving a chaser and a target. The chaser is subject to constraints on impulse magnitude and time, while th...
Uloženo v:
| Vydáno v: | Advances in space research Ročník 75; číslo 10; s. 7377 - 7396 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
15.05.2025
|
| Témata: | |
| ISSN: | 0273-1177 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Multi-impulse transfers between noncoplanar orbits are significant for on-orbit service spacecraft. This paper investigates the complex optimization problem of multi-impulse orbital transfer involving a chaser and a target. The chaser is subject to constraints on impulse magnitude and time, while the target may experience uncertain disturbances, causing it to deviate from the nominal orbit. The complexity of this problem imposes a significant computational burden on numerical methods, making it challenging for spacecraft to autonomously plan trajectory transfers in real time. To mitigate this burden, we propose a robust, fast, and autonomous algorithm for the optimization challenge, which can rapid plan transfer trajectories. Even if the terminal conditions suddenly change, our algorithm can quickly adjust the trajectory based on observed states without the need to completely re-plan. The algorithm comprises an intelligent trajectory generator and a Lambert transfer algorithm. The intelligent generator is based on a reinforcement learning (RL) method called contrastive-pre-trained Reinforcement Learning (CPRL), which emulates human learning habits to avoid the temporal credit assignment with long time horizons and sparse rewards during the training phase. When the chaser reaches an admissible range, determined by the impulse constraints and geometric relations of the conic curve, the algorithm adopts the Lambert transfer to complete the mission. Compared to traditional genetic and particle swarm algorithms, our method achieves a significant improvement in computational speed. Even with deviations, the average mission success rate remains at 96.8%. Numerical simulations confirm that our algorithm processes data quickly, can be deployed online, and is capable of handling various tasks in real time. |
|---|---|
| AbstractList | Multi-impulse transfers between noncoplanar orbits are significant for on-orbit service spacecraft. This paper investigates the complex optimization problem of multi-impulse orbital transfer involving a chaser and a target. The chaser is subject to constraints on impulse magnitude and time, while the target may experience uncertain disturbances, causing it to deviate from the nominal orbit. The complexity of this problem imposes a significant computational burden on numerical methods, making it challenging for spacecraft to autonomously plan trajectory transfers in real time. To mitigate this burden, we propose a robust, fast, and autonomous algorithm for the optimization challenge, which can rapid plan transfer trajectories. Even if the terminal conditions suddenly change, our algorithm can quickly adjust the trajectory based on observed states without the need to completely re-plan. The algorithm comprises an intelligent trajectory generator and a Lambert transfer algorithm. The intelligent generator is based on a reinforcement learning (RL) method called contrastive-pre-trained Reinforcement Learning (CPRL), which emulates human learning habits to avoid the temporal credit assignment with long time horizons and sparse rewards during the training phase. When the chaser reaches an admissible range, determined by the impulse constraints and geometric relations of the conic curve, the algorithm adopts the Lambert transfer to complete the mission. Compared to traditional genetic and particle swarm algorithms, our method achieves a significant improvement in computational speed. Even with deviations, the average mission success rate remains at 96.8%. Numerical simulations confirm that our algorithm processes data quickly, can be deployed online, and is capable of handling various tasks in real time. |
| Author | Zhong, Rui Ren, He Gui, Haichao |
| Author_xml | – sequence: 1 givenname: He surname: Ren fullname: Ren, He email: renhe_email@163.com – sequence: 2 givenname: Haichao surname: Gui fullname: Gui, Haichao email: hcgui@buaa.edu.cn – sequence: 3 givenname: Rui surname: Zhong fullname: Zhong, Rui email: zhongruia@163.com |
| BookMark | eNp9kE1LAzEQhnOoYKv-AG_7B3bNJN3NFk9S6gcUvOg5pMlEU3aTJUkL_nuz1LOn4R14XmaeFVn44JGQe6ANUOgejo1KsWGUtQ1lDV1vFmRJmeA1gBDXZJXSkVJgQtAl-d5Z67RDnyt7wqEOU3ajGqrxNGRXu3E6DQmrEA8ul22OyieLsTo7VengS07ZnbGaItYlOI-miui8DVHjOLcOqKJ3_uuWXFlVuu7-5g35fN59bF_r_fvL2_ZpX2vWQq45E7oXXQ-GCw4ALba65Yb3ClGtaSeQ9xpMz7Swa9NBC5ZxBVofNpQyo_gNgUuvjiGliFZOsXwUfyRQOeuRR1n0yFmPpEwWPYV5vDBYDjs7jDLNSjQaF1FnaYL7h_4FjLV0Bw |
| Cites_doi | 10.1016/j.asr.2023.06.015 10.1016/j.ast.2019.105400 10.1002/rnc.6270 10.1007/978-981-19-6613-2_514 10.2514/1.G006091 10.1016/j.dt.2021.02.006 10.1016/j.ast.2019.105529 10.2514/1.G001198 10.1016/j.asr.2015.09.014 10.34133/space.0086 10.2514/1.A34946 10.2514/1.24701 10.1016/j.asr.2022.08.002 10.1016/j.cja.2023.03.021 10.34133/space.0047 10.1016/j.asr.2018.09.023 10.1109/AERO58975.2024.10521334 10.1016/j.actaastro.2024.08.029 10.2514/1.49683 10.1016/j.actaastro.2021.05.002 10.1016/j.ast.2018.01.003 10.1109/MCS.2022.3187542 10.1007/s40295-015-0073-x 10.2514/3.21786 10.2514/1.55592 10.1016/j.actaastro.2016.11.012 10.1016/j.asr.2023.03.014 10.1243/0954410041321998 10.2514/1.8392 10.2514/1.G001598 10.1023/B:COSM.0000033300.18460.a4 10.1016/j.ast.2005.12.007 10.1016/j.asr.2023.07.028 10.1061/(ASCE)AS.1943-5525.0001464 10.1109/TNNLS.2022.3185949 10.2514/3.56656 10.1016/j.asr.2023.03.050 10.1016/j.ast.2017.11.025 |
| ContentType | Journal Article |
| Copyright | 2025 COSPAR |
| Copyright_xml | – notice: 2025 COSPAR |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.asr.2025.02.049 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Astronomy & Astrophysics Physics |
| EndPage | 7396 |
| ExternalDocumentID | 10_1016_j_asr_2025_02_049 S027311772500184X |
| GroupedDBID | --K --M -~X .~1 0R~ 1RT 1~. 1~5 23M 4.4 457 4G. 53G 5GY 5VS 7-5 71M 8P~ 9JN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AATTM AAXKI AAXUO AAYWO ABJNI ABMAC ABNEU ABQEM ABQYD ACDAQ ACFVG ACGFS ACLVX ACRLP ACSBN ADBBV ADEZE AEBSH AEIPS AEKER AENEX AFJKZ AFTJW AFXIZ AGCQF AGRNS AGUBO AGYEJ AHHHB AIEXJ AIIUN AIKHN AITUG AIVDX AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU APXCP ATOGT AXJTR BKOJK BLXMC BNPGV CS3 EBS EFJIC EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA IMUCA J1W KOM LY3 LZ4 M41 MO0 N9A O-L O9- OAUVE OGIMB OZT P-8 P-9 P2P PC. Q38 ROL SDF SDG SEP SES SEW SPC SPCBC SSH SSQ SSZ T5K ZMT ~02 ~G- 1B1 9DU AAQXK AAYXX ABFNM ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADMUD ADNMO AEUPX AFPUW AGHFR AGQPQ AI. AIGII AKBMS AKYEP ASPBG AVWKF AZFZN CITATION EFKBS EFLBG EJD FEDTE FGOYB G-2 HMA HME HVGLF HX~ HZ~ IHE R2- RPZ SHN SSE T9H UHS VH1 VOH WUQ ZY4 ~HD |
| ID | FETCH-LOGICAL-c251t-327c87681d3731115e5c53d38aeea4067e38c1d82c7f4d6151f23a1ccb9002da3 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001488478700003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0273-1177 |
| IngestDate | Sat Nov 29 07:59:33 EST 2025 Sat Jun 07 17:01:49 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 10 |
| Keywords | Contrastive-pretrained reinforcement learning Efficient orbital transfer Trajectory optimization |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c251t-327c87681d3731115e5c53d38aeea4067e38c1d82c7f4d6151f23a1ccb9002da3 |
| PageCount | 20 |
| ParticipantIDs | crossref_primary_10_1016_j_asr_2025_02_049 elsevier_sciencedirect_doi_10_1016_j_asr_2025_02_049 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-05-15 |
| PublicationDateYYYYMMDD | 2025-05-15 |
| PublicationDate_xml | – month: 05 year: 2025 text: 2025-05-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationTitle | Advances in space research |
| PublicationYear | 2025 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | doi: 10.1016/j.asr.2015.09.014. Poozhiyil, M., Nair, M.H., Rai, M.C. et al. (2023). Active debris removal: A review and case study on leopard phase 0-a mission. Advances in Space Research, 72(8), 3386–3413. URL: https://www.sciencedirect.com/science/article/pii/S0273117723004453. doi: 10.1016/j.asr.2023.06.015. Xu, L., Zhang, G., Qiu, S. et al., 2023. Optimal multi-impulse linear rendezvous via reinforcement learning. Space: Science & Technology, 3, 0047. URL doi: 10.1016/j.ast.2018.01.003. Liang, H., Wang, J., Liu, J. et al., 2020. Guidance strategies for interceptor against active defense spacecraft in two-on-two engagement. Aerospace Science and Technology, 96, 105529. URL: https://www.sciencedirect.com/science/article/pii/S1270963819311964. doi: 10.1016/j.ast.2019.105529. doi: 10.1016/j.actaastro.2021.05.002. Zhang, Ma, Liu (b0270) 2022; 35 Lyu, B., Yue, X., & Liu, C. (2022). Constrained multi-observer-based fault-tolerant disturbance-rejection control for rigid spacecraft. International Journal of Robust and Nonlinear Control, 32(14), 8102–8133. URL: https://onlinelibrary.wiley.com/doi/abs/10.1002/rnc.6270. doi: 10.1002/rnc.6270. arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1002/rnc.6270. Hu, J., Yang, H., Li, S. et al., 2023. Densely rewarded reinforcement learning for robust low-thrust trajectory optimization. Adv. Space Res., 72(4), 964–981. URL Zhang, G., Mortari, D., Zhou, D., 2010. Constrained multiple-revolution lambert’s problem. J. Guidance, Control, Dynam., 33(6), 1779–1786. URL: doi: 10.2514/1.49683. arXiv:https://doi.org/10.2514/1.49683. Hong, Y., Xin-hong, L., & Wen-zhe, D. (2022). Interception time and uncertainty optimization for tangent-impulse orbit interception problem. Defence Technol., 18(3), 418–440. URL Lu, Li, Dong (b0120) 2024 doi: 10.1016/j.asr.2023.03.014. Guffanti, T., Gammelli, D., D’Amico, S. et al., 2024. Transformers for trajectory optimization with application to spacecraft rendezvous. (pp. 1–13). doi:10.1109/AERO58975.2024.10521334. Li, Luo (b0100) 2024 Yang, B., Li, S., Feng, J. et al. (2022a). Fast solver for j2-perturbed lambert problem using deep neural network. J. Guidance, Control, Dynam., 45(5), 875–884. URL: doi: 10.2514/1.G006091. doi:10.2514/1.G006091. arXiv:https://doi.org/10.2514/1.G006091. Ryoo, C.-K., Cho, H., & Tahk, M.-J. (2005). Optimal guidance laws with terminal impact angle constraint. Journal of Guidance, Control, and Dynamics, 28(4), 724–732. URL: doi: 10.2514/1.8392. doi:10.2514/1.8392. arXiv:https://doi.org/10.2514/1.8392. Battin, R.H., 1987. An introduction to the mathematics and methods of astrodynamics. URL Zhang, Ma (b0265) 2023; 1–13 Oghim, S., Leeghim, H., & Kim, D. (2019). Real-time spacecraft intercept strategy on j2-perturbed orbits. Advances in Space Research, 63(2), 1007–1016. URL: https://www.sciencedirect.com/science/article/pii/S027311771830721X. doi: 10.1016/j.asr.2018.09.023. Shen, Casalino, zhong Luo (b0195) 2015; 62 Espeholt, Soyer, Munos (b0045) 2018 Chen, Z., Tang, S., 2018. Neighboring optimal control for open-time multiburn orbital transfers. Aerospace Sci. Technol., 74, 37–45. URL Kaplanis, C., Shanahan, M., Clopath, C., 2019. Policy consolidation for continual reinforcement learning. arXiv preprint arXiv:1902.00255. arXiv:https://spj.science.org/doi/pdf/10.34133/space.0086. . Jiang, R., Ye, D., Xiao, Y. et al. (2023). Orbital interception pursuit strategy for random evasion using deep reinforcement learning. Space: Sci. Technol., 3, 0086. URL Tang, D., & Gong, S. (2023). Trajectory optimization of rocket recovery based on neural network and genetic algorithm. Advances in Space Research, 72(8), 3344–3356. URL: https://www.sciencedirect.com/science/article/pii/S027311772300563X. doi: 10.1016/j.asr.2023.07.028. Khadka, Tumer (b0095) 2018 Peloni, A., Rao, A.V., & Ceriotti, M. (2018). Automated trajectory optimizer for solar sailing (atoss). Aerospace Science and Technology, 72, 465–475. URL: https://www.sciencedirect.com/science/article/pii/S1270963817315869. doi: 10.1016/j.ast.2017.11.025. Luo, Y.-Z., Tang, G.-J., & yang Li, H. (2006). Optimization of multiple-impulse minimum-time rendezvous with impulse constraints using a hybrid genetic algorithm. Aerospace Science and Technology, 10(6), 534–540. URL: https://www.sciencedirect.com/science/article/pii/S1270963806000162. doi: 10.1016/j.ast.2005.12.007. Ellery (b0040) 2004; 218 doi: 10.1016/j.asr.2023.03.050. Pontani, M., Ghosh, P., & Conway, B.A. (2012). Particle swarm optimization of multiple-burn rendezvous trajectories. Journal of Guidance, Control, and Dynamics, 35(4), 1192–1207. URL: doi: 10.2514/1.55592. doi:10.2514/1.55592. arXiv:https://doi.org/10.2514/1.55592. Lyu, Liu, Yue (b0130) 2024 Xu, L., Zhang, G., Qiu, S. et al. (2024). Reinforcement learning-based multi-impulse rendezvous approach for satellite constellation reconfiguration. Acta Astronautica, 224, 325–337. URL Ying, Wang, Hu (b0255) 2024 Lillicrap, T.P., Hunt, J.J., Pritzel, A. et al. (2015). Continuous control with deep reinforcement learning. CoRR, abs/1509.02971. URL: https://api.semanticscholar.org/CorpusID:16326763. Wenzel, R.S., & Prussing, J.E., 1996. Preliminary study of optimal thrust-limited path-constrained maneuvers. J. Guidance, Control, Dynam., 19(6), 1303–1309. URL: doi: 10.2514/3.21786. arXiv:https://doi.org/10.2514/3.21786. doi: 10.1016/j.asr.2022.08.002. Yang, Z., Luo, Y.-Z., Zhang, J. et al. (2015). Homotopic perturbed lambert algorithm for long-duration rendezvous optimization. Journal of Guidance, Control, and Dynamics, 38(11), 2215–2223. URL: doi: 10.2514/1.G001198. doi:10.2514/1.G001198. arXiv:https://doi.org/10.2514/1.G001198. Barth, Roach, Ma (b0015) 2025 Cong, Liu, Wei (b0035) 2024 Malyuta, Reynolds, Szmuk (b0150) 2022; 42 arXiv:https://spj.science.org/doi/pdf/10.34133/space.0047. Gong, M., Zhou, D., Shao, C. et al., 2022. Optimal multiple-impulse time-fixed rendezvous using evolutionary algorithms. J. Spacecr. Rock., 59(2), 697–703. URL: doi: 10.2514/1.A34946. arXiv:https://doi.org/10.2514/1.A34946. Scorsoglio, A., Furfaro, R., Linares, R. et al., 2023. Relative motion guidance for near-rectilinear lunar orbits with path constraints via actor-critic reinforcement learning. Advances in Space Research, 71(1), 316–335. URL doi: 10.1016/j.actaastro.2024.08.029. Avendaño, M., Martín-Molina, V., Martín-Morales, J. et al., 2016. Algebraic approach to the minimum-cost multi-impulse orbit-transfer problem. J. Guidance, Control, Dynam., 39(8), 1734–1743. URL: doi: 10.2514/1.G001598. arXiv:https://doi.org/10.2514/1.G001598. Taur, D.-R., Coverstone-Carroll, V., & Prussing, J.E. (1995). Optimal impulsive time-fixed orbital rendezvous and interception with path constraints. Journal of Guidance, Control, and Dynamics, 18(1), 54–60. URL: doi: 10.2514/3.56656. doi:10.2514/3.56656. arXiv:https://doi.org/10.2514/3.56656. Shirazi, A., Ceberio, J., & Lozano, J.A. (2019). An evolutionary discretized lambert approach for optimal long-range rendezvous considering impulse limit. Aerospace Science and Technology, 94, 105400. URL: https://www.sciencedirect.com/science/article/pii/S127096381931586X. doi: 10.1016/j.ast.2019.105400. Zhao, L., Zhang, Y., Dang, Z., 2023. Prd-maddpg: An efficient learning-based algorithm for orbital pursuit-evasion game with impulsive maneuvers. Adv. Space Res., 72(2), 211–230. URL Garg, Setlur, Lipton (b0050) 2024; 36 doi: 10.1016/j.dt.2021.02.006. Wang, Z., Bapst, V., Heess, N. et al., 2016. Sample efficient actor-critic with experience replay. arXiv preprint arXiv:1611.01224. Harutyunyan, Bellemare, Stepleton (b0070) 2016 Butikov, E.I., 2015. Orbital maneuvers and space rendezvous. Adv. Space Res., 56(11), 2582–2594. URL Małkiński, Mańdziuk (b0145) 2022; 35 Lidtke, A.A., Lewis, H.G., Armellin, R. et al., 2017. Considering the collision probability of active debris removal missions. Acta Astronautica, 131, 10–17. URL: https://www.sciencedirect.com/science/article/pii/S0094576516305434. doi: 10.1016/j.actaastro.2016.11.012. Petukhov (b0165) 2004; 42 Ma, Zhang (b0140) 2023 Schulman, J., Wolski, F., Dhariwal, P. et al., 2017. Proximal policy optimization algorithms. arXiv:1707.06347. Yue, Y., Shan, H., Zhou, Z. et al., 2021. A fast calculation method for asteroid exploration window based on optimal and sub-optimal two-impulse transfer orbits. Acta Astronautica, 186, 171–182. URL Abdelkhalik, O., Mortari, D., 2007. N-impulse orbit transfer using genetic algorithms. J. Spacecr. Rock., 44(2), 456–460. doi:10.2514/1.24701. arXiv:https://doi.org/10.2514/1.24701. Haarnoja, Zhou, Abbeel (b0065) 2018 Yang, L., Li, H., Li, X. et al. (2022b). A reinforcement learning method to trajectory design for manned lunar mission via reshaping rewards. In International Conference on Guidance, Navigation and Control (pp. 5318–5329). Springer. Wu, Tan, Li (b0225) 2019; 21 10.1016/j.asr.2025.02.049_b0215 Cong (10.1016/j.asr.2025.02.049_b0035) 2024 Espeholt (10.1016/j.asr.2025.02.049_b0045) 2018 Malyuta (10.1016/j.asr.2025.02.049_b0150) 2022; 42 10.1016/j.asr.2025.02.049_b0090 10.1016/j.asr.2025.02.049_b0170 10.1016/j.asr.2025.02.049_b0250 10.1016/j.asr.2025.02.049_b0055 10.1016/j.asr.2025.02.049_b0010 10.1016/j.asr.2025.02.049_b0175 10.1016/j.asr.2025.02.049_b0210 Khadka (10.1016/j.asr.2025.02.049_b0095) 2018 10.1016/j.asr.2025.02.049_b0135 10.1016/j.asr.2025.02.049_b0105 Wu (10.1016/j.asr.2025.02.049_b0225) 2019; 21 Garg (10.1016/j.asr.2025.02.049_b0050) 2024; 36 Zhang (10.1016/j.asr.2025.02.049_b0265) 2023; 1–13 10.1016/j.asr.2025.02.049_b0060 Petukhov (10.1016/j.asr.2025.02.049_b0165) 2004; 42 10.1016/j.asr.2025.02.049_b0180 Li (10.1016/j.asr.2025.02.049_b0100) 2024 10.1016/j.asr.2025.02.049_b0260 10.1016/j.asr.2025.02.049_b0020 10.1016/j.asr.2025.02.049_b0185 10.1016/j.asr.2025.02.049_b0220 10.1016/j.asr.2025.02.049_b0025 10.1016/j.asr.2025.02.049_b0115 Lu (10.1016/j.asr.2025.02.049_b0120) 2024 Barth (10.1016/j.asr.2025.02.049_b0015) 2025 10.1016/j.asr.2025.02.049_b0190 10.1016/j.asr.2025.02.049_b0075 10.1016/j.asr.2025.02.049_b0030 10.1016/j.asr.2025.02.049_b0110 10.1016/j.asr.2025.02.049_b0275 10.1016/j.asr.2025.02.049_b0230 10.1016/j.asr.2025.02.049_b0155 10.1016/j.asr.2025.02.049_b0235 10.1016/j.asr.2025.02.049_b0005 10.1016/j.asr.2025.02.049_b0205 Zhang (10.1016/j.asr.2025.02.049_b0270) 2022; 35 Ellery (10.1016/j.asr.2025.02.049_b0040) 2004; 218 Haarnoja (10.1016/j.asr.2025.02.049_b0065) 2018 Ying (10.1016/j.asr.2025.02.049_b0255) 2024 Małkiński (10.1016/j.asr.2025.02.049_b0145) 2022; 35 Shen (10.1016/j.asr.2025.02.049_b0195) 2015; 62 10.1016/j.asr.2025.02.049_b0080 10.1016/j.asr.2025.02.049_b0280 Lyu (10.1016/j.asr.2025.02.049_b0130) 2024 10.1016/j.asr.2025.02.049_b0160 10.1016/j.asr.2025.02.049_b0240 10.1016/j.asr.2025.02.049_b0085 10.1016/j.asr.2025.02.049_b0200 Harutyunyan (10.1016/j.asr.2025.02.049_b0070) 2016 10.1016/j.asr.2025.02.049_b0125 Ma (10.1016/j.asr.2025.02.049_b0140) 2023 10.1016/j.asr.2025.02.049_b0245 |
| References_xml | – volume: 218 start-page: 79 year: 2004 end-page: 98 ident: b0040 article-title: An engineering approach to the dynamic control of space robotic on-orbit servicers publication-title: Proc. Inst. Mech. Eng., Part G: J. Aerospace Eng. – reference: Yue, Y., Shan, H., Zhou, Z. et al., 2021. A fast calculation method for asteroid exploration window based on optimal and sub-optimal two-impulse transfer orbits. Acta Astronautica, 186, 171–182. URL: – volume: 36 year: 2024 ident: b0050 article-title: Complementary benefits of contrastive learning and self-training under distribution shift publication-title: Adv. Neural Inform. Process. Syst. – volume: 35 start-page: 1941 year: 2022 end-page: 1953 ident: b0145 article-title: Multi-label contrastive learning for abstract visual reasoning publication-title: IEEE Trans. Neural Networks Learn. Syst. – reference: Taur, D.-R., Coverstone-Carroll, V., & Prussing, J.E. (1995). Optimal impulsive time-fixed orbital rendezvous and interception with path constraints. Journal of Guidance, Control, and Dynamics, 18(1), 54–60. URL: doi: 10.2514/3.56656. doi:10.2514/3.56656. arXiv:https://doi.org/10.2514/3.56656. – reference: Yang, B., Li, S., Feng, J. et al. (2022a). Fast solver for j2-perturbed lambert problem using deep neural network. J. Guidance, Control, Dynam., 45(5), 875–884. URL: doi: 10.2514/1.G006091. doi:10.2514/1.G006091. arXiv:https://doi.org/10.2514/1.G006091. – reference: Zhao, L., Zhang, Y., Dang, Z., 2023. Prd-maddpg: An efficient learning-based algorithm for orbital pursuit-evasion game with impulsive maneuvers. Adv. Space Res., 72(2), 211–230. URL: – reference: Wenzel, R.S., & Prussing, J.E., 1996. Preliminary study of optimal thrust-limited path-constrained maneuvers. J. Guidance, Control, Dynam., 19(6), 1303–1309. URL: doi: 10.2514/3.21786. arXiv:https://doi.org/10.2514/3.21786. – reference: Scorsoglio, A., Furfaro, R., Linares, R. et al., 2023. Relative motion guidance for near-rectilinear lunar orbits with path constraints via actor-critic reinforcement learning. Advances in Space Research, 71(1), 316–335. URL: – reference: . arXiv:https://spj.science.org/doi/pdf/10.34133/space.0086. – reference: Luo, Y.-Z., Tang, G.-J., & yang Li, H. (2006). Optimization of multiple-impulse minimum-time rendezvous with impulse constraints using a hybrid genetic algorithm. Aerospace Science and Technology, 10(6), 534–540. URL: https://www.sciencedirect.com/science/article/pii/S1270963806000162. doi: 10.1016/j.ast.2005.12.007. – reference: Shirazi, A., Ceberio, J., & Lozano, J.A. (2019). An evolutionary discretized lambert approach for optimal long-range rendezvous considering impulse limit. Aerospace Science and Technology, 94, 105400. URL: https://www.sciencedirect.com/science/article/pii/S127096381931586X. doi: 10.1016/j.ast.2019.105400. – start-page: 1 year: 2024 end-page: 12 ident: b0130 article-title: Integrated predictor-observer feedback control for vibration mitigation of large-scale spacecraft with unbounded input time delay publication-title: IEEE Trans. Aerosp. Electron. Syst. – reference: Yang, Z., Luo, Y.-Z., Zhang, J. et al. (2015). Homotopic perturbed lambert algorithm for long-duration rendezvous optimization. Journal of Guidance, Control, and Dynamics, 38(11), 2215–2223. URL: doi: 10.2514/1.G001198. doi:10.2514/1.G001198. arXiv:https://doi.org/10.2514/1.G001198. – reference: Yang, L., Li, H., Li, X. et al. (2022b). A reinforcement learning method to trajectory design for manned lunar mission via reshaping rewards. In International Conference on Guidance, Navigation and Control (pp. 5318–5329). Springer. – reference: Hong, Y., Xin-hong, L., & Wen-zhe, D. (2022). Interception time and uncertainty optimization for tangent-impulse orbit interception problem. Defence Technol., 18(3), 418–440. URL: – volume: 1–13 year: 2023 ident: b0265 article-title: Covariance analysis of the optimal orbital interception with navigation errors publication-title: IEEE Trans. Aerospace Electron. Syst., PP – reference: Wang, Z., Bapst, V., Heess, N. et al., 2016. Sample efficient actor-critic with experience replay. arXiv preprint arXiv:1611.01224. – reference: Lyu, B., Yue, X., & Liu, C. (2022). Constrained multi-observer-based fault-tolerant disturbance-rejection control for rigid spacecraft. International Journal of Robust and Nonlinear Control, 32(14), 8102–8133. URL: https://onlinelibrary.wiley.com/doi/abs/10.1002/rnc.6270. doi: 10.1002/rnc.6270. arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1002/rnc.6270. – volume: 62 start-page: 212 year: 2015 end-page: 232 ident: b0195 article-title: Global search capabilities of indirect methods for impulsive transfers publication-title: J. Astronaut. Sci. – reference: Kaplanis, C., Shanahan, M., Clopath, C., 2019. Policy consolidation for continual reinforcement learning. arXiv preprint arXiv:1902.00255. – reference: Battin, R.H., 1987. An introduction to the mathematics and methods of astrodynamics. URL: – volume: 42 start-page: 250 year: 2004 end-page: 268 ident: b0165 article-title: Optimization of multi-orbit transfers between noncoplanar elliptic orbits publication-title: Cosm. Res. – reference: Guffanti, T., Gammelli, D., D’Amico, S. et al., 2024. Transformers for trajectory optimization with application to spacecraft rendezvous. (pp. 1–13). doi:10.1109/AERO58975.2024.10521334. – start-page: 1 year: 2024 end-page: 15 ident: b0100 article-title: Deep reinforcement learning for nash equilibrium of differential games publication-title: IEEE Transactions on Neural Networks and Learning Systems – reference: Xu, L., Zhang, G., Qiu, S. et al., 2023. Optimal multi-impulse linear rendezvous via reinforcement learning. Space: Science & Technology, 3, 0047. URL: – reference: Avendaño, M., Martín-Molina, V., Martín-Morales, J. et al., 2016. Algebraic approach to the minimum-cost multi-impulse orbit-transfer problem. J. Guidance, Control, Dynam., 39(8), 1734–1743. URL: doi: 10.2514/1.G001598. arXiv:https://doi.org/10.2514/1.G001598. – start-page: 1 year: 2024 end-page: 17 ident: b0120 article-title: Intelligent decision-making approach for contingency return trajectory based on production rule base and deep learning publication-title: IEEE Trans. Aerosp. Electron. Syst. – reference: . doi: 10.1016/j.ast.2018.01.003. – reference: Lidtke, A.A., Lewis, H.G., Armellin, R. et al., 2017. Considering the collision probability of active debris removal missions. Acta Astronautica, 131, 10–17. URL: https://www.sciencedirect.com/science/article/pii/S0094576516305434. doi: 10.1016/j.actaastro.2016.11.012. – reference: Schulman, J., Wolski, F., Dhariwal, P. et al., 2017. Proximal policy optimization algorithms. arXiv:1707.06347. – reference: Zhang, G., Mortari, D., Zhou, D., 2010. Constrained multiple-revolution lambert’s problem. J. Guidance, Control, Dynam., 33(6), 1779–1786. URL: doi: 10.2514/1.49683. arXiv:https://doi.org/10.2514/1.49683. – start-page: 31 year: 2018 ident: b0095 article-title: Evolution-guided policy gradient in reinforcement learning publication-title: Advances in Neural Information Processing Systems – reference: . doi: 10.1016/j.asr.2022.08.002. – start-page: 3966 year: 2024 end-page: 3976 ident: b0255 article-title: Unsupervised generative feature transformation via graph contrastive pre-training and multi-objective fine-tuning publication-title: In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining – reference: . doi: 10.1016/j.asr.2023.03.050. – reference: Liang, H., Wang, J., Liu, J. et al., 2020. Guidance strategies for interceptor against active defense spacecraft in two-on-two engagement. Aerospace Science and Technology, 96, 105529. URL: https://www.sciencedirect.com/science/article/pii/S1270963819311964. doi: 10.1016/j.ast.2019.105529. – reference: Chen, Z., Tang, S., 2018. Neighboring optimal control for open-time multiburn orbital transfers. Aerospace Sci. Technol., 74, 37–45. URL: – reference: Butikov, E.I., 2015. Orbital maneuvers and space rendezvous. Adv. Space Res., 56(11), 2582–2594. URL: – year: 2023 ident: b0140 article-title: Fast calculation method for mission opportunities in orbital interception and rendezvous problems publication-title: Chin. J. Aeronaut. – reference: . doi: 10.1016/j.dt.2021.02.006. – reference: . doi: 10.1016/j.actaastro.2021.05.002. – reference: Ryoo, C.-K., Cho, H., & Tahk, M.-J. (2005). Optimal guidance laws with terminal impact angle constraint. Journal of Guidance, Control, and Dynamics, 28(4), 724–732. URL: doi: 10.2514/1.8392. doi:10.2514/1.8392. arXiv:https://doi.org/10.2514/1.8392. – reference: . doi: 10.1016/j.asr.2015.09.014. – reference: Peloni, A., Rao, A.V., & Ceriotti, M. (2018). Automated trajectory optimizer for solar sailing (atoss). Aerospace Science and Technology, 72, 465–475. URL: https://www.sciencedirect.com/science/article/pii/S1270963817315869. doi: 10.1016/j.ast.2017.11.025. – start-page: 1 year: 2024 end-page: 24 ident: b0035 article-title: Observation method for autonomous maneuver of spacecraft under emergency conditions publication-title: Dynamic Games Appl. – reference: Oghim, S., Leeghim, H., & Kim, D. (2019). Real-time spacecraft intercept strategy on j2-perturbed orbits. Advances in Space Research, 63(2), 1007–1016. URL: https://www.sciencedirect.com/science/article/pii/S027311771830721X. doi: 10.1016/j.asr.2018.09.023. – start-page: 305 year: 2016 end-page: 320 ident: b0070 article-title: Q ( ) with off-policy corrections publication-title: In International Conference on Algorithmic Learning Theory – volume: 21 year: 2019 ident: b0225 article-title: Multi-objective optimization for time-open lambert rendezvous between non-coplanar orbits publication-title: Int. J. Aeronaut. Space Sci. – reference: . doi: 10.1016/j.asr.2023.03.014. – reference: Xu, L., Zhang, G., Qiu, S. et al. (2024). Reinforcement learning-based multi-impulse rendezvous approach for satellite constellation reconfiguration. Acta Astronautica, 224, 325–337. URL: – start-page: 1861 year: 2018 end-page: 1870 ident: b0065 article-title: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor publication-title: International conference on machine learning – start-page: 1003 year: 2025 ident: b0015 article-title: Machine learning-based optimal trajectory planning for spacecraft passively flying around a satellite for proximity operations publication-title: AIAA SCITECH 2025 Forum – start-page: 1407 year: 2018 end-page: 1416 ident: b0045 article-title: Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures publication-title: International conference on machine learning – volume: 42 start-page: 40 year: 2022 end-page: 113 ident: b0150 article-title: Convex optimization for trajectory generation: A tutorial on generating dynamically feasible trajectories reliably and efficiently publication-title: IEEE Control Syst. Mag. – reference: Tang, D., & Gong, S. (2023). Trajectory optimization of rocket recovery based on neural network and genetic algorithm. Advances in Space Research, 72(8), 3344–3356. URL: https://www.sciencedirect.com/science/article/pii/S027311772300563X. doi: 10.1016/j.asr.2023.07.028. – reference: . – reference: Jiang, R., Ye, D., Xiao, Y. et al. (2023). Orbital interception pursuit strategy for random evasion using deep reinforcement learning. Space: Sci. Technol., 3, 0086. URL: – reference: Lillicrap, T.P., Hunt, J.J., Pritzel, A. et al. (2015). Continuous control with deep reinforcement learning. CoRR, abs/1509.02971. URL: https://api.semanticscholar.org/CorpusID:16326763. – reference: Abdelkhalik, O., Mortari, D., 2007. N-impulse orbit transfer using genetic algorithms. J. Spacecr. Rock., 44(2), 456–460. doi:10.2514/1.24701. arXiv:https://doi.org/10.2514/1.24701. – reference: Poozhiyil, M., Nair, M.H., Rai, M.C. et al. (2023). Active debris removal: A review and case study on leopard phase 0-a mission. Advances in Space Research, 72(8), 3386–3413. URL: https://www.sciencedirect.com/science/article/pii/S0273117723004453. doi: 10.1016/j.asr.2023.06.015. – reference: . doi: 10.1016/j.actaastro.2024.08.029. – reference: Gong, M., Zhou, D., Shao, C. et al., 2022. Optimal multiple-impulse time-fixed rendezvous using evolutionary algorithms. J. Spacecr. Rock., 59(2), 697–703. URL: doi: 10.2514/1.A34946. arXiv:https://doi.org/10.2514/1.A34946. – volume: 35 start-page: 04022066 year: 2022 ident: b0270 article-title: Lambert’s problem with multiple constraints publication-title: J. Aerospace Eng. – reference: . arXiv:https://spj.science.org/doi/pdf/10.34133/space.0047. – reference: Hu, J., Yang, H., Li, S. et al., 2023. Densely rewarded reinforcement learning for robust low-thrust trajectory optimization. Adv. Space Res., 72(4), 964–981. URL: – reference: Pontani, M., Ghosh, P., & Conway, B.A. (2012). Particle swarm optimization of multiple-burn rendezvous trajectories. Journal of Guidance, Control, and Dynamics, 35(4), 1192–1207. URL: doi: 10.2514/1.55592. doi:10.2514/1.55592. arXiv:https://doi.org/10.2514/1.55592. – ident: 10.1016/j.asr.2025.02.049_b0175 doi: 10.1016/j.asr.2023.06.015 – ident: 10.1016/j.asr.2025.02.049_b0215 – ident: 10.1016/j.asr.2025.02.049_b0200 doi: 10.1016/j.ast.2019.105400 – ident: 10.1016/j.asr.2025.02.049_b0135 doi: 10.1002/rnc.6270 – ident: 10.1016/j.asr.2025.02.049_b0245 doi: 10.1007/978-981-19-6613-2_514 – volume: 21 year: 2019 ident: 10.1016/j.asr.2025.02.049_b0225 article-title: Multi-objective optimization for time-open lambert rendezvous between non-coplanar orbits publication-title: Int. J. Aeronaut. Space Sci. – start-page: 1 year: 2024 ident: 10.1016/j.asr.2025.02.049_b0100 article-title: Deep reinforcement learning for nash equilibrium of differential games – ident: 10.1016/j.asr.2025.02.049_b0240 doi: 10.2514/1.G006091 – ident: 10.1016/j.asr.2025.02.049_b0075 doi: 10.1016/j.dt.2021.02.006 – ident: 10.1016/j.asr.2025.02.049_b0105 doi: 10.1016/j.ast.2019.105529 – ident: 10.1016/j.asr.2025.02.049_b0250 doi: 10.2514/1.G001198 – start-page: 1 year: 2024 ident: 10.1016/j.asr.2025.02.049_b0035 article-title: Observation method for autonomous maneuver of spacecraft under emergency conditions publication-title: Dynamic Games Appl. – ident: 10.1016/j.asr.2025.02.049_b0025 doi: 10.1016/j.asr.2015.09.014 – ident: 10.1016/j.asr.2025.02.049_b0085 doi: 10.34133/space.0086 – start-page: 1003 year: 2025 ident: 10.1016/j.asr.2025.02.049_b0015 article-title: Machine learning-based optimal trajectory planning for spacecraft passively flying around a satellite for proximity operations – volume: 1–13 year: 2023 ident: 10.1016/j.asr.2025.02.049_b0265 article-title: Covariance analysis of the optimal orbital interception with navigation errors publication-title: IEEE Trans. Aerospace Electron. Syst., PP – volume: 36 year: 2024 ident: 10.1016/j.asr.2025.02.049_b0050 article-title: Complementary benefits of contrastive learning and self-training under distribution shift publication-title: Adv. Neural Inform. Process. Syst. – ident: 10.1016/j.asr.2025.02.049_b0055 doi: 10.2514/1.A34946 – ident: 10.1016/j.asr.2025.02.049_b0005 doi: 10.2514/1.24701 – ident: 10.1016/j.asr.2025.02.049_b0115 – ident: 10.1016/j.asr.2025.02.049_b0190 doi: 10.1016/j.asr.2022.08.002 – year: 2023 ident: 10.1016/j.asr.2025.02.049_b0140 article-title: Fast calculation method for mission opportunities in orbital interception and rendezvous problems publication-title: Chin. J. Aeronaut. doi: 10.1016/j.cja.2023.03.021 – ident: 10.1016/j.asr.2025.02.049_b0230 doi: 10.34133/space.0047 – ident: 10.1016/j.asr.2025.02.049_b0155 doi: 10.1016/j.asr.2018.09.023 – ident: 10.1016/j.asr.2025.02.049_b0060 doi: 10.1109/AERO58975.2024.10521334 – ident: 10.1016/j.asr.2025.02.049_b0235 doi: 10.1016/j.actaastro.2024.08.029 – ident: 10.1016/j.asr.2025.02.049_b0275 doi: 10.2514/1.49683 – ident: 10.1016/j.asr.2025.02.049_b0260 doi: 10.1016/j.actaastro.2021.05.002 – ident: 10.1016/j.asr.2025.02.049_b0185 – ident: 10.1016/j.asr.2025.02.049_b0030 doi: 10.1016/j.ast.2018.01.003 – volume: 42 start-page: 40 issue: 5 year: 2022 ident: 10.1016/j.asr.2025.02.049_b0150 article-title: Convex optimization for trajectory generation: A tutorial on generating dynamically feasible trajectories reliably and efficiently publication-title: IEEE Control Syst. Mag. doi: 10.1109/MCS.2022.3187542 – volume: 62 start-page: 212 year: 2015 ident: 10.1016/j.asr.2025.02.049_b0195 article-title: Global search capabilities of indirect methods for impulsive transfers publication-title: J. Astronaut. Sci. doi: 10.1007/s40295-015-0073-x – start-page: 31 year: 2018 ident: 10.1016/j.asr.2025.02.049_b0095 article-title: Evolution-guided policy gradient in reinforcement learning – start-page: 1 year: 2024 ident: 10.1016/j.asr.2025.02.049_b0130 article-title: Integrated predictor-observer feedback control for vibration mitigation of large-scale spacecraft with unbounded input time delay – ident: 10.1016/j.asr.2025.02.049_b0220 doi: 10.2514/3.21786 – ident: 10.1016/j.asr.2025.02.049_b0170 doi: 10.2514/1.55592 – ident: 10.1016/j.asr.2025.02.049_b0020 – start-page: 3966 year: 2024 ident: 10.1016/j.asr.2025.02.049_b0255 article-title: Unsupervised generative feature transformation via graph contrastive pre-training and multi-objective fine-tuning – start-page: 1407 year: 2018 ident: 10.1016/j.asr.2025.02.049_b0045 article-title: Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures – ident: 10.1016/j.asr.2025.02.049_b0110 doi: 10.1016/j.actaastro.2016.11.012 – ident: 10.1016/j.asr.2025.02.049_b0280 doi: 10.1016/j.asr.2023.03.014 – volume: 218 start-page: 79 issue: 2 year: 2004 ident: 10.1016/j.asr.2025.02.049_b0040 article-title: An engineering approach to the dynamic control of space robotic on-orbit servicers publication-title: Proc. Inst. Mech. Eng., Part G: J. Aerospace Eng. doi: 10.1243/0954410041321998 – ident: 10.1016/j.asr.2025.02.049_b0180 doi: 10.2514/1.8392 – start-page: 305 year: 2016 ident: 10.1016/j.asr.2025.02.049_b0070 article-title: Q ( ) with off-policy corrections – ident: 10.1016/j.asr.2025.02.049_b0010 doi: 10.2514/1.G001598 – start-page: 1861 year: 2018 ident: 10.1016/j.asr.2025.02.049_b0065 article-title: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor – volume: 42 start-page: 250 year: 2004 ident: 10.1016/j.asr.2025.02.049_b0165 article-title: Optimization of multi-orbit transfers between noncoplanar elliptic orbits publication-title: Cosm. Res. doi: 10.1023/B:COSM.0000033300.18460.a4 – ident: 10.1016/j.asr.2025.02.049_b0125 doi: 10.1016/j.ast.2005.12.007 – ident: 10.1016/j.asr.2025.02.049_b0090 – ident: 10.1016/j.asr.2025.02.049_b0205 doi: 10.1016/j.asr.2023.07.028 – volume: 35 start-page: 04022066 issue: 5 year: 2022 ident: 10.1016/j.asr.2025.02.049_b0270 article-title: Lambert’s problem with multiple constraints publication-title: J. Aerospace Eng. doi: 10.1061/(ASCE)AS.1943-5525.0001464 – volume: 35 start-page: 1941 issue: 2 year: 2022 ident: 10.1016/j.asr.2025.02.049_b0145 article-title: Multi-label contrastive learning for abstract visual reasoning publication-title: IEEE Trans. Neural Networks Learn. Syst. doi: 10.1109/TNNLS.2022.3185949 – ident: 10.1016/j.asr.2025.02.049_b0210 doi: 10.2514/3.56656 – ident: 10.1016/j.asr.2025.02.049_b0080 doi: 10.1016/j.asr.2023.03.050 – start-page: 1 year: 2024 ident: 10.1016/j.asr.2025.02.049_b0120 article-title: Intelligent decision-making approach for contingency return trajectory based on production rule base and deep learning – ident: 10.1016/j.asr.2025.02.049_b0160 doi: 10.1016/j.ast.2017.11.025 |
| SSID | ssj0012770 |
| Score | 2.4331982 |
| Snippet | Multi-impulse transfers between noncoplanar orbits are significant for on-orbit service spacecraft. This paper investigates the complex optimization problem of... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 7377 |
| SubjectTerms | Contrastive-pretrained reinforcement learning Efficient orbital transfer Trajectory optimization |
| Title | Efficient fuel-optimal multi-impulse orbital transfer via contrastive pre-trained reinforcement learning |
| URI | https://dx.doi.org/10.1016/j.asr.2025.02.049 |
| Volume | 75 |
| WOSCitedRecordID | wos001488478700003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0273-1177 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0012770 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Rb9MwELagA2k8ICigbTDkB8QDKCi149p5rFDZ4GGaYEh9ixzHhU5rWjXNtP373dlO520gARIvUWo1reX7ev18d76PkDcDPeWi1CLRQ5nCBkVU4AeVTlJZyiw3SjJunNiEPDpSk0l-HNIFjZMTkHWtLi7y5X81NYyBsfHo7F-Ye_OhMAD3YHS4gtnh-keGH7umEK7nUmvPkgX4hDkeEcHKwWQ2X7ZnTsypRLUQVIgA3mpX789n2pet68YVE2F1iJOPsHi8xbVXNS6S2OlM_Ihp7chXErjaWnBRBrVYojAZJnS8ezvc4Oig9XrZGuv2F9fx61Ai_LWdxQEJJjCX7o9k-ijZnZMyzpkBTUowQRx7Xq-Z0iEsjfyo5OGdNrz0srd3_L0PPZx-0A32dmXC9V_1PVBvtdH-hjPACQDnS2FbO7lPtpgUueqRrdHn8eTLJvfEpPSRuTDjLhfuqgJvfdGv2UzEUE6ekMdha0FHHhJPyT1b98nOqMFkx2J-Sd9Sd-9jWU2fPIp6UfbJw2M__oz83CCIxgiiNxBEA4JohyAKCKIRgmiEIHoDQbRD0HPy_dP45ONhEgQ5EgM0eJ1wJuHXO4QtDse1HAgrjOAVV9paDcxQWq7MoFLMyGlWIVeeMq4HxpQ5_PFWmr8gvXpR2x1CbammmufKAkXO8mqoGTBNa4EelxmKpO2Sd93CFkvfd6XoChJPC7BCgVYoUlaAFXZJ1i19EYijJ4QF4OT3j-3922MvyfY17F-R3nrV2n3ywJyvZ83qdUDTFeWXlUU |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Efficient+fuel-optimal+multi-impulse+orbital+transfer+via+contrastive+pre-trained+reinforcement+learning&rft.jtitle=Advances+in+space+research&rft.au=Ren%2C+He&rft.au=Gui%2C+Haichao&rft.au=Zhong%2C+Rui&rft.date=2025-05-15&rft.pub=Elsevier+B.V&rft.issn=0273-1177&rft.volume=75&rft.issue=10&rft.spage=7377&rft.epage=7396&rft_id=info:doi/10.1016%2Fj.asr.2025.02.049&rft.externalDocID=S027311772500184X |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0273-1177&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0273-1177&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0273-1177&client=summon |