Robot Hand Characteristic Estimation From Gripping Torque Signals

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In manufacturing processes, particularly in factories where products are gripped by robot hands, estimating characteristics such as size, shape, and hardness of objects can be time-consuming and labor-intensive, hindering efficient inspection and quality control.

Innovation Solution

A characteristic estimation system comprising a user terminal, a robot controller, and a robot hand equipped with sensors, which acquires physical quantities like torque signals during object gripping and uses estimation modules to determine object characteristics based on these signals.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual inspection methods are used to estimate object characteristics, then measurement precision can be maintained, but loss of time and productivity decrease

Engineering Contradiction:
Improvecharacteristic estimation accuracyVSAvoidinspection time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical inspection with an automated system using robot hands equipped with force sensors and torque sensors. The sensors detect physical quantities during gripping operations, and a computer analyzes this data to estimate object characteristics, substituting human mechanical inspection with automated sensor-based measurement.

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

Solution Approach 2:

The system enables objects to be inspected during their normal handling operations. The robot hand performs gripping necessary for manufacturing processes, and simultaneously the sensors capture data for characteristic estimation, making the inspection self-service rather than requiring separate manual examination.

Inventive Principle:
Principle #25Self-service

2Productivity

If automated sensor-based estimation is implemented, then productivity increases, but device complexity increases

Engineering Contradiction:
Improveinspection efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The robot hand serves multiple functions: it performs gripping operations necessary for manufacturing processes and simultaneously acts as a measurement device for characteristic estimation. The force sensors and torque sensors are integrated into the robot hand structure, allowing dual functionality without adding separate inspection equipment.

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

Solution Approach 2:

The computer acts as an intermediary that receives physical quantity data from the sensors and processes it to estimate object characteristics. This intermediary component simplifies the overall system by centralizing the analysis function rather than requiring complex direct sensor-to-result processing.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If multiple sensors are integrated in the robot hand, then measurement precision improves, but ease of operation decreases

Engineering Contradiction:
Improvephysical quantity detection accuracyVSAvoidrobot hand operation simplicity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The force sensors and torque sensors are merged into the robot hand structure, combining multiple measurement functions into a single integrated device. This merging allows simultaneous detection of multiple physical quantities without requiring separate inspection tools or complex coordination between multiple independent systems.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3659758B1Characteristic estimation system, characteristic estimation method, and program
Publication Date: 2025.02.12 YASKAWA DENKI KK
  • EP3659758B1 patent drawingFigure 1
  • EP3659758B1 patent drawingFigure 2
  • EP3659758B1 patent drawingFigure 3

AI summary

A robot hand (31) of a characteristic estimation system (1) is configured to grip an object (O). An operation control module (200) is configured to cause the robot hand (31) to operate based on operation information defining an operation of the robot hand (31). A physical quantity acquisition module (101) is configured to acquire a physical quantity at a time when the robot hand (31) grips the object (O). An estimation module (102) is configured to estimate a characteristic of the object (O) based on the physical quantity.