In a complex underwater environment, finding a viable, collision-free path for an autonomous underwater vehicle (AUV) is a challenging task. The purpose of this paper is to establish a safe, real-time, and robust method of collision avoidance that improves the autonomy of AUVs. We propose a method based on active sonar, which utilizes a deep reinforcement learning algorithm to learn the processed sonar information to navigate the AUV in an uncertain environment. We compare the performance of double deep Q-network algorithms with that of a genetic algorithm and deep learning. We propose a line-of-sight guidance method to mitigate abrupt changes in the yaw direction and smooth the heading changes when the AUV switches trajectory. The different experimental results show that the double deep Q-network algorithms ensure excellent collision avoidance performance. The effectiveness of the algorithm proposed in this paper was verified in three environments: random static, mixed static, and complex dynamic. The results show that the proposed algorithm has significant advantages over other algorithms in terms of success rate, collision avoidance performance, and generalization ability. The double deep Q-network algorithm proposed in this paper is superior to the genetic algorithm and deep learning in terms of the running time, total path, performance in avoiding collisions with moving obstacles, and planning time for each step. After the algorithm is trained in a simulated environment, it can still perform online learning according to the information of the environment after deployment and adjust the weight of the network in real-time. These results demonstrate that the proposed approach has significant potential for practical applications.

Target state estimation is a key technology for unmanned underwater vehicles to achieve target tracking, collision avoiding, formation control, and other tasks. Compared with other measurement methods, underwater measurement has lower reliability due to the uncertainty of sonar detection. In this case, the performance of target state estimation depends heavily on the target motion model. However, the dynamics of unmanned underwater vehicles are very complex and nonlinear. Although many state estimation methods for nonlinear systems have been proposed, the complex dynamics of unmanned underwater vehicle and uncertainty in sonar detection remain challenges for underwater target state estimation problems. This paper proposes a gated recurrent units-based particle filter to improve the performance of the target state estimator for unmanned underwater vehicles. A deep neural network framework based on gated recurrent units is used to establish the mapping between the previous measurements and the current target states. This neural network learns the dynamics model of unmanned underwater vehicles and recognizes the measurement noise. The proposed filter samples from previous measurements of the target unmanned underwater vehicle, and the fully trained deep neural network predicts the current states of the sampled particles. The proposed method solves the low accuracy and instability caused by motion modeling errors and system nonlinearity. Simulation results show that the proposed gated recurrent units-based particle filter for unmanned underwater vehicle state estimation has better accuracy and stability than the traditional state estimation methods. All simulations are done with the noise which is Gaussian noise pass through a nonlinear transformation.

Autonomous collision avoidance is a critical technology in intelligent control, which is of great significance for autonomous navigation and operation of Unmanned Underwater Vehicles (UUVs). To enhance the autonomy of UUV collision avoidance and improve its adaptability to unstable forward-looking sonar observation and uncertain environments, we propose a novel Transformer-based Dual-Channel Self-attention (TDCS) architecture for UUV collision avoidance. TDCS is a network architecture composed of two encoders and a decoder, which integrates dynamic/static obstacle recognition, obstacle motion prediction, collision risk assessment, and collision avoidance decision. The two encoders extract the observation features of different sensors in parallel, and this dual-channel structure avoids the mutual interference of input information. Moreover, the two encoders are beneficial for adaptive learning to focus on sensor information with varying forms of representation. The fusion layer integrates the bimodal features extracted from different sensors by the dual-channel encoder. Finally, the fusion features and historical decisions are recombined through the decoder to form a new decision.

The challenges facing unmanned underwater vehicle (UUV) target state estimation are observation uncertainty, the unpredictability of the target motion model, and the complex relative motion of the moving target to the observer. Aiming at the above problems, a convolutional neural network particle filter (CNNPF) is proposed and applied to UUV target state estimation using forward-looking sonar. First, we design a target state prediction network based on convolutional neural network (CNN) to describe the nonlinear measurement and non-Markov target motion process models. Then, a target state prediction dataset is established for the prediction network to build the state space of UUV target state estimation and extract target motion features from the nonsequential measurements. Moreover, particles are sampled from the observations with disturbed time series to approximate the non-Gaussian distribution of measurements. The sampling particles in the target measured state space are mapped to target predictive state space through the prediction network. Convolutional and pooling layers impart invariance to the prediction network and improve its adaptability to uncertain measurement. Finally, the predicted states of particles are used to estimate the target states. The statistical experiment, simulation cases, and hardware-in-the-loop experiment proved the applicability and performance of the CNNPF.

In this paper, we present an online obstacle avoidance planning method for unmanned underwater vehicle (UUV) based on clockwork recurrent neural network (CW‐RNN) and long short‐term memory (LSTM), respectively. In essence, UUV online obstacle avoidance planning is a spatiotemporal sequence planning problem with the spatiotemporal data sequence of sensors as input and control instruction to motion controller of UUV as output. And recurrent neural networks (RNNs) have proven to give state‐of‐the‐art performance on many sequence labeling and sequence prediction tasks. In order to train the networks, a UUV obstacle avoidance dataset is generated and an offline training and testing is adopted in this paper. Finally, the proposed two types of RNN based online obstacle avoidance planners are compared in path cost, obstacle avoidance planning success rate, training time, time‐consumption, learning, and generalization, respectively. And the good performance of the proposed methods is demonstrated with a series of simulation experiments in different environments.

Uncrewed underwater vehicles (UUVs) are usually deployed to track noncooperative targets in industrial or military applications. However, the sonar measurement data usually show high unreliability due to the particularity of underwater environments. We propose a novel AKansformer Target Tracking (AKTT) approach to improve the accuracy and robustness of UUV tracking of noncooperative targets under unreliable measurement. First, a historical measurements–based non-Markov state-space model is constructed to capture the complexity of target dynamics under unreliable measurement conditions. Second, we develop a multistep prediction network that integrates the axial attention mechanism with Kolmogorov–Arnold networks (KANs) based on the sonar measurement model and target state transition model. The prediction network learns from massive offline data and predicts the regular transition of the target state, which provides a powerful prediction ability for the tracking approach. In view of the unreliability of the sonar measurement and the uncertainty of the posterior distribution, this article uses the Monte Carlo principle and the proposed multistep prediction network to transform the non-Markov system model into a recursive first-order Markov model and constructs the corresponding recursive filtering model. Finally, we conduct a comprehensive evaluation of the AKTT through an array of statistical experiments and simulation cases. The results validate the efficacy of the AKTT, showcasing its robustness and superiority in tracking noncooperative targets under unreliable, even intermittently failing, sonar measurements.