Real-Time Decentralized Neural Control via Backstepping for a Robotic Arm Powered by Industrial Servomotors

Deep residual neural-network-based robot joint fault diagnosis method

A data driven method-based robot joint fault diagnosis method using deep residual neural network (DRNN) is proposed, where Resnet-based fault diagnosis method is introduced. The proposed method mainly deals with kinds of fault types, such as gain error, offset error and malfunction for both sensors and actuators, respectively. First, a deep residual network fault diagnosis model is derived by stacking small convolution cores and increasing the core size. meanwhile, the gaussian white noise is injected into the fault data set to verify the noise immunity for the proposed deep residual network. Furthermore, a simulation is conducted, where different fault diagnosis methods including support vector machine (SVM), artificial neural network (ANN), convolutional neural network (CNN), long-term memory network (LTMN) and deep residual neural network (DRNN) are compared, and the simulation results show the accuracy of fault diagnosis for robot system using DRNN is higher, meanwhile, DRNN needs less model training time. Visualization analysis proved the feasibility and effectiveness of the proposed method for robot joint sensor and actuator fault diagnosis using DRNN method.

CED: A Distance for Complex Mass Functions

Evidence theory is an effective methodology for modeling and processing uncertainty that has been widely applied in various fields. In evidence theory, a number of distance measures have been presented, which play an important role in representing the degree of difference between pieces of evidence. However, the existing evidential distances focus on traditional basic belief assignments (BBAs) modeled in terms of real numbers and are not compatible with complex BBAs (CBBAs) extended to the complex plane. Therefore, in this article, a generalized evidential distance measure called the complex evidential distance (CED) is proposed, which can measure the difference or dissimilarity between CBBAs in complex evidence theory. This is the first work to consider distance measures for CBBAs, and it provides a promising way to measure the differences between pieces of evidence in a more general framework of complex plane space. Furthermore, the CED is a strict distance metric with the properties of nonnegativity, nondegeneracy, symmetry, and triangle inequality that satisfies the axioms of a distance. In particular, when the CBBAs degenerate into classical BBAs, the CED will degenerate into Jousselme et al.'s distance. Therefore, the proposed CED is a generalization of the traditional evidential distance, but it has a greater ability to measure the difference or dissimilarity between pieces of evidence. Finally, a decision-making algorithm for pattern recognition is devised based on the CED and is applied to a medical diagnosis problem to illustrate its practicability.

Exponential H∞ Filtering for Continuous-Time Switched Neural Networks Under Persistent Dwell-Time Switching Regularity

This paper focuses on the exponential H_∞ filtering issue for a class of continuous-time switched neural networks (NNs). Our aim is to design a mode-dependent filter acquiring the state of the investigated system, and ensuring the global uniform exponential stability of the resulting filtering error system. The persistent dwell-time (PDT) switching strategy is employed to represent the switching among NNs. By utilizing a suitable Lyapunov function and the switched system theory, some criteria for the solvability of the addressed problem are presented under the full consideration of switching frequency. Finally, the filter gains are derived by a straightforward decoupling method, and with the aid of the algorithm of the continuous-time PDT switching regularity, the availability of the filter is expounded through a numerical example.

Q-learning trajectory planning based on Takagi–Sugeno fuzzy parallel distributed compensation structure of humanoid manipulator

NAO is the first robot created by SoftBank Robotics. Famous around the world, NAO is a tremendous programming tool and he has especially become a standard in education and research. Aiming at the large error and poor stability of the humanoid robot NAO manipulator during trajectory tracking, a novel framework based on fuzzy controller reinforcement learning trajectory planning strategy is proposed. Firstly, the Takagi–Sugeno fuzzy model based on the dynamic equation of the NAO right arm is established. Secondly, the design and the gain solution of the state feedback controller based on the parallel feedback compensation strategy are studied. Finally, the ideal trajectory of the motion is planned by reinforcement learning algorithm so that the end of the manipulator can track the desired trajectory and realize the valid obstacle avoidance. Simulation and experiment shows that the end of the manipulator based on this scheme has good controllability and stability and can meet the accuracy requirements of trajectory tracking accuracy, which verifies the effectiveness of the proposed framework.

A wavelet neural control scheme for a quadrotor unmanned aerial vehicle

Wavelets are designed to have compact support in both time and frequency, giving them the ability to represent a signal in the two-dimensional time-frequency plane. The Gaussian, the Mexican hat and the Morlet wavelets are crude wavelets that can be used only in continuous decomposition. The Morlet wavelet is complex-valued and suitable for feature extraction using the continuous wavelet transform. Continuous wavelets are favoured when high temporal and spectral resolution is required at all scales. In this paper, considering the properties from the Morlet wavelet and based on the structure of a recurrent high-order neural network model, a novel wavelet neural network structure, here called a recurrent Morlet wavelet neural network, is proposed in order to achieve a better identification of the behaviour of dynamic systems. The effectiveness of our proposal is explored through the design of a decentralized neural backstepping control scheme for a quadrotor unmanned aerial vehicle. The performance of the overall neural identification and control scheme is verified via simulation and real-time results.This article is part of the theme issue 'Redundancy rules: the continuous wavelet transform comes of age'.