Advancing Shared and Multi-Agent Autonomy in Underwater Missions: Integrating Knowledge Graphs and Retrieval-Augmented Generation

TL;DR

This paper demonstrates how integrating knowledge graphs and retrieval-augmented generation with large language models enhances multi-agent autonomy and human-robot interaction in complex underwater missions, achieving full mission validation.

Contribution

It introduces a novel approach combining knowledge graphs and RAG with LLMs to improve autonomous decision-making and shared control in underwater robotics.

Findings

Achieved 100% mission validation and behavior completeness.

Structured knowledge reduces hallucinations in LLMs.

Knowledge integration improves decision accuracy in dynamic environments.

Abstract

Robotic platforms have become essential for marine operations by providing regular and continuous access to offshore assets, such as underwater infrastructure inspection, environmental monitoring, and resource exploration. However, the complex and dynamic nature of underwater environments, characterized by limited visibility, unpredictable currents, and communication constraints, presents significant challenges that demand advanced autonomy while ensuring operator trust and oversight. Central to addressing these challenges are knowledge representation and reasoning techniques, particularly knowledge graphs and retrieval-augmented generation (RAG) systems, that enable robots to efficiently structure, retrieve, and interpret complex environmental data. These capabilities empower robotic agents to reason, adapt, and respond effectively to changing conditions. The primary goal of this work is to demonstrate both multi-agent autonomy and shared autonomy, where multiple robotic agents operate independently while remaining connected to a human supervisor. We show how a RAG-powered large language model, augmented with knowledge graph data and domain taxonomy, enables autonomous multi-agent decision-making and facilitates seamless human-robot interaction, resulting in 100\% mission validation and behavior completeness. Finally, ablation studies reveal that without structured knowledge from the graph and/or taxonomy, the LLM is prone to hallucinations, which can compromise decision quality.