Cooperative localization is critical for UAV swarm operations in GNSS-denied environments. The backbone-listener scheme, using a small subset of agents as active backbone nodes and others as passive listeners, offers notable advantages in reducing communication overhead and enhancing swarm scalability. Building on this scheme, we propose a formation-constrained cooperative localization method to improve accuracy by integrating known formation geometry into the localization process. First, backbone node selection uses a formation-constrained greedy node activation (GNA) strategy with weighted distance fusion, combining measured and ideal formation distances to enable near-optimal selection aligned with formation structure. Second, listener node localization incorporates formation constraints into Chan’s algorithm, paired with angle-of-arrival (AOA) refinement, to ensure estimated positions match expected inter-agent distances. Third, global optimization uses a gradient descent-based refinement to enforce formation constraints across all agent positions. Our theoretical derivations and simulations are limited to the two-dimensional (2D) case. Simulation results validate the proposed method’s improved success rate, reliability, and stability. Its effectiveness is demonstrated across various formation types, with robust adaptability to asymmetric geometries shown to be a valuable feature for practical deployment.

To tackle the frequent missed and false detection issues arising from the tiny scale of objects and strong background clutter in UAV aerial photography scenarios, this paper proposes a novel algorithm named SODet-YOLO for UAV aerial imagery. First, to effectively extract the features of aerial objects and alleviate background interference, we integrate a high-resolution detection head denoted as P2 into the YOLO11n, which is connected to the feature layer from the second downsampling stage of the Backbone and Neck networks, we design the Fine-Grained Aggregation-Asymptotic Feature Pyramid Network (FGA-AFPN) to realize adequate fusion of feature information at different levels. Second, we redesign the original C3k2 module by embedding the Inception Depthwise Convolution (IDC). This design effectively expands the receptive field, enriches multi-scale contextual feature extraction, and mitigates adverse interference from complex background clutter. In addition, a novel IoU loss function named MPDInterpIoU is proposed by combining InterpIoU with MPDIoU. This function promotes faster convergence at the early learning stage and optimizes detection-related performance. Finally, the Parallelized Patch-aware Attention (PPA) is incorporated before the downsampling module to preserve the key features of small objects throughout multiple downsampling steps. The experimental findings validate that SODet-YOLO achieves an mAP@0.5 score of 41.487% on the VisDrone2019 object detection dataset, representing an 8.92% performance enhancement relative to the baseline YOLO11n model. However, the computational cost increases moderately, with the number of parameters increasing by 1.08 M, the computational complexity increasing by 26.1 GFLOPs, and the average inference time growing by 34.7 ms.

In this paper, a robust block MMSE-DFE (joint minimum mean square error and decision feedback equalization) framework with joint time-frequency domain processing is developed for UAV-to-Ground single carrier modulation with frequency domain equalization (SC-FDE) communication systems. Two important issues related to iterative block decision feedback equalization (IBDFE) are discussed here, i.e., the complexity of iterative operations and the feedback symbols reliability. Firstly, in order to simplify the operation process, we directly use the results of MMSE to avoid the complexity of iterative operation. Then in the feedback loop of the MMSE-DFE, we proposed a criterion for feedback symbol metric, which could help us control the error propagation process. This results in the improvement of the error propagation, one of the common problems in a DFE or IBDFE. Finally, simulation results demonstrate the robustness of our designed block MMSE-DFE with joint time-frequency domain processing. Firstly, the feedback correlation measurement criteria proposed in this paper can greatly control the error propagation of DFE, and further improve the balancing performance of DFE equalizer. Second, the equalization framework proposed in this paper can adapt to different modulation modes, different equalization algorithms, and can be well combined with coding algorithms.

To address the insufficiency of timeliness and accuracy in multi-UAV task allocation under dynamic environments, this paper proposes an intelligent decisionmaking optimization method based on Long Short-Term Memory (LSTM) networks. By analyzing task types and allocation constraints, the task allocation problem is transformed into an optimization problem. A four-layer model (input layer, LSTM layer, fully connected layer, output layer) is constructed, leveraging LSTM's gating mechanism to capture temporal dependencies between tasks and UAV states, thereby achieving precise matching of task priorities and UAV capabilities. Experiments show that compared to traditional RNN, the proposed method improves task allocation accuracy by 12.3% (reaching 94.0%), reduces average decision time to 0.89 seconds, and achieves a task completion rate of 96.8%, providing an effective technical approach for multi-UAV collaboration in complex dynamic scenarios.

Deep Reinforcement Learning (DRL) has demonstrated potential in addressing robotic local planning problems, yet its efficacy remains constrained in highly unstructured and dynamic environments. To address these challenges, this study proposes the ColorDynamic framework. First, an end-to-end DRL formulation is established, which maps raw sensor data directly to control commands, thereby ensuring compatibility with unstructured environments. Under this formulation, a novel network, Transqer, is introduced. The Transqer enables online DRL learning from temporal transitions, substantially enhancing decision-making in dynamic scenarios. To facilitate scalable training of Transqer with diverse data, an efficient simulation platform E-Sparrow, along with a data augmentation technique leveraging symmetric invariance, are developed. Comparative evaluations against state-of-the-art methods, alongside assessments of generalizability, scalability, and real-time performance, were conducted to validate the effectiveness of ColorDynamic. Results indicate that our approach achieves a success rate exceeding 90 (1.2-1.3 ms per planning). Additionally, ablation studies were performed to corroborate the contributions of individual components. Building on this, the OkayPlan-ColorDynamic (OPCD) navigation system is presented, with simulated and real-world experiments demonstrating its superiority and applicability in complex scenarios. The codebase and experimental demonstrations have been open-sourced on our website to facilitate reproducibility and further research.

To enhance the reliability of UAV-to-Ground data transmission in SC-FDE, this study proposes a combined MMSE equalization and LDPC-RS concatenated code approach, utilizing source redundancy to mitigate errors in low-elevation G2A communication. The proposed coding scheme combines a binary LDPC code as the outer code and an improved RS code as the inner code, resulting in improved resistance to burst and random errors. To address the coding aspect, this paper designs a coding table using RS coding as the underlying logic, enabling efficient coding. For decoding, a decoding scheme based on the minimum Euclidean distance criterion is devised, enabling high-performance decoding. Simulation results demonstrate that the proposed LDPC-RS concatenated coding scheme significantly enhances the performance of the communication system, thereby offering considerable potential for application in UAV video transmission systems.

For Takagi–Sugeno fuzzy systems subject to inexact membership functions, bounded disturbances, and noises, an output feedback robust model predictive control (RMPC) approach with time-varying robust tubes is investigated. The membership functions errors are bounded within convex sets via the properties of zonotopes and interval matrices. An offline table stores a series of structures that include nested robust positive invariant sets with the corresponding nominal feedback controller gains, ancillary controller gains, and observer gains. According to bounds of real-time estimation error sets, the time-varying structures in the offlined table are searched. Then, the output feedback RMPC problem with time-varying tightened constraints on inputs and states is optimized to stabilize the nominal system. The output feedback RMPC approach can not only update bounds of the estimation errors and uncertain terms resulting from inexact membership functions, but also reduce the computational burden. The proposed RMPC algorithm with recursive feasibility guarantees the robust stability of the controlled systems.

For constrained linear parameter varying (LPV) systems, this survey comprehensively reviews the literatures on output feedback robust model predictive control (OFRMPC) over the past two decades from the aspects on motivations, main contributions, and the related techniques. According to the types of state observer systems and scheduling parameters of LPV systems, different kinds of OFRMPC approaches are summarized and compared. The extensions of OFRMPC for LPV systems to other related uncertain systems are also investigated. The methods of dealing with system uncertainties and constraints in different kinds of OFRMPC optimizations are given. Key issues on OFRMPC optimizations for LPV systems are discussed. Furthermore, the future research directions on OFRMPC for LPV systems are suggested.

Distance measure plays a critical role in various applications of polarimetric synthetic aperture radar (PolSAR) image data. In recent decades, plenty of distance measures have been developed for PolSAR image data from different perspectives, which, however, have not been well analyzed and summarized. In order to make better use of these distance measures in algorithm design, this paper provides a systematic survey of them and analyzes their relations in detail. We divide these distance measures into five main categories (i.e., the norm distances, geodesic distances, maximum likelihood (ML) distances, generalized likelihood ratio test (GLRT) distances, stochastics distances) and two other categories (i.e., the inter-patch distances and those based on metric learning). Furthermore, we analyze the relations between different distance measures and visualize them with graphs to make them clearer. Moreover, some properties of the main distance measures are discussed, and some advice for choosing distances in algorithm design is also provided. This survey can serve as a reference for researchers in PolSAR image processing, analysis, and related fields.

针对输入受限的多旋翼无人机轨迹跟踪问题设计了鲁棒正定不变集.考虑多旋翼无人机的非线性动力学模型、外部不确定干扰以及输入饱和约束等因素,首先设计带有干扰抵消项的非线性控制律以保证无人机轨迹跟踪的稳定性,进而基于线性矩阵不等式(LMIs)构造了鲁棒正定不变集.在所设计的控制律作用下,无人机轨迹跟踪误差一旦进入所构造的不变集则将始终处于该集合内,并最终趋于零.理论推导过程与仿真实验结果均验证了以上特性.

This article proposes a robust distributed receding horizon control (RDRHC) synthesis approach for the simultaneous tracking, regulation and formation of multiple perturbed wheeled vehicles with collision avoidance. By successfully extending a tube‐based RHC approach proposed in our previous work and elaborately designing the collision avoidance and compatibility constraints, a nominal control optimization problem is constructed for each vehicle with recursive feasibility guarantee, and the associated RDRHC algorithms with and without on‐line optimization are presented for implementation. By applying the presented algorithms, the multiple perturbed wheeled vehicles can be steered to achieve the desired tracking, regulation and formation objective with satisfying the pre‐specified constraints and avoiding collision. Both theoretical properties and practical effectiveness of the proposed approach are verified through a simulation example.

Recently, convolutional neural networks (CNNs) have been successfully developed and used in the classification of polarimetric synthetic aperture radar (PolSAR) images. However, they often suffer from some problems, such as time-consuming, unsatisfactory detail-preservation, and bad effectiveness given limited training samples. Focusing on these problems, we propose a complex-valued CNN (CV-CNN)-based algorithm for PolSAR image classification in this article. On the one hand, a superpixel-oriented (SPO) scheme is employed to reduce the computational cost of the algorithm and preserve image details simultaneously, which takes superpixels instead of single pixels as classification units. In particular, to meet the input requirement of CV-CNN, three alternative methods of superpixel regularization are designed and compared. On the other hand, considering that both measured data (MD) and manually designed polarimetric features (PFs) have their own advantages, the hybrid data (HD) combining them is employed to drive CV-CNN, which is helpful to improve the effectiveness of the algorithm. We perform experiments on three actual PolSAR image data sets acquired by AIRSAR and Radarsat-2 systems as well as a semisimulated data set. The experimental results demonstrate that, compared to conventional pixel-oriented methods, the proposed SPO scheme is much more time-efficient and is also beneficial to detail preservation. Moreover, the CV-CNN driven by HD generally obtains consistently better classification results than that driven by pure MD or manually designed PFs.

In this paper, we proposed a structure oriented descriptor (SOD) for local image feature description. Different from the traditional methods, we explored the structure information via hierarchical strategy and structure coding elements. Firstly, the support region is partitioned into hierarchical sub-regions according to the intensity orders. Secondly, a pre-designed structure coding image is explored to pooling the features according to the hierarchical sub-regions. The final descriptor is a conjunction of the feature of each sub-region. We evaluated the proposed descriptor on the public dataset and compared it with the state-of-the-art works. The experimental results indicate that the proposed descriptor is robust to image appearance change and outperform the state-of-the-art works in most cases.

Summary The present paper addresses an observer‐based output feedback robust model predictive control for the linear parameter varying system with bounded disturbance and noise subject to input and state constraints. The main contribution is that the on‐line convex optimization problem not only simultaneously optimizes the observer and controller gains to stabilize the augmented closed‐loop system but also incorporates the refreshment of bounds of the estimation error set. The optimization problem steers the nominal augmented closed‐loop system to converge to the origin, and the real augmented closed‐loop system bounded within robust positive invariant set converges to a neighborhood of the origin such that recursive feasibility of the optimization and robust stability of the controlled system are ensured. Two numerical examples are given to illustrate the effectiveness of the method.

In this study, a weakly supervised classification method is proposed to classify the Polarimetric Synthetic Aperture Radar (PolSAR) images based on sample refinement using a Complex-Valued Convolutional Neural Network (CV-CNN) to solve the problem that the bounding-box labeled samples contain many heterogeneous components. First, CV-CNN is used for iteratively refining the bounding-box labeled samples, and the CV-CNN that can be used for direct classification is trained simultaneously. Then, the given PolSAR image is classified using the trained CV-CNN. The experimental results obtained using three actual PolSAR images demonstrate that the heterogeneous components can be effectively eliminated using the proposed method, obtaining significantly better classification results when compared with those obtained using the traditional fully supervised classification method in which original bounding-box labeled samples are used. Furthermore, the proposed method with CV-CNN is superior to those in which the classical Support Vector Machine(SVM) and Wishart classifier are used.

An efficient binary feature is proposed in this paper to compromise the efficiency of simple hash feature and the discrimination of float-point feature. The proposed feature extraction method integrates a hierarchical feature descriptor and a simple but effective hash algorithm. Firstly, the local patch or image area is extracted from the test image. Then, the hierarchical feature descriptor is utilized to embed the structure information as well as the color information of pixels. Finally, a simple binary hash algorithm is proposed to change the hierarchical feature descriptor to a compact binary feature. The proposed binary feature is evaluated based on image retrieval on COREL-1K dataset. The experimental results show that the proposed binary feature is efficient while owns a comparable discrimination to the related works.

For unsupervised classification of polarimetric synthetic aperture radar (PolSAR) images, it is a challenge task to determine an appropriate number of categories. Recently, a method called clustering by fast search and find of density peaks (CFSFDP) has provided a good solution. However, it requires to select the cluster centers by visual observation, which is not only less automated but also may be difficult to implement for some data sets. Focusing on this problem, this paper proposes a method of detecting cluster centers with the constant false alarm rate (CFAR) criterion, and also applies it to the unsupervised classification of PolSAR images. In our method, a variable called center-likelihood for each data point is constructed by multiplying its local density and distance that defined in the CFSFDP algorithm. Then, after estimating the probability density of the center-likelihood, the threshold to detect cluster centers is obtained with the CFAR criterion. The effectiveness of the proposed method is verified by the experimental results of two actual PolSAR images.

This paper focuses on stabilization of T–S fuzzy control systems. We use the information of the premises of the T–S fuzzy control systems to reduce the conservativeness of the stabilization conditions. First, the membership functions (MFs) in the premises are approximated with their piecewise multi-linear interpolations. In this way, different types of MFs can be tackled in a unified approach. We use the errors between the T–S fuzzy systems and the interpolated systems as feedbacks to ensure that the errors tend to zero. Then, we design stable controllers for the fuzzy control systems based on the obtained systems with piecewise multi-linear interpolations and express our results as a group of linear matrix inequalities. It is proved that when the MFs are both single-variate and multi-variate, our results can stabilize the T–S fuzzy control systems. Finally, several simulation examples are utilized to illustrate the merits of the proposed method with both PDC and non-PDC in this paper.

Recently, a complex-valued convolutional neural network (CV-CNN) has been used for the classification of polarimetric synthetic aperture radar (PolSAR) images, and has shown superior performance to most traditional algorithms. However, it usually yields unreliable results for the pixels distributing within heterogeneous regions or the edge areas. To solve this problem, in this paper, an edge reassigning scheme based on Markov random field (MRF) is considered to combine with the CV-CNN. In this scheme,both the polarimetric statistical property and label context information are employed. The experiments performed on a benchmark PolSAR image of Flevoland has demonstrated the superior performance of the proposed algorithm.