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...

ver descrição completa

Detalhes bibliográficos
Autores: Fernández Becerra, Laura, Guerrero Higueras, Ángel Manuel, Rodríguez Lera, Francisco Javier, Matellán Olivera, Vicente
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2026
País:España
Recursos:Universidad de León
Repositorio:BULERIA. Repositorio Institucional de la Universidad de León
OAI Identifier:oai:dnet:buleria_____::9a7fa319498f1d0c4850c1c70dc50e5e
Acesso em linha:https://hdl.handle.net/10612/28306
Access Level:acceso abierto
Palavra-chave:Informática
Explainable AI
Robotics
LLM agents
Agentic retrieval-augmented generation
Explainability evaluation
Generative AI
3304.06 Arquitectura de Ordenadores
id ES_6fbdea4a7c7f9b7c7e7aba9bb6a4011a
oai_identifier_str oai:dnet:buleria_____::9a7fa319498f1d0c4850c1c70dc50e5e
network_acronym_str ES
network_name_str España
repository_id_str
spelling Generating trustworthy and context-aware explanations for autonomous robots using an LLM agent-based RAG architectureFernández Becerra, LauraGuerrero Higueras, Ángel ManuelRodríguez Lera, Francisco JavierMatellán Olivera, VicenteInformáticaExplainable AIRoboticsLLM agentsAgentic retrieval-augmented generationExplainability evaluationGenerative AI3304.06 Arquitectura de Ordenadores[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.SIThis publication is part of the TESCAC project, financed “by European Union NextGeneration-EU, the Recovery Plan, Transformation and Resilience, through INCIBE”.ElsevierArquitectura y Tecnologia de ComputadoresEscuela de Ingenierias Industrial, Informática y Aeroespacial2026info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttps://hdl.handle.net/10612/28306reponame:BULERIA. Repositorio Institucional de la Universidad de Leóninstname:Universidad de LeónIngléshttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:dnet:buleria_____::9a7fa319498f1d0c4850c1c70dc50e5e2026-06-24T12:43:27Z
dc.title.none.fl_str_mv Generating trustworthy and context-aware explanations for autonomous robots using an LLM agent-based RAG architecture
title Generating trustworthy and context-aware explanations for autonomous robots using an LLM agent-based RAG architecture
spellingShingle Generating trustworthy and context-aware explanations for autonomous robots using an LLM agent-based RAG architecture
Fernández Becerra, Laura
Informática
Explainable AI
Robotics
LLM agents
Agentic retrieval-augmented generation
Explainability evaluation
Generative AI
3304.06 Arquitectura de Ordenadores
title_short Generating trustworthy and context-aware explanations for autonomous robots using an LLM agent-based RAG architecture
title_full Generating trustworthy and context-aware explanations for autonomous robots using an LLM agent-based RAG architecture
title_fullStr Generating trustworthy and context-aware explanations for autonomous robots using an LLM agent-based RAG architecture
title_full_unstemmed Generating trustworthy and context-aware explanations for autonomous robots using an LLM agent-based RAG architecture
title_sort Generating trustworthy and context-aware explanations for autonomous robots using an LLM agent-based RAG architecture
dc.creator.none.fl_str_mv Fernández Becerra, Laura
Guerrero Higueras, Ángel Manuel
Rodríguez Lera, Francisco Javier
Matellán Olivera, Vicente
author Fernández Becerra, Laura
author_facet Fernández Becerra, Laura
Guerrero Higueras, Ángel Manuel
Rodríguez Lera, Francisco Javier
Matellán Olivera, Vicente
author_role author
author2 Guerrero Higueras, Ángel Manuel
Rodríguez Lera, Francisco Javier
Matellán Olivera, Vicente
author2_role author
author
author
dc.contributor.none.fl_str_mv Arquitectura y Tecnologia de Computadores
Escuela de Ingenierias Industrial, Informática y Aeroespacial
dc.subject.none.fl_str_mv Informática
Explainable AI
Robotics
LLM agents
Agentic retrieval-augmented generation
Explainability evaluation
Generative AI
3304.06 Arquitectura de Ordenadores
topic Informática
Explainable AI
Robotics
LLM agents
Agentic retrieval-augmented generation
Explainability evaluation
Generative AI
3304.06 Arquitectura de Ordenadores
description [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.
publishDate 2026
dc.date.none.fl_str_mv 2026
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/10612/28306
url https://hdl.handle.net/10612/28306
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:BULERIA. Repositorio Institucional de la Universidad de León
instname:Universidad de León
instname_str Universidad de León
reponame_str BULERIA. Repositorio Institucional de la Universidad de León
collection BULERIA. Repositorio Institucional de la Universidad de León
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869410530228174848
score 15.198674

Registos relacionados