arXiv：cs.LG· Jannik Graebner, Ryne Beeson·· 3 小时前
用扩散模型与MCMC迁移学习多目标间接低推力轨迹
Transfer Learning of Multiobjective Indirect Low-Thrust Trajectories Using Diffusion Models and Markov Chain Monte Carlo
AI 导读
研究者提出一种迁移学习框架，将任务参数的同伦方法与MCMC结合，用于更高效生成扩散模型的训练数据，并把多目标优化重构为costate空间中的非归一化目标分布采样。在圆型限制性三体问题的平面多圈转移测试中，基于梯度的MCMC变体在样本质量与计算成本间取得最佳权衡，可行解比基于伴随控制变换与梯度优化的SOTA间接方法多出40%，Pareto前沿质量更高；生成的样本还用于微调以质量参数为条件的扩散模型。
正文
Abstract:Preliminary low-thrust spacecraft mission design is a global search problem characterized by a complex solution landscape, multiple objectives, and numerous local minima. During this phase, mission parameters are often not yet fully defined, requiring new solutions to be generated at a high cadence across varying parameter values. When combined with the indirect approach to optimal control, diffusion models can accelerate this search by learning distributions that represent high-quality initial costates. However, generating training data remains expensive, and opportunities exist to better exploit past data. We propose a transfer-learning framework that combines homotopy in a mission parameter with Markov chain Monte Carlo (MCMC) to generate training data more efficiently. The approach reformulates a multiobjective optimization problem as sampling from an unnormalized target distribution in costate space. We compare three MCMC algorithms on a planar multi-revolution transfer in the circular restricted three-body problem, with homotopy in the system mass parameter. The results show that gradient-based MCMC variants achieve the best trade-off between sample quality and computational cost. For the test transfer, the proposed framework generates 40 % more feasible solutions and achieves a higher-quality Pareto front than a state-of-the-art indirect approach based on adjoint control transformations and gradient-based optimization. Finally, the MCMC-generated samples are used to fine-tune a diffusion model conditioned on the mass parameter, enabling it to learn a global representation of the underlying solution distribution and efficiently generate new solutions. These findings establish the transfer-learning framework as a practical method for efficiently solving indirect trajectory optimization problems with varying parameters.
| Comments: | v2: Updated publication information only; manuscript content is unchanged. The version of record is available at this https URL |
| Subjects: | Systems and Control (eess.SY); Machine Learning (cs.LG); Optimization and Control (math.OC) |
| Cite as: | arXiv:2605.09125 [eess.SY] |
| (or arXiv:2605.09125v2 [eess.SY] for this version) | |
| https://doi.org/10.48550/arXiv.2605.09125 arXiv-issued DOI via DataCite |
|
| Journal reference: | The Journal of the Astronautical Sciences 73 (2026) 91 |
| Related DOI: | https://doi.org/10.1007/s40295-026-00630-x
DOI(s) linking to related resources |
Submission history
From: Jannik Graebner [view email]
[v1]
Sat, 9 May 2026 19:15:54 UTC (18,565 KB)
[v2]
Thu, 8 Oct 2026 15:04:03 UTC (18,565 KB)
来源：arXiv：cs.LG · arxiv.org