Line Matching in Visual Servoing for Precise Workpiece Installation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional methods for teaching industrial robots to perform precise pick and place operations, such as component assembly, are unintuitive, time-consuming, and lack positional accuracy, especially when relying on human demonstration without motion capture systems, leading to inaccuracies in visual servoing control.

Innovation Solution

A line matching method for image-based visual servoing that uses a cost function optimized with 2D data in the camera image plane to accurately match lines between target and current images, minimizing rotational and translational errors, thereby improving the precision of robot motion control during workpiece placement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If teaching by human demonstration from camera images is used, then ease of operation is improved, but manufacturing precision deteriorates

Engineering Contradiction:
Improveease of robot teachingVSAvoidworkpiece placement accuracy
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The patent replaces traditional mechanical teaching methods (teach pendants, motion capture systems) with an image-based visual servoing system that uses computer vision and optimization algorithms to achieve both ease of operation and manufacturing precision

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the parameter space from 3D depth data to 2D image plane data, formulating the cost function in terms of 2D coordinates to avoid inaccuracies in depth perception while maintaining placement precision

Inventive Principle:
Principle #35Parameter changes

2Loss of information

If 3D depth data is used for line matching, then completeness of feature information is improved, but measurement precision deteriorates

Engineering Contradiction:
Improvefeature information completenessVSAvoiddepth data accuracy
Core Design Contradiction:
Loss of informationVSMeasurement precision

Solution Approach 1:

The patent extracts only the necessary 2D image plane information for line matching, discarding the inaccurate 3D depth data while retaining sufficient feature information for precise workpiece placement

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent transitions from 3D depth space to 2D image plane space, formulating the line matching cost function in 2D coordinates to eliminate depth-related inaccuracies while maintaining geometric feature matching capability

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Ease of operation

If geometric features are not accurately matched in visual servoing, then ease of operation is maintained, but manufacturing precision deteriorates

Engineering Contradiction:
Improvevisual servoing implementationVSAvoidcomponent assembly accuracy
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The patent implements a feedback mechanism where the cost function continuously evaluates the matching quality between target and current line pairs, and the optimization algorithm adjusts the transformation parameters to minimize matching error, ensuring accurate geometric feature alignment

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent performs preliminary line identification and initial pairing based on distance and angle criteria before the optimization computation, preparing the data structure needed for accurate geometric feature matching during visual servoing

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12017371B2Efficient and robust line matching approach
Publication Date: 2024.06.25 FANUC LTD
  • US12017371B2 patent drawing
  • US12017371B2 patent drawing
  • US12017371B2 patent drawing

AI summary

A method for line matching during image-based visual servoing control of a robot performing a workpiece installation. The method uses a target image from human demonstration and a current image of a robotic execution phase. A plurality of lines are identified in the target and current images, and an initial pairing of target-current lines is defined based on distance and angle. An optimization computation determines image transposes which minimize a cost function formulated to include both direction and distance between target lines and current lines using 2D data in the camera image plane, and constraint equations which relate the lines in the image plane to the 3D workpiece pose. The rotational and translational transposes which minimize the cost function are used to update the line pair matching, and the best line pairs are used to compute a difference signal for controlling robot motion during visual servoing.