Full autonomy in underwater robotics systems: A realistic prospect?

Abstract

Autonomous Underwater Systems (AUS) are transforming underwater exploration, environmental monitoring, and subsea operations by reducing reliance on human intervention. This review explores the advancements and challenges in achieving full operational autonomy in AUS, focusing on navigation, perception, communication, energy management, control systems, and decision-making frameworks. Current systems predominantly exhibit partial autonomy, performing pre-defined missions with limited adaptability. However, advancements in hybrid localisation techniques, multi-modal sensor fusion, and Artificial Intelligence (AI)-driven decision-making are pushing the boundaries of autonomy, enabling AUS to adapt dynamically to complex underwater environments. The integration of subsystems remains a central challenge. Navigation systems address positional drift through cooperative approaches, while perception systems enhance environmental understanding via sensor fusion. Communication technologies, although constrained by underwater limitations, are advancing through hybrid protocols that strike a balance between bandwidth and range. Energy management is evolving with innovations in battery technology, energy harvesting, and predictive resource allocation. Control systems, increasingly incorporating AI-based frameworks, translate mission commands into precise actions, bridging the gap between decision-making and physical execution. Decision-making frameworks synthesise inputs from all subsystems, enabling real-time prioritisation and adaptive behaviour. Despite significant progress, achieving full autonomy requires further innovation in subsystem integration, real-time processing, and environmental adaptability. This review emphasises the need for modular architectures and standardised protocols to ensure interoperability and scalability. The potential of fully autonomous underwater systems extends beyond technical achievements, offering profound implications for ocean exploration, resource sustainability, and environmental stewardship. The question posed – Full Autonomy in Underwater Systems: A Realistic Prospect? – is addressed with cautious optimism. While partial autonomy is well within reach, achieving full autonomy depends on sustained innovation across multiple domains. This manuscript provides a comprehensive roadmap for advancing AUS, laying the foundation for transformative advancements in one of Earth’s least understood frontiers. • Reviews progress and challenges toward full autonomy in underwater systems. • Examines partial autonomy and adaptability in predefined underwater missions. • Discusses hybrid localisation, sensor fusion, and AI-driven decision-making. • Highlights integration challenges in navigation, perception, and control. • Concludes prospects for autonomous ocean exploration and sustainability.