Mathematics Model for 6-DOF Joints Manipulation Robots

Abstract

A universal solution to an applied problem related to the study of deviations occurring in the joints of manipulation robots, for example, due to elastic deformations or gaps in them, is proposed. A mathematical (dynamic) model obtained by the Lagrange–Euler method is presented, making it possible to investigate such deviations. Six generalized coordinates, three linear and three angulars, were used to describe the variations of each joint in the dynamic model. This made it possible to introduce into consideration joints with six degrees of freedom (6-DOF joints). In addition, mathematical models for external forces acting on the links of manipulation robots are presented. When composing matrices of coefficients of equations of motion, elements identically equal to zero were excluded, which significantly increased the computational efficiency of these equations. The dynamic model based on the obtained equations can be used in the computer simulation of manipulation robots.

Development of an Artificial Vision for a Parallel Manipulator Using Machine-to-Machine Technologies

“…In this study, the authors achieved a 2–3% increase in accuracy rates, achieving 88% for MobileNetV2, 91% for ResNet50, and 92% for DenseNet121 by adding a squeeze-and-excitation (SE) block that allows the neural network to better extract important features. This study, along with the study by the authors [ 13 ], demonstrates that the use of modern machine learning and deep learning techniques combined with advanced neural network architectures can not only improve the accuracy of detecting abnormal situations depending on various factors but also significantly accelerate the data processing process.…”

A Novel Robotic Controller Using Neural Engineering Framework-Based Spiking Neural Networks

“…When dealing with highly redundant robots and those with numerous degrees of freedom, finding the solution to inverse kinematics becomes an even more complex task, as demonstrated by the works presented in [22,23]. A variant of a recurrent SNN, known as LSNN (Long Short-Term Memory spiking neural network), trainable through error gradients, was introduced in [24,25].…”

Adhesion Coefficient Identification of Wheeled Mobile Robot under Unstructured Pavement

“…However, these visual information-based methods are susceptible to light. In addition, scholars make the best use of different vehicle dynamics models [ 29 , 30 , 31 , 32 , 33 , 34 ] and various kinds of filters [ 35 , 36 , 37 , 38 ] to estimate the adhesion coefficient. For example, the vehicle dynamic model, the tire model, and the wheel model were introduced into the unscented Kalman filter to accurately identify the adhesion coefficient of roads in reference [ 36 ].…”