Robot Imaging for Thickness Measurement of Stacked Workpieces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robot systems face challenges in accurately measuring the thickness of stacked workpieces, such as cardboard boxes, as conventional three-dimensional measuring devices require a specific positional relation and cannot measure when workpieces are stacked or when the side surface does not face the sensor.
Innovation Solution
A robot system equipped with an image capturing unit that captures two-dimensional images of workpieces, an image processing unit that acquires distance information, a distance image generation unit, and a thickness calculation unit, which calculates the thickness based on the distance image, allowing the system to capture images regardless of the positional relation between the workpiece and the image capturing unit.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a conventional three-dimensional measuring device is used to measure workpiece thickness, then measurement can be performed, but the device requires a specific positional relation where the side surface of the workpiece must face the sensor, which limits measurement capability when workpieces are stacked
Solution Approach 1:
The patent transitions from conventional three-dimensional sensors requiring specific spatial orientation to a two-dimensional image processing approach that extracts thickness information from planar images. By capturing images from above (top-down view) and processing them through distance information extraction and perspective transformation, the system eliminates the need for side-surface orientation while still achieving accurate thickness measurement. This dimensional approach change allows measurement of stacked workpieces without requiring specific positional relations between the sensor and workpiece side surfaces.
2Adaptability or versatility
If the image capturing unit captures images regardless of positional relation, then versatility is improved, but measurement precision may be compromised due to varying angles and distances
Solution Approach 1:
The patent implements a feedback mechanism through the image processing unit that continuously adjusts and corrects distance information based on the captured two-dimensional images. By extracting distance information from the images and using perspective transformation to account for varying angles and distances, the system compensates for positional variations and maintains measurement precision. The processing unit calculates thickness based on corrected distance data, ensuring accurate measurements even when the workpiece position or orientation varies relative to the image capturing unit.
Solution Approach 2:
The patent changes the processing parameters by transforming the captured two-dimensional images into distance information maps and then applying perspective transformation to correct for viewing angles. This parameter transformation allows the system to maintain measurement precision across varying positional relations. The thickness calculation unit uses these transformed parameters to compute accurate thickness values regardless of the workpiece's position or orientation in the imaging field.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate thickness measurement of workpieces, including stacked ones, without the need for a reference position, improving precision and versatility in handling and loading operations.
Implementation Method 1
an image capturing unit that captures a two-dimensional image of a workpiece
Implementation Method 2
an image processing unit that acquires distance information of the workpiece based on the two-dimensional image
Data Source
AI summary
Provided are a robot system and a control method with which it is possible to highly precisely acquire the thickness of an object. This robot system comprises an imaging unit that is mounted on a robot and that captures a two-dimensional image of an object, an image processing unit that acquires distance information pertaining to the object on the basis of the two-dimensional image, a distance image generation unit that generates a distance image on the basis of the distance information, and a thickness calculation unit that calculates the thickness of the object on the basis of the distance image, the imaging unit capturing the two-dimensional image of the object irrespective of the positional relationship between the side surface of the object and the imaging unit.