Manipulator trajectory tracking based on adaptive sliding mode control

Abstract

A manipulator is a complex electromechanical system that is nonlinear, strongly coupled, and uncertain. Achieving its precise and high-quality trajectory control is difficult.Sliding mode control (SMC) is one of the common control methods for manipulators.However, discontinuities in SMC can cause jitter and vibration in the manipulator system, leading to a reduction in the performance of the control system. For the self-adaptive capability jitter vibration problem of SMC, the Dobot magician manipulator is treated as the research object in this article. The dynamics equations of the manipulator are established by Lagrange method, and a simplified model of the manipulator dynamics is constructed. The method of self-adaptive sliding mode control is proposed. Self-adaptive parameters are added to the SMC to achieve self-adaptive adjustment of the SMC parameters. In the MATLAB/Simulink simulation environment analysis show that the self-adaptive SMC method has better self-tuning ability and trajectory tracking ability than the traditional SMC, and weakens the jitter phenomenon existing in the traditional SMC.

Manipulator trajectory tracking based on adaptive fuzzy sliding mode control

“…It requires only the velocity variables for each build and does not need to take into account internal forces. Therefore, the Lagrange method is used to analyze the dynamics of manipulators 89–91 …”

“…Therefore, the Lagrange method is used to analyze the dynamics of manipulators. [89][90][91] Letting the coupling term T(q) = 0, the kinetic equation can be obtained as:…”

A siamese network-based approach for vehicle pose estimation

“…For vehicles, the process of changing pose represents the interaction between the vehicle and the environment, which is very important for the vehicle to perceive the environment. Intelligent algorithms have been applied to various fields, and have made a series of amazing achievements (Chen et al, 2021a;Chen et al 2021b;Chen et al 2022a;Li et al, 2022;Sun et al, 2022), especially deep learning (Hao et al, 2021;Huang et al, 2022;Sun et al, 2020;Jiang et al, 2021;Yun et al, 2022;Zhao et al, 2022). However, there are still many issues, such as high cost of obtaining and labeling high quality data, which limits the potential of supervised learning (Sünderhauf et al, 2018;Chen et al, 2022b;Chen et al, 2022c).…”

Improved single shot detection using DenseNet for tiny target detection

“…So how to improve the accuracy of small target detection has become a research hotspot. Along with the rapid changes in science and technology, [13][14][15][16][17][18][19] target detection methods based on deep learning can be divided into two categories, One-stage target detection methods and two-stage target detection methods. Among them, two-stage target detection methods have higher detection accuracy and good detection effect especially for small targets, but the training process has more stages, large space-time cost and slower speed, which is represented by R-CNN, 20 SPPnet, 21 Fast R-CNN 22 and Faster R-CNN 23 and other common networks.…”