Autonomous underwater vehicles (AUVs) may deviate from their predetermined trajectory in underwater currents due to the complex effects of hydrodynamics on their maneuverability. Model-based control methods are commonly employed to address this problem, but they suffer from issues related to the time-variability of parameters and the inaccuracy of mathematical models. To improve these, a meta-learning and self-adaptation hybrid approach is proposed in this paper to enable an underwater robot to adapt to ocean currents. Instead of using a traditional complex mathematical model, a deep neural network (DNN) serving as the basis function is trained to learn a high-order hydrodynamic model offline; then, a set of linear coefficients is adjusted dynamically by an adaptive law online. By conjoining these two strategies for real-time thrust compensation, the proposed method leverages the potent representational capacity of DNN along with the rapid response of adaptive control. This combination achieves a significant enhancement in tracking performance compared to alternative controllers, as observed in simulations. These findings substantiate that the AUV can adeptly adapt to new speeds of ocean currents.

Underwater vehicles play a crucial role in various underwater applications, such as data collection in underwater sensor networks, target detection and tracking, and underwater pipeline monitoring. Real-time acquisition of their states, particularly their location and velocity, is vital for their operation and navigation. Consequently, the development of a remote tracking system to monitor these states is essential. In this paper, we propose a system that can track the underwater vehicle’s location and velocity. We take a systematic approach that encompasses the system architecture, system composition, signal processing, and mobility state estimation. We present the system architecture and define its components, along with their relationships and interfaces. The beacon signal employed in the system features dual-hyperbolic-frequency-modulated (HFM) waveform and an OFDM symbol with cyclic prefix (CP). Based on this beacon signal, we demonstrate how signal processing techniques are utilized to precisely determine the time of arrival and reduce false alarm rates in underwater acoustic channels affected by impulsive noise. Additionally, we explain how the CP-OFDM symbol is used to measure the Doppler scaling factor and transmit essential information for localization and velocity estimation purposes. Utilizing the measurements obtained through signal processing, least squares estimators are used for estimating both the location and velocity. To validate the effectiveness of our approach, we implement the system and conduct field trials. Two separate experiments were conducted in which the diagonal lengths of the square topology were designed to be 1000 m and 800 m. The minimum/maximum root mean square error of localization in the first and second experiment is 2.36/2.91 m and 1.47/2.49 m, respectively. And the minimum/maximum root mean square error of velocity estimation in the first and second experiment is 0.16/0.47 m/s and 0.21/0.76 m/s, respectively. Results confirm the effectiveness of the proposed method in estimating the location and velocity of the underwater vehicle. Overall, this paper provides a practical and effective design of a system to track the location and velocity of underwater vehicles. By leveraging the proposed system, signal processing, and mobility state estimation methods, our work offers a systematic solution. And, the successful field experiment serves as evidence of the feasibility and effectiveness of the proposed system, making it a valuable contribution to the field of tracking underwater vehicles.

Underwater Internet-of-Things (UIoT) is an extension of Internet-of-Things technology in underwater. The underwater acoustic network with WiFi architecture (UW-WiFi), as a specific deployment of UIoT, has been proved to be a promising technique for wide-ranging marine applications. However, due to the unique features of underwater acoustic channel, such as long and variable propagation delay, low available bandwidth and high bit error rate, conventional medium access control (MAC) protocols designed for terrestrial WiFi networks need an overhaul to work efficiently for UW-WiFi networks. In consideration of the aforementioned channel features, different demands of nodes to occupy channel resources and the reliability of data transmission, a time sequence-based dynamic on-demand assignment (SDDA) MAC protocol for UW-WiFi networks is proposed in this paper. In SDDA, the collision-free scheduling is integrated with the reservation mechanism, aiming to address the issue of various access requirements of diverse task nodes on channel resources in the UW-WiFi network system. The designed protocol employs propagation delays and the amount of data to be sent by terminal nodes to achieve non-conflict transmissions of control packets and on-demand scheduling of data packets. Additionally, the scheme does not require extra overhead for time synchronization. Comparison simulations demonstrate that SDDA provides considerable benefits in terms of channel utilization, end-to-end delay and packet delivery ratio. At last, the SDDA protocol is implemented and a UW-WiFi network system is set up in the marine environment. The ocean field experiment results agree well with the simulated ones and also verify that the proposed protocol achieve conflict-free on-demand scheduling, fairness among terminal nodes at different ranges and the practicability in actual environments.

The establishment of the Underwater Internet of Things (UIoT) and the realization of interconnection between heterogeneous underwater intelligent devices are urgent global challenges. Underwater acoustic networking is the most suitable technology to achieve UIoT for medium to long ranges. This paper presents an underwater Wi-Fi network, called uw-WiFi, that utilizes a master–slave mode architecture. uw-WiFi is dedicated to solving the problem of underwater acoustic networking with limited coverage range and number of nodes. To ensure the reliability of different types of data in the network, a reliable segmentation transmission protocol based on data type is designed. Additionally, on-demand scheduling based on the reservation MAC protocol is developed to solve the channel resource sharing problem. The uw-WiFi system has undergone shallow sea tests, and the experimental results demonstrate that the uw-WiFi network is capable of achieving a network throughput of 500 bps or higher, indicating superior network performance.

Underwater sensor networks (UWSNs) play a crucial role in subsea operations like marine exploration and environmental monitoring. A major challenge for UWSNs is achieving effective and energy-efficient data collection, particularly in deep-sea mining, where energy limitations and long-term deployment are key concerns. This study introduces a Channel-Aware AUV-Aided Data Collection Scheme (CADC) that utilizes deep reinforcement learning (DRL) to improve data collection efficiency. It features an innovative underwater node traversal algorithm that accounts for unique underwater signal propagation characteristics, along with a DRL-based path planning approach to mitigate propagation losses and enhance data energy efficiency. CADC achieves a 71.2% increase in energy efficiency compared to existing clustering methods and shows a 0.08% improvement over the Deep Deterministic Policy Gradient (DDPG), with a 2.3% faster convergence than the Twin Delayed DDPG (TD3), and reduces energy cost to only 22.2% of that required by the TSP-based baseline. By combining a channel-aware traversal with adaptive DRL navigation, CADC effectively optimizes data collection and energy consumption in underwater environments.

The most significant increase of current task is in the desire for operational flexibility and agility in large-scale underwater network application scenarios in recent years. In order to address the challenging problems in Underwater Wireless Sensor Networks (UWSNs), we propose a large-scale UWSN based on the cellular network architecture called Underwater Cellular (uw-Cellular) network. It is designed especially for application scenarios where a large number of both fixed and mobile network nodes exist in a wide area to monitor the underwater environment. We also design protocols in each network layer in order to ensure reasonable channel sharing, data forwarding path selection and data reliability. The purpose of the simulation study we implement is to evaluate the performance of the CLA routing strategy compared to the VBF and the MFLOOD protocols in the uw-Cellular network. We also deploy a twenty-node uw-Cellular network in the real-world environment as the field case study. The experimental results showed that the Data Rate between any nodes could reach above 500 bps, and the network Average Throughput was no less than 550 bps under various load situations.