Diffusion Policies for Generative Modeling of Spacecraft Trajectories

TL;DR

This paper introduces a diffusion modeling approach for spacecraft trajectory generation that adapts efficiently to new data and constraints, reducing retraining needs and enabling flexible, real-time trajectory planning.

Contribution

It presents a novel compositional diffusion modeling framework for 6 DoF spacecraft trajectories that handles diverse constraints and variations with minimal retraining.

Findings

Effective in 6 DoF trajectory generation with few-shot adaptation.

Supports compositional constraint representation for flexible planning.

Enables real-time, dynamically feasible trajectory solutions.

Abstract

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-to-solution 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 degree-of-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.