Four switch Buck boost (FSBB) converters are widely used in the fields of new energy and DC interconnection due to their ability to convert DC voltage up and down and bidirectional power flow. Quadrilateral inductor c...
详细信息
Traffic text, as a special type of natural scene text, plays an important role in intelligent transportation. Apart from the challenges faced by general natural scene text detection, the presence of a large amount of ...
详细信息
Traffic text, as a special type of natural scene text, plays an important role in intelligent transportation. Apart from the challenges faced by general natural scene text detection, the presence of a large amount of non-traffic text which leads to false alarms further complicates the problem of traffic text detection, e.g., billboards, building signs, etc. In this work, we infer text component relationships via a component relationship reasoning network (CR2-Net) for traffic text detection. The method contains main contributions as follows: (1) explored a GCN-based component-relational reasoning traffic text detection network by leveraging global contextual information and reasoning about intrinsic connections between text components to improve traffic text detection performance. (2) designed a Group Deformable Convolution Network (GDCN) and adaptively adjusting the convolutional manner to enhance the feature extraction capability of the network for text regions. (3) proposed a Fusion Attention Module (FAM) to enhance the network adaptive ability by assigning feature map weights to different channels. To demonstrate the effectiveness, we evaluate CR2-Net on four standard benchmarks. Experimental results demonstrate that our method achieves remarkable performance on two traffic text datasets, i.e., CTST-1600, and TPD. Especially, our results on TPD dataset surpass all previously reported results to the best of our knowledge. Additionally, our approach exhibits competitive results on general natural scene text datasets, such as ICDAR 2015, and SCUT-CTW1500, thereby fully demonstrating the superiority and adaptability of our method. The code will be publicly available at https://***/runminwang/CR2-Net. IEEE
This paper studies secure output synchronization for heterogeneous multi-agent systems against false data injection(FDI) attacks. Both the sensors and actuators of agents may be injected into FDI *** mitigate the mali...
详细信息
This paper studies secure output synchronization for heterogeneous multi-agent systems against false data injection(FDI) attacks. Both the sensors and actuators of agents may be injected into FDI *** mitigate the malicious impact of these attacks on synchronization performance, a desired reference model,which is combined with an auxiliary system, is first designed for each agent to simulate its normal system dynamics. Then, based on this reference model, a state feedback cooperative controller and a static output feedback cooperative controller, which consist of adaptive compensators, are proposed, respectively. The integrated control protocols can ensure that the output synchronization error is small by adjusting some designed parameters even in the presence of FDI attacks. An illustrative example is employed to demonstrate the effectiveness of the proposed method.
Numerous complex nonlinear systems in the real-world constantly suffer from random noises, which contribute to the enormous challenge of system control. Additionally, unknown powers in nonlinear systems always lead to...
Numerous complex nonlinear systems in the real-world constantly suffer from random noises, which contribute to the enormous challenge of system control. Additionally, unknown powers in nonlinear systems always lead to the inapplicability of many reported control methods. This article investigates the control issue of stochastic systems which contain complicated nonlinearities and unknown system powers. With the newly constructed Lyapunov function, as well as the control algorithm presented in this work, the authors successfully obtain a controller so that the closed-loop system is semiglobally finite-time stable in probability(SGFSP). Besides, the system output can trackthe reference signal fast. The presented method significantly enlarges the range of application for nonlinear systems. The presented strategy is successfully applied to the liquid-level system.
Robotic microinjection has been widely applied in biomedical engineering, but faces a great challenge on the precise force interaction with cells due to their inherently deformable, fragile, and nonlinear viscoelastic...
详细信息
This article presents an adaptive optimal control method for a semi-active suspension *** model of the suspension system is built,in which the components of uncertain parameters and exogenous disturbance are *** adapt...
详细信息
This article presents an adaptive optimal control method for a semi-active suspension *** model of the suspension system is built,in which the components of uncertain parameters and exogenous disturbance are *** adaptive optimal control law consists of the sum of the optimal control component and the adaptive control ***,the optimal control law is designed for the model of the suspension system after ignoring the components of uncertain parameters and exogenous disturbance caused by the road *** optimal control law expresses the desired dynamic characteristics of the suspension ***,the adaptive component is designed with the purpose of compensating for the effects caused by uncertain parameters and exogenous disturbance caused by the road surface;the adaptive component has adaptive parameter rules to estimate uncertain parameters and exogenous *** exogenous disturbances are eliminated,the system responds with an optimal controller *** separating theoretically the dynamic of a semi-active suspension system,this solution allows the design of two separate controllers easily and has reduced the computational burden and the use of too many tools,thus allowing for more convenient hardware *** simulation results also show the effectiveness of damping oscillations of the proposed solution in this article.
To improve pure integral calculations with integral drift and dc bias, and poor dynamic response under conventional direct power control, a grid-voltage sensorless predictive current control strategy of three-phase PW...
详细信息
With the widespread application of legged robot in various fields,the demand for a robot with high locomotion and manipulation ability is *** an extra arm is a useful but general method for a legged robot to obtain ma...
详细信息
With the widespread application of legged robot in various fields,the demand for a robot with high locomotion and manipulation ability is *** an extra arm is a useful but general method for a legged robot to obtain manipulation ***,this paper proposes a novel hexapod robot with two integrated leg–arm limbs that obtain dexterous manipulation functions besides locomotion ability without adding an extra *** manipulation modes can be divided into coordinated manipulation condition and single-limb manipulation *** former condition mainly includes fixed coordinated clamping case and fixed coordinated shearing *** the fixed coordinated clamping case,the degrees of freedom(DOFs)analysis of equivalent parallel mechanism by using screw theory and the constraint equation of two integrated limbs are *** the fixed coordinated shearing case,the coordinated working space is determined,and an ideal coordinated manipulation ball is presented to guide the coordinated shearing *** addition,the constraint analysis of two adjacent integrated limbs is ***,mobile manipulation with one integrated leg–arm limb while using pentapod gait is discussed as the single-limb manipulation condition,including gait switching analysis between hexapod gait and pentapod gait,different pentapod gaits analysis,and a complex six-DOF manipulation while *** experiments are implemented,including clamping tasks with two integrated limbs,coordinated shearing task by using two integrated limbs,and mobile manipulation with pentapod *** robot provides a new approach to building a multifunctional locomotion platform.
The concept of aborted lane-change is introduced in this paper, and the lane-change decisions are divided into four states: lane-keeping, lane-change, keeping lane-change and aborting lane-change. Considering the lane...
详细信息
This paper investigates the robust control of discrete delayed networked systems with stochastic communication protocol (SCP), quantization and packet loss. Considering limited communication resources and network band...
详细信息
暂无评论