From Domain Documents to Requirements: Retrieval-Augmented Generation in the Space Industry

2025-07-10

AI Summary

In aerospace engineering, small organizations face challenges in efficiently extracting high-precision, compliance-aware requirements from unstructured mission briefs, interface specifications, and regulatory standards. To address this, we propose a lightweight, modular Retrieval-Augmented Generation (RAG) framework that integrates document semantic classification, multi-granularity retrieval, and large language model–driven generation to automate requirement extraction and structured output. Our key innovation lies in embedding aerospace-specific standards into both retrieval and generation phases, enabling mission-specific constraint modeling and lightweight compliance alignment. Evaluated on real-world aerospace documentation, the method reduces manual requirements engineering effort by approximately 40%, improves requirement coverage by 28%, and increases regulatory compliance adherence by 35%. This advancement lowers the industry entry barrier for safety-critical aerospace missions.

Technology Category

• Natural Language Processing: Generation
• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Requirements engineering (RE) in the space industry is inherently complex, demanding high precision, alignment with rigorous standards, and adaptability to mission-specific constraints. Smaller space organisations and new entrants often struggle to derive actionable requirements from extensive, unstructured documents such as mission briefs, interface specifications, and regulatory standards. In this innovation opportunity paper, we explore the potential of Retrieval-Augmented Generation (RAG) models to support and (semi-)automate requirements generation in the space domain. We present a modular, AI-driven approach that preprocesses raw space mission documents, classifies them into semantically meaningful categories, retrieves contextually relevant content from domain standards, and synthesises draft requirements using large language models (LLMs). We apply the approach to a real-world mission document from the space domain to demonstrate feasibility and assess early outcomes in collaboration with our industry partner, Starbound Space Solutions. Our preliminary results indicate that the approach can reduce manual effort, improve coverage of relevant requirements, and support lightweight compliance alignment. We outline a roadmap toward broader integration of AI in RE workflows, intending to lower barriers for smaller organisations to participate in large-scale, safety-critical missions.

Problem

• Automate requirements generation from space domain documents
• Improve precision and compliance in space industry requirements
• Reduce manual effort for small space organizations

Innovation

• Modular AI-driven approach for space requirements
• Retrieval-Augmented Generation for context-aware synthesis
• Semantic classification of mission documents