Robot Gripping Mode Selection for Recognition Accuracy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing robot systems struggle to grip target objects effectively under adverse conditions such as poor illumination or stains, leading to decreased work efficiency due to incomplete recognition of the object's position and orientation.

Innovation Solution

A robot control apparatus that includes an acquisition unit for obtaining information about the target object's position and orientation, a selection unit for choosing a gripping mode based on the captured image, and a generation unit for creating gripping operation data, allowing the robot to grip the object even if precise recognition is not possible.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the robot relies on precise image recognition to grip the target object, then the gripping accuracy is improved, but the system fails under poor illumination or stains causing incomplete recognition

Engineering Contradiction:

Improveposition and orientation recognition accuracyVSAvoidgripping success rate under adverse conditions

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The robot dynamically adjusts the gripping mode based on the recognition accuracy of the target object. When recognition is successful, precise gripping is used; when recognition fails due to poor illumination or stains, the system switches to a different gripping mode, making the system adaptable to varying conditions rather than static

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the gripping parameters (gripping mode) based on the recognition results. By monitoring whether the target object's position and orientation are successfully recognized, the system adjusts the gripping approach to maintain reliability under different environmental conditions

Inventive Principle:

Principle #35Parameter changes

2Reliability

If the robot uses multiple gripping modes to handle adverse conditions, then the gripping reliability is improved, but the control system complexity increases

Engineering Contradiction:

Improvegripping success rateVSAvoidcontrol system structure

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The gripping control is segmented into multiple modes (precise gripping and other gripping modes), where each mode handles specific conditions. This segmentation allows the system to address adverse conditions effectively while keeping each individual mode relatively simple

Inventive Principle:

Principle #1Segmentation

3Productivity

If the robot attempts precise gripping under all conditions, then the work efficiency is maintained, but the system fails when recognition is incomplete

Engineering Contradiction:

Improvework efficiencyVSAvoidgripping success rate

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system uses feedback from the image recognition process to determine whether to proceed with precise gripping or switch to alternative gripping modes. This feedback mechanism ensures that the robot maintains work efficiency by adapting to actual conditions rather than attempting precise gripping when recognition is incomplete

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS10695905B2Robot control apparatus and robot control method

Publication Date: 2020.06.30 CANON KK

AI summary

A robot control apparatus that controls operation of a robot that grips a target object includes an acquisition unit that obtains information about a position and orientation of the target object, a selection unit that selects one of a plurality of gripping modes based on a captured image of the target object, and a generation unit that generates, based on the obtained position and orientation and the selected gripping mode, gripping operation data that defines a gripping operation of the robot.