To meet the requirements of large-scale on-orbit service mission planning, existing research is usually confined to static scenarios, making it difficult to tackle the invalidation of initial plans caused by unexpected events such as spacecraft failures and task changes. This calls for on-the-fly replanning with flexible Lambert transfers. Meanwhile, this mission is a mixed-integer programming problem involving three nested optimization layers: trajectory planning, sequence planning, and task assignment. Current strategies involve extensive iterative computations, especially for Lambert transfers that require numerical iterative solutions, which severely limits their practical engineering applications. To address this challenge, this paper proposes an efficient algorithmic framework: first, for the underlying trajectory planning and sequence planning problems, deep neural networks and attention models are adopted respectively to replace the online optimization iteration process, enabling fast solutions. Second, for the upper-layer task assignment problem, a Beam Pre-search and Neighborhood Optimization Algorithm (BPNOA) based on historical pre-plans is proposed, which enables efficient solutions through mechanisms including target assignment state labeling, coarse screening of suitable spacecraft based on combined orbit transfer strategies, pre-plan adjustment using beam search and auction strategies, and local optimization, thus realizing an efficient solution process characterized by “fast initial optimization followed by fine-tuning”. Finally, scenarios constructed using real orbital data from the CelesTrak website are used to compare the performance of the proposed method with that of genetic algorithms. In small-scale scenario tests, the proposed method exhibits an average convergence efficiency over 150 times higher; in 99 Monte Carlo tests of large-scale scenarios, with the same calculations, the average optimization result of the proposed method is im-proved by 71%, and the standard deviation of multiple solutions is reduced by 84.1%. The convergence is better and more robust. The results verify the effectiveness of the new method, which can significantly improve the efficiency of task replanning and meet the real-time requirements of future applications.
[1]许英杰, 刘晓路, 贺仁杰, 等.空间碎片主动移除任务规划研究综述[J].控制与决策, 2024, 39(2):371-380.XU Y J, LIU X L, HE R J.Space debris active removal mission planning: A review[J].Control and Decision, 2024, 39(2):371-380
[2] 朱阅訸.面向大规模目标访问任务的飞行序列规划方法[D]. 长沙: 国防科技大学, 2020: 28-35.ZHU Y H.Flight sequence planning method for large-scale-object visiting mission[D]. Chang’sha: National University of Defense Technology, 2020: 28-35 (in Chinese).
[3]ZHAO Y, CAO Y, CHEN Y, et al.Mission planning of geo active debris removal based on revolver mode[J]. Mathematical Problems in Engineering, 2021: 1-10.
[4]XU H, SONG B, GUO Y, et al.Lambert property-based swarm search algorithm for the multiple-rendezvous trajectory optimization[J].Journal of Spacescraft and rockets, 2024, 61(3):660-673
[5]ZHANG T, SHEN H, LI H, et al.Ant colony optimization based design of multiple target active debris removal mission[J].Transactions of the Japan Soci-ety for Aeronautical and Space Sciences, 2018, 61(5):201-210
[6] FEDERICI L, ZAVOLI A, COLASURDO G.A time-dependent tsp formulation for the design of an active debris removal mission using simulated annealing[C]//AAS/AIAA Astrodynamics Specialist Conference. 2019.
[7] ADRIAN, URRUTXUA H, CADARSO L.Large-scale object selection and trajectory planning for multi-target space debris removal missions[J]. Acta Astronautica, 2020, 170: 289-301.
[8]ZHAO Z, ZHANG J, LI H, et al.Leo cooperative multi-spacecraft refueling mission optimization considering j2 perturbation and target’s surplus propellant constraint[J].Advances in Space Re-search, 2017, 59(1):252-262
[9]ZHANG Z, ZHANG N, JIAO Y, et al.Global trajectory optimization of multispacecraft successive rendezvous using multitree search[J].Journal of Guidance, control, and Dynamics, 2024, 47(3):503-517
[10]LI H, BAOYI H.Optimization of multiple debris removal missions using an evolving elitist club algorithm[J].IEEE Transactions On Aerospace and Electronic Systems, 2019, 56(1):773-784
[11]XU H, LIU L J, GUO Y N, et al.Mission planning for repeated multi-spacecraft non-contact debris removal[J].Chinese Journal of Aeronautics, 2025, 38(10):103464-
[12]杨保臻, 钱霙婧.基于目标分配策略的空间碎片清除方案设计[J].空间控制技术与应用, 2023, 49(3):36-45. Yang B Z, QIAN Y J.Design of space debris clearance scheme based on target allocation strategy[J].Aerospace Control and Application, 2023, 49(3):36-45
[13]徐杭, 梁维奎, 刘鲁江, 等.面向 目标的快速在线在轨服务任务规划[J].宇航学报, 2022, 43(11):1454-1465.XU H, LIANG W K, LIU L J.Fast on-board on-orbit service mission planning for GEO targets[J].Journal of Astronautics, 2022, 43(11):1454-1465
[14]杨家男, 侯晓磊, , 等.基于启发强化学习的大规模 任务优化方法[J].航空学报, 2021, 42(4):36-45. YANG J N, HOU X L, HU Y H, et al.Heuristic enhanced reinforcement learning method for large-scale multi-debris active removal mission planning[J].Acta Aeronautica et Astronautica Sinica, 2021, 42(4):36-45
[15] XU Y, LIU X, HE R, et al.Active debris removal mission planning method based on machine learn-ing[J]. Mathematics, 2023, 11: 1419.
[16]严冰, 张进, 罗亚中, 等.采用注意力模型的多星交会序列优化方法[J].宇航学报, 2023, 44(11):1683-1692. YAN B, ZHNAG J, LUO Y Z, et al.Sequence optimization method for multi-satellite rendezvous using
attention model[J].Journal of Astronautics, 2023, 44(11): 1683-1692 (in Chinese).
[17]徐杭, 宋斌, 余建慧, 等.基于深度神经网络的高轨最优变轨规划[J].控制与决策, 2024, 39(9):2969-2976. XU H, SONG B, YU J H, et al.Optimal high-orbit Lambert transfer planning based on deep neural network[J].Control and Decision, 2024, 39(9):2969-2976
[18]牟帅, 卜慧蛟, 张进, 等.面向突发任务的空间站任务重规划方法[J].航空学报, 2017, 38(7):320793. MU S, BU H J, ZHANG J, et al.Re-planning method for space station pop-up missions[J].Acta Aeronautica et Astronautica Sinica, 2017, 38(7):320793-
[19]刘勇, , 吴海燕, 等.一种面向动态需求的多优先级天文观测卫星任务重规划方法[J].空间科学学报, 2020, 40(3):401-407.LIU Y, JAUBERT J, WU H Y, et al.Research on multi-priority astronomical observing satellite task replanning method for dynamic requirement[J].Chinese Journal of Space Science, 2020, 40(3):401-407
[20]杨和星, 赵清杰, 王鑫, 等.多节点探测器附着任务分层约束图模型及重规划算法[J].控制与决策, 2025, 40(2):626-634.YANG H X, ZHAO Q J, WANG X, et al. Layered constraint graph model and re-planning algorithm for landing of probe with multiple nodes[J].Control and Decision, 2025, 40(2):626-634
[21]周文惠, 齐瑞云, 姜斌, 等.面向突发故障的分布式多无人机任务重规划方法[J].控制与决策, 2023, 38(5):1373-1385.ZHOU W H, QI R Y, JIANG B, et al. Mission re-planning method of distributed multiple unmanned aerial vehicles for pop-up faults[J].Control and De-cision, 2023, 38(5):1373-1385
[22] XU H, SONG B, GUO Y N, et al.An optimization framework with improved auction-based initialization for highly constrained on-orbit servicing mis-sion planning[J]. Applied Soft Computing, 2023, 149, Part A: 110983.
[23]罗棕, 杜春, 陈浩, 等.基于层次预测的多星应急观测任务规划方法[J].航空学报, 2021, 42(4):524721.LUO Z, DU C, CHEN H, et al.Multi-satellite scheduling approach for emergency scenarios based on hierarchical forecasting with Transformer network[J].Acta Aeronautica et Astronautica Sinica, 2021, 42(4):524721-
[24] KOOL W, HOOF H V, WELLING M.Attention, learn to solve routing problems[C]. International Conference on Learning Representations, 2019.
[25] CELESTRAK.IRIDIUM 33 Debris [Internet]. 2025 Aug [cited 2025 Aug 14]. Available from: https://celestrak.org/.
CJA