Visual Servo Actuation System Using Multi-Camera Coordinate Conversion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional actuation systems face challenges in achieving precise control and reliability due to limitations in their configuration, leading to inconveniences in visual servo feedback control, particularly in determining target objects and maintaining desired positions and attitudes.

Innovation Solution

An actuation system comprising a movable member, an actuator, image-taking units, and a coordinate conversion unit that performs visual servo control by converting image data from different camera systems to an arithmetic coordinate system, allowing for precise control and robust operation even without strict calibration or teaching.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional visual servo control is used with limited configuration, then the system is simpler to implement, but control precision and reliability deteriorate

Engineering Contradiction:
Improvecontrol precisionVSAvoidsystem configuration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the visual servo control into two independent coordinate systems: image-taking coordinate system (from camera images) and arithmetic coordinate system (for control calculations). This segmentation allows each coordinate system to be processed independently through dedicated conversion units, improving control precision without requiring a completely complex reconfiguration of the entire system.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

A coordinate conversion unit acts as an intermediary between the image-taking coordinate system and the arithmetic coordinate system. This intermediary component enables precise control by accurately transforming image coordinates to arithmetic coordinates, thereby improving control precision while maintaining relatively simple system architecture through a dedicated conversion module.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If strict calibration and teaching are required, then coordinate accuracy is improved, but ease of operation and setup time deteriorate

Engineering Contradiction:
Improvecoordinate accuracyVSAvoidsetup ease
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system performs self-calibration by automatically establishing the relationship between image-taking coordinate system and arithmetic coordinate system through the coordinate conversion unit. This self-service mechanism eliminates the need for manual strict calibration and teaching operations, thereby maintaining coordinate accuracy while significantly improving ease of operation and reducing setup time.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The coordinate conversion unit performs preliminary coordinate transformation operations to establish the mapping relationship between different coordinate systems before actual control operations begin. This preliminary action ensures coordinate accuracy is achieved automatically without requiring subsequent manual calibration steps, thereby improving ease of operation while maintaining precision.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If multiple cameras are used for visual servo control, then reliability is improved, but device complexity and processing time increase

Engineering Contradiction:
Improvecontrol reliabilityVSAvoidcamera system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the processing of multiple camera inputs by assigning each camera to capture images in its own image-taking coordinate system. The coordinate conversion unit then processes each camera's image independently, converting to the arithmetic coordinate system. This segmentation approach maintains control reliability through multiple camera inputs while managing device complexity through systematic coordinate handling.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The coordinate conversion unit serves as a universal processing component that handles coordinate transformation for images from multiple different cameras. This multi-functional unit processes various camera inputs through a unified conversion mechanism, thereby maintaining control reliability through diverse camera inputs while avoiding proportional increase in system complexity through standardized processing.

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

4Measurement precision

If coordinate conversion from image-taking system to arithmetic system is performed, then control accuracy is improved, but processing time increases

Engineering Contradiction:
Improvecontrol accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The coordinate conversion unit performs coordinate transformation as a preliminary operation before control calculations are executed. By establishing the coordinate mapping in advance, the system achieves improved control accuracy without requiring repeated conversions during control operations, thereby reducing overall processing time while maintaining precision.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The coordinate conversion operates continuously and efficiently, transforming image coordinates to arithmetic coordinates in real-time as images are captured. This continuous conversion process ensures control accuracy is maintained without introducing significant processing delays, as the conversion is integrated into the ongoing control loop rather than being a separate batch operation.

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentUS10695912B2Actuation system and computer program product utilizing visual servo control based on images from multiple cameras
Publication Date: 2020.06.30 KK TOSHIBA
  • US10695912B2 patent drawing
  • US10695912B2 patent drawing
  • US10695912B2 patent drawing

AI summary

According to an embodiment, an actuation system includes a movable member, an actuator, at least one image taking unit, a coordinate conversion unit and a first actuation control unit. The actuator moves the movable member. The coordinate conversion unit performs coordinate conversion from an image-taking coordinate system of a taken image taken by the image taking unit to an arithmetic coordinate system for performing comparison. The first actuation control unit controls the actuator to reduce a deviation according to visual servo in the arithmetic coordinate system.