The demand for heterogeneous unmanned aerial vehicles (UAVs) equipped with various types and complementary resources to perform complex tasks is increasing. Existing researches on game theory-based resource allocation primarily focus on continuous resources, by establishing models and transforming them into convex optimization problems. However, the discrete task resource allocation problem considered in this paper does not meet the assumptions of continuous optimization models, therefore, a reasonable allocation method is needed. To enhance the allocation efficiency for multi-UAVs operating under discrete resource constraints, we design a heuristic task allocation method based on game theory. Our method integrates multiple critical factors, including task priority and dynamic task benefits, into the resource matching process, offering a robust solution tailored to the diverse demands. Specifically, we first establish an optimization model encompassing UAVs, requirements and revenue, then we adopt a utility function to depict these relationships. Furthermore, considering the distributed cooperative characteristics of UAVs during task execution, we incorporate the correspondence between UAVs and tasks into the framework of a coalition formation game (CFG). Building on this foundation, we develop a heuristic allocation method based on task validity matching and an ineffective resource exit mechanism. We also introduce tabu lists to avoid ineffective searches, aiming to enhance resource utilization while ensuring task utility. Finally, we analyze the convergence of our proposed algorithm and conduct simulation validations across various scenarios. The results indicate that our algorithm can adapt to dynamic changes in task demands, exhibits good scalability, and is capable of enhancing task utility.

The method proposed in this letter for synthetic aperture radar (SAR) image classification has two main stages. In the first stage, a convolutional neural network (CNN) is trained for normal SAR image classification task. After training, the sample features can be obtained by extracting the output of middle layer in the forward propagation process of CNN. In the second stage, an end-to-end metric network is trained to measure the relations between sample features. The method proposed in this letter is tested with some of the larger targets in OpenSARShip data set which is collected from Sentinel-1 satellite, and it is also tested with the MSTAR data set which is created by the U.S. Air Force Laboratory. The experimental results show that our method can get a higher recognition accuracy than normal CNN structure.

With the development of robotics, the multiple mobile robot system (MMRS) has been an attention-getting subject in recent years and has been widely used in military, civilian and other fields. Cooperative localization is the key technology of the MMRS. And observability analysis for MMRS and nonlinear problem are the foremost problems to cooperative localization. In order to enhance the accuracy of cooperative localization for MMRS, a novel cooperative localization algorithm based on hybrid topology architecture under the framework of extended Kalman filter (EKF) is proposed in this paper. In this novel algorithm, a hybrid topology architecture based on the relative position measurement graph method is adopted to enhance the usage efficiency of observations, improving the cooperative localization accuracy. Meanwhile, EKF is used in this novel cooperative localization algorithm to solve the nonlinearity of the MMRS. Finally, a real dataset is used to verify the availability and superiority of this novel algorithm.