AI-Driven Maritime Autonomous Navigation Safety and Environmental Observation: Multimodal Perception and Waterborne Traffic Knowledge Discovery

As global maritime transportation systems advance toward autonomy and intelligence, ocean observation platforms — including autonomous surface vessels, AIS networks, and multi-sensor arrays — are becoming central tools for understanding navigation safety, environmental conditions, and human activity at sea. Unlike terrestrial systems, maritime observation operates in a highly unstructured, dynamic, and harsh environment characterized by adverse weather, low visibility, complex hydrodynamic conditions, and long communication latency. Advancing AI-enabled sensing and knowledge-discovery methods for these platforms is essential not only for autonomous navigation itself, but for the broader ocean observation community’s ability to monitor vessel traffic, environmental compliance, and coastal/offshore activity at scale.This Research Topic invites original research that uses AI to enhance maritime observation, safety, and traffic knowledge discovery through autonomous and multi-sensor platforms. At the sensing level, we welcome robust image restoration and object perception under extreme weather, low-light, and sensor-degraded conditions, with applications to environmental monitoring and maritime surveillance. At the platform level, we seek innovations in vessel intent comprehension, multi-agent collaboration, and collision avoidance for autonomous observation vessels operating safely alongside crewed traffic, including how such systems can be validated against navigational rules (e.g., COLREGs) as an engineering safety benchmark. At the data level, contributions on AIS trajectory mining, carbon-aware navigation support, and large-model-enhanced maritime safety assessment are encouraged, particularly where they generate observational knowledge relevant to environmental monitoring, traffic pattern discovery, or evidence for maritime governance bodies.The objective is to demonstrate how AI-enabled autonomous platforms and multimodal perception can expand the reach, resolution, and reliability of ocean observation, while improving maritime safety and supporting evidence-based decision-making for environmental and navigational stewardship.Topics of interest include, but are not limited to:Vessel Intent-Aware Decision Making and Multi-Agent Collision Avoidance for Autonomous Observation Platforms in Complex Waterway EncountersRobust Multimodal Perception for Maritime Surveillance and Environmental Compliance Verification under Adverse Weather and Sensor-Degraded ConditionsFoundation Model-Enabled Maritime Safety Assessment for Autonomous Ships and Observation PlatformsVisual Enhancement and Object Perception for Maritime Environmental Monitoring under Complex Atmospheric and Aquatic ConditionsAIS Trajectory Mining and Data-Driven Analytics for Vessel Traffic Pattern Discovery and Anomaly DetectionCarbon-Constrained Navigation Assistance with Multi-Sensor Fusion for Observation and Compliance SupportMulti-Source Data Fusion for Maritime Situational Awareness under Degraded Observation ConditionsCross-Jurisdictional Traffic Management and Regulatory Harmonization Informed by AI-Based Observation Data Topic editors: Xinqiang Chen, Salvatore Antonio Biancardo, Mozi Chen, Haoyang Liang, Zhangcun Yan Source: https://www.frontiersin.org/research-topics/83801/ai-driven-maritime-autonomous-navigation-safety-and-environmental-observation-multimodal-perception-and-waterborne-traffic-knowledge-discovery