Trajectory tracking control method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a trajectory tracking control method and device, equipment and a storage medium. The method comprises the steps of obtaining a current state of a controlled object, and representing the current state by graph information; inputting the graph information into a preset graph neural network model, and determining a current optimal control sequence in combination with a preset target trajectory, wherein the preset graph neural network model is obtained after training based on a random trajectory data set, and the random trajectory data set comprises a random trajectory state graph and an output label. According to the embodiment of the invention, the graph neural network model is adopted to perform trajectory tracking control on the controlled object, so that the uncertainty of a motion model and a motion environment of the underwater controlled object can be overcome, and efficient and accurate trajectory tracking control on the controlled object is realized.

Description

technical field [0001] The present invention relates to the technical field of machine motion control, in particular to a trajectory tracking control method, device, equipment and storage medium. Background technique [0002] Due to the complexity of the underwater environment, and the underactuated, strong coupling, and nonlinear characteristics of the bionic robotic fish, the trajectory tracking control of the bionic robotic fish has become a very challenging research field. [0003] The control difficulty of the bionic robot fish in the underwater environment is much higher than that of the mobile robot on the ground. Although many traditional control methods such as PID control can realize the control of bionic robotic fish, they are often difficult to cope with dynamic strategies and complex underwater environments. [0004] Model predictive control is an advanced process control method, and its realization depends on dynamic predictive models. In the control time dom...

AI Technical Summary

Problems solved by technology

However, the dynamic prediction model in the model predictive control method is implemented by a multi-layer neural network. This simple multi-layer neural network model has poor representation ability for the relationship between the joints in the physical model of the bionic robotic fish, which will lead to the trajectory tracking of the bionic robotic fish. The deviation of the results is large, and the trajectory tracking control of the bionic robot fish cannot be performed accurately.

[0006] There are more or less problems in the existing trajectory tracking control methods, and the results of the existing trajectory tracking deviate greatly from the target trajectory. Therefore, there is an urgent need for an efficient and accurate method to control the Control object for trajectory tracking control

Images