Robot Arm Vision System for Unconstrained Article Picking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Robots face challenges in unconstrained environments when picking up articles of varying orientations, as they lack information about the article's orientation and motion path, making it difficult to determine the appropriate gripping tool and motion path.

Innovation Solution

A method using a robot arm with a mounted camera to capture images, process them to locate a machine-readable symbol, decode it for orientation and information, and determine the appropriate gripping tool and motion path, allowing the robot to adjust its tools and motion accordingly to grip the article.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If the robot arm is used to grip an article in unconstrained environment, then the robot can handle articles of varying orientations, but the robot does not know the motion path or orientation information of the article

Engineering Contradiction:

Improveability to handle articles of varying orientationsVSAvoidlack of orientation and motion path information

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system performs preliminary actions by moving the robot arm with a mounted camera around the article to capture images before gripping. The machine-readable symbol is decoded in advance to obtain orientation patterns and encoded information, allowing the robot to plan the gripping motion path beforehand rather than reacting after losing information

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

A machine-readable symbol with orientation pattern serves as an intermediary carrier between the article and the robot system. This symbol encodes orientation and article information that the robot can decode to understand the article's state, effectively bridging the information gap in unconstrained environments

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If the robot arm moves in a space around the article to capture images, then the robot can locate the machine-readable symbol, but the system complexity increases

Engineering Contradiction:

Improveability to locate machine-readable symbolVSAvoidsystem complexity with camera and image processing

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The robot arm serves multiple functions: it both captures images with the mounted camera and executes the gripping action. This multi-functionality reduces the need for separate dedicated imaging equipment and simplifies the overall system architecture while maintaining measurement precision

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The machine-readable symbol on the article serves itself by providing both orientation pattern and encoded information about the article in a single element. This self-contained approach eliminates the need for separate orientation markers and information tags, reducing system complexity

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS9138895B2Method for picking up an article using a robot arm and associated system

Publication Date: 2015.09.22 VISUAL MATHEMATICS LLC

AI summary

A method for picking up an article using a robot arm includes capturing images with a camera and processing the captured images to locate a machine-readable symbol affixed to the article. The machine-readable symbol includes an orientation pattern and encoded information pertaining to the article. The orientation pattern provides information to determine x, y, and z coordinates and Rx, Ry and Rz of a gripping tool attached to the robot arm. The encoded information provides information to determine the appropriate gripping tool, gripping location and gripping motion path.