Underwater Embodied Intelligence for Autonomous Robots: A Constraint-Coupled Perspective on Planning, Control, and Deployment

TL;DR

This paper reviews the challenges and recent advances in underwater autonomous robots, emphasizing the importance of understanding and addressing the tightly coupled physical and informational constraints for reliable ocean exploration.

Contribution

It introduces a constraint-coupled perspective on underwater embodied intelligence, synthesizing recent progress and proposing a taxonomy for failure modes in complex, uncertain ocean environments.

Findings

Cross-layer coupling impacts robot performance and reliability.

Error cascades across perception, planning, and control layers under uncertainty.

Research directions include physics-grounded models and certifiable learning-enabled control.

Abstract

Autonomous underwater robots are increasingly deployed for environmental monitoring, infrastructure inspection, subsea resource exploration, and long-horizon exploration. Yet, despite rapid advances in learning-based planning and control, reliable autonomy in real ocean environments remains fundamentally constrained by tightly coupled physical limits. Hydrodynamic uncertainty, partial observability, bandwidth-limited communication, and energy scarcity are not independent challenges; they interact within the closed perception-planning-control loop and often amplify one another over time. This Review develops a constraint-coupled perspective on underwater embodied intelligence, arguing that planning and control must be understood within tightly coupled sensing, communication, coordination, and resource constraints in real ocean environments. We synthesize recent progress in reinforcement learning, belief-aware planning, hybrid control, multi-robot coordination, and foundation-model integration through this embodied perspective. Across representative application domains, we show how environmental monitoring, inspection, exploration, and cooperative missions expose distinct stress profiles of cross-layer coupling. To unify these observations, we introduce a cross-layer failure taxonomy spanning epistemic, dynamic, and coordination breakdowns, and analyze how errors cascade across autonomy layers under uncertainty. Building on this structure, we outline research directions toward physics-grounded world models, certifiable learning-enabled control, communication-aware coordination, and deployment-aware system design. By internalizing constraint coupling rather than treating it as an external disturbance, underwater embodied intelligence may evolve from performance-driven adaptation toward resilient, scalable, and verifiable autonomy under real ocean conditions.