Robotic Singulation of Mixed Items in Cluttered Flow
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 option 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 to destinations, but the process becomes labor-intensive and inefficient with suboptimal collective throughput
Solution Approach 1:
The system enables self-service through automated robotic arms that independently identify, grasp, and place items without human intervention. The computer vision system autonomously tracks items and the robotic system automatically routes them to destinations, eliminating the need for manual labor while maintaining high throughput
Solution Approach 2:
Manual mechanical sorting is replaced with an automated robotic system. The patent substitutes human workers with robotic arms equipped with computer vision and automated control systems, transitioning from manual mechanical operations to automated electromechanical systems that achieve superior productivity
2Extent of automation
If robotic arms are used for singulation, then automation and throughput can be improved, but it becomes difficult to identify, grasp, and separate items due to the dynamic and cluttered nature of item arrival
Solution Approach 1:
The system performs preliminary actions by using computer vision to identify and track items before the robotic arm attempts to grasp them. The vision system pre-processes the cluttered scene, identifies graspable items, and plans trajectories in advance, making the subsequent grasping action feasible despite the dynamic and cluttered environment
Solution Approach 2:
The computer vision system acts as an intermediary between the cluttered item flow and the robotic arm. It processes the complex visual information from the cluttered scene, identifies suitable grasp points, and translates this into actionable commands for the robotic arm, bridging the gap between chaotic input and precise robotic action
3Productivity
If multiple workers are used to fill single item spots, then more items can be processed, but downstream workers have fewer locations to place singulated items resulting in bottlenecks
Solution Approach 1:
The robotic system provides multi-functionality by performing multiple tasks at each station: identifying items, tracking their flow, determining grasp strategies, and placing them in destinations. A single robotic system replaces multiple specialized workers, reducing overall system complexity while maintaining or improving productivity
Solution Approach 2:
The system dynamically adapts to the flow of items and available destinations. The computer vision system continuously tracks item positions and the robotic arm dynamically adjusts its grasping and placement actions based on real-time conditions, allowing flexible coordination without requiring fixed rigid structures or multiple static workstations
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 enhances the efficiency and accuracy of singulation by automating the process, reducing labor costs and increasing collective throughput, while ensuring that items are properly oriented and sorted for downstream machine processing.
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.