Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2026 Feb 13;26(4):1227.
doi: 10.3390/s26041227.

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

Oxana Sachenkova  1 , Melker Andreasson  1 , Dongzhu Tan  1 , Alisa Lincke  2
Affiliations

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

Oxana Sachenkova et al. Sensors (Basel). .

Abstract

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.

Keywords: GenAI; IoT; LLMs; RAG; maritime industry; sensor data.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Proposed System Architecture for a Sensor Analysis Bot—Lighthouse Bot.
Figure 2
Figure 2
Test Suite Distribution: (a) Complexity distribution (Simple, Moderate, Complex); (b) Domain distribution (Route Optimization/Operations, Fuel Efficiency, Environmental Impact); (c) Interaction type distribution (Retrieval, Aggregation, Comparison); (d) Data variation tags showing the frequency of RT, FY, TP, HR, and DIR across test cases. The X-axis in panels (a–c) represents the number of test cases (count), with each segment corresponding to a specific category within the test suite.
Figure 3
Figure 3
Heatmap of model performance (Calculated Factual Correctness) across test cases.
See this image and copyright information in PMC

References

    1. Raza Z., Woxenius J., Vural C.A., Lind M. Digital transformation of maritime logistics: Exploring trends in the liner shipping segment. Comput. Ind. 2023;145:103811. doi: 10.1016/j.compind.2022.103811. - DOI
    1. DNV. Singapore Maritime Foundation The Future of Seafarers 2030: A Decade of Transformation. 2023. [(accessed on 1 November 2025)]. Available online: https://www.smf.com.sg/wp-content/uploads/2023/04/The-Future-of-Seafarer....
    1. Zeng F., Chen A., Xu S., Chan H.K., Li Y. Digitalization in the Maritime Logistics Industry: A Systematic Literature Review of Enablers and Barriers. J. Mar. Sci. Eng. 2025;13:797. doi: 10.3390/jmse13040797. - DOI
    1. Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser Ł., Polosukhin I. Attention is all you need. arXiv. 2017 doi: 10.48550/arXiv.1706.03762.1706.03762 - DOI
    1. Brown T., Mann B., Ryder N., Subbiah M., Kaplan J.D., Dhariwal P., Neelakantan A., Shyam P., Sastry G., Askell A., et al. Language Models are Few-Shot Learners. In: Larochelle H., Ranzato M., Hadsell R., Balcan M., Lin H., editors. Proceedings of the Advances in Neural Information Processing Systems. Volume 33. Curran Associates, Inc.; Red Hook, NY, USA: 2020. [(accessed on 1 November 2025)]. pp. 1877–1901. Available online: https://proceedings.neurips.cc/paper_files/paper/2020/file/1457c0d6bfcb4....

LinkOut - more resources