Neural Approximators for Low-Thrust Trajectory Transfer Cost and Reachability

2025-08-04

AI Summary

To address the low accuracy and poor generalizability in predicting fuel consumption (Δv) and trajectory feasibility for low-thrust orbital missions, this paper proposes a universal performance surrogate model based on a pre-trained neural network. We first validate the effectiveness of scaling laws in low-thrust trajectory approximation, construct the largest multi-task dataset to date for such problems, and introduce a self-similar spatial transformation enabling zero-shot generalization across semi-major axes, inclinations, and central bodies. Trajectory data are generated via the homotopy shooting method. The model is efficiently deployed across C++, Python, and MATLAB. Experimental results demonstrate a relative Δv prediction error of only 0.78% and a minimum transfer time error of 0.63%. High accuracy and real-time performance are further validated on third-party datasets and multi-flyby mission scenarios.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Learning to Search
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

In trajectory design, fuel consumption and trajectory reachability are two key performance indicators for low-thrust missions. This paper proposes general-purpose pretrained neural networks to predict these metrics. The contributions of this paper are as follows: Firstly, based on the confirmation of the Scaling Law applicable to low-thrust trajectory approximation, the largest dataset is constructed using the proposed homotopy ray method, which aligns with mission-design-oriented data requirements. Secondly, the data are transformed into a self-similar space, enabling the neural network to adapt to arbitrary semi-major axes, inclinations, and central bodies. This extends the applicability beyond existing studies and can generalize across diverse mission scenarios without retraining. Thirdly, to the best of our knowledge, this work presents the current most general and accurate low-thrust trajectory approximator, with implementations available in C++, Python, and MATLAB. The resulting neural network achieves a relative error of 0.78% in predicting velocity increments and 0.63% in minimum transfer time estimation. The models have also been validated on a third-party dataset, multi-flyby mission design problem, and mission analysis scenario, demonstrating their generalization capability, predictive accuracy, and computational efficiency.

Problem

• Predict fuel consumption for low-thrust missions
• Estimate trajectory reachability in space missions
• Generalize neural approximators across diverse scenarios

Innovation

• Pretrained neural networks predict trajectory metrics
• Homotopy ray method constructs largest dataset
• Self-similar space enables generalization across missions