Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program

2025-05-26

AI Summary

This work investigates the feasibility of large language models (LLMs) as autonomous spacecraft operators in non-cooperative space maneuvering tasks, using the Kerbal Space Program Differential Game (KSPDG) challenge as the experimental testbed. Method: We propose an end-to-end LLM agent architecture that integrates prompt engineering, few-shot learning, and supervised fine-tuning—without reinforcement learning or task-specific action decoders—to directly map natural-language commands to executable, continuous-control sequences compatible with high-fidelity physics engines. Contribution/Results: To our knowledge, this is the first study to deploy a pure LLM for real-time, language-driven satellite maneuver planning and closed-loop control in a realistic orbital dynamics simulation. Our agent achieved second place in KSPDG, demonstrating robust multi-step mission planning, dynamic environmental adaptation, and precise trajectory execution under physical constraints. The results establish a novel paradigm for LLM-augmented autonomous space systems, highlighting their potential for interpretable, generalizable, and human-aligned space operations.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

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 Control in space, enabling LLMs to play 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. The project comprises several open repositories to facilitate replication and further research. The codebase is accessible on href{https://github.com/ARCLab-MIT/kspdg}{GitHub}, while the trained models and datasets are available on href{https://huggingface.co/OhhTuRnz}{Hugging Face}. Additionally, experiment tracking and detailed results can be reviewed on href{https://wandb.ai/carrusk/huggingface}{Weights &Biases

Problem

• Using LLMs for autonomous spacecraft decision-making in space operations
• Developing LLM-based agents for non-cooperative satellite maneuvering challenges
• Pioneering LLM integration in space research with prompt engineering techniques

Innovation

• LLM-based autonomous satellite decision-making system
• Prompt engineering and few-shot prompting techniques
• Fine-tuned LLM agent for space operations