Autonomous Underwater Vehicle System Research Articles

Research on Modeling Method of Autonomous Underwater Vehicle Based on a Physics-Informed Neural Network

Research on Modeling Method of Autonomous Underwater Vehicle Based on a Physics-Informed Neural Network

Research on model predictive control of autonomous underwater vehicle based on physics informed neural network modeling

In the rapidly evolving field of Autonomous Underwater Vehicles (AUVs), achieving precise control remains a critical endeavor. This study presents a pioneering integration of Model Predictive Control (MPC) with a Physics-Informed Neural Network (PINN), aiming to enhance control system precision and operational efficiency in AUVs. The efficacy of MPC lies in its adept handling of the intricate constraints and inherent nonlinear dynamics intrinsic to AUV systems. Concurrently, the PINN architecture incorporates the fundamental physical laws represented by Partial Differential Equations (PDEs), augmenting the predictive fidelity of the system. Firstly, this research implements the novel PINN-enhanced MPC framework for trajectory tracking and conducts a comparative evaluation against adaptive proportional-integral-derivative (PID) and Gaussian-process-based MPC controllers. This comparative analysis elucidates the advancements in control mechanisms attributable to the PINN integration. Furthermore, this study meticulously assesses the PINN-MPC's proficiency in navigating through static and dynamic obstacles within three-dimensional marine environments, a critical capability for AUV operations. Through extensive and meticulous simulations, the proposed approach demonstrates notable progress in overcoming environmental challenges and executing intricate operational tasks, such as obstacle avoidance, with heightened efficiency and dexterity. This research constitutes a substantial contribution to the theoretical advancement and elucidation of control systems in the AUV domain, bearing profound practical implications. It lays the foundation for the development of increasingly sophisticated, advanced, and reliable AUV missions, signifying a crucial advancement in the realms of underwater exploration and operational technology.

Segmented hybrid event‐triggered control for underactuated autonomous underwater vehicles with an asymmetrical prescribed performance constraint

AbstractIn this technical article, the trajectory‐tracking problem of event‐based adaptive prescribed performance control for underactuated autonomous underwater vehicles (AUVs) is considered. The primary innovation of this article is the proposal of a segmented event‐triggered mechanism (SETM) that incorporates preselected convergence time. This mechanism allows for the regulation of communication frequency in the control channel (controller‐to‐actuator) according to the dynamic characteristics of the AUV system at different stages. In addition to presenting new design scheme based on SETM, an enhanced vision known as segmented hybrid event‐triggered mechanism (SHETM) is introduced. Notably, the minimum and maximum triggering intervals (MITI and MATI) for these two ETMs can be calculated from the corresponding resettable dynamic variables presented in the trigger conditions. Subsequently, by utilizing the proposed asymmetrical prescribed performance control (APPC) strategy, the system's output tracking error behaviors in both transient and steady‐state stages can be qualitatively predetermined through design parameters within the boundary function. Moreover, the minimum learning parameter (MLP) based RBFNN adaptive control law is developed to counteract the effects of model uncertainties and ocean current perturbations. Finally, rigorous theoretical analysis and simulation results confirm the viability of the proposed scheme.

Fuzzy neural network adaptive AUV control based on FTHGO

ABSTRACT A fuzzy radial basis function neural network (Fuzzy RBFNN) adaptive control scheme, based on fixed-time high gain state observer (FTHGO), is proposed to address the unpredictability of real-time state and composite interference in the trajectory tracking of the fully driven Autonomous Underwater Vehicle (AUV), ensuring fixed-time system convergence regardless of initial conditions. Firstly, a fixed-time backstepping controller is designed and a first-order fixed-time filter is introduced to tackle the differential explosion issue. Secondly, an FTHGO is developed to observe the real-time states of the AUV without assuming global known state signal. Then, the composite interference in the AUV system is effectively compensated by integrating the Fuzzy RBFNN technique. Finally, the fixed-time stability of the entire closed-loop system is proven utilising the Lyapunov stability theory. The effectiveness of the proposed algorithm is proved by the simulation experiment.

Imitation learning from imperfect demonstrations for AUV path tracking and obstacle avoidance

Autonomous underwater vehicle (AUV) is widely used for complex underwater tasks such as seafloor exploration. In recent years, deep reinforcement learning (DRL) has been introduced to the AUV control due to its capability to improve the autonomy of AUV. However, it is usually very difficult to design an effective reward function for the DRL methods. Generative adversarial imitation learning (GAIL) can allow AUVs to learn control policies from expert demonstrations instead of pre-defined reward functions, but suffers from the deficiency of requiring optimal expert demonstrations and not surpassing the provided demonstrations. This paper builds upon the GAIL algorithm for AUV learning control policies from expert demonstrations. We proposed an importance reweighting generative adversarial imitation learning (WGAIL) algorithm by using confidence scores to indicate the optimality of the demonstrated trajectories, which can facilitate AUVs to learn control policies from expert demonstrations of different levels. Our experimental results on a simulated AUV system modeling Sailfish 210 of our lab in the Gazebo simulation environment show that an AUV trained via WGAIL can achieve a better performance than the one trained via GAIL with different levels of expert sub-optimal demonstrations. Moreover, control policies trained via WGAIL in simple tasks can generalize better to complex tasks than those trained via GAIL, greatly extending the applicability of the AUV learning from expert demonstrations.

Design and extensibility analysis of a variable buoyancy system for small autonomous underwater vehicles

PurposeA switching depth controller based on a variable buoyancy system (VBS) is proposed to improve the performance of small autonomous underwater vehicles (AUVs). First, the requirements of VBS for small AUVs are analyzed. Second, a modular VBS with high extensibility and easy integration is proposed based on the concepts of generality and interchangeability. Subsequently, a depth-switching controller is proposed based on the modular VBS, which combines the best features of the linear active disturbance rejection controller and the nonlinear active disturbance rejection controller.Design/methodology/approachThe controller design and endurance of tiny AUVs are challenging because of their low environmental adaptation, limited energy resources and nonlinear dynamics. Traditional and single linear controllers cannot solve these problems efficiently. Although the VBS can improve the endurance of AUVs, the current VBS is not extensible for small AUVs in terms of the differences in individuals and operating environments.FindingsThe switching controller’s performance was examined using simulation with water flow and external disturbances, and the controller’s performance was compared in pool experiments. The results show that switching controllers have greater effectiveness, disturbance rejection capability and robustness even in the face of various disturbances.Practical implicationsA high degree of standardization and integration of VBS significantly enhances the performance of small AUVs. This will help expand the market for small AUV applications.Originality/valueThis solution improves the extensibility of the VBS, making it easier to integrate into different models of small AUVs. The device enhances the endurance and maneuverability of the small AUVs by adjusting buoyancy and center of gravity for low-power hovering and pitch angle control.

Robust model predictive control for perturbed nonlinear systems via an error differential-integral based event-triggered approach

This paper aims to establish a new event-triggered model predictive control (MPC) strategy for perturbed nonlinear systems working in a networked environment, which can effectively save the computation and communication resources while ensuring control performance. The core of the framework is a new event-triggered mechanism, which is built by combining the differential and integral (D-I) information of the error between the optimal state and the actual state in a pre-specified time horizon. Based on such a triggering mechanism, a D-I based event-triggered robust MPC algorithm is proposed to stabilise the system and reduce the computation/communication resource consumption. In addition, sufficient conditions to ensure the feasibility and stability of the proposed MPC algorithm and avoid Zeno behaviour are obtained through rigorous theoretical analysis. Finally, the proposed control framework is implemented in the nonlinear cart-damper-spring and autonomous underwater vehicle systems to verify its effectiveness.

High-Power-Density Wireless Power Transfer System for Autonomous Underwater Vehicle Based on a Variable Ring-Shaped Magnetic Coupler

High-Power-Density Wireless Power Transfer System for Autonomous Underwater Vehicle Based on a Variable Ring-Shaped Magnetic Coupler

Addressing Actuator Saturation during Fault Compensation in Model-Based Underwater Vehicle Control

Robust control systems are a necessity for autonomous underwater vehicle (AUV) systems due to the challenges they face during operation. Many AUV control-design methods have been developed for different actuator configurations, with robustness against model parameter uncertainties, environmental disturbances, and system faults. Actuator faults can reduce the physical capabilities of a system, which can be compensated for through control re-allocation. However, the increased control allocation to the remaining actuators may cause actuator saturation and reduce controller performance. In this work, we present a depth-pitch model-based nonlinear control law that directly considers actuator saturation, and a fault-tolerant control allocation method for a hybrid AUV actuator configuration. Two types of actuator faults are considered for an underwater vehicle with a hybrid actuator configuration. The proposed controller is implemented in a simulated system, and its trajectory tracking performance is compared with a baseline system without fault or saturation tolerance. To determine the utility of the proposed saturation and fault tolerance control methods, the tracking performance in these simulations is quantified in terms of the settling time, post-fault peak values, and root mean square of the depth and pitch errors.

Model-Based Digital Overall Integrated Design Method of AUVs

Autonomous underwater vehicles (AUVs) have the characteristics of a high performance, a complex coupling mechanism, a compact, complex system composition, as well as high requirements for design constraints, quality, and reliability. In the traditional overall design process, numerous design tools and software programs are used, which results in poor model data sharing, a lack of uniqueness and synchronization between system levels, and difficulty in process tracing. Moreover, it is challenging to meet the technical requirements for close collaboration and rapid iteration of multiple positions. To address the aforementioned limitations, this study proposes a digital overall integrated design method for the design and simulation integration of AUVs and defines a unified architecture and interface for system-level design simulation models, thus solving the interoperability and consistency problems in multiple tools and models. In addition, a model-based AUV system integration design verification method that combines different processes, specifications, and models is designed, and software similar to Cameo, which can provide technical means for system-level integrated design and achieve rapid modeling and simulation verification based on system design solutions, is developed. Finally, a practical system design is conducted by taking specific AUV equipment as a research object, and the proposed methods are compared with traditional methods to prove the improvement effect of the technical route on the equipment and development efficiency.

Parameter identification and model prediction path following control of underactuated AUV: Methodology and experimental verification

This paper explores the integrated optimal control scheme from the identification of underactuated autonomous underwater vehicle (AUV) system dynamics model parameters to the application of Model Predictive Control (MPC) technology in underactuated AUV motion control, and presents the simulation and field test results. First, the AUV kinematics and dynamics models are introduced to represent the horizontal plane motion characteristics. Based on Computational Fluid Dynamics (CFD) numerical simulation and overset mesh technology, AUV plane motion is simulated to determine the unknown hydrodynamic coefficients in the model, and the accuracy of the mathematical model is validated by comparing the maneuverability simulation and field test results. After that, an adaptive line-of-sight (ALOS) guiding algorithm with exponentially variable forward distance is utilized in the guidance layer to reconcile the rapidity and stability of tracking. The path following problem is formulated as an MPC optimization problem that takes into account multiple realistic constraints and then converted into a standard convex quadratic programming structure, permitting for online real-time optimization. Simulation and field test results indicate that the control algorithm proposed in this paper provides a more effective control strategy than the traditional LOS+PID controller in tracking effect and robustness.

Impulsive consensus tracking for leader-following multi-AUV system with sampled information

In this paper, impulsive consensus tracking for a leader-following multiple autonomous underwater vehicles (multi-AUV) system with sampled information is studied. Two novel impulsive consensus protocols are proposed to address both the multi-AUV system recovery problem with the static leader and the formation tracking problem with the dynamic leader. It is worth noting that the proposed control protocols do not require continuous information exchange between AUVs. For the static leader case, each AUV only needs to exchange position information with its neighbors at sampling instants. For the dynamic leader case, only partial follower AUVs can obtain position information of the leader AUV at sampling instants. By using the stability theory of impulsive systems and algebraic graph theory, sufficient conditions to guarantee the leader-following consensus of the multi-AUV system are obtained. Furthermore, both the proposed algorithms can save the bandwidth of underwater acoustic communication and improve the robustness of the system. Finally, two numerical simulations are provided to demonstrate the effectiveness of the proposed theoretical analysis.

Cooperative Formation Control for Multiple AUVs With Intermittent Underwater Acoustic Communication in IoUT

Autonomous Underwater Vehicle (AUV) system has played an important role in complex Internet of Underwater Things (IoUT). As we know, single AUV is inefficient in collecting data in large-scale IoUT. In order to improve the timeliness of data, this paper uses multiple AUVs with specific formation shape to collect sensory data. However, the intermittent and unreliable characteristics of underwater acoustic communication between AUVs seriously affects the performance of formation control. To solve this issue, this paper mainly investigates formation control problem of leader-follower structured AUVs with state prediction estimation under the condition of unreliable underwater acoustic channel. Firstly, a novel formation control law derived from backstepping sliding mode method is proposed, and then a suitable Lyapunov functional is constructed to prove sufficient stability conditions. Secondly, Gaussian prediction model considering time delay and packet dropout has been designed to estimate the intermittent communication channel. Moreover, a new metric named formation uniform degree (FUD) is proposed to measure the degree of queue uniformity in a quantitative manner. Finally, extensive simulation results compared with traditional methods based on ideal channel model demonstrate the effectiveness of proposed formation control method.

Single neural network-based asymptotic adaptive control for an autonomous underwater vehicle with uncertain dynamics

This paper focuses on the adaptive asymptotic tracking control problem for an autonomous underwater vehicle (AUV) with un-modeled dynamics and unknown input saturation by combining the backstepping control strategy and the neural network (NN) method. In our controller, a novel single neural network-based backstepping control method is proposed to address the uncertain problem, and the input saturation issue is overcome in virtue of a hyperbolic tangent function. The approximation error of the neural network is also compensated by a new adaptive mechanism in order to achieve the zero-error regulation. Furthermore, the nonlinear transformation is incorporated into the backstepping-based framework to improve the AUV performance. And then, the performance analysis illustrates that the designed controller can realize the asymptotic stability of the AUV system. Finally, the effectiveness of our control strategy is validated through simulation results.

Improving the Misalignment Tolerance of Wireless Power Transfer System for AUV with Solenoid-Dual Combined Planar Magnetic Coupler

In order to solve the problem of power transmission efficiency reduction resulting from misalignment in the Wireless Power Transfer (WPT) system for Autonomous Underwater Vehicle (AUVs), a novel coupling structure with strong tolerance to misalignment is proposed. A solenoid coil is selected as the transmitting coil, and the receiving coil is composed of dual combined planar coils. The WPT system can still maintain stable output under uncertain axial misalignments for AUVs. The magnetic field distribution of the proposed magnetic coupling structure is analyzed theoretically, and the distance between the coils in the dual combined planar receiving coil is optimized. The theoretical analysis shows that the proposed solenoid-dual combined planar coils coupling structure can effectively maintain a stable mutual inductance between the transmitting coil and receiving coil under different axial misalignments compared with solenoid-unipolar planar coil coupling structure. An S-S resonant compensated WPT experimental prototype is built to verify the output characteristics of the proposed magnetic coupling structure. Compared to the magnetic coupler with the unipolar planar coil, it is validated by experiment that the proposed magnetic coupler substantially enhances the stability of power transmission efficiency and output power when axial misalignment occurs. The power transmission efficiency decreases by 6.74% when axial misalignment increases from 0 to 40 mm in saltwater. Meanwhile, the variation of output power is less than 4.15%.

Fixed-time velocity-free safe formation control of AUVs with actuator saturation and unknown disturbances

This paper designs a fixed-time formation control law for multiple autonomous underwater vehicle (AUV) system (MAS) subjected to unmeasurable velocities, actuator saturation and time-varying disturbances. To address these challenges, the actuator saturation and time-varying disturbances are initially integrated into lumped disturbances, the initial step is to integrate actuator saturation and time-varying disturbances into lumped disturbances, followed by designing a fixed-time extended state observer (FTESO) to estimate the unavailable velocities and the lumped disturbances in fixed time. Moreover, a nonlinear filter is also utilized to eliminate the problem of computational explosion that arises due to derivatives in the controller design process. Additionally, a tan-type barrier Lyapunov function (TT-BLF) is presented to constrain the tracking errors within a predetermined time-varying constraint function. Then, a novel fixed-time formation control algorithm based on FTESO and TT-BLF is further designed to ensure that the formation tracking errors converge to a small neighborhood near origin in fixed time, and the fast formation task can be completed within a fixed time. Finally, the simulation experiments verify the effectiveness of the proposed controller.

EXPERIMENTAL STUDY OF A VARIABLE BUOYANCY SYSTEM FOR LOW DEPTH OPERATION

Autonomous Underwater Vehicles (AUVs) are used for the underwater survey both in coastal areas and deep sea without any human intervention during their operations. However, high energy consumptions required by the thrusters of the AUV’s adversely affect their performance such as range and endurance, etc. Herein, we have presented a novel design and development of a standalone variable buoyancy system for autonomous underwater vehicle and investigated the numerical and experimental analysis of Variable Buoyancy System (VBS) in standalone mode. Design idea is based upon the ‘Pump Driven Variable Buoyancy System (PDVBS)’ using ‘Water Hydraulic Variable Buoyancy System (WHVBS)’ method to control the buoyancy using a diaphragm type positive displacement pump (PDP) with capacity of the maximum buoyancy change rate of 4.5 kg/min. Detail experimental and simulation performance of the developed VBS has been investigated. Developed VBS is tested for maximum depth of 5 m and compared the performance of the experimental and simulation results. Presented results demonstrate that designed VBS is effective in changing buoyancy and controlling heave velocities and that will result to achieve the higher range and endurance and better performance in rescue/attack operations.

Research on the Control Problem of Autonomous Underwater Vehicles Based on Strongly Coupled Radial Basis Function Conditions

This paper addresses tracking control problems for autonomous underwater vehicle (AUV) systems with coupled nonlinear functions. For the first time, the radial basis function (RBF) is applied to the model reference adaptive control system, and the vehicle horizontal plane model is proposed. When the AUV movement is affected by the driving force, ocean resistance, and the force generated by the water current, the expected output of the AUV’s system is difficult to meet the expectations, making the AUV trajectory tracking problems challenging. There are two main options for finding suitable controllers for AUVs. The first is making the AUV model achieve better stability using a more complex controller. The second is the simpler controller structure, which can ensure faster system feedback. The RBF and model reference adaptive control (MEAC) system are combined to increase the number of hidden layers, increasing the AUV tracking stability. Because the embedded computing module of an AUV is a bit limited, 31 hidden layers are chosen to simplify the controller structures. A couple of Lyapunov functions are designed for the expected surge and sway velocities, and the vehicle tracking error gradually converges to (0,0). The controller design results are imported into the AUV actuator model by software, and after 0.64 s, the AUV tracking error is less than 1%. At last, the vehicle tracking experiments were carried out, showing that after 0.5 s, the AUV tracking error was less than 1%.

Feedback error-state Kalman filter with time-delay compensation for hydroacoustic-aided inertial navigation of underwater vehicles

This article is intended as a tutorial to assist engineers who want to develop and implement low-cost underwater vehicle inertial navigation systems (INS) aided by time-delayed hydroacoustic position measurements. A discrete-time unit quaternion error-state Kalman filter (ESKF) is used for sensor fusion. The ESKF is implemented as a feedback algorithm with reset functionality. This is motivated by the need for long-endurance autonomous underwater vehicles (AUVs). Proprietary navigation systems do not allow users to add more measurement equations to the code if additional sensors are available. However, the open-source filter architecture presented in the article provides for this. The article also aims to make in-house development of strapdown INS accessible and affordable for vendors of low-cost AUV systems. Finally, a case study of an AUV with a standard sensor suite is included to demonstrate the performance of the ESKF aided by time-delayed position measurements.

Nonlinear model predictive control for hydrobatics: Experiments with an underactuated AUV

AbstractHydrobatic autonomous underwater vehicles (AUVs) can be efficient in range and speed, as well as agile in maneuvering. They can be beneficial in scenarios such as obstacle avoidance, inspections, docking, and under‐ice operations. However, such AUVs are underactuated systems—this means exploiting the system dynamics is key to achieving elegant hydrobatic maneuvers with minimum controls. This paper explores the use of model predictive control (MPC) techniques to control underactuated AUVs in hydrobatic maneuvers and presents new simulation and experimental results with the small and hydrobatic SAM AUV. Simulations are performed using nonlinear model predictive control (NMPC) on the full AUV system to provide optimal control policies for several hydrobatic maneuvers in Matlab/Simulink. For implementation on AUV hardware in robot operating system, a linear time varying MPC (LTV‐MPC) is derived from the nonlinear model to enable real‐time control. In simulations, NMPC and LTV‐MPC shows promising results to offer much more efficient control strategies than what can be obtained with PID and linear quadratic regulator based controllers in terms of rise‐time, overshoot, steady‐state error, and robustness. The LTV‐MPC shows satisfactory real‐time performance in experimental validation. The paper further also demonstrates experimentally that LTV‐MPC can be run real‐time on the AUV in performing hydrobatic maneouvers.