Energy Constrained Hierarchical Underwater Monitoring via Local Multi-Agent RAG
2026-07-27 • Information Retrieval
Information RetrievalComputer Vision and Pattern RecognitionMultiagent SystemsRobotics
AI summaryⓘ
The authors designed a low-energy underwater monitoring system that keeps simple sensors running all the time and only powers a more powerful computer when needed. The powerful computer processes data from cameras and microphones to identify marine species and create helpful reports locally, reducing the need to send large amounts of data over limited underwater networks. Their system uses smart organization and classification methods to recognize species and manage info efficiently. This approach helps save energy and cuts down on communication, making underwater monitoring more practical.
edge sensingmicrocontrollersmultimodal dataspecies identificationembedding-based indexingChromaDBenergy managementlocal reasoningmarine monitoringLangChain
Authors
Mohamed Amine Janati, Laurent Gautier, Stéphane Barbot
Abstract
Marine life monitoring is limited by strict energy constraints, poor underwater connectivity, and the high cost of transmitting raw multimodal data from remote deployments. This paper proposes a low-consumption underwater monitoring architecture that combines always-on edge sensing with selective high-performance local reasoning. The system follows a hierarchical master--satellite design in which ultra-low-power MAX78000/MAX78002 microcontrollers continuously monitor visual and acoustic signals, while an NVIDIA Jetson Orin NX is activated only for scheduled processing, event-driven analysis, or researcher interaction. Once active, the Jetson executes a fully local multimodal pipeline for data ingestion, visual target extraction, embedding-based indexing, species identification, retrieval-augmented reasoning, and automated reporting. BioCLIP/OpenCLIP embeddings are used to organize mission data, marine taxonomic references, scientific documents, and operational metadata in local ChromaDB collections. A dedicated identification layer combines visual similarity search, centroid-based classification, and supervised classifiers to support adaptive species recognition. A LangChain-based multi-agent framework coordinates query routing, structured analysis, energy management, hardware reconfiguration, and report generation. The architecture is evaluated through visual and acoustic monitoring case studies. The proposed system bridges ultra-low-power continuous sensing with local multimodal intelligence, enabling underwater stations to produce structured, researcher-ready knowledge while compressing local data for flexible acoustic, optical, or satellite transmission, minimizing both energy use and communication overhead.