This paper investigates the position and attitude tracking control problem of a quadrotor unmanned aerial vehicle subject to modeling uncertainties and actuator failures. A comprehensive mathematical model reflecting the nonlinearity and state-space coupling of the dynamics as well as actuation faults and external disturbances is derived. By combining the radial basis function neural networks (NNs) with virtual parameter estimating algorithms, an indirect NN-based adaptive fault-tolerant control scheme is developed, which exhibits several attractive features as compared with most existing methods: 1) it is not only robust and adaptive to nonparametric uncertainties but also tolerant to unexpected actuation faults; 2) it ensures stable tracking without the need for precise information on system model; and 3) it only involves one lumped parameter adaptation, thus is structurally simpler and computationally less expensive, rendering the resultant scheme less demanding in programming and more affordable for onboard implementation. The effectiveness and benefits of the proposed method are confirmed via computer simulation.
One major reason for the success of convolutional neural networks (CNNs) is the availability of large-scale labeled data. Effective training of CNNs relies on large annotated data. Unfortunately, large amounts of data with corresponding annotations are too expensive to obtain in some real-world applications. One reasonable alternative is to use data augmentation techniques to automatically generate annotated samples. In this paper, a novel data augmentation framework based on perspective transformation is proposed. This method automatically generates new annotated data without extra manual labeling, thus effectively extends the inadequate dataset. Perspective transformation can produce new images captured from any cameras viewpoints. Therefore, our method can mimic images taken at the angle that the camera cannot reach. Extensive experimental results on several datasets have demonstrated that our perspective transformation data augmentation strategy is an effective tool when using deep CNNs on small or imbalance datasets.
We propose a tilt sensing scheme using a physical model with three sensitive axes of microelectromechanical systems (MEMS) accelerometers. Based on the physical model in which the gravitational acceleration is resolved into three components, we propose three numerical models to sense the tilt angle. First, two exact numerical models are presented to measure the gravitational acceleration and its one component along the tilt direction, respectively. The parameters of these two models are specific angles of the physical model, which can be used to assess the configuration of the physical model. Next, the measurement bias model is introduced to reduce the error resulting from the nonlinear relation between the gravitational acceleration and the tilt angle. Third, all the three numerical models are unified into a linear model whose parameters can be efficiently estimated using the least squares method. In the experiments, we evaluate the performance of the proposed scheme by examining the mean, the standard deviation, and the maximum of the errors. The experiment results show that our scheme is able to perform accurate tilt sensing with the average error below 0.1 ° in the measurement range (0 ° , 120 ° ).