Qixin Sha

Fuzzy controller used smoothing function for depth control of autonomous underwater vehicle

Autonomous Underwater Vehicle (AUV) is a typical system which is characterized by nonlinearity, uncertainty of system parameters, and it is also affected by many external disturbances. Therefore, it is difficult to achieve the accurate AUV motion control, which includes depth control, heading control and so on. In order to improve the stability and robustness of depth control system of AUV, this paper researches the model of AUVs motion, analyzes the characteristics of the main existing methods for AUV depth control, including PID, variable structure control (VSC) and fuzzy logic control (FLC). Then, a new method of fuzzy controller used smoothing function (SFFC) for depth control of AUV is proposed based on VSC and fuzzy logic. Finally, simulation and comparison experiments based on dynamic model of AUV are carried out to verify the validity of this method. The results show that the SFFC has better stability and robustness for AUVs depth control system than VSC and PID control.

Gaussian derivative models and ensemble extreme learning machine for texture image classification

Abstract In this paper, we propose an innovative classification method which combines texture features of images filtered by Gaussian derivative models with extreme learning machine (ELM). In the texture image classification, feature extraction is a very crucial step. Thusly, we use linear filters consisting of two Gaussian derivative models, difference of Gaussian (DOG) and difference of offset Gaussian (DOOG), to detect texture information of images. Besides, ensemble extreme learning machine (E2LM) is proposed to reduce the randomness of original ELM and used as the classifier in this paper. We evaluate the performance of both the texture features and the classifier E2LM by using three datasets: Brodatz album, VisTex database and Berkeley image segmentation database. Experimental results indicate that Gaussian derivative models are superior to Gabor filters, and E2LM outperforms the support vector machine (SVM) and ELM in classification accuracy.

The application of AUV navigation based on cubature Kalman filter

Precise positioning of AUV plays an important role in the efficient and reliable underwater operation. The extended Kalman filter (EKF) is the most commonly used method, because this algorithm is easy to implement. However, EKF is only effective for nonlinear systems with approximate linearity, then truncation error is introduced. When the initial state error is large or the system model has high nonlinearity, the estimation effect is poor and the convergence rate is slow. In order to overcome the shortcomings of the EKF, Ienkaran Arasaratnam and Simon Haykin put forward the cubature Kalman filter (CKF). Cubature Kalman filter (CKF) based on the third-degree spherical-radial cubature rule has been proposed and used in many applications, such as positioning, sensor data fusion, and attitude estimation [1]. A large number of experiments by the Swordfish-AUV system platform were carried out in Yantai Menlou reservoir. We analyze the experimental data and conclude that CKF algorithm is closer to the real trajectory than the EKF algorithm.

Nonlinear path following of autonomous underwater vehicle considering uncertainty

In order to complete nonlinear path following smoothly and accurately, this paper proposes a method utilizing the Serret-Frenet Line-of-Sight (LOS) guidance with adaptive compensation in the horizontal plane. All regular paths are feasible. Our method takes three steps to accomplish the path following. First, the guidance law calculates the desired yaw angle. Then an adaptive compensation is added on the desired yaw which considering uncertainty and input saturation. Last, the PID controller is extended to cope with the yaw tracking and velocity control. Simulations and outfield experiments are conducted to verify the feasibility and superiority of the novel approach.

Heading control for an Autonomous Underwater Vehicle using ELM-based Q-learning

Heading control is an important part of Autonomous Underwater Vehicle (AUV) control. But its control performance is restricted to the uncertainty environments, and lack of understanding of dynamic characteristics of AUV. As a model-free method, the Q-learning achieves its control motivation by interacting with the environment and maximizing a reward, so suits the complicated applications in heading control of AUV. However, Q Learning algorithms are not competent for continuous space problems. So, Extreme Learning Machine(ELM) is proposed to guarantee the generalization performance and work with continuous states and actions. In this paper, the method of using ELM based Q Learning is proposed for heading control. The results have shown that the proposed method for heading control has good performance.

Application of modified EKF algorithm in AUV navigation system

The challenge in the Autonomous Underwater Vehicle (AUV) navigation technology is how to ensure precise localization accurately. Extended Kalman filter (EKF) is the most widely used navigation method. Despite its long successful application, EKF has a number of problems in application, for instance, the system motion model usually not appropriate to be described as a linear system. This paper proposed a modified algorithm which combined the Least Squares with Extended Kalman Filter (LS-EKF). The experimental results show that the navigation accuracy of the AUV based on LS-EKF is higher than the EKF.

Classification and mosaicking of side scan sonar image

As an underwater detection sensor, side-scan sonar plays an important role in marine survey, mineral exploration, underwater archaeology and so on. During the use of side-scan sonar, classifiication and mosaicking of collected images is essential in most cases. There are two main contributions in our work. On the one hand, we propose a supervised learning method based on kernel-based extreme learning machine (KELM) to perform image classification. As a single-hidden layer feedforward neural network, ELM has one hidden layer and one output layer. It has been proved that ELM provides better performance in classification and regression at shorter consumed time than some others, such as traditional support vector machine (SVM), without complex parameter adjustment. However, the weights of ELM hidden layer are randomly produced and the classification results of ELM are different because of this. To solve this problem, the kernel-based ELM was proposed, in which the hidden layer was processed with a kernel function to eliminate randomness. On the other hand, the side-scan sonar images and the classified image data will be geo-referenced mosaicked using positions produced by extended Kalman filter (EKF) with sensor data from an autonomous underwater vehicle (AUV). To eliminate gaps in the mosaicking images, image dilation is adopted in our work. Experimental results demonstrate that the proposed classification method works well, and the proposed image mosaicking method is applicable when concerns real side-scan sonar images.

Path following for an autonomous underwater vehicle using GP-LOS

In this paper, we propose a new structure that combines Grey Prediction with Line of Sight (GP-LOS) to predict yaw angle in order to achieve path following for autonomous underwater vehicle (AUV). The proposed structure can be described by two stages. First, we use grey prediction to predict the position coordinates of the next time. Second, taking advantage of the principles of the Line of Sight, we can obtain the desired heading in advance. Then we take the classical PID as control algorithm of AUV because it has the advantage to be easily implemented and to provide reliable control performance. The simulation results have shown that the GP-LOS can achieve the path following effectively whether straight line or curve.