Generating trustworthy and context-aware explanations for autonomous robots using an LLM agent-based RAG architecture

[EN] Effective communication in Human-Robot Interaction (HRI) is essential for building trust in autonomous systems. Robotic agents must provide clear, factual explanations that help non-expert users understand their decisions and actions, thereby promoting transparency and acceptance. However, gene...

Descripción completa

Detalles Bibliográficos
Autores: Fernández Becerra, Laura, Guerrero Higueras, Ángel Manuel, Rodríguez Lera, Francisco Javier, Matellán Olivera, Vicente
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2026
País:España
Institución:Universidad de León
Repositorio:BULERIA. Repositorio Institucional de la Universidad de León
OAI Identifier:oai:dnet:buleria_____::9a7fa319498f1d0c4850c1c70dc50e5e
Acceso en línea:https://hdl.handle.net/10612/28306
Access Level:acceso abierto
Palabra clave:Informática
Explainable AI
Robotics
LLM agents
Agentic retrieval-augmented generation
Explainability evaluation
Generative AI
3304.06 Arquitectura de Ordenadores
Descripción
Sumario:[EN] Effective communication in Human-Robot Interaction (HRI) is essential for building trust in autonomous systems. Robotic agents must provide clear, factual explanations that help non-expert users understand their decisions and actions, thereby promoting transparency and acceptance. However, generating structured, contextually relevant, and well-reasoned explanations remains a significant challenge, especially in dynamic environments, where rapidly changing circumstances make it difficult to ensure accuracy, consistency, and timeliness. To address this problem, we propose an architecture that generates natural language explanations grounded in accountable agent data. A distributed event streaming platform captures and processes high-volume system data in real time, which is then used by an agent-based Retrieval-Augmented Generation (RAG) approach to produce accurate and context-aware explanations. By decoupling explanation generation from the robot’s onboard resources, the architecture enables scalable and efficient reasoning while minimizing computational overhead. Experiments on robotic navigation tasks demonstrate that the system achieves high performance across quantitative metrics, with Context Recall consistently above 85%, Faithfulness over 78%, and Semantic Similarity near 96%. Criteria-based evaluations show high levels of Correctness (97.5-100%), with scores for Understandability, Informativeness, and Coherence exceeding 4.0 on a 5-point scale. These results provide strong evidence that integrating curated real-time data with agent-based reasoning enhances the interpretability, reliability, and user trust in autonomous robot behavior.