Autonomous Underwater Vehicle System Research Articles

Hyperparameter Optimization for the LSTM Method of AUV Model Identification Based on Q-Learning

An accurate mathematical model is a basis for controlling and estimating the state of an Autonomous underwater vehicle (AUV) system, so how to improve its accuracy is a fundamental problem in the field of automatic control. However, AUV systems are complex, uncertain, and highly non-linear, and it is not easy to obtain through traditional modeling methods. We fit an accurate dynamic AUV model in this study using the long short-term memory (LSTM) neural network approach. As hyper-parameter values have a significant impact on LSTM performance, it is important to select the optimal combination of hyper-parameters. The present research uses the improved Q-learning reinforcement learning algorithm to achieve this aim by improving its recognition accuracy on the verification dataset. To improve the efficiency of action exploration, we improve the Q-learning algorithm and choose the optimal initial state according to the Q table in each round of learning. It can effectively avoid the ineffective exploration of the reinforcement learning agent between the poor-performing hyperparameter combinations. Finally, the experiments based on simulated or actual trial data demonstrate that the proposed model identification method can effectively predict kinematic motion data, and more importantly, the modified Q-Learning approach can optimize the network hyperparameters in the LSTM.

A Low-Complexity Underwater Acoustic Coherent Communication System for Small AUV

While underwater acoustic (UWA) communication offers a practical way to establish a wireless link with underwater vehicles, designing a UWA communication system onboard a small autonomous underwater vehicle (AUV) still poses significant challenges. As the adoption of the low-complexity, robust noncoherent communication technology is limited by low bandwidth efficiency and a low data rate, coherent UWA communication requires Doppler mitigation and channel equalization measures to achieve a relatively high data rate in a moving state. Due to the strict constraints of a small-scale AUV in terms of resources and energy consumption, it is not appropriate to use high-complexity Doppler/multipath compensation technology from the prospect of system implementation. In this paper, an efficient and low-complexity UWA differential binary phase-shift keying (DBPSK) system onboard a small AUV is proposed by simplifying the Doppler and multipath compensation. Specifically, for Doppler, the delay of the adjacent DBPSK symbols is calculated according to the Doppler estimate to facilitate delay-tuning Doppler correction. For multipath, low-complexity LMS channel equalization is incorporated with error correction coding to enable multipath mitigation. With a simple structure and low computational complexity, the proposed scheme facilitates the practical hardware implementation and system integration in the small AUV platform. The numerical simulations are conducted to assess the validity of the proposed scheme under different channel conditions and the effectiveness of the proposed scheme is further verified by two UWA communication field tests, which are performed at a practical shallow water sea and lake, respectively.

A SINS/DVL/USBL integrated navigation and positioning IoT system with multiple sources fusion and federated Kalman filter

The navigation and positioning subsystem offers important position information for an autonomous underwater vehicle (AUV) system. It plays a crucial role during the underwater exploration and operations of AUV. Many scholars research underwater navigation and positioning. Various improved methods and systems were presented. However, as the diversity of the ocean environment, the random drift of the gyroscope, error accumulation, the variety of tasks, and other negative factors, the navigation and positioning results are uncertain and incredible. The accuracy, stability, and robustness are not guaranteed, which cannot meet the increasing application requirement. Therefore, we put forward a SINS/DVL/USBL integrated navigation and positioning IoT system with multiple resource fusion and a federated Kalman filter. In this method, we first present an improved SINS/DVL combined subsystem with a filtering gain compensation strategy. So we can enhance the accuracy and stability of the navigation and position system. Secondly, we proposed a USBL positioning subsystem with the Kalman filtering acoustic signals to improve USBL positioning performance. Lastly, we present a federated Kalman filter to fuse the positioning information from the SINS/DVL combined positioning subsystem and the USBL positioning subsystem. Through the three methods, we can enhance the positioning accuracy and robustness. Comprehensive simulation results indicated the feasibility and effectiveness of the proposed SINS/DVL/USBL integrated navigation and positioning system, which provides critical reference for other positioning method, and it also offers crucial position information for AUV to achieve high accuracy and efficiency tasks.

A Novel Conformal Coil Structure Design of Wireless Power Transfer System for Autonomous Underwater Vehicles

A coil structure that is compatible with the structure of the autonomous underwater vehicles (AUVs) and preventing the rotational misalignment is proposed for stabilizing the output power of a wireless power transfer (WPT) system. The transmitting coil and the receiving coil are wound on the structure of the energy base station and the AUV in a spiral tube type, respectively. This arrangement not only guarantees a constant mutual inductance when the AUV rotates, but it also maintains the efficient transmission of energy when the receiving coil is conformal with the AUV by optimizing the size of the magnetic core and the distance between the coil and the metal structure. The performance of the proposed coil structure is experimentally evaluated by building an inductor–capacitor–capacitor series (LCC-S)-compensated WPT prototype. It was found that the system can stably deliver a 2 kW power with a dc–dc efficiency of 92.7%.

Resilient sliding mode control of multiple autonomous underwater vehicles under stochastic DoS attack

This paper is concerned with the security sliding mode-based leader-following control of multiple autonomous unmanned underwater vehicles (AUVs) system subject to stochastic DoS attacks. Firstly, a Bernoulli variable is used to describe the phenomenon of stochastic DoS attacks between controllers and actuators, and the attack probability is known for controller design. Secondly, the closed-loop system is established by taking the integral sliding mode control scheme and stochastic DoS attacks into account. Then, the conditions of stochastic stability for system are given by using the stochastic systems analysis method and the model decomposition technique. In the simulation part, a group of AUVs models is used to verify the validity of the proposed state consensus control scheme. The simulation example shows that all the state can achieve consensus even in presence of randomly launched DoS attack.

Decentralized formation trajectory tracking control of multi-AUV system with actuator saturation

This paper focuses on the three-dimensional (3-D) formation tracking of multiple autonomous underwater vehicle (multi-AUV) system in complex ocean environments. An observer-controller scheme based on decentralized estimation and control is designed. Develop an observer for each AUV to estimate the overall state of the system, then integrate it with collective task variables to produce the control inputs. It enables the multi-AUV system to perform formation trajectory tracking tasks that depend on global information. In the design stage, utilizing hyperbolic tangent function reduces the risk of actuator saturation, and the measurement noise and nonlinearities of the system are addressed. Next, under the connected undirected topology, as well as for the cases of unsaturated and saturated control inputs, the stability analysis based on the Lyapunov method proves the convergence of estimation errors and task errors. Simultaneously, sufficient conditions for the formation tracking convergence are given. Finally, the simulation results in different cases demonstrate the effectiveness of the proposed method.

Decoupling Control Scheme Bridging Frequency Tracking and DC Output Stabilizing for Wireless Charging System of Autonomous Underwater Vehicles

Decoupling Control Scheme Bridging Frequency Tracking and DC Output Stabilizing for Wireless Charging System of Autonomous Underwater Vehicles

Broadband Acoustic Communication Aided Underwater Inertial Navigation System

We present an underwater localization system for medium-sized Autonomous Underwater Vehicles (AUVs) that leverages a broadband wireless acoustic communication system for GPS-denied underwater localization. Many current acoustic localization systems assume a single line-of-sight path and use either narrow-band signals or short-duration pings for the convenience of mitigating motion-induced Doppler at the expense of the time-of-arrival (TOA) accuracy and operational flexibility. We propose a novel acoustic localization system that utilizes the aggressive signal processing embedded in underwater acoustic communication systems to resolve multi-path and Doppler distortion and finely estimate timing information using broadband communication signals. Timing and Doppler information extracted from this process is then used to estimate biases and drift from an inertial navigation system (INS) using a Bayesian framework. To demonstrate the feasibility of the system model, co-simulations are created from the MACE10 experimental data. Our results show dramatic improvement in localization accuracy, with an error of less than 120 m achieved over the 3 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 7 km distance range from the MACE 10 experiment between an AUV and a remote beacon with an acoustic communication transmission interval of 30 seconds.

An Embedded Linear Model Three-Dimensional Fuzzy PID Control System for a Bionic AUV under Wave Disturbance

This study provides a new embedded linear model (ELM) three-dimensional fuzzy PID control method for a bionic autonomous underwater vehicle (AUV), which is disturbed by ocean waves. The uncertainty of the ocean waves will make it difficult for the AUV to achieve good sailing quality, especially near the sea surface. In view of this problem, an ELM fuzzy PID controller, which adopts three-dimensional fuzzy control rules, is designed. In the ELM fuzzy PID controller, a linear model of AUV is established in order to actively perceive the effect of waves on AUV. Hence, the wave disturbance can be reflected in the control signal earlier and faster. Finally, three simulations are carried out to verify the control effect of the ELM fuzzy PID controller. An ocean wave disturbance model is established in order to simulate the force and the moment acting on the AUV. The results imply that compared with the classical PID controller and normal fuzzy PID controller, the ELM fuzzy PID controller can significantly enhance the stability of AUV and make the response faster and overshoot smaller.

Depth Control of an Oil Bladder Type Deep-Sea AUV Based on Fuzzy Adaptive Linear Active Disturbance Rejection Control

The deep-sea autonomous underwater vehicle (AUV) is equipment of vital importance for ocean exploration, monitoring, and surveying. With a variable buoyancy system (VBS), AUV can achieve rising, diving, and hovering in the water column. This paper proposes a deep-sea AUV with an oil bladder type hydraulic VBS, which controls the oil flow rate with a proportional valve. However, the implementation of accurate depth control for AUV faces various challenges due to the varying water density with depth, the non-linear feature of the hydraulic system, and the disturbance from sea flows and currents. To tackle these problems, a third-order linear active disturbance rejection controller (LADRC) and its fuzzy adaptive version were designed and implemented in MATLAB/Simulink based on the state-space function of the proposed AUV system. Compared with the conventional PID controller, the simulation results indicate that the proposed LADRC controller shows strong robustness to disturbance, with other advantages including smaller steady-state error, overshoot, settling time, and response time. Moreover, the proposed fuzzy LADRC controller could further decrease the overshoot caused by the increasing target distance. The results prove that the designed depth controllers can meet the control requirements of the proposed deep-sea AUV.

Modeling, Trajectory Analysis and Waypoint Guidance System of a Biomimetic Underwater Vehicle Based on the Flapping Performance of Its Propulsion System

The performance of biomimetic underwater vehicles directly depends on the correct design of their propulsion system and its control. These vehicles can attain highly efficient motion, hovering and thrust by properly moving part(s) of their bodies. In this article, a mathematical modeling and waypoint guidance system for a biomimetic autonomous underwater vehicle (BAUV) is proposed. The BAUV achieves sideways and dorsoventral thunniform motion by flapping its caudal fin through a parallel mechanism. Also, an analysis of the vehicle’s design is presented. A thrust analysis was performed based on the novel propulsion system. Furthermore, the vehicle’s kinematics and dynamic models were derived, where hydrodynamic equations were obtained as well. Computed models were validated using simulations where thrust and moment analysis was employed to visualize the vehicle’s performance while swimming. For the path tracking scheme, a waypoint guidance system was designed to correct the vehicle’s direction toward several positions in space. To accurately obtain waypoints, correction over the propeller’s flapping frequency and bias was employed to achieve proper thrust and orientation of the vehicle. The results from numerical simulations showed how by incorporating this novel propulsion strategy, the BAUV improved its performance when diving and maneuvering based on the dorsoventral and/or sideways configuration of its swimming mode. Furthermore, by designing proper strategies to regulate the flapping performance of its caudal fin, the BAUV followed the desired trajectories. The efficiency for the designed strategy was obtained by comparing the vehicle’s traveled distance and ideal scenarios of straight-line trajectories between targets. During simulations, the designed guidance system presented an efficiency of above 80% for navigation tasks.

Singularity avoidance adaptive output‐feedback fixed‐time consensus control for multiple autonomous underwater vehicles subject to nonlinearities

AbstractThis article investigates the singularity avoidance adaptive output‐feedback fixed‐time consensus control problem for multiple autonomous underwater vehicles (AUVs) subject to nonlinearities. A distributed state observer is designed to reconstruct the unmeasurable coupling states of each AUV system. In order to handle the unknown nonlinearities of the multi‐AUV systems, the fuzzy logic systems are adopted to approximate unknown hydrodynamic parameters. By combining adaptive fixed‐time control with backstepping technology, an adaptive singularity avoidance fixed‐time consensus control algorithm is developed, where a new error switching mechanism is designed for avoiding the singularity problem caused by the differentiation of the virtual control law. Subsequently, a singularity avoidance distributed adaptive output‐feedback fixed‐time fuzzy controller is presented, under which an auxiliary function is designed to handle the difficulty of the fixed‐time stability analysis under the output‐feedback control strategy, where two types of observer errors are needed in the designed Lyapunov function to achieve the fixed‐time stability. Then, based on the fixed‐time stability criterion, it is proved that both the consensus tracking performance and the closed‐loop stability can be guaranteed in fixed time. Finally, a simulation example verifies the effectiveness of the developed control strategy.

Learning‐based robust control methodologies under information constraints

Learning‐based robust control methodologies under information constraints

Design and Motion Performance Analysis of Turbulent AUV Measuring Platform.

The use of a multi-functional autonomous underwater vehicle (AUV) as a platform for making turbulence measurements in the ocean is developed. The layout optimization of the turbulence package and platform motion performance are limitation problems in turbulent AUV design. In this study, the computational fluid dynamics (CFD) method has been used to determine the optimized layout position and distance of the shear probe integrated into an AUV. When placed 0.8 D ahead of the AUV nose along the axis, the shear probe is not influenced by flow distortion and can contact the water body first. To analyze the motion of the turbulence AUV, the dynamic model of turbulence AUV for planar flight is obtained. Then, the mathematical equations of speed and angle of attack under steady-state motion have also been obtained. By calculating the hydrodynamic coefficients of the turbulence AUV and given system parameters, the simulation analysis has been conducted. The simulation results demonstrated that the speed of turbulent AUV is 0.5–1 m/s, and the maximum angle of attack is less than 6.5°, which meets the observation requirements of the shear probe. In addition, turbulence AUV conducted a series of sea-trials in the northern South China Sea to illustrate the validity of the design and measurement. Two continuous profiles (1000 m) with a horizontal distance of 10 km were completed, and numerous high-quality spatiotemporal turbulence data were obtained. These profiles demonstrate the superior flight performance of turbulence AUV. Analysis shows that the measured data are of high quality, with the shear spectra being in very good agreement with the Nasmyth spectrum. Dissipation rates are consistent with background shear. When shear velocity is weak, the measurement of dissipation rate is 10−10 W Kg−1. All indications are that the turbulence AUV is suitable for long-term, contiguous ocean microstructure measurements, which will provide data needed to understand the temporal and spatial variability of the turbulent processes in the oceans.

Uniform Power IPT System With Quadruple-Coil Transmitter and Crossed Dipole Receiver for Autonomous Underwater Vehicles

Autonomous underwater vehicle (AUV) is a key mobile node in the ocean observation network. However, the limited endurance capacity and limited cruising range have become the bottlenecks in the wide application of the AUVs. In order to extend cruising range, this article develops a uniform power inductive power transfer (IPT) system for AUVs. A novel magnetic coupler with a low output fluctuation, low weight of receiver and a low space occupation of the AUV is proposed in this article. The proposed magnetic structure employing a quadruple-coil transmitter and a crossed dipole receiver utilizes uniform horizontal magnetic flux to establish stable coupling against rotational and axial misalignment. An IPT circuit topology is designed and analyzed in detail, meanwhile, the phase difference of the excitation currents is optimized to achieve the power and efficiency stability versus misalignments. The proposal is analyzed, established, and tested in this article. The magnetic receiver weighs only 414&#x00A0;g. The results show that the prototype can deliver 964.7&#x00A0;W with a dc&#x2013;dc efficiency of 90.9&#x0025;. In the process of rolling dislocation from &#x2013;20&#x00B0; to 20&#x00B0; and axial dislocation from &#x2013;30&#x00A0;mm to 30&#x00A0;mm, the maximum fluctuation of output power is 12.1&#x0025; and 20.2&#x0025;, respectively.

Research on Hover Control of AUV Uncertain Stochastic Nonlinear System Based on Constructive Backstepping Control Strategy

The paper is concerned with station keeping control problem via backstepping for an autonomous underwater vehicle (AUV) systems with nonlinear continuous function. This paper is the first time to using backstepping control method for stochastic nonlinear systems. Under nonlinear growth conditions, when the AUV motion affected the driving force, resistance of ocean and the force generated by current the difficulty arising from the underwater robot system output feedback makes the station keeping problems challenging and forward-looking. There exist two problems to research the fast response time and good station keeping, respectively. There a new control method is proposed for the first time to construct a backstepping stabilizing controller. In this paper, a concept of randomness to study the station keeping control problem of output feedback of stochastic nonlinear systems, remove the original harsher growth conditions, make it meet the more general function growth conditions. In order to deal with the station error of system converges to arbitrarily small domains. Under all the states of the system meet boundedness, a coordinate transformation is proposed. A useful technical theorem is proposed in the stability analysis to show that combined with the backstepping method to cleverly construct a set of Lyapunov functions, and obtain the output controller to ensure that the system is asymptotically probabilistic in the global scope. Finally, through the ocean library in the Simulation X simulation software and the Hardware-in-the-loop simulation, the controller design results are imported into the AUV actuator model to verify the effectiveness of the controller design.

Comparison Survey of Effects of Hull on AUVs for Underwater Capacitive Wireless Power Transfer System and Underwater Inductive Wireless Power Transfer System

Underwater wireless power transfer (UWPT) system has attracted widespread attention. It has been used for power delivery for underwater equipment in the marine environment with high safety and convenience. However, the material of metal plates and the shape which will affect the high frequency alternating electromagnetic fields and the high frequency alternating electric fields for the inductive wireless power transfer (IPT) system and the capacitive wireless power transfer (CPT) system. This paper presents the effects of the hull of the autonomous underwater vehicle (AUV) on the underwater wireless power transfer system including the underwater capacitive wireless power transfer (UCWPT) system and underwater inductive wireless power transfer (UIWPT) system. The features of underwater wireless power transfer systems have been carefully studied with simulation and experimental work. The experimental water tank has been constructed with the 35‰ salinity water. The hull of AUVs has been respectively simulated and built with rectangle metal plates and curved metal plates. The original experimental data and phenomenon have been presented in this paper. The different performance of the UCWPT system and UIWPT system is provided and discussed in this paper. The comparison work with the related paper has been analyzed. This paper could be acted as the reference for designing the underwater wireless power transfer system for AUVs.

Employing NMPC scheme utilizing improved cubature Kalman filter for an AUV system

This paper deals with the diving-plane controller design problem for a class of torpedo-type Autonomous Underwater Vehicles (AUVs). Complex hydrodynamic characteristics of AUVs are truly onerous to model and control. AUVs exhibit peculiar nonlinear behaviour and have a high degree of coupling. As a result, they suffer from many practical limitations, such as a lack of hovering capability, limited payload-carrying capacity, poor pitch and roll motion stability, etc. To design an effective and reliable diving-plane control scheme for AUVs, this paper develops a new Stochastic Nonlinear Model Predictive Control (SNMPC) scheme relying on an improved Cubature Kalman Filtering (ICKF) algorithm. This scheme enables an AUV to reach the desired depth underwater and keep hovering at that depth. The ICKF algorithm estimates both the states and plant parameters to update the control law, which helps to reducethe effect of measurement noise and input disturbances. An in-depth simulation case study has been conducted in the presence of external disturbances, noises and plant-parameter variations to demonstrate the usefulness of the proposed ICKF-based NMPC scheme. The results are further analysed based on 'root mean square error' to show the controller's performance.

Real-time implementation of an online path replanner for an AUV operating in a dynamic and unexplored environment

This study describes the implementation of an online path planner in an autonomous underwater vehicle (AUV) system by using an open-source system architecture, MOOS-IvP. The path planner employed a path replanning scheme and the selective differential evolution quantum-behaved particle swarm optimization (SDEQPSO) algorithm. The implementation was based on a modular framework to ensure the robustness of the path replanner during a mission. The performance of the path replanner was evaluated and verified under stochastic processes in hardware-in-the-loop (HIL) tests, in which the replanner interacted with the onboard controllers and actuators of an Explorer AUV. The experimental results showed the path replanner can be run seamlessly with the hardware onboard an Explorer AUV in real time to generate and continuously refine a safe and feasible path for a dynamic and unexplored environment.

Adaptive dynamic event-triggered consensus control of multiple autonomous underwater vehicles

This paper addresses the dynamic event-triggered consensus problem of multiple autonomous underwater vehicles (AUVs) via the adaptive control method. First, due to limited bandwidth resources, an adaptive dynamic event-triggered mechanism (ADEM) with coefficients automatically adjusted according to the triggering errors is proposed to reduce the transmission burden. second, for the AUV model, an auxiliary variable is introduced to simplify the AUV system to a first-order model that is easy to analyse. Meanwhile, a novel adaptive dynamic event-triggered consensus control protocol is developed for each AUV to achieve consensus. Third, it is shown that, with the ADEM, the minimum interevent time between any two consecutive triggering instants can be prolonged to avoid the Zeno phenomenon for each AUV. Finally, the simulation results demonstrate the advantage of the proposed scheme.