Automated guided vehicle, control method thereof, and control system thereof

Abstract

The embodiments of the invention disclose an automated guided vehicle, a control method thereof, and a control system thereof. The control method of the automated guided vehicle includes the steps: establishing a kinetics model of the automated guided vehicle, and by means of the kinetics model, calculating the pose data of the automated guided vehicle; according to the pose data and the error ofthe target movement path, by means of a section II type fuzzy control algorithm, calculating the adjustment amount of the automated guided vehicle; and through the adjustment amount, controlling the automated guided vehicle to move along the target movement path. The control method of the automated guided vehicle employs the control strategy of section II type fuzzy control, so as to enable AGV (Automated Guided Vehicle) to have higher robustness during the path tracking process, and can be applied to more different scenes.

Description

technical field [0001] The invention relates to the technical field of automatic control, in particular to an automatic guided transport vehicle, a control method and a control system thereof. Background technique [0002] Automated Guided Vehicle AGV is an automated material handling equipment. It is equipped with automatic guidance devices such as electromagnetic or optical, which can drive along the predetermined target guidance path, and has safety protection and various transfer functions. The motion control of AGV is one of the key technologies to realize the high-precision, stable and smooth operation of self-guided forklifts. The design of traditional controllers depends on the precise model of the controlled object, and the relevant motion models will have different changes under different conditions such as vehicle no-load and heavy-load. Moreover, the model of the forklift itself is nonlinear, and the effect of applying traditional linear control algorithms is n...

AI Technical Summary

Problems solved by technology

However, due to the complexity of AGV movement, it is difficult to establish an accurate model, and the so-called optimal can only be theoretical

[0006] The neural network control method is suitable for the control of nonlinear systems, but the neural network control method needs to turn all the characteristics of the problem into numbers, and turn all reasoning into numerical calculations. For self-guided forklifts with more complex travel paths, It is completely impossible to collect all the information of forklifts at different deviations and speeds. When the data is insufficient, the neural network cannot work, and the accuracy of AGV walking cannot be guaranteed.

[0007] In the process of realizing the present invention, the inventors found the following problems in related technologies: Among the several existing control strategies, the linear model control method needs to establish an accurate mathematical model for the controlled object, and the control parameters cannot be changed after they are determined. With adaptive ability, it is difficult to make online adjustments to industrial AGV deviation changes, environmental changes and changes in motion characteristics, thus affecting the path tracking accuracy

However, the robustness of the optimal control algorithm is not good enough. When the parameters of the forklift or the operating environment of the forklift change slightly, the control effect cannot be guaranteed.

In addition, the learning speed of the neural network control method is slow and may converge to a low-quality local optimal point of the objective function. At the same time, each neuron and weight in the network cannot be given a clear physical meaning, so the existing knowledge to improve the structural design of the network to speed up learning and avoid low-quality local optima

Images