Robotic Singulation of Mixed Items Using 3D Flow Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual singulation of mixed items in parcel and distribution centers is labor-intensive and inefficient, and the use of robots is challenging due to the dynamic and cluttered nature of item arrival, making it difficult to identify, grasp, and separate items in an automated manner.
Innovation Solution
A robotic singulation system that uses a combination of computer vision, suction-based end effectors, and coordinated robotic arms to model item flow, anticipate item locations, and grasp items from a flowing pile, even in cluttered conditions, with the ability to invoke human assistance when necessary to maximize throughput and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual singulation is used, then items can be separated and routed, but labor intensity is high and throughput is low
Solution Approach 1:
The system enables automated singulation where robots autonomously identify, grasp, and separate items from cluttered mixes without continuous human intervention. The robotic system serves itself by using computer vision to locate items and coordinated motion to extract them, replacing manual labor with autonomous automated operation.
Solution Approach 2:
The patent replaces the manual mechanical system of human workers with an automated robotic system. Robots equipped with specialized end effectors substitute human hands, and computer vision systems replace human visual inspection, creating a fully automated mechanical system that achieves higher throughput and consistency.
2Extent of automation
If robots are used for singulation, then automation increases, but difficulty in identifying and grasping items from cluttered mixes increases
Solution Approach 1:
The robotic system divides the challenging task of singulation into distinct sequential segments: first computer vision identifies and locates target items in the cluttered mix, then the system plans a grasp strategy, executes the grasp with specialized end effectors, and finally places items in designated locations. This segmentation allows each subtask to be optimized independently.
Solution Approach 2:
The patent introduces computer vision systems and sophisticated control algorithms as intermediaries between the cluttered item mix and the robotic manipulators. These intermediaries process visual information to identify items, determine their positions and orientations, and generate appropriate grasp plans, bridging the gap between chaotic input and precise robotic action.
3Productivity
If multiple workers are used for singulation, then throughput may increase, but coordination complexity and potential conflicts increase
Solution Approach 1:
The robotic system performs multiple functions within a unified automated platform: computer vision identifies items, motion planning determines extraction paths, grasping mechanisms secure items, and placement systems deliver them to correct locations. This multi-functionality consolidates what would require multiple coordinated human workers into a single integrated robotic system, eliminating coordination conflicts while maintaining high throughput.
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 significantly increases the efficiency and accuracy of singulation, reducing labor costs and improving collective throughput by enabling robots to handle a diverse mix of items automatically, while also ensuring that items are properly oriented for machine-readable information, thus streamlining the sorting and routing process.
Implementation Method 1
suction-based end effectors
Data Source
AI summary
A robotic singulation system is disclosed. In various embodiments, sensor data including image data associated with a workspace is received. The sensor data is used to generate a three dimensional view of at least a portion of the workspace, the three dimensional view including boundaries of a plurality of items present in the workspace. The three dimensional view as generated at successive points in time is used to model a flow of at least a subset of said plurality of items through at least a portion of the workspace. The model is used to determine and implement a plan to autonomously operate a robotic structure to pick one or more items from the workplace and place each item singly in a corresponding location in a singulation conveyance structure.