In order to overcome the vulnerability of the global navigation satellite system (GNSS) and provide robust position, navigation and time (PNT) information in marine navigation, the autonomous positioning system based on ranging-mode Automatic Identification System (AIS) is presented in the paper. The principle of the AIS autonomous positioning system (AAPS) is investigated, including the position algorithm, the signal measurement technique, the geometric dilution of precision, the time synchronization technique and the additional secondary factor correction technique. In order to validate the proposed AAPS, a verification system has been established in the Xinghai sea region of Dalian (China). Static and dynamic positioning experiments are performed. The original function of the AIS in the AAPS is not influenced. The experimental results show that the positioning precision of the AAPS is better than 10 m in the area with good geometric dilution of precision (GDOP) by the additional secondary factor correction technology. This is the most economical solution for a land-based positioning system to complement the GNSS for the navigation safety of vessels sailing along coasts.

Deep learning-based Synthetic Aperture Radar (SAR) ship detection methods are significant in signal processing and radar imaging. However, these approaches always require large-scale SAR ship images with labels to train the model. Due to the inaccessibility of SAR sensors, it is difficult to acquire enough SAR images. Annotating ship targets also demands resources and manpower. To tackle this issue, we propose a novel SAR image generation method named SARGAN for SAR ship detection task. Given the position and category, SARGAN can generate realistic SAR images with SAR ship targets, land and background in the desired location. In the SARGAN, there are five components: target encoder, scene constructor, SAR image generator, and target and image discriminators. The target encoder is introduced to predict the latent vector for each target while the scene constructor integrates all targets in the entire scene using convolutional LSTM. We improve the structure of the SAR image generator by adding operations to generate high-quality images. The image and target discriminators are responsible for distinguishing between real and fake samples, with the latter also predicting the category. To promote the generation of diverse and realistic SAR ship images, multiple loss functions are employed for training. Additionally, we have annotated the lands and background in the HRSID dataset and combined them with labeled ships to create a new dataset for training and testing of SARGAN. Extensive experiments demonstrate that SARGAN outperforms other SAR image generation methods, and the generated SAR ship images are highly conducive for SAR ship detection task.

This article investigates an adversarial domain protection scenario involving multiple defending underactuated autonomous surface vehicles (ASVs) against an equal number of attacking ASVs in an obstructive environment. The defending ASVs can only obtain the positions of the attacking ASVs susceptible of stochastic measurement noises. A three-layer attack-defense guidance structure is proposed such that the defending ASVs are able to intercept the attacking ASVs with collision-free behaviors. In the first layer, an auction theory is utilized to achieve the attack-defense matching that efficiently assigns multiple defending ASVs to corresponding attacking ASVs in a distributed manner. In the second layer, an adaptive attack-defense guidance method is proposed, enabling each underactuated defending ASV to implement the appropriate guidance law aligned with the optimal interception point. In the last layer, a quadratic programming problem is formulated using speed-heading-constraint control barrier functions, and a neurodynamics optimization approach is employed to achieve real-time resolution of the optimal attack-defense guidance signal. The stability and safety analyses show that the system error is practically stochastic input-to-state stable, and the system is guaranteed to be safe. Experiment results demonstrate the effectiveness of the proposed neurodynamics-based attack-defense guidance method for domain protection.