Language Models are Spacecraft Operators

TL;DR

This paper demonstrates how large language models can be used as autonomous agents for space satellite maneuvering, achieving high performance in a space operations challenge and pioneering their application in space research.

Contribution

It introduces a novel LLM-based approach for autonomous satellite control in space, applying prompt engineering and fine-tuning techniques, and achieving a top ranking in a relevant competition.

Findings

LLM-based agents can effectively perform satellite maneuvering tasks.

The approach achieved 2nd place in the KSPDG challenge.

This work pioneers the use of LLMs in space research applications.

Abstract

Recent trends are emerging in the use of Large Language Models (LLMs) as autonomous agents that take actions based on the content of the user text prompts. We intend to apply these concepts to the field of Guidance, Navigation, and Control in space, enabling LLMs to have a significant role in the decision-making process for autonomous satellite operations. As a first step towards this goal, we have developed a pure LLM-based solution for the Kerbal Space Program Differential Games (KSPDG) challenge, a public software design competition where participants create autonomous agents for maneuvering satellites involved in non-cooperative space operations, running on the KSP game engine. Our approach leverages prompt engineering, few-shot prompting, and fine-tuning techniques to create an effective LLM-based agent that ranked 2nd in the competition. To the best of our knowledge, this work pioneers the integration of LLM agents into space research. Code is available at https://github.com/ARCLab-MIT/kspdg.