Autonomous Underwater Vehicle Motion Research Articles

Prediction-Based Submarine Cable-Tracking Strategy for Autonomous Underwater Vehicles with Side-Scan Sonar

This study investigates the tracking of underwater cables using autonomous underwater vehicles (AUVs) equipped with side-scan sonar (SSS). AUV motion stability is crucial for effective SSS imaging, which is essential for continuous cable tracking. Traditional methods that derive AUV guidance rates directly from measured cable states often cause unnecessary jitter when imaging, complicating accurate detection. To address this, we propose a non-myopic receding-horizon optimization (RHO) strategy designed to maximize cable imaging quality while considering AUV maneuvering constraints. This strategy identifies the optimal heading decision sequence over a future horizon, ensuring stable and efficient cable tracking. We also employ a long short-term memory (LSTM) network to predict future cable states, further minimizing AUV motion instability during abrupt path changes. Given the computational limitations of AUVs, we have developed an efficient decision-making framework that can execute resource-intensive algorithms in real time. Finally, the robustness and effectiveness of the proposed algorithm were validated through comparative experiments. The results demonstrate that the proposed method outperforms existing methods in key metrics such as cable-tracking accuracy and AUV motion stability. This ensures that the AUV can acquire high-quality acoustic images of the submarine cable in an optimal state, enhancing the continuity and reliability of cable-tracking tasks.

Deep Learning-Based Nonparametric Identification and Path Planning for Autonomous Underwater Vehicles

As the nonlinear and coupling characteristics of autonomous underwater vehicles (AUVs) are the challenges for motion modeling, the nonparametric identification method is proposed based on dung beetle optimization (DBO) and deep temporal convolutional networks (DTCNs). First, the improved wavelet threshold is utilized to select the optimal threshold and wavelet basis functions, and the raw model test data are denoising. Second, the bidirectional temporal convolutional networks, the bidirectional gated recurrent unit, and the attention mechanism are used to achieve the nonlinear nonparametric model of the AUV motion. And the hyperparameters are optimized by the DBO. Finally, the lazy-search-based path planning and the line-of-sight-based path following control are used for the proposed AUV model. The simulation shows that the prediction accuracy of the DBO-DTCN is better than other artificial intelligence methods and mechanical models, and the path following of AUV is feasible. The methods proposed in this paper can provide an effective strategy for AUV modeling, searching, and rescue cruising.

Оценка безопасности движения большого автономного необитаемого подводного аппарата

The problems of ensuring the safe motion of a large autonomous underwater vehicle (AUV) when it passes through sections with different environmental conditions are considered by the example of the development of the Northern Sea Route. An analysis was made of the influence of various environmental conditions - open and coastal water, fast ice and ice conditions - on the safety of the operation of a large AUV. An approach is proposed to assess the vehicle safety in various environments using a dynamic Bayesian network and conditional probability tables. To test the algorithms for controlling the the vehicle motion and the vehicle itself, a digital test site was developed in the form of a stand for simulating the functioning of the AUV. The development of digital twins in the form of software simulators of the vehicle devices and mechanisms made it possible to test control algorithms on the simulation stand both during normal operation of its systems and in the event of malfunctions due to functioning in various environments. The results obtained on a simulation stand for a large AUV operating on the farthest and most complicated part of the Northern Sea Route - the Vilkitski Strait, helped us to assess the safety of the vehicle operation and outline the ways to improve the safety by upgrading the algorithms for controlling the AUV motion in difficult environmental conditions.

Distributed short-term predictive control for AUV clusters in underwater cooperative hunting tasks

A distributed short-term predictive control method is proposed to be applied to autonomous underwater vehicle (AUV) clusters for underwater cooperative hunting tasks. To support AUV clusters in unknown underwater dynamic environments, the constraints of information acquisition, AUV motion constraints, collision avoidance, and smoothness requirements of motion paths in the tasks are considered. First, a distributed multi-constraint optimization model including target attraction, interactions between AUVs, continuous obstacle avoidance, and control effort is proposed. Effective information between AUVs is extended under limited information conditions. Second, each AUV solves the distributed optimization problem and determines the desired trajectory in real time using information from the prediction horizon. In the simulation experiments, the proposed method is demonstrated to provide at least 12.19%, 11.08%, and 79.89% improvement in terms of task completion time, energy consumption, and path smoothing, respectively, when compared to other methods under the same information conditions. The robustness of the proposed method under different noise conditions is verified by positioning noise experiments, and the task can still be accomplished even if the noise level reaches 75% of the safe distance. The adaptability of the proposed method is demonstrated by simulations in different environments.

Gaussian Process-Based Model Predictive Control for Autonomous Underwater Vehicles

Traditional MPC algorithms, assuming constant values, suffer from performance degradation caused by model mismatch. This paper addresses the enhancement of predictability in Autonomous Underwater Vehicles (AUVs) under uncertain disturbances and unknown system dynamics through the design of Model Predictive Controllers (MPCs). We propose a hybrid model that integrates a first-principles nominal model with a learning-based model utilizing Gaussian Processes (GPs). The algorithm addresses the problem of model mismatch in AUV motion control by constructing a precise GP model, which captures the dynamic characteristics of the process through the collection and learning of deviations between the reference model and the controlled system. Additionally, the GP model transforms stochastic constraints into deterministic convex constraints, enhancing safety guarantees in complex and challenging environments. The effectiveness of the proposed algorithm is demonstrated through two simulation examples.

Nonlinear dynamics of novel flight-style autonomous underwater vehicle with bow wings, Part I: ASE and CFD based estimations of hydrodynamic coefficients, Part II: Nonlinear dynamic modeling and experimental validations

Accurate dynamic modeling is essential for precise prediction of six degrees-of-freedom (6-DOF) motion and model-based controller design of an autonomous underwater vehicle (AUV). The accuracy of dynamic model of an AUV largely depends upon the precise estimation of hydrodynamic coefficients. Accordingly, to establish the dynamic model based on ASE-estimated hydrodynamic coefficients of the novel flight-style AUV and experimental validations, the study is presented in two parts (Part I: ASE and CFD based estimations of hydrodynamic coefficients and Part II: Nonlinear dynamic modeling and experimental validations).Part I: In this part complete set of nonlinear hydrodynamic coefficients including, added mass, drag, and lift forces and moment coefficients are estimated using ASE technique, which is specifically developed to accurately comprehend the novel AUV design including, AUV hull, fixed wings, control fins, and appendages. Additionally, an improved ASE approach is also proposed to estimate cross flow drag force coefficients. In proposed improved ASE technique, (Cdc) in mathematical formulation is taken from the experimental results of 3D flow past over circular cylinder instead of 2D, as followed previously to estimate the nonlinear cross-flow drag force and moment coefficients (Yvv,Zww,Mww,Nvv,Yrr,Zqq,Mqq&Nrr). The proposed ASE technique is verified and validated in two stages: first, by comparing the ASE-estimated results with CFD-based estimations, and second, by investigating the 6-DOF motion response of the AUV. When compared ASE-estimations with the CFD results for the cross-flow drag force and moment coefficients, the proposed ASE technique has shown a significant improvement (approximately 20%) over the previously employed ASE method. The ASE-estimated results are validated through 6-DOF motion response of AUV during free-running underwater experiments, provided in ‘Part II’. Overall, the proposed ASE technique is considered more effective, direct, and less costly in terms of time and computational efforts, compared to CFD-based or experimental-based estimations of hydrodynamic coefficients of AUVs, particularly torpedo-shaped AUVs.Part II: This part presents a nonlinear dynamic model for a newly designed torpedo-shaped flight-style AUV having complex bow and stern fixed wings and control fins configuration. The model includes precise mathematical formulations to accurately represent the physics of the AUV and underwater environment in terms of hydrodynamic derivatives such as added mass, drag, and lift forces and moment coefficients. These coefficients have been estimated using an ASE method provided in ‘Part I’. The 6-DOF motion response of the AUV has been simulated in both horizontal and vertical planes which includes, zigzag yaw, circle, zigzag pitch, and spiral maneuvers. The lift generated by the bow and stern control fins has been investigated both separately and collectively, especially during complex spiral ascending maneuvers. Moreover, improved ASE technique for cross flow drag coefficients has also been validated through 6-DOF free-running underwater experiments of AUV and insights on impact of cross flow drag coefficients on 6-DOF motion response of AUV has also been provided. Overall, the comparison between the simulated AUV motion and free-running underwater experiments demonstrated consistency, thereby validating the accuracy of the nonlinear dynamic modeling, ASE-based hydrodynamic coefficient predictions, and effectiveness of the newly designed flight-style AUV for underwater operations.

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.

Research on Practical Path Tracking Control of Autonomous Underwater Vehicle Based on Constructive Dynamic Gain Controller

In this study, the stochastic nonlinear system-based trajectory tracking control problem of an autonomous underwater vehicle (AUV) is studied. We investigate the time-varying gain adaptive control method to find possible approaches to reduce the excessive computational burden. Enhanced adaptive algorithms are devised by considering the dynamic characteristics of AUV motion. By transforming the original controller design problems into parameter selection problems and subsequently solving them using the functional time-varying observer technical theorem, we can achieve optimal control performance. The control system is shown to constrain system state error due to stochastic disturbances within arbitrarily small domains. A coordinate transformation is proposed for all system states to meet boundedness conditions. We show that the closed-loop stability is confirmed, the system is asymptotically probabilistically stable, and contraction limits given in the stability analysis may be used to certify the convergence of the AUV trajectory errors. A large number of simulation studies using an underwater vehicle model have proved the effectiveness and robustness of the proposed approach. A real-time, time-varying gain constructive control strategy is further developed for the hardware-in-the-loop simulation; the effectiveness of the controller design is confirmed by introducing the controller into the AUV actuator model.

Underwater Localization of AUVs in Motion Using Two-Way Travel Time Measurements With Unknown Sound Velocity

For an autonomous underwater vehicle (AUV) underwater localization system based on acoustic two-way travel time measurements, the motion of the AUV during the interrogation-reception time interval, unknown underwater sound velocity, and beacon calibration error affect the performance of the positioning solution. Ignoring these factors significantly deteriorates the performance of the localization system. This paper focuses on the localization problem of AUV in motion with an unknown sound velocity and beacon calibration error. The Cramér–Rao lower bound of the concerned localization problem is first derived as the performance bound of an unbiased estimator. Next, through multi-stage processing, we design a closed-form solution that can attain the corresponding performance bound under small measurement noise conditions. Furthermore, considering that the AUV motion velocity is typically much lower than the sound velocity in practical applications, a simpler and more efficient simplified closed-form solution is proposed, which can guarantee localization performance under the condition that the AUV motion speed is low, as well as small measurement noise. Finally, the theoretical performance and superiority of the proposed solutions were verified through numerical simulation.

Evaluation of autonomous underwater vehicle motion trajectory optimization algorithms

The operation of autonomous underwater vehicles (AUVs) relies on three major motions: yaw, theta, and depth, each requiring its own set of proportional integral derivative (PID) controller gain criteria. Thus, different issues arise, including the availability of multiple criteria for optimization algorithm evaluation, the importance of these criteria, the trade-off between criterion performance, and criterion critical values. These issues make the evaluation of optimization algorithms for AUV motion control a complex multicriteria decision-making (MCDM) problem. This research proposes a novel selection-integrated approach for AUV optimization algorithms in different motions using two MCDM methods: fuzzy-weighted zero-inconsistency (FWZIC) for criteria weighting and fuzzy decision by opinion score method (FDOSM) for optimization algorithm selection. The approach comprises three main phases: development of PID, FWZIC-based criteria weighting, and FDOSM-based optimization algorithm selection. In all three motion types – “depth”, “yaw”, and “theta” – Kp_θ had the highest weight value, with respective weights of 0.143, 0.149, and 0.142. In contrast, Ki_depth consistently received the lowest weight value across all three motion types, with respective weights of 0.057, 0.0598, and 0.057. Regarding the “depth” motion, the Archimedes optimization algorithm (AOA) was the highest-performing alternative with a score of 0.077, while the eagle strategy–particle swarm optimization algorithm was the worst alternative with a score of 0.022. The Cuckoo optimization algorithm was identified as the best alternative for the “yaw” motion with a score of 0.072, whereas black hole optimization had the lowest score of 0.036. The best alternative for the “theta” motion was AOA with a score of 0.067, and the worst algorithm was sunflower optimization with a score of 0.028. This developed approach was evaluated based on systematic ranking and sensitivity analysis, which confirmed the validity of the proposed work.

Comprehensive Ocean Information-Enabled AUV Motion Planning Based on Reinforcement Learning

Motion planning based on the reinforcement learning algorithms of the autonomous underwater vehicle (AUV) has shown great potential. Motion planning algorithms are primarily utilized for path planning and trajectory-tracking. However, prior studies have been confronted with some limitations. The time-varying ocean current affects algorithmic sampling and AUV motion and then leads to an overestimation error during path planning. In addition, the ocean current makes it easy to fall into local optima during trajectory planning. To address these problems, this paper presents a reinforcement learning-based motion planning algorithm with comprehensive ocean information (RLBMPA-COI). First, we introduce real ocean data to construct a time-varying ocean current motion model. Then, comprehensive ocean information and AUV motion position are introduced, and the objective function is optimized in the state-action value network to reduce overestimation errors. Finally, state transfer and reward functions are designed based on real ocean current data to achieve multi-objective path planning and adaptive event triggering in trajectorytracking to improve robustness and adaptability. The numerical simulation results show that the proposed algorithm has a better path planning ability and a more robust trajectory-tracking effect than those of traditional reinforcement learning algorithms.

Autonomous underwater vehicle motion state recognition and control pattern mining

Self-awareness of its own state during autonomous operation is critical for Autonomous Underwater Vehicles (AUVs) to execute tasks and monitor their health. Automated data analysis methods appear to be the most appropriate tool for attempting to understand and elucidate the motion states of AUVs. However, research scholars often focus on the state recognition of small AUVs used for shallow water detection, and the relevant conclusions cannot be directly applied to deep-sea AUVs. As a representative deep-sea AUV, Qianlong-3 is studied in this paper. In this study, a data-driven approach was employed to recognize the motion states and control modes of the Qianlong-3 AUV while retaining the original data noise. First, the class imbalance problem in the data was addressed, and then the data features were enhanced through a sliding window statistical method. By comparing the differences in the accuracy of motion state recognition after class imbalance processing using different supervised learning methods, the Random Forest (RF) algorithm was found to be the most suitable classification algorithm. In addition, the Toeplitz Inverse Covariance-Based Clustering (TICC) algorithm was used to recognize and mine the motion states and control modes of the AUV. The TICC algorithm was effective in extracting latent information from the actual data. Finally, through correlation analysis, the three motion states of the AUV were discussed, and the control modes for each of these states were determined. Overall, this study demonstrates the feasibility of relevant algorithms in practical deep-sea applications for state recognition and control mode mining. This provides valuable reference and experience for the development of future deep-sea AUV.

A LSSVR Interactive Network for AUV Motion Control

In view of the requirements on control precision of autonomous underwater vehicles (AUVs) in different operations, the improvement of AUV motion control accuracy is the focus of this paper. In regard to the unsatisfying robustness of traditional control methods, an interactive network based on Least Square Support Vector Regression (LSSVR) is therefore put forward. The network completed the identification of the strong nonlinear AUV dynamic characteristics based on the LSSVR theory and by virtue of the interactions between the offline and online modules, it achieved offline design and online optimization of the AUV control law. In addition to contrastive numerical simulations and sea trials with the classic S-plane method in AUV velocity and heading control, the LSSVR network was also tested in path following and long-range cruise. The precision and robustness and of the proposed network were verified by the high-accuracy control results of the aforesaid simulations and trials. The network can be of practical use in AUV control especially under unfamiliar water conditions with access to a limited number of control samples or little information of the operation site.

Data-Driven Fault Detection of AUV Rudder System: A Mixture Model Approach

Based on data-driven and mixed models, this study proposes a fault detection method for autonomous underwater vehicle (AUV) rudder systems. The proposed method can effectively detect faults in the absence of angle feedback from the rudder. Considering the parameter uncertainty of the AUV motion model resulting from the dynamics analysis method, we present a parameter identification method based on the recurrent neural network (RNN). Prior to identification, singular value decomposition (SVD) was chosen to denoise the original sensor data as the data pretreatment step. The proposed method provides more accurate predictions than recursive least squares (RLSs) and a single RNN. In order to reduce the influence of sensor parameter errors and prediction model errors, the adaptive threshold is mentioned as a method for analyzing prediction errors. In the meantime, the results of the threshold analysis were combined with the qualitative force analysis to determine the rudder system’s fault diagnosis and location. Experiments conducted at sea demonstrate the feasibility and effectiveness of the proposed method.

A general motion control framework for an autonomous underwater vehicle through deep reinforcement learning and disturbance observers

This paper investigates the application of deep reinforcement learning (RL) in the motion control for an autonomous underwater vehicle (AUV), and proposes a novel general motion control framework which separates training and deployment. Firstly, the state space, action space, and reward function are customized under the condition of ensuring generality for various motion control tasks. Next, in order to efficiently learn the optimal motion control policy in the case that the AUV model is imprecise and there are unknown external disturbances, a virtual AUV model composed of the known and determined items of an actual AUV is put forward and a simulation training method is developed on this basis. Then, in the given deployment method, three independent extended state observers (ESOs) are designed to deal with the unknown items in different directions, and the final controller is obtained by compensating the estimated value of ESOs into the output of the optimal motion control policy obtained through simulation training. Finally, soft actor-critic is chosen as deep RL algorithm of the framework, and the generality and effectiveness of the proposed method are verified in four different AUV motion control tasks.

An Improved S-Plane Controller for High-Speed Multi-Purpose AUVs with Situational Static Loads

The classic S-plane control method combines PD structure with fuzzy control theory, with the advantages of a simple control structure and fewer parameters to be adjusted. It has been proved as a practical method in an autonomous underwater vehicle (AUV) motion control at low and medium speeds, but it takes no account of the situational static load and varying hydrodynamic forces which influence the control quality and even result in a “dolphin effect” at the time of high-speed movement. For this reason, an improved S-plane controller is designed based on the sliding mode variable structure, sliding mode surface, and control items in order to respond to the situational static load and high-speed movement. The improved S-plane controller is verified by Lyapunov stability analysis. The thrust allocation strategies are also discussed with constraints introduced in accordance with task requirements. In order to verify the practicability and effectiveness of the improved S-plane controller, both simulation experiments and field trials of AUV motion control, long-range cruise, and path point following were carried out. The results have demonstrated the superiority of the improved S-plane controller over the classic S-plane controller.

Date-Driven Tracking Control via Fuzzy-State Observer for AUV under Uncertain Disturbance and Time-Delay

This paper focuses on developing a data-driven trajectory tracking control approach for autonomous underwater vehicles (AUV) under uncertain external disturbance and time-delay. A novel model-free adaptive predictive control (MFAPC) approach based on a fuzzy state observer (FSO) was designed to achieve high precision. Concretely, the mathematical model of AUV motion was analyzed, and simplified via model decoupling, thus providing the model basis with an explicit physical explanation for the controller. Second, the MFAPC scheme for a multiple-inputs and multiple-outputs (MIMO) discrete time system was derived, that estimates system external disturbance. The controller can online estimate and predictive time-varying parameter pseudo-Jacobian matrix (PJM) to establish equivalent state space data-model for AUV motion system. Third, the Takagi–Sugeno (T–S) fuzzy model based state observer was designed to combine with the MFAPC scheme for the first time, which was used to online decline the state error generated by system uncertain time-delay. In addition, the stability of the proposed control scheme was analyzed. Finally, two trajectory tracking scenarios were designed to verify the effectiveness and robustness of the proposed FMFAPC scheme, and the simulations are implemented using the realistic parameters of T-SEA AUV.

Guided Trajectory Filtering for Challenging Long-Range AUV Navigation

Aiming at the challenging underwater navigation of autonomous underwater vehicle (AUV), this paper develops a novel filtering method with guided trajectory. The relatively low frequency of ultra-short baseline positioning system (USBL) measurement and the noise caused by complex scenes have a significant impact on the accuracy of AUV motion estimation. Although the existing adaptive extended Kalman filter (EKF) and adaptive unscented Kalman filter (UKF) which can roughly eliminate these outliers, the filtering results of these algorithms are not smooth and have the serious degree of the jitter, and then greatly affect the local consistency and quality of topographic map seamless stitching. We exploit the relatively smooth strap-down inertial navigation system (SINS) as the guided trajectory for motion estimation, and propose a trajectory smoothness preserving filter algorithm. This system has the advantage of maintaining local gradient consistency, which not only improves the navigation accuracy, but also ensures the smoothness of the estimation system. Simulation results show that our approach has high robustness and good smoothness. The effectiveness and practicability of the method are demonstrated by real experiments in multiple deep-sea areas with an average depth of more than 1000 meters in the southwest Indian Ocean.

System noise variance matrix adaptive Kalman filter method for AUV INS/DVL navigation system

The Inertial Navigation System (INS)/Doppler Velocity Log (DVL) navigation system is capable of locating the Autonomous Underwater Vehicle (AUV) in real-time. However, inherent errors of sensors, especially the inertial measurement unit (IMU) measurement noise changes during navigation, make the system noise variance matrix unknown and time-dependent, resulting in inaccurate Kalman filter estimates of velocity and reducing the accuracy of the navigation system. To solve this problem, this paper proposes an adaptive system noise variance matrix Kalman Filter method for AUV INS/DVL navigation system. In this method, the statistical characteristics of the IMU measurement noise are estimated by distinguishing the AUV motion information obtained by the IMU measurement and the IMU measurement noise by the frequency domain analysis method. The Kalman filter velocity estimation accuracy is improved by adaptively adjusting the system noise variance matrix based on the IMU measurement noise. Six different sets of trajectory experiments were used to validate the effectiveness and applicability of the algorithm proposed in this paper. The experimental results show that the improved KF algorithm improves the positioning accuracy by an average of 2.29‰ navigation distance compared with the traditional KF algorithm, which proves that the proposed method can improve navigation performance.

A general motion controller based on deep reinforcement learning for an autonomous underwater vehicle with unknown disturbances

This paper studies the application of deep Reinforcement Learning (RL) in the motion control of an underactuated autonomous underwater vehicle (AUV) with unknown disturbances. Firstly, a general state space, action space and reward function are designed for motion control problems rather than each specific motion control task, which ensures the generality of our method. Furthermore, a virtual AUV model with partial random disturbances is established, and on this basis, a simulation training method is developed to solve the problems of extremely high risk and extremely low efficiency caused by training in actual experiments. Then, in order to directly deploy the optimal control policy obtained through simulation training to an actual AUV, we employ Extended State Observers (ESOs) to estimate the unknown disturbances in five degrees of freedom, and give a deployment method using the estimated values as the disturbance state vector and compensation vector. Combining the above training method and deployment method, a novel general motion controller is proposed. Finally, four different AUV motion control simulations are carried out, and the results confirm the generality and effectiveness of our proposed controller.