Enhancing Operations at the Columbus Control-Center: A Hybrid Approach Utilizing Large Language Models, Knowledge Graphs, and Retrieval-Augmented Generation

Abstract

This paper investigates the combination of Large Language Models (LLMs) with Knowledge Graphs (KGs) and Retrieval-Augmented Generation (RAG) to enhance the operational efficiency of the flight control team at the Columbus Control-Center (COL-CC). COL-CC is responsible for the operations of the Columbus module of the International Space Station (ISS), and is part of German Aerospace Center's (DLR e.V.) German Space Operations Center (GSOC), located near Munich, Germany. LLMs have demonstrated a remarkable capacity to comprehend and produce human-like text, positioning themselves as an effective and efficient solution for automating routine tasks and delivering real-time support. However, their effectiveness can be constrained by a lack of domain-specific knowledge and the need for accurate, up-to-date information. To address these limitations, we propose a hybrid approach that combines LLMs with KGs and RAG. KGs offer a structured representation of domain-specific information, enabling more effective access to and utilization of specialized knowledge. Meanwhile, RAG enhances LLMs by retrieving relevant documents and data snippets, ensuring that the generated responses are grounded in current information. This integrated system can support the flight control team at COL-CC by automating the generation of operational reports, providing real-time answers to technical queries, and assisting in anomaly detection and resolution. The paper presents the architecture of this hybrid system, discusses its implementation challenges, and evaluates its potential impact on the efficiency and accuracy of Columbus module operations. By leveraging the strengths of LLMs, KGs, and RAG, this work aims to create a more intelligent and responsive support system for space missions, ultimately contributing to the safety and success of ISS and Columbus operations.