Global Search for Optimal Low Thrust Spacecraft Trajectories using Diffusion Models and the Indirect Method

2025-01-13

AI Summary

To address the sensitivity to initial guesses, high computational cost, and poor adaptability to dynamic mission parameter changes in global optimization of long-duration, low-thrust spacecraft trajectories, this paper introduces diffusion models into costate-space modeling for the first time. Integrated with the indirect method based on Pontryagin’s Minimum Principle, the proposed framework generates high-quality initial guesses driven by thrust parameters. It uncovers structural regularities of locally optimal solutions in the costate domain, enabling generalization to unseen thrust configurations and efficient warm-start initialization. Validated under the circular restricted three-body problem dynamics, the method achieves a 10–100× increase in the number of successfully converged solutions per minute after warm-start, compared to uniform sampling and adjoint-control transformation baselines. This substantially improves both efficiency and robustness in multi-scenario mission design.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Constraint Optimization
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Long time-duration low-thrust nonlinear optimal spacecraft trajectory global search is a computationally and time expensive problem characterized by clustering patterns in locally optimal solutions. During preliminary mission design, mission parameters are subject to frequent changes, necessitating that trajectory designers efficiently generate high-quality control solutions for these new scenarios. Generative machine learning models can be trained to learn how the solution structure varies with respect to a conditional parameter, thereby accelerating the global search for missions with updated parameters. In this work, state-of-the-art diffusion models are integrated with the indirect approach for trajectory optimization within a global search framework. This framework is tested on two low-thrust transfers of different complexity in the circular restricted three-body problem. By generating and analyzing a training data set, we develop mathematical relations and techniques to understand the complex structures in the costate domain of locally optimal solutions for these problems. A diffusion model is trained on this data and successfully accelerates the global search for both problems. The model predicts how the costate solution structure changes, based on the maximum spacecraft thrust magnitude. Warm-starting a numerical solver with diffusion model samples for the costates at the initial time increases the number of solutions generated per minute for problems with unseen thrust magnitudes by one to two orders of magnitude in comparison to samples from a uniform distribution and from an adjoint control transformation.

Problem

• Optimal trajectory planning
• Long-duration low-thrust spacecraft
• Efficient computational methods

Innovation

• Diffusion Model
• Optimization Technique
• Low-thrust Spacecraft Trajectory