No abstract

No abstract

Hand gesture recognition is an intuitive and effective way for humans to interact with a computer due to its high processing speed and recognition accuracy. This paper proposes a novel approach to identify hand gestures in complex scenes by the Single-Shot Multibox Detector (SSD) deep learning algorithm with 19 layers of a neural network. A benchmark database with gestures is used, and general hand gestures in the complex scene are chosen as the processing objects. A real-time hand gesture recognition system based on the SSD algorithm is constructed and tested. The experimental results show that the algorithm quickly identifies humans’ hands and accurately distinguishes different types of gestures. Furthermore, the maximum accuracy is 99.2%, which is significantly important for human-computer interaction application.

In this article, a fault-tolerant control method based on augmented improved extended state observer and non-singular high-order fast terminal sliding mode is proposed for a class of second-order systems with actuator faults. First, the initial peak of the traditional extended state observer is avoided by improving the structure of the observer. Second, the total disturbance and its change trend are observed simultaneously, so as to better realize the compensation of total disturbance. The convergence of the observer is proved theoretically. In addition, by designing non-singular high-order fast terminal sliding mode surface, the sliding mode variable converges rapidly during the whole process to improve the algorithm’s rapidity. Finally, the chattering of control signal caused by sliding mode control is greatly reduced using high-order sliding mode technology, and the stability of the whole closed-loop system is proved by Lyapunov criterion. The comparative experimental results on the fault-tolerant control platform of the quadrotor unmanned aerial vehicle demonstrate the effectiveness and superiority of the proposed observer and controller.

In this paper, a new congestion controller is developed to obtain a feedforward and feedback optimal control for networked control systems (NCS) with persistent disturbances. The disturbances have known dynamic characteristics but unknown initial conditions. The disturbance observer is proposed to make the feedforward control law realizable physically. In the approach only the non-linear compensating term, solution of a sequence of adjoint vector differential equations, is required iteration. By taking the finite iteration of non-linear compensating term of optimal solution sequence, a suboptimal control law for NCS with time delay can be obtained.