RT Conference Proceedings
T1 Autonomous Multi-Agent AI Systems for Satellite Mission Design.
A1 Navarro, Tomás
A1 Stroescu, Ana
A1 Izzo, Dario
A1 Gálvez-Rojas, Sergio
A1 López-Valverde, Francisco
K1 Inteligencia artificial
K1 Sistemas de comunicaciones inalámbricos
K1 Aprendizaje automático (Inteligencia artificial)
K1 Proceso en lenguaje natural (Informática)
K1 Procesado de señales
K1 Satélites artificiales
K1 Exploración espacial
AB The integration of Artificial Intelligence (AI) agents in supporting engineering design is rapidly gaining attention due to their potential to accelerate decision-making, optimise designs, and reduce costs. This paper presents a comprehensive evaluation of two different AI agentic systems, each system run by a different LLM (Large Language Model): DeepSeek-R1-70B and GPT-4o. The agents are evaluated in supporting satellite constellation design across key domains: market analysis, frequency filing, mission planning, payload feasibility, and cost analysis. Four distinct satellite designs were analysed per model, and expert evaluations were conducted to assess their effectiveness. This study highlights both the benefits and shortcomings of AI agents in satellite design, providing a comparative assessment and discussing implications for future AI-driven space mission planning.
PB IEEE
YR 2025
FD 2025-10
LK https://hdl.handle.net/10630/40345
UL https://hdl.handle.net/10630/40345
LA eng
NO https://conferences.ieeeauthorcenter.ieee.org/author-ethics/guidelines-and-policies/post-publication-policies/
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 19 ene 2026