The paper presents a novel 2D geometrical path plan algorithm that reduces calculation load and time by filtering obstacles before path planning starts by the newly introduced hexagon filter and also while path search is in progress. Unlike other methods that use only obstacle filtering before path planning starts. The suggested algorithm was able to solve a randomly created maze that contains 400 obstacles with 800 nodes, which was considered before, as next to impossible to solve. This is because computational time is proportional to n ²log(n) where n is the number of obstacles, node suggested algorithm reduced the computational time to about 1 in 2500 times compared to the best of (ESOVG, DVG or ECoVG). In addition, the suggested algorithm can be used in the case of a fixed start point and different target points (e.g. a swarm of robots leaving from the same start point with different targets).

Formation recognition is a significant focus of maritime target recognition. Automatic formation extraction and recognition facilitate autonomous decision‐making. However, few studies have explored formation extraction prior to recognition. This paper introduces a density‐based spatial clustering of applications with noise (DBSCAN) method based on Gaussian kernel to extract formation targets. On this basis, a depthwise separable convolutional neural network (DSCNN) method is proposed for formation recognition. A track simulation system is established to form a track dataset containing three different proportions of clutter, and the formation extraction method is examined using track dataset. Subsequently, the image dataset with eight different types of formation is formulated, on the basis of various detection errors, the DSCNN method for formation recognition is compared with several typical deep learning methods. As exposed in experimental results, the DBSCAN method based on Gaussian kernel can guarantee accurate extraction of formation targets subject to different proportions of clutter. Hence, it is greatly robust and capable of effective formation extraction. Under different radar detection errors, the formation recognition accuracy of DSCNN is 91.5%–99.5%, which achieves performance improvement by up to 12.5% compared with other deep learning methods. The combination of DBSCAN and DSCNN can well realise formation extraction and recognition with different proportions of clutter in tracks and various radar detection errors.

In this paper, the terrain effect on parameter inversion performance of polarimetric synthetic aperture radar (PolSAR) and polarimetric SAR interferometry (PolInSAR) are analysed first. Based on the analysis of the terrain effect on single pixel processing, the terrain effect between adjacent pixels is addressed for both PolSAR and PolInSAR image pairs. Through the analysis, the terrain effect should be considered not only for the single pixel data calibration but also for the adjacent pixels of PolSAR and PolInSAR parameter inversion processing. Therefore, combining with the geometric model correction of sloped‐random volume over ground, the terrain‐compensated procedure is proposed for PolInSAR parameter inversion. The parameter inversion performance is improved effectively with terrain effect consideration. The effectiveness of the proposed method is investigated by the PolSARPro simulated dataset and the real Phased Array L‐Band Synthetic aperture Radar (PALSAR) dataset.

Space‐time adaptive processing with finite samples is supposed to be a crucial technique for airborne radar systems. Inspired by the application of Gaussian prior in sparse Bayesian learning algorithm and the adaptive least absolute shrinkage and selection operator algorithm, a hierarchical Bayesian framework with adaptive Laplace priors is proposed. In this paper, a novel method is applied to avoid the high‐dimension matrix inverse operation in the proposed algorithm. Moreover, in order to apply the method in the complex‐valued domain, the complex‐valued signal is split into two independent variables. Then, the sparse recovery problem in the complex‐valued domain can be transformed into the real‐value domain. Simulation experiments show that the proposed algorithm can achieve great clutter suppression performance and also ensure high computational efficiency.

In recent years, bistatic inverse synthetic aperture radar (Bi‐ISAR) imaging of targets with sparse aperture has attracted more and more attention. One of the critical issues is that the Bi‐ISAR imaging of some large targets with rotational motions is prone to migration through resolution cells, which increases the imaging difficulty. In order to enhance the compensation for through resolution cell migration in those scenarios and improve the accuracy and resolution of Bi‐ISAR images under sparse aperture, that is, improving the target recognition of Bi‐ISAR, the authors aimed at the high‐order migration term and the high‐order phase error term and proposed a Bi‐ISAR sparse aperture high‐resolution imaging algorithm based on complex Bayesian compressed sensing and frequency resampling. The algorithm was solved by ‘distributed’ iteration. The migration compensation under the sparse aperture conditions was completed, and the quality of the reconstructed images was improved. Simulation results verified the effectiveness and superiority of the proposed algorithm.