Diffusion Policies for Generative Modeling of Spacecraft Trajectories

Machine learning has demonstrated remarkable promise for solving the trajectory generation problem and in paving the way for online use of trajectory optimization for resource-constrained spacecraft. However, a key shortcoming in current machine learning-based methods for trajectory generation is that they require large datasets and even small changes to the original trajectory design requirements necessitate retraining new models to learn the parameter-tosolution mapping. In this work, we leverage compositional diffusion modeling to efficiently adapt out-of-distribution data and problem variations in a few-shot framework for 6 degreeof- freedom (DoF) powered descent trajectory generation. Unlike traditional deep learning methods that can only learn the underlying structure of one specific trajectory optimization problem, diffusion models are a powerful generative modeling framework that represents the solution as a probability density function (PDF) and this allows for the composition of PDFs encompassing a variety of trajectory design specifications and constraints. We demonstrate the capability of compositional diffusion models for inference-time 6 DoF minimum-fuel landing site selection and composable constraint representations. Using these samples as initial guesses for 6 DoF powered descent guidance enables dynamically feasible and computationally efficient trajectory generation.

机器学习在求解轨迹生成问题，以及为资源受限航天器的轨迹优化在线应用铺平道路方面，展现出了显著的潜力。然而，当前基于机器学习的轨迹生成方法存在一项关键缺陷：这类方法需要依赖大规模数据集，且即便原始轨迹设计需求仅发生细微调整，也需要重新训练全新模型以学习参数到解的映射关系。本研究利用组合扩散建模（compositional diffusion modeling），在少样本（few-shot）框架下高效适配分布外数据与各类问题变体，用于六自由度（degree-of-freedom, DoF）动力下降轨迹生成。与仅能学习单一特定轨迹优化问题底层结构的传统深度学习方法不同，扩散模型是一种强大的生成式建模范式，可将解表示为概率密度函数（probability density function, PDF），从而能够组合涵盖多种轨迹设计规范与约束条件的概率密度函数集合。我们验证了组合扩散模型在推理阶段完成六自由度动力下降的最小燃料着陆点选择以及可组合约束表示的能力。将这些生成的样本作为六自由度动力下降制导的初始猜测值，可实现动态可行且计算高效的轨迹生成。

搜集汇总

背景与挑战

背景概述

该数据集是关于航天器轨迹生成的机器学习研究，具体聚焦于使用组合扩散模型来高效生成6自由度动力下降轨迹。它解决了传统方法需要大量数据和重新训练的问题，支持少样本适应和推理时的约束组合。数据集以PDF文件形式提供，包含相关论文，用于演示如何为轨迹优化提供动态可行且计算高效的初始猜测。