Unknown Underwater Environment Research Articles

Research on single target search and rescue in underwater environment based on machine learning

Machine learning has demonstrated its exceptional performance in addressing complex problems across various domains. This paper proposes an underwater search-rescue system based on the artificial immune algorithm, which effectively solve the problem of finding the optimal local search network in unknown underwater environments and shorten searching time. The system comprises multiple underwater search-rescue robots that form a global search network. Once target victims are identified, the global search network is broken down to form one or more local search networks to track and rescue them. To evaluate the robustness and effectiveness of the system, three indicators were designed: searching time, energy consumption, and tracking distance, and a simulation experiment with a single target is conducted. The results demonstrate that under the identical conditions, the artificial immune algorithm outperforms other methods in underwater target search-rescue tasks.

Underwater Side-Scan Sonar Target Detection: YOLOv7 Model Combined with Attention Mechanism and Scaling Factor

Side-scan sonar plays a crucial role in underwater exploration, and the autonomous detection of side-scan sonar images is vital for detecting unknown underwater environments. However, due to the complexity of the underwater environment, the presence of a few highlighted areas on the targets, blurred feature details, and difficulty in collecting data from side-scan sonar, achieving high-precision autonomous target recognition in side-scan sonar images is challenging. This article addresses this problem by improving the You Only Look Once v7 (YOLOv7) model to achieve high-precision object detection in side-scan sonar images. Firstly, given that side-scan sonar images contain large areas of irrelevant information, this paper introduces the Swin-Transformer for dynamic attention and global modeling, which enhances the model’s focus on the target regions. Secondly, the Convolutional Block Attention Module (CBAM) is utilized to further improve feature representation and enhance the neural network model’s accuracy. Lastly, to address the uncertainty of geometric features in side-scan sonar target features, this paper innovatively incorporates a feature scaling factor into the YOLOv7 model. The experiment initially verified the necessity of attention mechanisms in the public dataset. Subsequently, experiments on our side-scan sonar (SSS) image dataset show that the improved YOLOv7 model has 87.9% and 49.23% in its average accuracy (mAP0.5) and (mAP0.5:0.95), respectively. These results are 9.28% and 8.41% higher than the YOLOv7 model. The improved YOLOv7 algorithm proposed in this paper has great potential for object detection and the recognition of side-scan sonar images.

Camera-Based Net Avoidance Controls of Underwater Robots.

Fishing nets are dangerous obstacles for an underwater robot whose aim is to reach a goal in unknown underwater environments. This paper proposes how to make the robot reach its goal, while avoiding fishing nets that are detected using the robot's camera sensors. For the detection of underwater nets based on camera measurements of the robot, we can use deep neural networks. Passive camera sensors do not provide the distance information between the robot and a net. Camera sensors only provide the bearing angle of a net, with respect to the robot's camera pose. There may be trailing wires that extend from a net, and the wires can entangle the robot before the robot detects the net. Moreover, light, viewpoint, and sea floor condition can decrease the net detection probability in practice. Therefore, whenever a net is detected by the robot's camera, we make the robot avoid the detected net by moving away from the net abruptly. For moving away from the net, the robot uses the bounding box for the detected net in the camera image. After the robot moves backward for a certain distance, the robot makes a large circular turn to approach the goal, while avoiding the net. A large circular turn is used, since moving close to a net is too dangerous for the robot. As far as we know, our paper is unique in addressing reactive control laws for approaching the goal, while avoiding fishing nets detected using camera sensors. The effectiveness of the proposed net avoidance controls is verified using simulations.

An Information-Assisted Deep Reinforcement Learning Path Planning Scheme for Dynamic and Unknown Underwater Environment.

An autonomous underwater vehicle (AUV) has shown impressive potential and promising exploitation prospects in numerous marine missions. Among its various applications, the most essential prerequisite is path planning. Although considerable endeavors have been made, there are several limitations. A complete and realistic ocean simulation environment is critically needed. As most of the existing methods are based on mathematical models, they suffer from a large gap with reality. At the same time, the dynamic and unknown environment places high demands on robustness and generalization. In order to overcome these limitations, we propose an information-assisted reinforcement learning path planning scheme. First, it performs numerical modeling based on real ocean current observations to establish a complete simulation environment with the grid method, including 3-D terrain, dynamic currents, local information, and so on. Next, we propose an information compression (IC) scheme to trim the mutual information (MI) between reinforcement learning neural network layers to improve generalization. A proof based on information theory provides solid support for this. Moreover, for the dynamic characteristics of the marine environment, we elaborately design a confidence evaluator (CE), which evaluates the correlation between two adjacent frames of ocean currents to provide confidence for the action. The performance of our method has been evaluated and proven by numerical results, which demonstrate a fair sensitivity to ocean currents and high robustness and generalization to cope with the dynamic and unknown underwater environment.

Robust cardinalized probability hypothesis density filter based underwater multi-target direction-of-arrival tracking with uncertain measurement noise

Direction-of-arrival (DOA) tracking of underwater targets is an important research topic in sonar signal processing. Considering the underwater DOA tracking is a typical multi-target scenario with uncertain measurement noise caused by unknown underwater environment, a robust underwater multi-target DOA tracking method with uncertain measurement noise is proposed by implementing a spatial matrix filtering (SMF) technique in the framework of the cardinalized probability hypothesis density (CPHD) filter. Firstly, the kinematic model of underwater targets and the measurement model based on the received signal of the hydrophone array (array signal) are established. Thus, the multi-target DOA tracking algorithm is derived by using the CPHD filter based on the established model. Moreover, to avoid the effect of the uncertain measurement noise, the SMF technique is implemented to process the array signal to extract the signal in the bearing angle of the target. Then, the output of the SMF is substituted into the CPHD filter. In this manner, the robust underwater multi-target DOA tracking method for uncertain measurement noise scenario is proposed. Finally, comprehensive simulations and experimental data processing are performed to prove the robustness of the proposed method in the scenario of multi-target DOA tracking with uncertain measurement noise. Compared with the existing DOA estimation and DOA tracking methods, the proposed methods significantly improve the robustness and the precision of the DOA of the underwater target.

A Multidirectional External Perception Soft Actuator Based on Flexible Optical Waveguide for Underwater Teleoperation

As a friendly tool, the soft gripper can be used directly for grasping vulnerable objects in underwater environments. These tasks are generally performed by teleoperation based on the visual feedback, rather than the soft actuators’ sensing information. However, vision sensors’ function may be restricted in some complex underwater environments with poor visibility and narrow spaces. This will greatly reduce the efficiency of the underwater operations. Therefore, soft actuators strongly require an organism‐like perception system to sense environmental stimuli and can be applied to complex underwater environments. To address the problem, a multidirectional external perception soft actuator based on two flexible optical waveguide sensors is developed and machine learning methods are utilized to build its perceptual model herein. The experimental results indicate that the soft actuator can recognize 12 contact positions based on the sensing model, and the identifying accuracy is up to 99.82%. Additionally, according to the contact location feedback, teleoperation can be more efficiently completed in unknown underwater environments.

Variational Bayesian cardinalized probability hypothesis density filter for robust underwater multi-target direction-of-arrival tracking with uncertain measurement noise

The direction-of-arrival (DOA) tracking of underwater targets is an important research topic in sonar signal processing. Considering that the underwater DOA tracking is a typical multi-target problem under unknown underwater environment with missing detection, false alarm, and uncertain measurement noise, a robust underwater multi-target DOA tracking method for uncertain measurement noise is proposed. First, a kinematic model of the multiple underwater targets and bearing angle measurement model with missing detection and false alarms are established. Then, the multi-target DOA tracking algorithm is derived by using the cardinalized probability hypothesis density (CPHD) filter, the performance of which largely depends on the accuracy of the parameter of measurement noise variance. In addition, the variational Bayesian approach is used to adaptively estimate the uncertain measurement of noise variance for each measurement of target in the real time of tracking. Thus, the robust underwater multi-target DOA tracking is carried out. Finally, comprehensive experimental validations and discussions are made to prove that the proposed algorithm can provide robust DOA tracking in the multi-target tracking scenario with uncertain measurement noise.

Remora Jaya Optimization-Enabled Deep Quantum Neural Network for Underwater Target Tracking Using Radar Images

The Ocean boundaries can be protected by pursuing an underwater uncooperative target and permits for the exploitation of ocean resources. This research design a novel technique, named Remora Jaya Optimization (RJO)-enabled Deep Quantum Neural Network (DQN) by considering the impacts of an unknown underwater environment for effective underwater target tracking in radar images. Here, the image is modified effectively using the RJO algorithm because the input radar signal is applied to the image reconstruction process. The modified image is fed up to the gridding phase, where the image is partitioned into a number of grids. The feature extraction process is carried out to extract the significant features after the gridding step is over. This data augmentation method is carried out to increase the data dimensionality. Accordingly, the augmented result is forwarded to the DQN for target tracking, where the network is tuned efficiently by the algorithm of RJO, which is devised by the integration of Jaya Optimization and Remora optimization algorithm (ROA). Moreover, the RJO-based DQN has achieved a minimum Means Square Error (MSE) of 0.168 and maximum detection rate of 0.914, and minimum MSE of 0.168 based on Vertical-Vertical (VV) polarity. The proposed method showed higher effectiveness in detecting the underwater target system in the marine environment.

Robust Underwater Direction-of-Arrival Tracking Based on AI-Aided Variational Bayesian Extended Kalman Filter

The AI-aided variational Bayesian extended Kalman filter (AI-VBEKF)-based robust direction-of-arrival (DOA) technique is proposed to make reliable estimations of the bearing angle of an uncooperative underwater target with uncertain environment noise. Considering that the large error of the guess of the initial mean square error matrix (MSEM) will lead to inaccurate DOA tracking results, an attention-based deep convolutional neural network is first proposed to make reliable estimations of the initial MSEM. Then, by utilizing the AI-VBEKF estimating scheme, the uncertain measurement noise caused by the unknown underwater environment along with the bearing angle of the target can be estimated simultaneously to provide reliable results at every DOA tracking step. The proposed technique is demonstrated and verified by both of the simulations and the real sea trial data from the South China Sea in July 2021, and both the robustness and accuracy are proven superior to the traditional DOA-estimating methods.

Robust underwater direction-of-arrival tracking based on variational Bayesian extended Kalman filter.

The variational Bayesian extended Kalman filter (VB-EKF) based robust direction-of-arrival (DOA) tracking technique is proposed to make reliable estimations of the bearing angle of an underwater target with uncertain environment noise. By utilizing the VB-EKF scheme, the uncertain measurement noise caused by an unknown underwater environment along with the bearing angle of the target can be estimated simultaneously to provide reliable results at every tracking step. The proposed technique is demonstrated and verified by the sea trial data from the South China Sea in July 2021 and both the robustness and accuracy are proved superior to the traditional DOA estimating methods.

Autonomous Underwater Vehicle Path Planning Method of Soft Actor–Critic Based on Game Training

This study aims to solve the issue of the safe navigation of autonomous underwater vehicles (AUVs) in an unknown underwater environment. AUV will encounter canyons, rocks, reefs, fish, and underwater vehicles that threaten its safety during underwater navigation. A game-based soft actor–critic (GSAC) path planning method is proposed in this study to improve the adaptive capability of autonomous planning and the reliability of obstacle avoidance in the unknown underwater environment. Considering the influence of the simulation environment, the obstacles in the simulation environment are regarded as agents and play a zero-sum game with the AUV. The zero-sum game problem is solved by improving the strategy of AUV and obstacles, so that the simulation environment evolves intelligently with the AUV path planning strategy. The proposed method increases the complexity and diversity of the simulation environment, enables AUV to train in a variable environment specific to its strategy, and improves the adaptability and convergence speed of AUV in unknown underwater environments. Finally, the Python language is applied to write an unknown underwater simulation environment for the AUV simulation testing. GSAC can guide the AUV to the target point in the unknown underwater environment while avoiding large and small static obstacles, canyons, and small dynamic obstacles. Compared with the soft actor–critic(SAC) and the deep Q-network (DQN) algorithm, GSAC has better adaptability and convergence speed in the unknown underwater environment. The experiments verifies that GSAC has faster convergence, better stability, and robustness in unknown underwater environments.

A Variational Bayesian-Based Simultaneous Localization and Mapping Method for Autonomous Underwater Vehicle Navigation

Simultaneous Localization and Mapping (SLAM) is a well-known solution for mapping and realizing autonomous navigation of an Autonomous Underwater Vehicle (AUV) in unknown underwater environments. However, the inaccurate time-varying observation noise will cause filtering divergence and reduce the accuracy of localization and feature estimation. In this paper, VB-AUFastSLAM based on the unscented-FastSLAM (UFastSLAM) and the Variational Bayesian (VB) is proposed. The UFastSLAM combines unscented particle filter (UPF) and unscented Kalman filter (UKF) to estimate the AUV poses and features. In addition, to resist the unknown time-varying observation noise, the method of Variational Bayesian learning is introduced into the SLAM framework. Firstly, the VB method is used to estimate the joint posterior probability of the AUV path and observation noise. The Inverse-Gamma distribution is used to model the observation noise and real-time noise parameters estimation is performed to improve the AUV localization accuracy. Secondly, VB is reused to estimate the noise parameters in the feature update stage to enhance the performance of the feature estimation. The proposed algorithms are first validated in an open-source simulation environment. Then, an AUV SLAM system based on the Inertial Navigation System (INS), Doppler Velocity Log (DVL), and single-beam Sonar are also built to verify the effectiveness of the proposed algorithms in the marine environment. The accuracy of the proposed methods can reach 0.742% and 0.776% of the range, respectively, which is much better than 1.825% and 1.397% of the traditional methods.

A learning method for AUV collision avoidance through deep reinforcement learning

This paper investigates the collision avoidance problem for autonomous underwater vehicle (AUV) with limited detection range via deep reinforcement learning method in an unknown underwater environment. Firstly, to deal with both unknown static and dynamic obstacles, we introduce two different event-triggered mechanism to generate obstacle-related states and reward the safe collision avoidance action of AUV, respectively. Secondly, the complete state space is customized by combining the state of AUV itself and the state related to a target area. In addition, considering the task requirement of reaching a target area with the shortest path, the complete reward function is designed. Then, we propose a novel event-triggered soft actor–critic (ET-SAC) algorithm for AUV collision avoidance, and give its detailed pseudo code and implementation architecture. Finally, training and evaluation are carried out in the simulation platform we designed, including unknown static obstacle environment and unknown dynamic obstacle environment in 2D/3D space, and the results confirm that the proposed algorithm of this paper is feasible and effective for AUV to avoid collision safely.

Robust underwater direction-of-arrival tracking with uncertain environmental disturbances using a uniform circular hydrophone array.

Underwater direction-of-arrival (DOA) tracking using a hydrophone array is an important research subject in passive sonar signal processing. In this study, considering that an unknown underwater environment results in uncertain disturbances to the measurements, robust underwater DOA tracking with regard to uncertain environmental disturbances was studied. Because the uniform circular array (UCA) is free from the port and starboard ambiguity problem, a UCA was used to obtain the measurements for a long-time tracking scenario. First, a kinematic model of an underwater target and a measurement model based on the received signal of the UCA were established. Then, a DOA tracking algorithm was derived based on the extended Kalman filter (EKF), whose performance is significantly affected by the accuracy of the measurement noise covariance matrix (MNCM). Finally, considering that uncertain disturbances carry out unstable measurement noise, the modified Sage-Husa algorithm was used to obtain accurate MNCMs during the process of the derived EKF-based DOA tracking algorithm. Thus, a robust DOA tracking method with uncertain environmental disturbances using a UCA was proposed. The accuracy and reliability of the suggested method was verified via Monte Carlo simulations of a DOA tracking scenario and an experiment in the South China Sea in July 2021.

Simple agents, smart swarms: a cooperative search algorithm for swarms of autonomous underwater vehicles

Searching within an unknown environment quickly by utilising a small number of high-capacity robots or a large number of low-cost robots poses an endless question with a non-trivial answer. If the robot's operating environment is underwater, the problem becomes even more complicated due to its three-dimensional nature and the communication restrictions. In this paper, we propose an algorithm appropriate for target searching in unknown underwater environments. The proposed method considers a homogeneous decentralised multi-robot coordination scheme applied from a single-robot configuration to a large swarm. In this model, simple agents (SA) form smart swarms (SS), despite SA do not need to have a strong ability to transmit search and location information, and the SS can efficiently perform search tasks in unknown environments. Specifically, when a swarm performs a search task, agents only search according to the simple strategy and share mapping information within their communication range, enhancing search efficiency. Simulation results demonstrate the effectiveness and that search time reduces proportionally by increasing the number of robots comprising the swarm, while the repetition search rate does not increase with the expansion of the swarm size. We believe that our SS architecture provides insights into the future application of swarm intelligence.

尤度推定手法を用いた超音波漏洩箇所推定システムに関する基礎研究

In the decommissioning process of the Fukushima Daiichi Nuclear Power Plant of the Tokyo Electric Power Company, Incorporated (TEPCO), it is necessary to investigate the leakage area of coolant and so on. We have focused on ultrasonic measurement as an investigation method to supplement optical measurement methods such as cameras.In this study, we have developed and verified a measurement system using ultrasonic velocity distribution measurement and ultrasonic environmental measurement to measure the velocity distribution in a wide area and to estimate the leakage point in unknown underwater environment, aiming to apply the measurement method to a robot for the investigation in the reactor during the decommissioning work process.

Target Search Algorithm for AUV Based on Real-Time Perception Maps in Unknown Environment

For the problem of AUV target searches in unknown underwater environments, a target search algorithm for AUVs based on a real-time perception map is proposed. Real-time perception maps, including target existence probability maps, uncertainty maps, and pheromone maps and their updating rules, are established. Attraction source maps and search status maps based on the environmental information detected by the AUV are established. The maps are used for the AUV to search for corner areas that are unknown to a high degree and areas with low coverage around the current location. At the same time, a release mechanism for attraction and revisiting pheromones is established by combining a neural excitation network algorithm to make the gradient spread in the pheromone grid map. By setting up a search revenue function based on real-time perception maps, an AUV search decision-making method is established. When the AUV finds a suspected target, the AUV approaches the suspected target. The path planning of the AUV is carried out through an improved artificial potential field method. The short-distance confirmation of the target and obstacle avoidance in the search process are realized. The simulation results show that the algorithm has high search efficiency. Additionally, when the target exists in a corner area, the probability of the AUV to quickly search for the target is fast and feasible.

Adaptive Two-Step Bearing-Only Underwater Uncooperative Target Tracking with Uncertain Underwater Disturbances.

The bearing-only tracking of an underwater uncooperative target can protect maritime territories and allows for the utilization of sea resources. Considering the influences of an unknown underwater environment, this work aimed to estimate 2-D locations and velocities of an underwater target with uncertain underwater disturbances. In this paper, an adaptive two-step bearing-only underwater uncooperative target tracking filter (ATSF) for uncertain underwater disturbances is proposed. Considering the nonlinearities of the target’s kinematics and the bearing-only measurements, in addition to the uncertain noise caused by an unknown underwater environment, the proposed ATSF consists of two major components, namely, an online noise estimator and a robust extended two-step filter. First, using a modified Sage-Husa online noise estimator, the uncertain process and measurement noise are estimated at each tracking step. Then, by adopting an extended state and by using a robust negative matrix-correcting method in conjunction with a regularized Newton-Gauss iteration scheme, the current state of the underwater uncooperative target is estimated. Finally, the proposed ATSF was tested via simulations of a 2-D underwater uncooperative target tracking scenario. The Monte Carlo simulation results demonstrated the reliability and accuracy of the proposed ATSF in bearing-only underwater uncooperative tracking missions.

3D Underwater Uncooperative Target Tracking for a Time-Varying Non-Gaussian Environment by Distributed Passive Underwater Buoys.

Accurate 3D passive tracking of an underwater uncooperative target is of great significance to make use of the sea resources as well as to ensure the safety of our maritime areas. In this paper, a 3D passive underwater uncooperative target tracking problem for a time-varying non-Gaussian environment is studied. Aiming to overcome the low observability drawback inherent in the passive target tracking problem, a distributed passive underwater buoys observing system is considered and the optimal topology of the distributed measurement system is designed based on the nonlinear system observability analysis theory and the Cramer–Rao lower bound (CRLB) analysis method. Then, considering the unknown underwater environment will lead to time-varying non-Gaussian disturbances for both the target’s dynamics and the measurements, the robust optimal nonlinear estimator, namely the adaptive particle filter (APF), is proposed. Based on the Bayesian posterior probability and Monte Carlo techniques, the proposed algorithm utilizes the real-time optimal estimation technique to calculate the complex noise online and tackle the underwater uncooperative target tracking problem. Finally, the proposed algorithm is tested by simulated data and comprehensive comparisons along with detailed discussions that are made to demonstrate the effectiveness of the proposed APF.

Multi-autonomous underwater vehicles collaboratively search for intelligent targets in an unknown environment in the presence of interception

We present a bionic neural wave network that uses multiple autonomous underwater vehicles to search and acquire intelligent targets in an unknown underwater environment. The neuron pheromone content is arranged according to neural wave diffusion and layer-by-layer energy attenuation, when underwater mesh space based on neural wave diffusion theory was established that the neuron nodes in the neural network structure correspond to obstacles, autonomous underwater vehicles, and targets in the environment. In order to solve the problems of over-allocation and under-allocation of the multi-autonomous underwater vehicles system during the cooperative capture of targets, a redistribution mechanism based on the improved self-organizing map algorithm is implemented and directed to rationalize task distribution. Two different taboo search methods are employed to update the autonomous underwater vehicle path in real time, and the polynomial coefficient solution method is used to fit partial path data. So that the autonomous underwater vehicle trajectory can be obtained and an interceptor position coordinate can be predicted. An auxiliary autonomous underwater vehicle is aimed to replace the intercepted autonomous underwater vehicle and the matching capture points are tracked to ensure the completion of the task so that the full range of hunting targets is identified. In order to simulate an unknown complex underwater environment, obstacles are randomly arranged around the target, the location information of the obstacle, and the target is unknown and unpredictable. Four simulation experiments were performed to verify the accuracy and efficiency of the algorithm under unknown environment. The results show that this algorithm can improve the path update average efficiency by 66% compared with other algorithms. Obviously, this algorithm is reasonable and effective.