Go Deep or Broad? Exploit Hybrid Network Architecture for Weakly Supervised Object Classification and Localization.

Weakly supervised object classification and localization are learned object classes and locations using only image-level labels, as opposed to bounding box annotations. Conventional deep convolutional neural network (CNN)-based methods activate the most discriminate part of an object in feature maps and then attempt to expand feature activation to the whole object, which leads to deteriorating the classification performance. In addition, those methods only use the most semantic information in the last feature map, while ignoring the role of shallow features. So, it remains a challenge to enhance classification and localization performance with a single frame. In this article, we propose a novel hybrid network, namely deep and broad hybrid network (DB-HybridNet), which combines deep CNNs with a broad learning network to learn discriminative and complementary features from different layers, and then integrates multilevel features (i.e., high-level semantic features and low-level edge features) in a global feature augmentation module. Importantly, we exploit different combinations of deep features and broad learning layers in DB-HybridNet and design an iterative training algorithm based on gradient descent to ensure the hybrid network work in an end-to-end framework. Through extensive experiments on caltech-UCSD birds (CUB)-200 and imagenet large scale visual recognition challenge (ILSVRC) 2016 datasets, we achieve state-of-the-art classification and localization performance.

Performance-guaranteed distributed control for multiple plant protection UAVs with collision avoidance and a directed topology.

The urgent requirement for improving the efficiency of agricultural plant protection operations has spurred considerable interest in multiple plant protection UAV systems. In this study, a performance-guaranteed distributed control scheme is developed in order to address the control of multiple plant protection UAV systems with collision avoidance and a directed topology. First, a novel concept called predetermined time performance function (PTPF) is proposed, such that the tracking error can converge to an arbitrary small preassigned region in finite time. Second, combined with the two-order filter for each UAV, the information estimation from the leader is generated. The distributed protocol avoids the use of an asymmetric Laplace matrix of a directed graph and solves the difficulty of control design. Furthermore, by introducing with a collision prediction mechanism, a repulsive force field is constructed between the dynamic obstacle and the UAV, in order to avoid the collision. Finally, it is rigorously proved that the consensus of the multiple plant protection UAV system can be achieved while guaranteeing the predetermined time performance. A numerical simulation is carried out to verify the effectiveness of the presented method, such that the multiple UAVs system can fulfill time-constrained plant protection tasks.

Fault Detection Filter Design and Optimization for Switched Systems with All Modes Unstable.

This problem of intelligent switched fault detection filter design is investigated in this article. Firstly, the mode-dependent average dwell time (MDADT) method is applied to generate the time-dependent switching signal for switched systems with all subsystems unstable. Afterwards, the switched fault detection filter is proposed for the generation of residual signal, which consists of dynamics-based filter and learning-based filter. The MDADT method and multiple Lyapunov function (MLF) method are employed to guarantee the stability and prescribed attenuation performance. The parameters of dynamics-based filter are given by solving a series of linear matrix inequalities. To improve the transient performance, the deep reinforcement learning is introduced to design learning-based filter in the framework of actor-critic. The output of learning-based filter can be viewed as uncertainties of dynamics-based filter. The deep deterministic policy gradient algorithm and nonfragile control are adopted to guarantee the stability of algorithm and compensate the external disturbance. Finally, simulation results are given to illustrate the effectiveness of the method in the paper.

Intelligent Guidance and Control Methods for Missile Swarm.

High-speed unmanned aerial vehicles (UAVs) are more and more widely used in both military and civil fields at present, especially the missile swarm attack, and will play an irreplaceable key role in the future war as a special combat mode. This study summarizes the guidance and control methods of missile swarm attack operation. First, the traditional design ideas of the guidance and control system are introduced; then, the typical swarm attack guidance and control methods are analyzed by taking their respective characteristics into considering, and the limitations of the traditional design methods are given. On this basis, the study focuses on the advantages of intelligent integrated guidance and control design over traditional design ideas, summarizes the commonly used integrated guidance and control design methods and their applications, and explores the cooperative attack strategy of missile swarm suitable for the integrated guidance and control system. Finally, the challenges of missile swarm guidance and control are described, and the problems worthy of further research in the future are prospected. Summarizing the guidance and control methods of missile will contribute to the innovative research in this field, so as to promote the rapid development of unmanned swarm attack technology.