The paper presents an overview of neural network (NN) technologies applied in navigation support of marine surface vehicles. It considers the problems related to motion path generation, detection, classification, and avoiding collisions with approaching ships, as well as navigation data integration and cybersecurity issues. 

Algorithms for detecting the runway contours in video images based on YOLOv8 neural network (NN) are presented, differing by the types of problems it is trained to (detection, segmentation, pose estimation). The accuracy and speed of these algorithms run on NVIDIA Jetson NANO computer module are analyzed. Using the analysis results, the best detection algorithm is selected based on certain parameters (speed, accuracy, range). The results confirm that the algorithm can be applied in onboard software of unmanned aerial vehicles (UAV).

The paper proposes a technique for constructing the simulation model of a surface ship motion based on the specified composition and parameters of actuators. As an example, constructing the simulation model of a car and train ferry is considered. Based on the model, control algorithms have been developed for stabilizing the longitudinal component of the ship linear velocity and heading stabilization.  

 In recent times, there has been a notable increase in the use of Unmanned Aerial Vehicles (UAVs) worldwide, driven by a growing demand for their versatile applications across various domains. However, alongside their beneficial applications, there has been a concerning emergence of malicious UAVs use by cyber criminals. These unauthorized activities pose significant risks, with the potential for destructive consequences. Consequently, there is a pressing need for the development and implementation of detection, protection, and prevention measures to mitigate these threats effectively. The primary objective of this paper is to explore the evolving risks associated with cyber-attacks in formation flights of UAVs, along with the corresponding countermeasures aimed at tolerating such threats. The work proposes a hybrid fault diagnosis scheme and fault-tolerant cooperative controllers for multiple UAVs under faults and cyber attacks. The proposed hybrid fault diagnosis scheme combines rule-based and model-based approaches. Three realistic attack scenarios are simulated including the Man-in-the-Middle attack and the GPS spoofing. The results show that the proposed scheme is able to ensure the safe operation of UAVs in the fleet by effectively diagnosing faults and enabling proactive measures to mitigate potential risks.

The paper considers the structure of a portable or mobile energy signal detector using a detection threshold determination algorithm adaptive to the observation conditions to stabilize the false alarm probability under rapid changes in the signal-to-noise ratio (for example, caused by the readjusting the receiver parameters, external interference, etc.) [1]. The detector constructs a normalized histogram of background noise power distribution and calculates its parameters in real time. To ensure the required false alarm probability, triangular approximation is applied to the tail of the background noise distribution law with smoothing of the detection threshold estimates. The article presents the results of experimental studies of the noise power under different observation conditions. A comparative analysis of the false alarm and detection probabilities obtained using the Neyman-Pearson criterion and the adaptive detection threshold algorithm in the energy detector is carried out.

The paper describes an approach to designing an attitude control system for small spacecraft (SS), adaptive to possible failures of sensors and actuators. With this aim in view, the system loop includes its digital twin, which is designed to detect failures of measuring equipment using predicted measurement values calculated based on onboard adaptive SS motion models. This approach increases the SS onboard computational burden, but prevents processing of unreliable measurement data in the feedback loop. Compensation for the failure of sensors and actuators is performed by reconfiguring the algorithmic support used to determine the SS attitude. To compensate for failures of actuators’ individual channels, an algorithm for SS attitude control is proposed, the structure of which has the form of even Fourier series. 

We report a recursive positioning algorithm for an autonomous underwater vehicle (AUV) based on measurements of ranges to acoustic beacons, water speed log and heading indicator data. Two types of desynchronization between the beacon and AUV time scales are considered: random and unknown. The algorithm starts without using AUV a priori coordinates when simultaneous measurements from minimum two or three beacons (depending on the desynchronization type) are first obtained. The newly coming measurements and those saved before the algorithm start are processed in forward and backward time in the same filter. If AUV coordinate estimates are ambiguous, two filters are implemented, which process the same data with different measurement linearization points. Ambiguity is resolved based on the ratio of a posteriori probabilities of hypotheses on AUV position. This ratio is calculated using the filters' outputs. 

The paper describes an algorithm for determining the depth of a sound source using a multielement bottom linear antenna, based on measurements of differences in signal delays in a multipath channel. The accuracy of the algorithm is confirmed by simulation and verified experimentally.

The possibility of using multi-frequency signals in hydroacoustic navigation systems with an ultra-short measuring baseline is considered. The reception of an external signal by a circular antenna, the aperture of which is several wavelengths of a medium-frequency wave signal, is analyzed. The proposed model for determining the time delays of antenna elements based on determination of total phases at each frequency of a multi-frequency signal has shown the possibility of increasing the accuracy of measurements of the navigation object angular position.