Robot Vision Detection of Layer Dividers in Irregular Stacks

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current robotic systems lack the sophistication to effectively detect and manage layer dividers between objects on loading or transportation platforms, particularly due to irregular arrangements and shapes, which complicates the identification and retrieval of these dividers.

Innovation Solution

A computing system is developed that includes a control system communicating with a robot equipped with a camera and a robot arm, using 3D and 2D image information to identify edges, contours, and extension lines to detect the presence of layer dividers and determine their contours, allowing for precise robotic movement and trajectory planning to interact with the dividers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional robotic systems are used to detect layer dividers, then the system structure is simple, but the detection precision and accuracy are insufficient due to irregular arrangements and shapes of objects

Engineering Contradiction:
Improvedetection precisionVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The detection process is divided into multiple stages: first detecting the stack contour, then identifying extension lines from the perimeter toward the center, and finally detecting layer dividers based on interrupted extension lines. This segmentation of the detection process enables precise detection of irregular objects by breaking down the complex task into manageable steps.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system transitions from 2D image information to 3D spatial understanding by detecting extension lines that extend from the perimeter toward the center of the stack. This dimensional approach allows the system to detect layer dividers by identifying where extension lines are interrupted, providing accurate detection even for irregularly shaped objects.

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

2Productivity

If simple detection methods are used, then the device complexity is low, but the speed and accuracy of detecting layer dividers are insufficient

Engineering Contradiction:
Improvedetection speedVSAvoidprocessing complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system performs preliminary detection of the stack contour and extension lines before detecting the layer dividers. By first establishing the perimeter and generating extension lines, the system creates a framework that speeds up the subsequent layer divider detection process, as the dividers are identified by interruptions in the pre-computed extension lines rather than searching the entire image.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces traditional mechanical or simple optical detection methods with a computer vision-based system that processes 2D and 3D image information. This substitution enables faster and more accurate detection of irregularly shaped layer dividers by using algorithms to detect contours, extension lines, and interruptions, rather than relying on physical contact or simple optical sensors.

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

3Manufacturing precision

If traditional image processing is used, then the system is simple, but the ability to identify irregular shapes and contours is limited

Engineering Contradiction:
Improvecontour identification accuracyVSAvoidimage processing complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system uses dynamic extension lines that adapt to the specific geometry of each stack. Rather than using fixed detection patterns, the extension lines are generated based on the detected perimeter and dynamically extend toward the center, allowing the system to accurately identify contours and layer dividers for any irregular arrangement or shape of objects in the stack.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4488012A1Robotic system and method with object detection
Publication Date: 2025.01.08 MUJIN INC
  • EP4488012A1 patent drawingFigure 1A
  • EP4488012A1 patent drawingFigure 1B
  • EP4488012A1 patent drawingFigure 1C

AI summary

A computing system including a processor configured to identify a contour of a stack of objects based on 3D image information obtained, identify a top surface of the stack of objects based on the contour of the stack of obj ects, detect extension lines, each corresponding to an edge of an object or a gap between objects, extending from a perimeter towards a center of the top surface based on 2D image information of the top surface of the stack of objects, detect a presence of the layer divider based on a length of each of the extension lines being less than a line-length threshold, identify a contour of the layer divider according to points on the top surface corresponding to termination points of the extension lines, and determine a trajectory to control a movement of a robot based on the contour.