AGV path tracking method based on inversion sliding mode control

Abstract

The invention belongs to the field of AGV motion control, and relates to an AGV path tracking method based on inversion sliding mode control. The AGV path tracking method comprises the following steps: determining a control target and a control quantity of an AGV system through kinematics modeling, designing an inversion sliding mode controller for the control quantity, and adding a constant-speedreaching law to obtain a system control law containing sliding mode control switching item gain; designing a performance index function of a RBF neural network by taking the buffeting amount as a learning signal, and dynamically adjusting the sliding mode control switching item gain; and optimizing the initial values of the iteratively updated control parameters in the RBF neural network by using a particle swarm algorithm. The buffeting amount is used as the learning signal of the neural network, system buffeting is suppressed more directly and effectively, and the particle swarm algorithmis utilized to calculate the optimal initial value of the parameters so as to accelerate convergence of the AGV system. The stability and the robustness of sliding mode control are fully utilized, buffeting of the AGV system is directly and effectively restrained and accurate and rapid path tracking of the AGV system is achieved.

Description

technical field [0001] The invention relates to the field of AGV motion control, in particular to an AGV path tracking method based on inversion sliding mode control. Background technique [0002] AGV (Automated Guided Vehicle) is an automatic guided vehicle, also known as a mobile robot, which is a handling device that realizes automatic driving with the help of a guiding device. The key technologies of AGV include guidance technology, positioning technology and motion control technology. According to different principles, the guidance methods can be roughly divided into electromagnetic or tape guidance, optical guidance, laser guidance, visual guidance and inertial guidance. Positioning technology uses various sensing devices to obtain real-time pose data of the AGV in the operating environment. [0003] The motion control technology of AGV will directly determine whether it can accurately run on the specified path, which is the core technology of the AGV system. The mot...

AI Technical Summary

Problems solved by technology

However, the non-ideality of the actual system in various aspects makes the switching of the variable structure control delayed, and the system state is difficult to slide strictly along the sliding surface, but crosses back and forth on both sides of the sliding surface, resulting in chattering of the system. This kind of chattering cannot be completely eliminated, it can only be suppressed as much as possible

Images