From Voice to Mutual Understanding: An AI Vision for VHF Radio Communication in the Autonomous Era

This is the authors' abstract. We don't add key points for this paper.

The growing adoption of autonomous technologies in the maritime industry creates a critical challenge for safe navigation: a communication gap between Maritime Autonomous Surface Ships (MASS) and human operators, both on conventionally crewed vessels and in shore-based control centers like Vessel Traffic Services (VTS). This gap is particularly pronounced in voice-based Very High Frequency (VHF) radio communication, which remains essential for mutual intent-sharing, conflict resolution, and coordinated navigation in a mixed-fleet environment. This paper introduces a forward-looking vision for an artificial intelligence (AI) powered framework aimed at achieving fully digitized maritime radio communication for MASS. The proposed system is structured around four tightly integrated modules: Sensory Input Stage, Text and Context Extraction, Contextualization and Reasoning - LLM Agent Loop, and Response Generation and Broadcasting. These components work cohesively to transform traditional voice radio exchanges into a machine-interpretable and protocol-compliant communication pipeline. This paper presents a comprehensive exposition of the framework’s architecture, accompanied by a structured development roadmap and appropriate evaluation methodologies for each module. It also introduces a novel concept of tiered autonomy levels for digital radio communication, emphasizing the critical role of human-in-the-loop supervision. By enabling autonomous ships to interpret, process, and respond to VHF transmissions in real time, this framework not only enhances operational efficiency but also contributes to the safe and standardized integration of autonomous technologies within the complex maritime ecosystem.