Towards Robust Spacecraft Trajectory Optimization via Transformers

2024-10-08

arXiv.org

AI Summary

Autonomous spacecraft rendezvous under uncertainty poses significant challenges for robust trajectory planning, particularly due to non-convexity, poor convergence, and low feasibility of optimal control solvers. Method: This paper proposes a robust trajectory planning framework integrating artificial intelligence and optimal control. It introduces an Attention-based Robust Trajectory (ART) model—built upon the Transformer architecture—to provide warm starts for chance-constrained optimal control; further, it establishes a sequential generative modeling and posterior trajectory evaluation framework to enhance solution safety and trustworthiness. Contribution/Results: The method substantially improves convergence, feasibility, and fuel efficiency of non-convex optimal control solutions. In low-Earth-orbit rendezvous simulations, it reduces mission cost by up to 30%, cuts infeasible cases by 50%, and significantly enhances convergence speed and robustness compared to baseline methods.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Future multi-spacecraft missions require robust autonomous trajectory optimization capabilities to ensure safe and efficient rendezvous operations. This capability hinges on solving non-convex optimal control problems in real-time, although traditional iterative methods such as sequential convex programming impose significant computational challenges. To mitigate this burden, the Autonomous Rendezvous Transformer (ART) introduced a generative model trained to provide near-optimal initial guesses. This approach provides convergence to better local optima (e.g., fuel optimality), improves feasibility rates, and results in faster convergence speed of optimization algorithms through warm-starting. This work extends the capabilities of ART to address robust chance-constrained optimal control problems. Specifically, ART is applied to challenging rendezvous scenarios in Low Earth Orbit (LEO), ensuring fault-tolerant behavior under uncertainty. Through extensive experimentation, the proposed warm-starting strategy is shown to consistently produce high-quality reference trajectories, achieving up to 30% cost improvement and 50% reduction in infeasible cases compared to conventional methods, demonstrating robust performance across multiple state representations. Additionally, a post hoc evaluation framework is proposed to assess the quality of generated trajectories and mitigate runtime failures, marking an initial step toward the reliable deployment of AI-driven solutions in safety-critical autonomous systems such as spacecraft.

Problem

• Optimal spacecraft trajectory
• Multi-spacecraft rendezvous
• Computational efficiency

Innovation

• ART Tool
• Resource Efficiency
• Reliability Assurance