Search

Efficiently predicting high-resolution and accurate flow fields through networked autonomous marine vehicles (AMVs) is crucial for diverse applications. Nonetheless, a research gap exists in the seamless integration of data-driven flow modeling, real-time data assimilation from flow sensing, and the optimization of AMVs' sensing strategies, culminating in a closed-loop dynamic data-driven application system (DDDAS). This article presents a novel DDDAS that systematically integrates flow modeling, data assimilation, and adaptive flow sensing using networked AMVs. It features a hybrid data-driven flow model, uniting a neural network for trend prediction and a Gaussian process model for residual fitting. The neural network architecture is designed using knowledge extracted from historic flow data through tidal harmonic analysis, enhancing its capability in flow prediction. The Kriged ensemble transform Kalman filter is introduced to assimilate spatially correlated flow-sensing data from AMVs, enabling effective model learning and accurate spatiotemporal flow prediction, while forming the basis for optimizing AMVs' flow-sensing paths. A receding horizon strategy is proposed to implement non-myopic optimal path planning, and a distributed strategy of implementing Monte Carlo tree search is proposed to solve the resulting large-scale tree searching-based optimization problem. Computer simulations, employing underwater gliders as sensing networks, demonstrate the effectiveness of the proposed DDDAS in predicting depth-averaged flow in nearshore ocean environments. [ABSTRACT FROM AUTHOR]

Ocean exploration is one of the fundamental issues for the sustainable development of human society, which is also the basis for realizing the concept of the Internet of Underwater Things (IoUT) applications, such as the smart ocean city. The collaboration of heterogeneous autonomous marine vehicles (AMVs) based on underwater wireless communication is known as a practical approach to ocean exploration, typically with the autonomous surface vehicle (ASV) and the autonomous underwater glider (AUG). However, the difference in their specifications and movements makes the following problems for collaborative work. First, when an AUG floats to a certain depth, and an ASV interacts via underwater wireless communication, the interaction has a certain time limit and their movements to an interaction position have to be synchronized; secondly, in the case where multiple AUGs are exploring underwater, the ASV needs to plan the sequence of surface interactions to ensure timely and efficient data collection. Accordingly, this paper proposes a heuristic surface path planning method for data collection with heterogeneous AMVs (HSPP-HA). The HSPP-HA optimizes the interaction schedule between ASV and multiple AUGs through a modified shuffled frog-leaping algorithm (SFLA). It applies a spatial-temporal k-means clustering in initializing the memeplex group of SFLA to adapt time-sensitive interactions by weighting their spatial and temporal proximities and adopts an adaptive convergence factor which varies by algorithm iterations to balance the local and global searches and to minimize the potential local optimum problem in each local search. Through simulations, the proposed HSPP-HA shows advantages in terms of access rate, path length and data collection rate compared to recent and classic path planning methods. [ABSTRACT FROM AUTHOR]

With the advancement of intelligent vehicles and unmanned systems, there is a growing interest in underwater surveys using autonomous marine vehicles (AMVs). This study presents an automated planning strategy for a long-term survey mission using a fleet of AMVs consisting of autonomous surface vehicles and autonomous underwater vehicles. Due to the complex nature of the mission, the actions of the vehicle must be of high-level abstraction, which means that the actions indicate not only motion of the vehicle but also symbols and semantics, such as those corresponding to deploy, charge, and survey. For automated planning, the planning domain definition language (PDDL) was employed to construct a mission planner for realizing a powerful and flexible planning system. Despite being able to handle abstract actions, such high-level planners have difficulty in efficiently optimizing numerical objectives such as obtaining the shortest route given multiple destinations. To alleviate this issue, a widely known technique in operations research was additionally employed, which limited the solution space so that the high-level planner could devise efficient plans. For a comprehensive evaluation of the proposed method, various PDDL-based planners with different parameter settings were implemented, and their performances were compared through simulation. The simulation result shows that the proposed method outperformed the baseline solutions by yielding plans that completed the missions more quickly, thereby demonstrating the efficacy of the proposed methodology.

Efficiently predicting high-resolution and accurate flow fields through networked autonomous marine vehicles (AMVs) is crucial for diverse applications. Nonetheless, a research gap exists in the seamless integration of data-driven flow modeling, real-time data assimilation from flow sensing, and the optimization of AMVs’ sensing strategies, culminating in a closed-loop dynamic data-driven application system (DDDAS). This article presents a novel DDDAS that systematically integrates flow modeling, data assimilation, and adaptive flow sensing using networked AMVs. It features a hybrid data-driven flow model, uniting a neural network for trend prediction and a Gaussian process model for residual fitting. The neural network architecture is designed using knowledge extracted from historic flow data through tidal harmonic analysis, enhancing its capability in flow prediction. The Kriged ensemble transform Kalman filter is introduced to assimilate spatially correlated flow-sensing data from AMVs, enabling effective model learning and accurate spatiotemporal flow prediction, while forming the basis for optimizing AMVs’ flow-sensing paths. A receding horizon strategy is proposed to implement non-myopic optimal path planning, and a distributed strategy of implementing Monte Carlo tree search is proposed to solve the resulting large-scale tree searching-based optimization problem. Computer simulations, employing underwater gliders as sensing networks, demonstrate the effectiveness of the proposed DDDAS in predicting depth-averaged flow in nearshore ocean environments.

This article studies the neural‐network based backstepping control problem for autonomous marine vehicles perturbed by external disturbances. The actuator dead‐zone phenomenon, which is a common non‐smooth property caused by the complicated operating environment of autonomous marine vehicles, is also considered. To cope with the issue of "complexity explosion" and further decrease the tracking errors, a command filtering compensation strategy is also proposed, which guarantees satisfactory tracking performance and boundedness of the closed‐loop system signals. Finally, simulation studies are given to further demonstrate the effectiveness of the proposed control method. [ABSTRACT FROM AUTHOR]

This paper presents a methodology for observing and analyzing marine ecosystems using images gathered from autonomous marine vehicles. Visual data is composed in photo-mosaics and classified using machine learning algorithms. The approach expands existing solutions, enabling extended monitoring in time, space, and depth. Imagery was collected during a field campaign in the Spanish marine and terrestrial protected area of Cabrera, Balearic Islands, colonized by the endemic seagrass species Posidonia oceanica (Po). The operations were performed using three distinct platforms, an Autonomous Underwater Vehicle (AUV), an Autonomous Surface Vehicle (ASV) and a Lagrangian Drifter (LD). Results are compared to prior habitat maps to assess seagrass meadow distribution. The proposed solution can be scaled and adapted to other locations and species, considering limitations in data storage and battery endurance. [Display omitted] • Seafloor habitat mapping with autonomous robots, filling gaps missed by divers. • Assessment of marine habitats using convolutional neural networks. • Methods apply to georeferenced imaging (e.g. drones, satellites) beyond subsea mapping. • Field campaign data from a marine area compared to previous habitat map data. [ABSTRACT FROM AUTHOR]

Collisions and groundings account for a great deal of fiscal losses and human risks in the statistics of marine accidents related to ocean going vessels. With highly automated vessels offering a high degree of situational awareness, algorithms can anticipate developments and suggest timely actions to avoid or deconflict critical events, in accordance to safe navigational practices and in compliance with the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). To avoid such accidents related to navigation, this article proposes a Short Horizon Planner (SHP) for decision support or automated route deviations, as a means to mitigate prevailing risks. The planner adopts a sampling-based planning framework that uses the concepts of cross-track error and speed loss during a steady turn, together with sampling spaces directly extracted from the electronic navigational chart to compute optimal and COLREGs compliant paths with the least deviation from the ship's nominal route. COLREGs compliance (rules 8, 13–17) is achieved through an elliptical-like representations of the given COLREGs, which rejects samples based on modified ship domains. High fidelity simulations show properties of the method and the information made available to human- or automated execution of route alterations. • A Short Horizon Planner for collision and grounding avoidance of marine crafts. • Performance indexes based on cross-track error, path elongation and speed loss. • Compliance with COLREGs rules 8, 13–17 using custom elliptical comfort zones. • Grounding avoidance using a specialised sampling scheme that triangulates the chart. • The grounding and collision avoidance is demonstrated on multiple vessel scenarios. [ABSTRACT FROM AUTHOR]