Multi-Method Object Recognition for Bulk and Aligned Workpieces

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies face difficulties in detecting and recognizing the state of workpieces in a bulk state due to deteriorated illumination conditions and similar colors with the background, making it challenging to accurately identify the edge and attitude of workpieces.

Innovation Solution

A target object recognition device with multiple calculation processing units that calculate the attitude state of objects using different techniques, a state recognition unit to determine the layout state, and a method determination unit to select the appropriate method for recognizing the attitude state, integrated with a manipulator and a mobile robot for gripping and conveying.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If edge detection technology is used to recognize workpiece positions, then aligned workpieces can be accurately detected, but workpieces in bulk state cannot be properly recognized due to deteriorated illumination and color matching with background

Engineering Contradiction:
Improveworkpiece position detection accuracyVSAvoidcapability to handle both aligned and bulk states
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The recognition system is segmented into multiple independent calculation processing units, each specialized for different workpiece states. The state recognition unit divides the overall recognition task by first identifying the layout state (aligned or bulk), then routing to appropriate calculation processing units. This segmentation allows each unit to optimize for its specific function without being constrained by the limitations of a single general-purpose approach.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically adapts its recognition method based on the detected layout state. The method determination unit selects different calculation techniques in real-time depending on whether workpieces are in aligned or bulk state. This dynamic adaptation enables the system to switch between edge detection for aligned states and alternative recognition methods for bulk states, thereby achieving versatility across different workpiece configurations.

Inventive Principle:
Principle #15Dynamics

2Device complexity

If a single recognition method is used for all workpiece arrangements, then the system structure remains simple, but the system cannot accurately recognize both aligned and bulk states

Engineering Contradiction:
Improverecognition system structureVSAvoidrecognition accuracy across different states
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The recognition system achieves multi-functionality by integrating multiple calculation processing units that can handle different workpiece states. The state recognition unit and method determination unit act as universal controllers that route inputs to appropriate processing units based on the detected state. This universal architecture allows a single system to perform both aligned state recognition and bulk state recognition accurately, rather than requiring separate dedicated systems for each state.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Quantity of substance

If workpieces are arranged in bulk state, then space utilization improves, but edge detection becomes difficult due to deteriorated illumination conditions and color matching with background

Engineering Contradiction:
Improveworkpiece density in space regionVSAvoidedge portion detectability
Core Design Contradiction:
Quantity of substanceVSDifficulty of detecting and measuring

Solution Approach 1:

The state recognition unit acts as an intermediary that assesses the layout state before the main recognition process. By first determining whether workpieces are in bulk state or aligned state, the system can then select appropriate calculation processing units that are optimized for each condition. This intermediary step enables the system to overcome the detection difficulties in bulk state by routing to specialized processing methods rather than attempting edge detection on unsuitable data.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3848898B1Target object recognition device, manipulator, and mobile robot
Publication Date: 2024.04.10 OMRON CORP
  • EP3848898B1 patent drawingFigure 1~2
  • EP3848898B1 patent drawingFigure 3
  • EP3848898B1 patent drawingFigure 4(a)~4(b)

AI summary

Provided is art capable of recognizing the states of a plurality of target objects arranged in a prescribed space region. This target object recognition device is provided with: a plurality of calculation processing units (21, 22) which each calculate the attitude state of a target object in a prescribed space region using a different technique; a state recognition unit (23) which recognizes the layout state of all of a plurality of target objects arranged in the space region; a method determination unit (24) which, in accordance with the result of the recognition by the state recognition unit (23), determines a method for using the results of the calculation performed by the calculation processing units (21, 22); and a target object recognition unit (25) which recognizes the attitude states of the target objects by means of the determined method for using the results of the calculation.