Position Of Autonomous Underwater Vehicle Research Articles

AUV position tracking and trajectory control based on fast-deployed deep reinforcement learning method

Aiming at the difficult problem of motion control of under-actuated and X-rudder autonomous underwater vehicle (AUV), the present work adopts deep reinforcement learning (DRL) method for its posture control. First, an AUV agent is trained with deep deterministic policy gradient (DDPG) algorithm in a simulation environment, and three-degree-of-freedom posture control of the AUV at a constant speed, fixed roll, variable pitch, and variable yaw, is successfully achieved. Subsequently, the AUV's yaw angle range is extended, and the control failure problem when AUV's yaw angle approaches a critical value is solved, realizing the rapid deployment of the DRL algorithm for AUV control. On this basis, the position-tracking task of AUV for targets in different orientations in three-dimensional space is completed, achieving a six-degree-of-freedom control of AUV. Additionally, by decomposing the trajectory control task of AUV in three-dimensional space into multiple position-tracking missions, the trajectory control of AUV in the underwater horizontal plane and underwater three-dimensional space is realized, demonstrating the significant task generalization ability of the control methods proposed.

Spatial Coherence of Speckle for Repeat-Pass Synthetic Aperture Sonar Micronavigation

Accurate positioning of autonomous underwater vehicles is a major challenge. The long-term drift is problematic if global position updates are not available, and for applications such as repeat-pass interferometry and coherent change detection, millimeter accuracy is needed. Repeat-pass synthetic aperture sonar (SAS) micronavigation is one potential technique for countering both challenges. While single-pass SAS micronavigation enabled successful coherent processing within one track, the potential is that repeat-pass SAS micronavigation can support coherent processing between passes. Both techniques are based on recognizing the speckle pattern in the seafloor return, but repeat-pass SAS micronavigation has additional challenges with the larger temporal and spatial separations between the observations. In this study, we investigate the spatial correlation of speckle as observed from SAS systems. We divide the different contributions to spatial decorrelation into three groups: 1) speckle decorrelation; 2) footprint mismatch; and 3) stretching. We examine each contribution separately and develop simplified formulas for their decorrelation baselines. When correlating synthetic aperture images, decorrelation from stretching dominates. When correlating single-element data recorded at low grazing angles common to SAS, speckle decorrelation dominates. We validate our findings on experimental data, and by combining elements into larger effective elements, we demonstrate increasing the across-track baseline for repeat-pass SAS micronavigation updates from less than 1 to 10 m.

Turning circle based trajectory planning method of an underactuated AUV for the mobile docking mission

In this paper, a turning circle based trajectory planning method (TCBTPM) is proposed to conduct trajectory planning of an underactuated autonomous underwater vehicle (AUV) for mobile docking mission. Firstly, the six degrees of freedom kinematics and dynamics model of underactuated AUV is acquired. Following this, the simulation of horizontal turning circle trial is studied and the overview of mobile docking mission is introduced. Furthermore, TCBTPM is used to predict the relative position of AUV and the mobile docking station (MDS) in advance and generate a feasible trajectory for the mobile docking mission. Finally, a mobile docking guidance system containing TCBTPM, pure pursuit (PP) guidance law and line-of-sight (LOS) guidance law is employed to obtain desired guidance commands and guides the underactuated AUV to dock efficiently and reliably.

Discrete-Time Position Control for Autonomous Underwater Vehicle under Noisy Conditions

This paper deals with the discrete-time position control problem for an autonomous underwater vehicle (AUV) under noisy conditions. Due to underwater noise, the velocity measurements returned by the AUV’s on-board sensors afford low accuracy, downgrading its control quality. Additionally, most of the hydrodynamic parameters of the AUV model are uncertain, further degrading the AUV control accuracy. Based on these findings, a discrete-time control law that improves the position control for the AUV trajectory tracking is presented to reduce the impact of these two factors. The proposed control law extends the Ensemble Kalman Filter and solves the problem of the traditional Ensemble Kalman Filter that underperforms when the hydrodynamic parameters of the AUV model are uncertain. The effectiveness of the proposed discrete-time controller is tested on various simulated scenarios and the results demonstrate that the proposed controller has appealing precision for AUV position tracking under noisy conditions and hydrodynamic parameter uncertainty. The proposed controller outperforms the conventional time-delay controller in root-mean-square error by a percentage range of approximately 72.1–97.4% and requires at least 89.5% less average calculation time than the conventional model predictive control.

Neural adaptive output feedback tracking control of underactuated AUVs

This paper addresses the three-dimensional tracking and stabilization problems simultaneously for underactuated autonomous underwater vehicles (AUVs) subjected to parametric uncertainties, external disturbances, unmeasured states and input saturation. A modified error state formulation is introduced to produce auxiliary virtual controls for the underactuated kinematics. A new high-gain observer is proposed to estimate unavailable velocities which doesn't need the position and orientation of AUVs to be bounded. Based on the backstepping technique and combinations of high-gain observer and radial-basis-function neural network (RBFNN) approximations, the kinematic and dynamic controllers are designed to force underactuated AUVs to track a time-varying trajectory or/and a stationary point, and guarantees the tracking errors convergent to a bounded neighborhood of the origin. Some comparative simulations are presented to validate the effectiveness and performance of the proposed control scheme.

Ubiquitous Tracking for Autonomous Underwater Vehicle With IoUT: A Rigid-Graph-Based Solution

Tracking an autonomous underwater vehicle (AUV) has been regarded as one of the most key applications for Internet of Underwater Things (IoUT). However, the strong mobility of AUV as well as asynchronous clock, stratification effect, and high energy consumption of acoustic communication make it challenging to achieve such a task. To handle the above issues, this article develops a ubiquitous tracking scheme for AUV. The tracking scheme is divided into two stages, i.e.: 1) motion prediction and 2) persistent tracking. In the first stage, an unscented transform-based localization estimator is utilized by sensor nodes to acquire the initial position of AUV, through which a terminal sliding-mode velocity observer is designed to predict the mobility trajectory of AUV. With the predicted mobility trajectory, a minimum rigid-graph-based tracking strategy is developed in the second stage to enable ubiquitously tracking. For the designed tracking strategy, the posterior Cramer-Rao lower bound is selected as the benchmark to optimize the network topology, such that a minimum rigid graph can be generated to balance the tradeoff between tracking accuracy and energy consumption. Particularly, the duty-cycle mechanism and the unscented Kalman filtering are jointly adopted to prolong the network lifetime and improve the tracking accuracy. Finally, simulation and experimental results are presented to show the effectiveness of our approach.

Study on the Arctic Underwater Terrain-Aided Navigation Based on Fuzzy-Particle Filter

The ultra-low resolution underwater terrain maps of the Arctic region reduce the localization and navigation accuracy of the underwater vehicle relying on terrain-aided navigation. In this paper, we study the navigation ability of Autonomous Underwater Vehicles (AUVs) under the ultralow-resolution terrain map. Firstly, the low-resolution map is transformed into a continuous map by bilinear interpolation. Then, a Terrain-Aided Navigation (TAN) system based on the Particle Filter (PF) is constructed to estimate the state of AUV position by particles. Particles of a random distribution of fixed variance can effectively track targets. However, a fixed variance distribution is not well adapted to many different situations. To improve navigation accuracy and robustness, fuzzy logic is used to estimate the distribution variance of particles under the current terrain gradient dynamically. The simulation results show that our proposed Fuzzy-PF TAN system is robust under various current disturbance situations. The position error of our system is within a map resolution unit of 500 m.

Research on Autonomous Underwater Vehicle Homing Method Based on Fuzzy-Q-FastSLAM

Abstract Autonomous docking guidance is one of the key technologies to achieve the autonomous underwater vehicle (AUV) docking with the sub-sea docking station (DS) to realize long-term resident operation. In the process of AUV docking, the combination of long-distance acoustic guidance based on acoustic sensor and terminal visual guidance based on camera is often adopted. However, affected by the accuracy of the navigation sensor and acoustic positioning sensor carried by AUV, as well as the ocean current, AUV cannot accurately know its own position and the position of the DS, resulting in a large acoustic guidance error and the inability to enter the visual guidance stage with a reasonable deviation, thus leading to the docking failure. In this article, an improved FastSLAM algorithm is proposed to estimate the position of AUV and DS simultaneously. The positioning accuracy of traditional FastSLAM algorithm is affected by such factors as the estimation accuracy of the statistical characteristics of process noise. An improved algorithm for FastSLAM based on fuzzy Q-learning is proposed. The homing path is planned based on the Dubins theory. The path is tracked by line-of-sight guidance. The results of matlab simulation and experimental data analyzing of the portable AUV are applied to verify the effectiveness of the proposed algorithm.

A New Coupled Method of SINS/DVL Integrated Navigation Based on Improved Dual Adaptive Factors

The integrated navigation of strap-down inertial navigation system (SINS) and Doppler velocity log (DVL) has a common application in the positioning of autonomous underwater vehicle (AUV). However, DVL may be interrupted for a short time when part of the beam cannot receive the reflected signal and DVL measurement information is easily affected by underwater complex environment and contains outliers. To solve the above problems, a Doppler shift-aided coupled method of SINS/DVL integrated navigation with pare of DVL beam measurements outages based on dual adaptive factors is proposed. In this article, a tightly coupled approach for SINS/DVL based on Doppler shifts is proposed to solve the short-term failure problem caused by the lack of part measurement in DVL. Then, a chi-square detection-aided dual factors’ adaptive filter is used to suppress the outliers. The dual factors are used to adjust the influence of imprecise information of dynamic model and observation model error. The chi-square detection is used to judge the outliers of measurements and the result of judgment is regarded as the precondition of factor selection. In order to verify the robustness of the proposed algorithm to outliers, simulation and Yangtze River experiments are carried out. The results of simulation and river experiments indicate that the tightly coupled approach obtains higher accuracy compared with the loosely coupled model and the proposed adaptive filter can effectively suppress the outliers. The method proposed in this article can achieve greater robustness in AUV underwater complex environment.

Multiple Model Algorithm for Single-Beacon Navigation of Autonomous Underwater Vehicle without Its A Priori Position. Part 1. Mathematical Formulation

The article considers a problem of autonomous underwater vehicle (AUV) positioning with acoustic measurements of range and possibly radial velocity relative to a single beacon, velocity components and coordinate increments from an inertial navigation system, and the data from a water-speed log or a ground log. Interruptions in acoustic measurements reception are acceptable. Availability of a priori information on relative position of AUV and the beacon is not assumed. In order to solve the problem, the author proposes a multiple model algorithm based on a bank of extended Kalman filters which independently estimate the initial horizontal range and errors of the used data under different hypotheses about a value of AUV initial azimuth relative to the beacon. Current coordinates of AUV are determined by the outputs of filters, taking into account the a posteriori probabilities of the corresponding hypotheses. The algorithm is rather simple for programming and does not require much computational power.

General Learning Modeling for AUV Position Tracking

In this article, we propose a nonlinear model based on hidden-layer neural networks and local Gaussian process regression. The hidden-layer neural networks have short training time, whereas the local Gaussian process regression is more suitable for nonlinearity. According to the abovementioned advantages of hidden-layer neural network and local Gaussian process regression, we get the measurement learning model and global process learning model offline and local process learning model online. Then, the proposed learning-based models have been applied to extended Kalman filter-simultaneous localization and mapping (EKF-SLAM), Rao-Blackwellised particle filter formulation of simultaneous localisation and mapping (FastSLAM), and unscented Kalman filter--simultaneous localization and mapping (UKF-SLAM) for autonomous underwater vehicles position tracking with field experiments. Compared with the conventional process and measurement models, improved position tracking performance can be achieved without cumbersome system analysis nor identification, benefiting from the proposed model. Experiments in more than 3883-m run show that the root-mean-square error has been improved by 36.95%, 37.14%, and 27.65% in EKF-SLAM, FastSLAM, and UKF-SLAM frameworks, respectively.

Application of gravity passive aided strapdown inertial navigation in underwater vehicles

Underwater navigation technology is the guarantee to ensure the underwater vehicles complete all tasks. A gravity passive aided strapdown inertial navigation system is proposed in order to improve the precision of position of autonomous underwater vehicles (AUVs). Improved unscented Kalman filter (IUKF) is applied in the novel integrated system which is based on gravity gradient characteristics. The main characteristics of strapdown inertial navigation system are presented, gravity-aided navigation system are introduced, and IUKF method is applied to the information fusion of integrated navigation system. Simulation experiments were carried out and the results show that the novel integrated navigation system proposed can get better performance of position precision comparing to the traditional Kalman filtering methods. The simulation experiment results suggest that the IUKF method applied in the gravity passive aided navigation system is capable of greatly improving the long-time navigation position, attitude and velocity precision comparing with the traditional information fusion method.

Application of gravity passive aided strapdown inertial navigation in underwater vehicles

Underwater navigation technology is the guarantee to ensure the underwater vehicles complete all tasks. A gravity passive aided strapdown inertial navigation system is proposed in order to improve the precision of position of autonomous underwater vehicles (AUVs). Improved unscented Kalman filter (IUKF) is applied in the novel integrated system which is based on gravity gradient characteristics. The main characteristics of strapdown inertial navigation system are presented, gravity-aided navigation system are introduced, and IUKF method is applied to the information fusion of integrated navigation system. Simulation experiments were carried out and the results show that the novel integrated navigation system proposed can get better performance of position precision comparing to the traditional Kalman filtering methods. The simulation experiment results suggest that the IUKF method applied in the gravity passive aided navigation system is capable of greatly improving the long-time navigation position, attitude and velocity precision comparing with the traditional information fusion method.

Improvements to Terrain Aided Navigation Accuracy in Deep-Sea Space by High Precision Particle Filter initialization

AUV (autonomous underwater vehicles) are required to have long-term and high-precision positioning capability relative to seabed targets in most deep-sea exploration tasks. However, acoustic positioning error is positively correlated with its operating range and inertial navigation has inevitable accumulated time errors, neither of which provide precise AUV positions. TAN (terrain aided navigation) directly calculates the AUV position to the seabed terrain coordinate system by tracking the seabed topographic characteristics, which can guide the AUV to seabed target accurately. However, the initial TAN positioning error will increase with the AUV operation depth, which causes a large PF (particle filter) initialization error and particle coverage interval, and will affect the convergence and stability of TAN. To solve this problem, we first propose a TAP (terrain aided position) confidence interval model. We then use the confidence interval to constrain the initial particles to a smaller range. Finally, the validity of the algorithm is verified by playback simulation with ship-borne multi-beam sonar sensor measured data. The results show that the TAP confidence interval can reduce the coverage of the initial particle, and can improve the convergence speed and filtering accuracy of the TAN.

Navnet: AUV Navigation Through Deep Sequential Learning

Achieving accurate navigation and localization is crucial for Autonomous Underwater Vehicle (AUV). Traditional navigation algorithms, such as Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF), require the system model and measurement model for state estimation to obtain the AUV position. However, this may introduce modeling errors and state estimation errors which will affect the final precision of AUV navigation system to a certain extent. To avoid these problems, in this paper, we proposed a deep framework - NavNet - by taking AUV navigation as a deep sequential learning problem. Firstly, the proposed NavNet can take raw sensor data at different frequencies as input, which benefits from the sequential learning capability of Recurrent Neural Network (RNN). Secondly, NavNet takes advantage of a simplified attention mechanism and Fully Connected (FC) layers to output AUV displacements per unit time, which accomplishes low-frequency AUV navigation by accumulation of it. More importantly, there is no need for the model building and state estimation with NavNet, which avoids the import of relevant errors. We compare the performance of NavNet to EKF and UKF using collected data by running Sailfish in the sea. Experimental results show that NavNet has an excellent performance in terms of both the navigation accuracy and fault tolerance. In addition, a reliable fusion strategy of NavNet and conventional method is applied to achieve high-frequency AUV navigation. The experimental results show that the proposed architecture can be a reliable supplement to limit the error growth of conventional algorithms.

On AUV Control with the Aid of Position Estimation Algorithms Based on Acoustic Seabed Sensing and DOA Measurements.

This article discusses various approaches to the control of autonomous underwater vehicles (AUVs) with the aid of different velocity-position estimation algorithms. Traditionally this field is considered as the area of the extended Kalman filter (EKF) application: It became a universal tool for nonlinear observation models and its use is ubiquitous. Meanwhile, the specific characteristics of underwater navigation, such as an incomplete sets of measurements, constraints on the range metering or even impossibility of range measurements, observations provided by rather specific acoustic beacons, sonar observations, and other features seriously narrow the applicability of common instruments due to a high level of uncertainty and nonlinearity. The AUV navigation system, not being able to rely on a single source of position estimation, has to take into account all available information. This leads to the necessity of various complex estimation and data fusion algorithms, which are the matter of the present article. Here we discuss some approaches to the AUV position estimation such as conditionally minimax nonlinear filtering (CMNF) and unbiased pseudo-measurement filters (UPMFs) in conjunction with velocity estimation based on the seabed profile acoustic sensing. The presented estimation algorithms serve as a basis for a locally optimal AUV motion control algorithm, which is also presented.

Research on position correction method for AUV large depth navigation based on ranging positioning

Autonomous Underwater Vehicle (AUV) is an important carrier for studying the ocean. AUV’s accurate navigation and positioning capabilities are most important in ocean exploration. Due to the limitation of communication, the limitation of cost, and the limitation of beacon use conditions, the navigation and positioning of AUV still rely on the sensor equipped with its own dead reckoning algorithm. In the deep sea, Extended Kalman Filtering(EKF), Unscented Kalman Filtering(UKF), and Adaptive Kalman Filtering(AKF) all produce error divergence in navigation and positioning. The article adopted the acoustic-based ranging and positioning method to analyze the error under different conditions, accurately compensate the error in the dead reckoning, and finally improve the navigation and positioning accuracy. Considering the controllability and observability of AUV during ranging positioning, the article proved the stability of AUV model. The article also explained the observability and selection of paths in the ranging and positioning methods to ensure the observability of AUV. The simulation results showed that compared with the dead reckoning method using Kalman filter, the method of introducing ranging location is effective and feasible. The article considered the direction and size of the actual current, and verifies the effectiveness of the method under different conditions. The article considered the divergence of the dead reckoning error and explores the optimal path size at different depths to better obtain the actual AUV motion position. The article also discussed the research that can be done in the future. In the practical application of underwater robots, the article proposed a solution to the inaccuracy of navigation and positioning in the case of large diving depth. The results of the article have practical application value.

End-to-end navigation for Autonomous Underwater Vehicle with Hybrid Recurrent Neural Networks

This paper presents a novel navigation method for Autonomous Underwater Vehicle (AUV). In respect of improving the precision of navigation, recent research mainly focused on how to reduce the system model error. However, existing optimization methods are less efficient and effective in decreasing interference of sensor deviation. Motivated by the excellent performance of deep-learning, a Hybrid Recurrent Neural Networks (Hybrid RNNs) framework is proposed to estimate the AUV position. Firstly, since the different sensors have different data frequency, this method employs unidirectional and bi-directional long short-term memory (LSTM) with multiple memory units to handle raw sensor values in a single calculation cycle. Subsequently, using the outputs of LSTMs and the time interval of the cycle above, the fully connected layers could obtain the displacements of AUV. Eventually, to verify the effectiveness of the proposed navigation algorithm, a series of evaluations have been carried out, which are based on a public dataset and real experimental data of our AUV. The evaluation results have been validated that the proposed method can reduce the interference of sensor deviation, and has better accuracy as well as fault tolerance for navigation. Meanwhile, it could also satisfy the real-time requirement.

Method to Obtain Target Speed with Underwater Acoustic Positioning System

There has been considerable recent interest in the positioning of autonomous underwater vehicles (AUVs). Underwater acoustic positioning system (UAPS) are usually used to determine position and speed of the moving target in water environment. Generally, moving target speed is estimated by derivative of the target position with traditional method. However, this approach relies heavily on accuracy of positioning. Thus, this paper presents a novel method for estimation of target speed with the UAPS only, especially with long baseline (LBL) acoustic positioning system. The method is made by estimating the Doppler frequency shift of the received signals and solving the set of linear equations. It could depend less on positioning accuracy than the traditional method. What’s more, it works well even though the moving target is subjected to acceleration or jerk. With simulations by MATLAB, it is shown that the method achieves very good performance.

Means and Methods for Hydrological–Acoustic Support of High-Precision Long-Range Positioning of Underwater Objects

The article discusses the application of methods and means of general and satellite oceanology for the high-precision acoustic positioning of autonomous underwater vehicles (AUVs) at distances of hundreds of kilometers from control stations. The authors present the results of analyzing their long-term acoustic ranging studies, which revealed the specific features of low-frequency pulsed signal propagation in different hydrological–acoustic conditions in which underwater sound channels (USCs) of different origin form. Special attention is devoted to the possibility and efficiency of using long-term oceanological observation databases to form the spatiotemporal characteristics of USCs in areas for long-range navigation support to AUVs. Additionally, the authors consider the possibilities of sea surface observation by means of satellites to provide the unit that computes the AUV coordinates with data on the integral (effective) sound speed in the near-surface sound channel (NSSC), which forms in winter. The experimental testing results on applying oceanographic technical tools in the Sea of Japan have shown that they improve the accuracy and reliability of AUV navigation support at distances of hundreds of kilometers from coastal control stations. It is been shown that in summer–autumn and winter hydrological conditions, it is possible to determine the AUV coordinates with errors not exceeding hundredths of a percent at distances of hundreds of kilometers.