Robot orientation and hand-eye relationship simultaneous calibration method based on beam adjustment

Abstract

The invention discloses a robot orientation and hand-eye relationship simultaneous calibration method based on bundle adjustment, which comprises the steps of performing three-dimensional reconstruction on a detection target through a monocular stereoscopic vision algorithm to obtain a camera external parameter matrix without a scale factor alpha; utilizing a robot kinematics equation to obtain arobot motion orientation matrix; representing a calibration equation A(alpha)X=ZB by using a matrix direct product parameter method, and solving a robot orientation and hand-eye relationship initial value; and carrying out iterative optimization on the robot orientation and hand-eye relationship initial value and a three-dimensional reconstruction result obtained by the monocular stereoscopic vision algorithm by using a beam adjustment optimization model. According to the robot orientation and hand-eye relationship simultaneous calibration method based on beam adjustment, based on the light beam adjustment model, accurate three-dimensional positioning can be performed on the target while the robot orientation and the hand-eye relationship are solved, accurate positioning of the detection target is also realized while dependence on the target is eliminated, and thus the intelligent robot is endowed with sensing and positioning functions.

Description

technical field [0001] The invention relates to the technical field of industrial robot vision calibration, in particular to a simultaneous calibration method for robot orientation and hand-eye relationship based on beam adjustment. Background technique [0002] Simulating the visual function of human beings, extracting effective information from the images of the objective world for processing and understanding is a main research purpose of bionic vision, which promotes the ability of intelligent robots to perceive three-dimensional environmental information through visual sensors, and according to their own needs. Pass to the final executive body to complete the hand-eye coordination task. Since Shakey, the world's first intelligent robot with visual sensors, was born in 1966, visual sensors have been widely used in robot autonomous obstacle avoidance and navigation, medical surgery, automobile manufacturing and other fields. When using the robot vision system for autonom...

AI Technical Summary

Problems solved by technology

[0003] 1) AX=XB calibration model, the model determines the camera motion pose matrix A through the plane target, and uses the robot kinematics model to obtain the transformation matrix B from the tool coordinate system to the base coordinate system, thereby obtaining the camera coordinate system and the robot tool coordinate system The hand-eye transformation matrix X; 2) AX=ZB calibration model, when using the plane target to solve the hand-eye relationship X, the model can also solve the orientation relationship Z of the robot base coordinate system and the world coordinate system in the calibration equation; 3) A(α )X=XB or A(α)X=ZB to calibrate the model, the model can use the motion recovery structure algorithm (SFM) to obtain the missing scale factor α camera motion pose matrix A(α) in the case of missing targets, and then use non For the scale factor α and the hand-eye relationship X in the calibration equation, the linear optimization method introduces an additional scale factor α as a parameter to be obtained in the calibration model solution process, resulting in unstable solution accuracy of the equation. Therefore, the third hand-eye calibration model without a target reference The accuracy is often lower than the previous two calibration models, which cannot meet the increasing accuracy requirements of current intelligent robot visual navigation and positioning

Images