Simultaneous Kinematic and Hand-Eye Calibration for Robot Vision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine vision systems face accuracy issues due to inadequate calibration of kinematic and hand-eye calibration parameters, leading to insufficient precision in Vision Guided Robot (VGR) applications.
Innovation Solution
A method that refines kinematic and hand-eye calibration parameters by capturing images and joint angles of a calibration target at multiple poses, using non-linear least squares to minimize a cost function, thereby determining more accurate calibration parameter values without requiring additional calibration targets or external equipment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional separate calibration methods are used for kinematic parameters and hand-eye calibration parameters, then the calibration process becomes simpler and more straightforward, but the overall accuracy and precision of the machine vision system deteriorates
Solution Approach 1:
The patent combines kinematic calibration and hand-eye calibration into a single simultaneous calibration process. The cost function integrates both calibration objectives, allowing both sets of parameters to be optimized together using image data from the camera and joint angle data from the robot, thereby achieving higher overall accuracy without requiring separate calibration procedures
Solution Approach 2:
The patent changes the calibration approach from separate parameter optimization to simultaneous parameter optimization. By formulating a unified cost function that includes both kinematic parameters and hand-eye calibration parameters, the system can refine all parameters together using non-linear least squares, leading to improved measurement precision
2Measurement precision
If multiple calibration targets or external measurement equipment are used to improve calibration accuracy, then the measurement precision improves, but the device complexity and cost increase
Solution Approach 1:
The machine vision system performs self-calibration by using its own camera and robot joint angle sensors to collect data for refining both kinematic and hand-eye calibration parameters. The system uses the calibration target imaged by its own camera and the joint angles from its own sensors, eliminating the need for external measurement equipment or additional calibration targets
Solution Approach 2:
The calibration process uses the existing camera and robot system for multiple purposes: capturing images of the calibration target, measuring joint angles, and refining both kinematic and hand-eye calibration parameters simultaneously. This multi-functional approach eliminates the need for dedicated external calibration equipment
Data Source
AI summary
Described are machine vision systems and methods for simultaneous kinematic and hand-eye calibration. A machine vision system includes a robot and a 3D sensor in communication with a control system. The control system is configured to move the robot to poses, and for each pose: capture a 3D image of calibration target features and robot joint angles. The control system is configured to obtain initial values for robot calibration parameters, and determine initial values for hand-eye calibration parameters based on the initial values for the robot calibration parameters, the 3D image, and joint angles. The control system is configured to determine final values for the hand-eye calibration parameters and robot calibration parameters by refining the hand-eye calibration parameters and robot calibration parameters to minimize a cost function.