State Estimation of Marine Vessels Affected by Waves by Unmanned Aerial Vehicles

2024-10-07

Ocean Engineering

AI Summary

To address the low accuracy of six-degree-of-freedom (6-DOF) state estimation and poor GNSS robustness for unmanned surface vehicles (USVs) operating in harsh maritime environments alongside unmanned aerial vehicles (UAVs), this paper proposes an air–sea collaborative perception method integrating visual–inertial SLAM with wave-motion compensation. The method innovatively unifies multi-view UAV visual localization, IMU-aided tightly coupled visual–inertial odometry (VIO), and sea-state-dependent ship motion disturbance modeling based on ocean wave spectra, establishing a real-time state filtering framework explicitly accounting for wave-induced perturbations. Experimental results demonstrate a 62% reduction in attitude estimation error, position drift constrained within 0.35 m, and a 4.8× improvement in GNSS robustness over standalone GNSS solutions. This work represents the first systematic integration of wave-compensation modeling with visual–inertial fusion for dynamic ship state estimation, significantly enhancing the reliability and precision of air–sea platform coordination.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Problem

• Robust state estimation of marine vessels in rough water
• Novel 6 DOF USV model for precise estimation
• Sensor fusion for redundancy under varying weather conditions

Innovation

• UAV-USV sensor data fusion
• 6-DOF nonlinear USV model
• Real-world experimental validation