Robotic Object Identification via Property Correlation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current robotic systems lack the ability to accurately and efficiently identify and handle objects in a collection, leading to inefficiencies and increased costs in industrial settings due to the inability to reliably select and manipulate objects based on their properties.

Innovation Solution

A robotic system that receives object entries with properties, calculates match probabilities between detected objects and stored properties, generates an object identity approximation, selects a target object, and implements a handling strategy to transfer the object, updating the object set to reflect removal, utilizing a control unit and storage for efficient operation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If robotic systems use traditional object detection methods, then they can detect objects, but they cannot accurately identify and select specific objects from a collection based on their properties

Engineering Contradiction:
Improveobject identification accuracyVSAvoidconsistent object selection
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The system uses sensor information to detect object properties, compares these properties against stored object entries, calculates match probabilities, and uses this feedback loop to identify and select target objects from a collection with high accuracy and consistency

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent replaces traditional mechanical object selection methods with an automated system that uses sensors, probability calculations, and control units to identify and select objects based on their properties, enabling reliable automated handling

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

2Measurement precision

If robotic systems process all objects in a collection to identify targets, then they can find the correct object, but processing time increases

Engineering Contradiction:
Improveobject identification accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system extracts only the necessary object properties detected by sensors and compares them against stored object entries, calculating match probabilities to identify the target object without processing all possible object attributes, thereby reducing processing time while maintaining accuracy

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system changes the parameter of object identification from exhaustive search to probability-based matching, where sensor data is compared against stored entries with calculated match probabilities, enabling faster identification of target objects

Inventive Principle:
Principle #35Parameter changes

3Productivity

If robotic systems lack object property correlation, then system complexity is reduced, but object handling efficiency decreases

Engineering Contradiction:
Improveobject handling efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by storing object entries with their properties beforehand, allowing the control unit to quickly compare sensor information against pre-stored data and calculate match probabilities, thereby improving handling efficiency without excessive complexity

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10987807B2Robotic system with object identification and handling mechanism and method of operation thereof
Publication Date: 2021.04.27 MUJIN INC
  • US10987807B2 patent drawing
  • US10987807B2 patent drawing
  • US10987807B2 patent drawing

AI summary

A robotic system includes: a control unit configured to: receive an object set including one or more object entries, wherein: the object entries correspond to source objects of an object source, each of the object entries are described by one or more object entry properties; receive sensor information representing one or more detectable object properties for detectable source objects of the object source; calculate an object match probability between the detectable source objects and the object entries based on a property correlation between the detectable object properties of the detectable source objects and the object entry properties of the object entries; generate an object identity approximation for each of the detectable source objects based on a comparison between the object match probability for each of the detectable source objects corresponding to a particular instance of the object entries; select a target object from the detectable source objects; generate an object handling strategy, for implementation by an object handling unit, to transfer the target object from the object source based on the object entry properties of the object entries corresponding to the object identity approximation; update the object set to indicate that the target object corresponding to a specific instance of the object entries has been removed from the object source; and a storage unit 204, coupled to the control unit, configured to store the object set.