Object Induction With Perception-Based Handling for Unknown SKUs

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing object distribution systems face challenges in efficiently and cost-effectively handling objects of varying sizes, weights, and compositions, particularly in automated systems where little information is available, leading to inefficiencies and impractical manual processing.

Innovation Solution

An object induction system that includes an analysis system for perception data, an association system for matching object characteristics with recorded data, and an assignment system for programmable motion device handling parameters, such as vacuum pressure and end effector settings, to optimize object handling and distribution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual processing is used for unknown objects, then handling flexibility is maintained, but labor costs increase and system efficiency decreases

Engineering Contradiction:

Improvehandling flexibilityVSAvoidsystem efficiency

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The system enables unknown objects to be automatically processed through self-learning. The perception system captures data about unknown objects, the association system attempts to match them with known objects, and when matching fails, the object is automatically added to the database as a new known object. This self-service mechanism eliminates the need for manual intervention while maintaining handling flexibility.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical processing with an automated computer-based system. The perception system uses sensors and cameras to detect objects, the association system uses algorithms to match objects with database entries, and the assignment system automatically determines handling parameters. This substitution of mechanical/manual operations with automated systems improves productivity while maintaining operational flexibility.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automated handling is implemented for all objects, then productivity increases, but system complexity increases and adaptability to unknown objects decreases

Engineering Contradiction:

Improvesystem efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The automated system is divided into distinct functional modules: the perception system for data capture, the association system for pattern matching, the database for storing object information, and the assignment system for determining handling parameters. This segmentation allows each module to be optimized independently and simplifies the overall system architecture, making it easier to manage and adapt to unknown objects.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by capturing perception data about unknown objects and attempting to associate them with known objects before actual handling occurs. This preliminary processing allows the system to prepare handling parameters in advance, reducing complexity during the actual handling operation while maintaining high productivity.

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If comprehensive object data is collected and stored, then handling accuracy improves, but information storage requirements and processing time increase

Engineering Contradiction:

Improvehandling accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The association system performs partial matching by comparing perception data with database entries using multiple criteria (visual appearance, dimensions, weight). Rather than requiring complete matching on all possible attributes, the system achieves sufficient accuracy for effective handling by matching on the most critical attributes, thereby reducing processing time while maintaining handling accuracy.

Inventive Principle:

Principle #16Partial or excessive action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system enables efficient and cost-effective handling of diverse objects by determining appropriate handling parameters for programmable motion devices, reducing labor and increasing system efficiency while ensuring accurate distribution and reduced manual intervention.

Implementation Method 1

The programmable motion device handling parameters include any of a vacuum pressure at an end effector

Methodology Applied

Scientific EffectVacuum pressure: Vacuum

Data Source

PatentUS12138790B2Systems and methods for SKU induction, decanting and automated-eligibility estimation

Publication Date: 2024.11.12 BERKSHIRE GREY OPERATING CO INC

AI summary

An object induction system is disclosed for assigning handling parameters to an object. The system includes an analysis system, an association system, and an assignment system. The analysis system includes at least one characteristic perception system for providing perception data regarding an object to be processed. The association system includes an object information database and assigns association data to the object responsive to commonality with any of the characteristic perception data with any of the characteristic recorded data. The assignment system is for assigning programmable motion device handling parameters to the indicia perception data based on the association data, and includes a workflow management system as well as a separate operational controller.