Position Of Autonomous Underwater Vehicle Research Articles

Voronoi Diagram-based USBL Outlier Rejection for AUV Localization

USBL systems are essential for providing accurate positions of autonomous underwater vehicles (AUVs). On the other hand, the accuracy can be degraded by outliers because of the environmental conditions. A failure to address these outliers can significantly impact the reliability of underwater localization and navigation systems. This paper proposes a novel outlier rejection algorithm for AUV localization using Voronoi diagrams and query point calculation. The Voronoi diagram divides data space into Voronoi cells that center on ultra-short baseline (USBL) data, and the calculated query point determines if the corresponding USBL data is an inlier. This study conducted experiments acquiring GPS and USBL data simultaneously and optimized the algorithm empirically based on the acquired data. In addition, the proposed method was applied to a sensor fusion algorithm to verify its effectiveness, resulting in improved pose estimations. The proposed method can be applied to various sensor fusion algorithms as a preprocess and could be used for outlier rejection for other 2D-based location sensors.

Development of Hydroacoustic Localization Algorithms for AUV Based on the Error-Corrected WMChan-Taylor Algorithm

Autonomous underwater vehicles (AUVs) are susceptible to non-line-of-sight (NLOS) errors and noise bias at receiving stations during the application of hydroacoustic localization systems, leading to a degradation in positioning accuracy. To address this problem, this paper optimizes the Chan-Taylor algorithm. Initially, we propose the Weighted Modified Chan-Taylor (WMChan-Talor) algorithm, which introduces dynamic weights into the Chan algorithm to correct noise variance at measurement stations, thereby improving the accuracy of AUV positioning. Computer simulations validate the effectiveness of the WMChan-Taylor algorithm in enhancing positioning accuracy. To further address the accuracy degradation caused by noise deviations across different receiving stations, we introduce an error-corrected WMChan-Taylor algorithm. This algorithm utilizes a standard residual function to eliminate significant delays caused by large errors at receiving stations and applies standard residual weighting to improve the combined positioning solution. The performance of the error-corrected WMChan-Taylor algorithm is demonstrated through both computer and semi-physical simulation experiments, confirming its capability to isolate noisier stations and thus enhance overall positioning accuracy.

Cooperative localization for master–salve multi-AUVs based on range measurements

Underwater localization has consistently remained a prominent technical challenge for autonomous underwater vehicles (AUVs). The advent of cooperative localization techniques has emerged as a novel avenue for enhancing localization accuracy. The master–slave cooperative localization mode has gained widespread adoption due to its cost-effectiveness in implementation. In view of the complexity of underwater noise characteristics, in the multi-AUVs cooperative localization system, this paper addresses scenarios involving distance-dependent noise in a master–slave-based multi-AUVs cooperative localization system. To tackle the negative impact of distance-dependent noise and the non-linearity of the distance function, a two-step algorithm is proposed that combines maximum likelihood estimation and the Gaussian belief propagation algorithm (ML-GBP) to estimate the positions of AUVs. The maximum likelihood estimation is employed to cope with the interference caused by distance-dependent noise, and subsequently, the Gaussian belief propagation algorithm, based on range observations and reference information, is used to achieve accurate estimation of AUV positions and implement position correction. Simulation results demonstrate that the proposed ML-GBP algorithm outperforms traditional extended Kalman filter (EKF) and nonparametric belief propagation (NBP) methods by enhancing the localization accuracy of the system while exhibiting superior performance in terms of computational complexity and system communication overhead.

Trajectory tracking of autonomous underwater vehicle under disturbance based on time-delay adaptive high-order sliding mode control

This paper introduces an innovative adaptive generalized super twisting algorithm (AGSTA) controller combined with a time-delay estimator (TDE) to address the trajectory-tracking issue in autonomous underwater vehicles (AUVs) impacted by disturbances. AUVs utilized in underwater exploration often carry sensors, such as Doppler velocity logs, for position and speed determination. However, owing to instrument precision limitations and other factors, these sensors suffer from a slow sampling speed. Furthermore, manual tuning requirement, conventional GSTAs do not provide substantial benefits in real-world applications, adversely affecting AUV position control. To rectify this issue, we proposed a TDE founded on delayed sensor data to estimate the vehicle fluid dynamics, integrated with an AGSTA, to enhance the controller performance. A comprehensive stability analysis of the control system was carried out under these parameters. The effectiveness of the proposed method was demonstrated through simulation results.

Waveguide invariant navigation of an autonomous underwater vehicle

Reliable navigation of an autonomous underwater vehicle (AUV) remains a challenge due to the unavailability of a global positioning system underwater. However, the self-localization uncertainty of an AUV with an acoustic receiver can potentially be reduced by leveraging passive acoustic ranging techniques. In particular, in shallow water, the range between an acoustic source and a passive receiver can be estimated using the waveguide invariant. In this work, we develop a sequential Bayes navigation filter that fuses passive recordings of an acoustic source with the measurements of an inertial sensor. The acoustic source can either be cooperative or a source of opportunity, e.g., a container ship. Using particle-based processing, our filter can either estimate the waveguide invariant or the AUV position by making use of a detailed nonlinear statistical model of the received signal. If the position of the AUV is accurately known, e.g., in the beginning of the AUV’s mission, the waveguide invariant can be estimated. Alternatively, assuming that accurate waveguide invariant information is available, range information can be obtained and used to improve the estimate of the AUV’s position. The navigation capability provided by the proposed sequential Bayes filter is demonstrated using simulated and real data.

On Variations of the Sound Signal Propagation Time under a Stationary Ice Cover

In experiments on a stationary acoustic track under a solid ice cover, estimates of possible sound signal propagation time variations at distances of ∼4 km with a period of more than 100 s were obtained. The experiments were carried out on Lake Baikal in the spring period, when the vertical profile of the sound speed has two sections characteristic of freshwater areas: an upper layer with a near constant sound speed and a lower layer with linear growth of sound speed. Under these conditions, the variations of the propagation time did not exceed ~10–4 s. Numerical modeling showed that the variations of propagation times due to the variability of the medium are minimal for the case when the sound source and receiver are located in the upper layer. It is demonstrated that in this case it is acceptable to take the sound speed in the upper quasi-homogeneous layer as the effective value of the sound speed, which determines the propagation time. The obtained results allowed us to formulate recommendations on under-ice acoustic positioning of autonomous underwater vehicles.

A Bio-Inspired MEMS Wake Detector for AUV Tracking and Coordinated Formation

AUV (Autonomous Underwater Vehicle) coordinated formation can expand the detection range, improve detection efficiency, and complete complex tasks, which requires each AUV to have the ability to track and locate. A wake detector provides a new technical approach for AUV cooperative formation warfare. Now, most of the existing artificial lateral line detectors are for one-dimensional flow field applications, which are difficult to use for wake detection of AUVs. Therefore, based on the pressure gradient sensing mechanism of the canal neuromasts, we apply Micro-Electro-Mechanical System (MEMS) technology to develop a lateral line-inspired MEMS wake detector. The sensing mechanism, design, and fabrication are demonstrated in detail. Experimental results show the detector’s sensitivity is 147 mV·(m/s)−1, and the detection threshold is 0.3 m/s. In addition, the vector test results verify it has vector-detecting capacity. This wake detector can serve AUVs wake detection and tracking technology, which will be promising in AUV positioning and coordinated formation.

A Study on a Novel Inverted Ultra-Short Baseline Positioning System and Phase Difference Estimation

Autonomous underwater vehicles (AUVs) are important tools for exploring and studying the ocean. To improve the stealthiness of AUV positioning, a new type of inverted ultra-short baseline (i-USBL) positioning system is proposed in this paper. The system uses a surface GPS buoy as a positioning base station to transmit positioning signals to the AUV, which receives the signals through the i-USBL and calculates its own coordinates. In this way, the power consumption of the AUV will be lower, improving its endurance. In addition, azimuth observation is one of the key observation quantities in ultra-short baseline positioning systems. Therefore, this paper derives two phase difference estimation algorithms for azimuth measurement, which are the Least Mean Square (LMS) algorithm and the Discrete Fourier Transform (DFT) algorithm. Simulation results show that when the signal-to-noise ratio (SNR) is less than or equal to 0 dB, the DFT algorithm has higher accuracy; when SNR is greater than or equal to 10 dB, LMS has slightly higher accuracy than DFT; however, DFT is more stable than LMS at all SNRs. When SNR is 20 dB, the maximum azimuth measurement error of LMS and DFT is 0.3301° and 0.2204°, respectively, which can meet the positioning accuracy requirements. The average running times of LMS and DFT are 0.085 s and 0.011 s, respectively, and LMS has a faster running speed. In summary, the LMS algorithm can be used for azimuth observation when the SNR is good, and DFT can be applied when the SNR is poor.

АСИМПТОТИЧЕСКИЕ МЕТОДЫ В ЗАДАЧАХ СУПЕРВИЗОРНОГО УПРАВЛЕНИЯ АВТОНОМНЫХ ПОДВОДНЫХ РОБОТОВ

The work is devoted to the relevant problem of control synthesis for autonomous underwater vehicles(AUVs). Since AUVs must perform actions in accordance with a given program under conditionsof a volatile predictable environment, it is necessary to provide working tools, the use of which, togetherwith the AUV position and orientation control requires, along with continuous local stabilization means,implementation of supervising and coordinated control algorithms at the upper level. Such a two-levelcontrol scheme, which can be called supervisory, is proposed in this paper to be implemented using twotypes of asymptotic methods: to separate movements into fast and slow, an apparatus for analyzing singularly perturbed differential equations is used, and the upper level control is based on the principleof large deviations. The general synthesis task is to control slow movements and stabilize fast movements.At the same time, in the stochastic problem formulation, it is assumed that there is a randomperturbation in fast movements. Given that fast movements are stabilized, it is high probable that thenoise influence averaged and does not significantly affect the behavior of slow variables. However, withsufficiently long observation it is possible to find a situation where at some period the perturbation valuesare not only uncompensated, but, on the contrary, line up in a sequence as specially intended toform an apparent deviation of the slow sub-vector from equilibrium. It is known from the theory of largedeviations that such a trajectory is the only and most likely of all those leading to a certain critical event.At the same time, the phase of this process can be used to judge the critical event proximity. For thisreason, the large deviations theory usage makes it possible to organize the control of deviations from aiven object’ t jecto y, capable of giving estimates on the probability of the controlled deviationscritical values. As a result, it is shown that if accelerations are formed by fast subsystems, then in slowsubsystems it is possible not only to achieve acceptable quality and accuracy at a fixed interval, but alsoto ensure this regardless of the disturbances. The validity of the proposed approach to synthesis, basedon the separation of movements and the large deviations theory, is shown on the example of an autonomousunderwater vehicle with two rudders (fore and aft) in the task of controlling longitudinal motion ata given depth. Simulation results and their discussion are presented.

Acoustic positioning of multiple AUVs by an ASV: experimental validation and performance characterisation

Cooperation among heterogeneous marine vehicles can offer several benefits to underwater applications, such as supporting the navigation of submerged robots by leveraging the information available to a surface vehicle. Within such context, this paper describes an acoustic positioning and communication protocol developed for the localisation of multiple Autonomous Underwater Vehicles (AUVs) by means of an Autonomous Surface Vehicle (ASV) equipped with an Ultra-Short BaseLine (USBL) device. To avoid packet collisions, access to the acoustic channel is managed through a time slot division mechanism. Unlike a classical Time Division Multiple Access (TDMA) protocol, the approach considered in this work consists of a centralised scheduling handled by the ASV, in which AUVs are localised at regular time epoch but can transmit only when queried. This allows to prioritise the number of position measurements taken by the ASV and then relayed back to the submerged vehicles, with the final goal of improving the navigation accuracy of the latter. The solution is also designed to handle the latency of acoustic communication and to correctly associate each position measurement with the corresponding acquisition time. Furthermore, it does not require any a priori synchronisation between the clocks of the vehicles involved and ensures complete decoupling between their navigation algorithms. Experimental activities in very-shallow waters, involving an ASV and two target nodes, were carried out to validate the multi-AUVs positioning system and to provide a characterisation of its performance.

A Tightly Integrated Navigation Method of SINS, DVL, and PS Based on RIMM in the Complex Underwater Environment

Navigation and positioning of autonomous underwater vehicles (AUVs) in the complex and changeable marine environment are crucial and challenging. For the positioning of AUVs, the integrated navigation of the strap-down inertial navigation system (SINS), Doppler velocity log (DVL), and pressure sensor (PS) has a common application. Nevertheless, in the complex underwater environment, the DVL performance is affected by the current and complex terrain environments. The outliers in sensor observations also have a substantial adverse effect on the AUV positioning accuracy. To address these issues, in this paper, a novel tightly integrated navigation model of the SINS, DVL, and PS is established. In contrast to the traditional SINS, DVL, and PS tightly integrated navigation methods, the proposed method in this paper is based on the velocity variation of the DVL beam by applying the DVL bottom-track and water-track models. Furthermore, a new robust interacting multiple models (RIMM) information fusion algorithm is proposed. In this algorithm, DVL beam anomaly is detected, and the Markov transfer probability matrix is accordingly updated to enable quick model matching. By simulating the motion of the AUV in a complex underwater environment, we also compare the performance of the traditional loosely integrated navigation (TLIN) model, the tightly integrated navigation (TTIN) model, and the IMM algorithm. The simulation results show that because of the PS, the velocity and height in the up-change amplitude of the four algorithms are small. Compared with the TLIN algorithm in terms of maximum deviation of latitude and longitude, the RIMM algorithm also improves the accuracy by 39.1243 m and 26.4364 m, respectively. Furthermore, compared with the TTIN algorithm, the RIMM algorithm improves latitude and longitude accuracy by 1.8913 m and 11.8274 m, respectively. A comparison with IMM also shows that RIMM improves the accuracy of latitude and longitude by 1.1506 m and 7.2301 m, respectively. The results confirm that the proposed algorithm suppresses the observed noise and outliers of DVL and further achieves quick conversion between different DVL models while making full use of the effective information of the DVL beams. The proposed method also improves the navigation accuracy of AUVs in complex underwater environments.

Integrated Localization and Tracking for AUV With Model Uncertainties via Scalable Sampling-Based Reinforcement Learning Approach

This article studies the joint localization and tracking issue for the autonomous underwater vehicle (AUV), with the constraints of asynchronous time clock in cyberchannels and model uncertainty in physical channels. More specifically, we develop a reinforcement learning (RL)-based asynchronous localization algorithm to localize the position of AUV, where the time clock of AUV is not required to be well synchronized with the real time. Based on the estimated position, a scalable sampling strategy called multivariate probabilistic collocation method with orthogonal fractional factorial design (M-PCM-OFFD) is employed to evaluate the time-varying uncertain model parameters of AUV. After that, an RL-based tracking controller is designed to drive AUV to the desired target point. Besides that, the performance analyses for the integration solution are also presented. Of note, the advantages of our solution are highlighted as: 1) the RL-based localization algorithm can avoid local optimal in traditional least-square methods; 2) the M-PCM-OFFD-based sampling strategy can address the model uncertainty and reduce the computational cost; and 3) the integration design of localization and tracking can reduce the communication energy consumption. Finally, simulation and experiment demonstrate that the proposed localization algorithm can effectively eliminate the impact of asynchronous clock, and more importantly, the integration of M-PCM-OFFD in the RL-based tracking controller can find accurate optimization solutions with limited computational costs.

AUV Path Planning Algorithm for Terrain Aided Navigation

Terrain aided navigation (TAN) technology can yield accurate navigation results in long-endurance underwater operation of autonomous underwater vehicles (AUVs). Most TAN research focus on the high-precision terrain matching algorithms. However, terrain matching algorithms estimate the position of the vehicle by observing a unique combination of features in the terrain, making it difficult to locate a vehicle with flat terrain. This paper presents a path planning method for AUV seabed TAN process to decrease positioning errors by avoiding flat areas. In this paper, a TAN path planning algorithm based on sector search is proposed. Parameters of the sector search algorithm are determined through theoretical analysis, which means the generated path can stably provide accurate TAN location results. Meanwhile, a control coefficient is proposed to maximize the terrain information contained in the sector searching area, bring out a high success rate of AUV positioning. The TAN performance of the paths generated using the proposed path planning method was verified in simulations, which show that the TAN can yield accurate positioning results stably on the path planned.

An automated framework for long-range acoustic positioning of autonomous underwater vehicles

An automated method was developed to align underwater acoustic receptions at various depths and ranges to a single reference prediction of long range acoustic arrival structure as it evolves with range in order to determine source-receiver range. Acoustic receptions collected by four autonomous underwater vehicles deployed in the Philippine Sea as part of an ocean acoustic propagation experiment were used to demonstrate the method. The arrivals were measured in the upper 1000 m of the ocean at ranges up to 700 km from five moored, low frequency broadband acoustic tomography sources. Acoustic arrival time structure for pulse compressed signals at long ranges is relatively stable, yet real ocean variability presents challenges in acoustic arrival matching. The automated method takes advantage of simple projections of the measured structure onto the model space that represents all possible pairings of measured peaks to predicted eigenrays and minimizes the average travel-time offset across selected pairings. Compared to ranging results obtained by manual acoustic arrival matching, 93% of the automatically-obtained range estimates were within 75 m of the manually-obtained range estimates. Least squares residuals from positioning estimates using the automatically-obtained ranges with a fault detection scheme were 55 m root-mean-square.

Prediction-Based Region Tracking Control Scheme for Autonomous Underwater Vehicle

This paper addresses the region tracking control problem for an autonomous underwater vehicle (AUV) and proposes a prediction-based region tracking control (PRTC) scheme for AUV. In the PRTC scheme, the idea of prediction is adopted to solve the problems of overshoot and high energy consumption due to the lack of consideration of the large inertia of the AUV in the traditional scheme. The PRTC scheme predicts the future position of AUV through the past time-series position of AUV and the outer boundary of the desired region, and then designs the controller depending on the predicted results. Furthermore, the relationship between the desired region and the control output of the proposed PRTC scheme is studied. It is found that its control output amplitude is susceptible to the desired region range, resulting in output saturation. Therefore, this paper proposes a control law optimization scheme considering the desired region. This optimization scheme modifies the error signal in the control law of the PRTC scheme so that it is only related to the relative position of the desired region where the AUV is located. Finally, the proposed schemes are applied on the ODIN AUV, and the simulation results verify the feasibility of the proposed schemes.

Development of a Lightweight Inertial Gravimeter for Use on Board an Autonomous Underwater Vehicle: Measurement Principle, System Design and Sea Trial Mission

The purpose of this paper is to present the design, development and testing of an innovative instrument called GraviMob, which allows performing dynamic measurements of underwater gravity anomalies. After recalling the interest in underwater gravimetry, we describe the system, the core of which consists of triads of accelerometers rigidly attached to an Autonomous Underwater Vehicle (AUV). The article also presents the mathematical methods for estimating the east, north and vertical components of the local gravity vector. An unscented Kalman filter, integrating AUV position and orientation data, performs estimation of gravity in a frame adapted to its interpretation. To assess its performance, GraviMob was tested in the Mediterranean Sea during the year 2016. A comparison of the surface gravimetric signal previously acquired by the French Navy indicates that the maximum discrepancy between the vertical gravity component and its reference is below 4 mGal. Components of the vertical deflection calculated from GraviMob’s measurements were compared with those calculated from recent gravity field models. While a remarkable agreement was found on the north component, there remains a discrepancy (7 arcsec) on the east component which can be largely reduced by refining the estimation of the orientation of GraviMob’s sensitive axes in the AUV.

Observation reconstruction and disturbance compensation-based position control for autonomous underwater vehicle

To address the position control problem of a six degrees of freedom autonomous underwater vehicle (AUV), the disturbance is observed by an observer and compensated by a controller in this paper. To ensure the vehicle reaches the specified position quickly, the sine cosine algorithm with individual memory is used to find suitable parameters for different controllers. The simulation results show that the observer can extract the system's internal and external uncertainty information in real-time, reduce the phase lag and improve the stability of AUV position control. For a system with complex nonlinearity such as AUV, the observer proposed in this paper has stronger applicability and better robustness.

Dynamic Positioning of Autonomous Underwater Vehicle in Shallow Water under the Influence of External Disturbances

В представленной работе рассматривается задача построения системы динамического позиционирования автономного необитаемого подводного аппарата в пространствеcмногоцелевой структурой. Стабилизация аппарата в заданном положении используется для обеспечения его стыковки с подводной станцией или получения более точной информации о морском дне при проведении исследований. Задача динамического позиционирования ‒ одна из основных задач управления как надводными, так и подводными морскими объектами. Для надводных судов представлены многочисленные решения данной проблемы. Для подводных аппаратов получено меньшее количество результатов из-за достаточно сложной математической модели. Однако в случае динамического позиционирования в мелководной зоне возможны упрощения уравнения динамики, которые позволяют применить существующие подходы к управлению надводными судами для подводных аппаратов. Цель данной работы ‒ усовершенствование системы управления с многоцелевой структурой, полученной на основе принципа разделения, за счет введения в закон управления дополнительного слагаемого, обеспечивающего астатизм замкнутой системы и экономичный режим работы приводов. Указанная система состоит из асимптотического наблюдателя, который восстанавливает скорости аппарата и очищает измерения от шума, и регулятора, решающего задачу динамического позиционирования. Предложенный в данной работе динамический корректор играет значительную роль на практике. Экономичный режим работы управляющих компонентов дает возможность уменьшить их износ и снизить общий расход топлива. Астатизм замкнутой системы позволяет исключить отклонение аппарата от заданного положения при воздействии на него постоянного возмущения, которое стандартно моделирует подводные и ветровые течения. Для иллюстрации эффективности системы проводится имитационное моделирование в среде Simulink на примере аппарата Kambara. This work is devoted to the formation of dynamic positioning system for autonomous underwater vehicle with multipurpose structure. Such vehicles are applied to oceanographic research and bottom exploration. To dock with an underwater station or obtain more accurate information about the bottom, it is necessary to stabilize the vehicle at a given point in space, in other words, position the device. The problem of dynamic positioning is one of the primary control problems of marine objects. Numerous solutions to this issue have been presented for vessels. Fewer results were obtained for underwater vehicles due to a rather complex mathematical model. However, simplifications of the dynamic equation are possible in the case of positioning in shallow water, which make it possible to apply existing approaches to vessel control for underwater vehicles. The purpose of this work is to enhance the control system with multipurpose structure obtained on the basis of the separation principle by introducing into the control law an additional term. The resulting system consists of the observer, which restores the speed components of the vehicle’s movement and clears measurements of noise, and the controller, which positions the vehicle in a given position, provides the integral action of the closed-loop system and the economical mode of operation of the actuators. The integral action allows us to eliminate the deviation of the vehicle from the desired position when exposed to a constant disturbance (underwater and wind currents). Economical mode of control components makes it possible to lower their wear and reduce overall fuel consumption. A simulation is run in Simulink to illustrate the effectiveness of the obtained system.

Position control for an autonomous underwater vehicle under noisy conditions

Position tracking of an autonomous underwater vehicle is not trivial as its accuracy is affected by process noise, measurement noise, and uncertain hydrodynamic parameters. Thus, in this article, we studied the position control of an autonomous underwater vehicle that operates under largely unbounded system uncertainties and large noise levels and proposed a method that reduces the interference and thereby enhances the overall autonomous underwater vehicle position estimation. Our technique extended the ensemble Kalman filter by combining it with a time-delay estimator to compensate against extended uncertainty of the system dynamics which cannot be solved by the traditional ensemble Kalman filter. Our synthetic simulations demonstrated the effectiveness of the proposed controller, highlighting its appealing position-control accuracy under simultaneous noise and uncertain hydrodynamics parameters. In addition, our simulation results showed that the proposed controller outperforms the conventional time-delay controller by a percentage range of approximately 30.8%–92.6% in terms of root-mean-square error and requires on average less than 88.2% calculation time than the conventional model predictive control.

Efficient Velocity Estimation and Location Prediction in Underwater Acoustic Sensor Networks

Underwater acoustic sensor networks (UASNs) have been widely applied in marine monitoring, military reconnaissance, hydrology surveys, etc. Their location information is an important apriori knowledge when they are carried out underwater. However, the complex underwater environments impose great challenges on location acquisition, especially for autonomous underwater vehicles (AUVs), because of their mobility and finite power. In UASNs, existing location and navigation methods can offer AUVs position information, but they may either need a doppler velocity log (DVL), which is inefficient due to the complex underwater environments, or they may require additional localization infrastructure to deploy underwater, which suffers from large communication latency among AUVs, and costs enormous power. In this article, an efficient velocity estimation and location prediction method (VELP) in UASNs is proposed to avoid the above restrictions. It only utilizes collaborations based on communication among AUVs to achieve higher precision location with lower cost. Specifically, we apply an AUV-assisted velocity estimation algorithm with Doppler shift estimation in the physical layer of UASNs to improve the velocity estimation accuracy instead of the DVL. Meanwhile, we build a belief propagation-neural network-based location prediction model, which decreases the communication requirements and obviates introducing modeling errors. Extensive experimental results show VELP achieves superior performance on both accuracy and efficiency, demonstrating its great advantage in offering AUVs’ location information.