Robot Object Verification Control for Misrecognition Prevention

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Robots often misrecognize objects, leading to unnecessary operations and decreased utility, such as approaching unwanted objects or mistaking animals for humans or reflections.

Innovation Solution

A robot equipped with an image sensor, driving part, memory, and processor that captures multiple images, uses object recognition models to compare reliability and identification information, and adjusts operations based on error determination results.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If the robot uses object recognition model to identify objects, then the robot can perform automated object identification and classification, but the robot may misrecognize objects leading to unnecessary operations

Engineering Contradiction:
Improveautomated object identificationVSAvoidobject recognition accuracy
Core Design Contradiction:
Extent of automationVSReliability

Solution Approach 1:

The system captures a first image, identifies an object, approaches the object, then captures a second image and compares it with the first image. This feedback loop allows the robot to verify its identification before executing operations, correcting potential misrecognitions by comparing recognition results across different positions and angles.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The robot performs preliminary verification by capturing multiple images from different positions before final identification. By approaching the object and capturing additional images in advance of the final operation, the system ensures accurate identification and avoids unnecessary operations.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If the robot approaches the object for verification, then the recognition accuracy can be improved, but the time and energy consumption increase

Engineering Contradiction:
Improverecognition accuracyVSAvoidverification time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The robot performs a partial approach to a predetermined distance rather than full approach, capturing verification images at this intermediate position. This partial action provides sufficient verification accuracy while minimizing the time and energy expenditure compared to complete approach and detailed inspection.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4197713B1Robot and method for controlling same
Publication Date: 2025.07.30 SAMSUNG ELECTRONICS CO LTD
  • EP4197713B1 patent drawingFigure 1
  • EP4197713B1 patent drawingFigure 2
  • EP4197713B1 patent drawingFigure 3

AI summary

A robot is provided. The robot includes an image sensor, a driving part, a memory configured to store at least one instruction, and a processor, and the processor is configured to obtain a first image captured by the image sensor, obtain first information on an object included in the first image, control the driving part for the robot to approach the object, obtain a second image while the robot is approaching the object, obtain second information on an object based on the second image, determine whether an error is present in first information or second information based on the first information and the second information, and control an operation of the robot based on a determination result.