Walking robot self-adaptation calibration method, system and facility and storage medium

Abstract

The invention provides a walking robot self-adaptation calibration method, system and facility and a storage medium. The method comprises the steps that a first weight coefficient related to the leftwheel linear speed of a walking robot, a second weight coefficient related to the right wheel linear speed and a third weight coefficient related to the angular speed are set; current theoretical coordinates are obtained through positioning iteration, and current actual coordinates are obtained through video positioning; and according to deflection of the current theoretical coordinates and the current actual coordinates, at least one set of first weight coefficient, second weight coefficient and third weight coefficient are solved, so that the theoretical coordinates are obtained. According to the walking robot self-adaptation calibration method, system and facility and the storage medium, for different application scenes, according to scene changes and robot motion character changes, self-adaptation calibration can be conducted, the robot can achieve good motion precision under various scenes, and the calibration accuracy and flexibility of application to different scenes are greatlyimproved.

Description

technical field [0001] The invention relates to the field of robot calibration, in particular to an adaptive calibration method, system, equipment and storage medium of a walking robot. Background technique [0002] With the development of computer technology, computer vision, as an important research field of artificial intelligence, has been widely used in various industries. Combining computer vision technology with robotics has also enabled the field of intelligent robotics to develop vigorously. For the grasping of the manipulator, the manual teaching method is traditionally used, such as breaking the manipulator by hand, so that the manipulator can go to a fixed position for grasping. This method is relatively inefficient and because the manipulator has no sense of the surrounding environment. , if the position of the robotic arm or the position of the object changes, the robotic arm cannot grasp the object. [0003] Applying computer vision to the field of robotics ...

AI Technical Summary

Problems solved by technology

However, the general hand-eye calibration process is complicated and requires manual intervention, or taking marker points, or manually recording data, which is inconvenient to use. However, hand-eye calibration is often used in vision experiments, whether it is the position of the camera or the position of the robot arm. Or when the type of the robot arm changes, the hand-eye calibration must be performed again, while the traditional hand-eye calibration takes a long time, which greatly lengthens the cycle of the visual experiment

Images