EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Agentic RAG for Maritime AIoT: Natural Language Access to Structured Data

Oxana Sachenkova iD, Melker Andreasson, Dongzhu Tan, Alisa Lincke iD

Sensors · 2026

DOI: 10.3390/s26041227 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Oxana Sachenkova und 3 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science and Media Technology Department, Linnaeus University, SE-391 31 Kalmar, Sweden. Hauptthemen laut MEDLINE: Artificial Intelligence, Information Storage and Retrieval, Natural Language Processing. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Swedish Transport Administration.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Maritime operations are increasingly reliant on sensor data to drive efficiency and enhance decision-making. However, despite rapid advances in large language models, including expanded context windows and stronger generative capabilities, critical industrial settings still require secure, role-constrained access to enterprise data and explicit limitation of model context. Retrieval-Augmented Generation (RAG) remains essential to enforce data minimization, preserve privacy, support verifiability, and meet regulatory obligations by retrieving only permissioned, provenance-tracked slices of information at query time. However, current RAG solutions lack robust validation protocols for numerical accuracy for high-stakes industrial applications. This paper introduces Lighthouse Bot, a novel Agentic RAG system specifically designed to provide natural-language access to complex maritime sensor data, including time-series and relational sensor data. The system addresses a critical need for verifiable autonomous data analysis within the Artificial Intelligence of Things (AIoT) domain, which we explore through a case study on optimizing ferry operations. We present a detailed architecture that integrates a Large Language Model with a specialized database and coding agents to transform natural language into executable tasks, enabling core AIoT capabilities such as generating Python code for time-series analysis, executing complex SQL queries on relational sensor databases, and automating workflows, while keeping sensitive data outside the prompt and ensuring auditable, policy-aligned tool use. To evaluate performance, we designed a test suite of 24 questions with ground-truth answers, categorized by query complexity (simple, moderate, complex) and data interaction type (retrieval, aggregation, analysis). Our results show robust, controlled data access with high factual fidelity: the proprietary Claude 3.7 achieved close to 90% overall factual correctness, while the open-source Qwen 72B achieved 66% overall and 99% on simple retrieval and aggregation queries. These findings underscore the need for a secure limited-context RAG in maritime AIoT and the potential for cost-effective automation of routine exploratory analyses.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceInformation Storage and RetrievalNatural Language ProcessingLarge Language ModelsIntelligent Systems

Stichwörter der Autor:innen

GenAIIoTLLMsRAGmaritime industrysensor data

Autor:innen und Institutionen

  • Computer Science and Media Technology Department, Linnaeus University, SE-391 31 Kalmar, Sweden.
  • Computer Science and Media Technology Department, Linnaeus University, SE-352 53 Växjö, Sweden.

ORCID-Profile: Oxana Sachenkova, Alisa Lincke

Förderung

  • Swedish Transport Administration

Zitieren

APA

Sachenkova, O., Andreasson, M., Tan, D., & Lincke, A. (2026). Agentic RAG for Maritime AIoT: Natural Language Access to Structured Data. Sensors. https://doi.org/10.3390/s26041227

Vancouver

Sachenkova O, Andreasson M, Tan D, Lincke A. Agentic RAG for Maritime AIoT: Natural Language Access to Structured Data. Sensors. 2026. doi:10.3390/s26041227

BibTeX
@article{Sachenkova2026,
  author = {Sachenkova, Oxana and Andreasson, Melker and Tan, Dongzhu and Lincke, Alisa},
  title = {Agentic RAG for Maritime AIoT: Natural Language Access to Structured Data},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26041227}
}
Kostenlos starten →