AI Object Routing and Classification for Faster Warehouse Picking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional object processing systems, such as automated storage and retrieval systems, face inefficiencies in time and resources required to move totes toward and away from personnel, and in the speed at which personnel can process totes, especially when handling a large number of objects.

Innovation Solution

The system incorporates a supply location, object processing stations, an object classification system, and a routing system. The object classification system identifies objects, assigns them to classes based on provided and determined information, and routes them to appropriate processing stations capable of handling those objects according to specific processing parameters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If conventional automated storage and retrieval systems bring totes to personnel for item picking, then personnel can process items at their own pace, but the time and resources required to move totes toward and away from each person increases significantly

Engineering Contradiction:

Improvepersonnel processing capabilityVSAvoidtime to move totes

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

Instead of bringing totes to personnel (traditional AS/RS approach), the system inverts the flow by having personnel come to the totes at centralized pick locations. This reverses the conventional material flow direction and eliminates the need for continuous tote transport to multiple workstations, thereby reducing time loss while maintaining operational ease

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The system merges multiple pick locations into centralized stations where personnel can access multiple totes simultaneously. This consolidation combines what were previously separate one-to-one tote-personnel interactions into many-to-few relationships, reducing the total number of transport cycles required

Inventive Principle:

Principle #5Merging (Combining)

2Loss of time

If conventional systems use centralized pick locations where personnel come to totes, then tote movement time is reduced, but the system complexity increases due to routing and classification requirements

Engineering Contradiction:

Improvetote movement timeVSAvoidrouting system complexity

Core Design Contradiction:

Loss of timeVSDevice complexity

Solution Approach 1:

The system implements self-service through automated classification and routing mechanisms that automatically direct totes to appropriate pick locations based on their contents and destination requirements. This automation eliminates the need for manual routing decisions, reducing perceived complexity while maintaining efficient tote distribution

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system uses feedback loops where tote contents are scanned and classified, then routed accordingly, with performance data continuously monitored and used to optimize routing algorithms. This feedback mechanism automates complex decision-making processes, reducing operational complexity while improving efficiency

Inventive Principle:

Principle #23Feedback

3Adaptability or versatility

If more object processing stations are added to handle diverse object classes, then object processing capability increases, but system complexity and resource requirements increase

Engineering Contradiction:

Improveobject processing capabilityVSAvoidnumber of processing stations

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system implements universal processing stations that can handle multiple object classes through automated classification and adaptive handling mechanisms. Rather than requiring specialized stations for each object type, single multi-functional stations perform various tasks based on real-time classification, thereby increasing versatility without proportionally increasing the number of stations

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system uses dynamic routing and classification that adapts processing station assignments based on current workload, object characteristics, and station availability. This dynamic allocation allows the system to efficiently utilize existing stations for diverse object types without requiring a fixed large number of specialized processing stations

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20250187833A1Systems and methods for learning to extrapolate optimal object routing and handling parameters

Publication Date: 2025.06.12 BERKSHIRE GREY OPERATING CO INC

AI summary

A system for object processing is disclosed. The system includes a framework of processes that enable reliable deployment of artificial intelligence-based policies in a warehouse setting to improve the speed, reliability, and accuracy of the system. The system harnesses a vast number of picks to provide data points to machine learning techniques. These machine learning techniques use the data to refine or reinforce in-use policies to optimize the speed and successful transfer of objects within the system. For example, objects in the system are identified at a supply location, a predetermined set of information regarding object is retrieved and combined with a set of object information and processing parameters determined by the system. The combined information is then used to determine routing of the object according to an initial policy. This policy is then observed, altered, tested, and re-implemented in an altered form.