Method and device for point-to-point trajectory planning of manipulator based on radial basis function

Abstract

An embodiment of the present application provides a point-to-point trajectory planning method for a manipulator based on radial basis functions. The method includes: using Gaussian radial basis functions to construct the motion trajectory of the manipulator; constructing a corresponding optimization objective equation based on the parameters of the radial basis functions , to optimize the time of the entire trajectory; the application can generate a smooth motion trajectory between any target points, and any order derivative of the trajectory is continuous and is not affected by the number of target points. At the same time, the generated trajectory has a simple form and a small amount of calculation. It can use unified parameters to optimize important parameters such as acceleration and jerk to improve the smoothness of the trajectory, thereby reducing the running time of the entire trajectory and improving the stability and workability of the robotic arm. efficiency.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a method and device for point-to-point trajectory planning of a robotic arm based on radial basis functions. Background technique [0002] As a highly automated and intelligent device, robotic arms have been widely used in industrial scenarios. In these work scenarios, the work of the robotic arm is to move from the initial point to the target point through its end effector to complete the specified task, so the motion of the robotic arm can be simplified into a series of point-to-point movements. The purpose of trajectory planning is to connect these points with a smooth motion trajectory. However, a good trajectory planning not only needs to ensure the continuity of the trajectory position, but also the continuity of the high-order derivatives of the trajectory such as velocity, acceleration and jerk (first-order derivative of acceleration), otherwise it will e...

AI Technical Summary

Problems solved by technology

In this type of method, the cubic spline function can only ensure the continuity of speed and acceleration, and it is difficult to improve the performance of the manipulator. In the actual application of the manipulator, it often causes the vibration of the manipulator.

For the quintic spline curve, because the order of the polynomial is too high, the speed, acceleration and other important parameters of the trajectory change too fast, resulting in unstable operation of the manipulator

3. Another method is the trajectory planning method based on B-splines. This method changes the shape of the curve through the control nodes, but the curve parameters are numerous and difficult to set, and the control points need to be back-calculated based on the target points, which is complex in theory and The amount of calculation is large, and the continuous order inside the trajectory is usually limited, which is very inconvenient in actual use

[0004] At the same time, these methods are difficult to adjust the important parameters of the trajectory such as the acceleration and jerk of the trajectory by adjusting simple parameters. It is often necessary to change the position of the target point to find a satisfactory trajectory through trial and error. Not only the steps are cumbersome, but the final effect also difficult to guarantee

Images