Adaptive Robotic Singulation for Cluttered Parcel Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual singulation of items in parcel distribution centers is labor-intensive and inefficient, and robotic singulation is challenging due to the dynamic and cluttered nature of item arrival, making it difficult to identify, grasp, and separate items autonomously.
Innovation Solution
A robotic system that determines a plan for singulating items based on sensor data, including attributes such as weight, size, and orientation, and dynamically updates paths to improve singulation efficiency, using multiple robots coordinated by a control computer to avoid collisions and optimize throughput.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual singulation is used, then items can be separated, but labor intensity is high and throughput is low
Solution Approach 1:
The robotic system autonomously performs singulation operations without human intervention. The robot identifies items in the cluttered mix, plans grasp strategies, executes picks, and places items on the conveyor belt automatically, making the system self-sufficient and eliminating manual labor while maintaining high throughput
Solution Approach 2:
The patent replaces the manual mechanical system with an automated robotic system equipped with sensors, computer vision, and intelligent control algorithms. The robotic arm with adaptive end effectors substitutes human hands, and the automated planning system replaces human decision-making, achieving both high productivity and reduced labor intensity
2Ease of operation
If robotic singulation is implemented, then labor intensity is reduced, but difficulty in identifying and grasping items in cluttered mix increases
Solution Approach 1:
The system performs preliminary actions by using sensors and computer vision to scan and identify items in the cluttered mix before attempting to grasp them. The robot plans the entire singulation sequence in advance, including grasp strategies and pick order, which simplifies the real-time execution phase and makes item identification more manageable
Solution Approach 2:
The robotic system employs dynamic adaptation through adjustable end effectors that can modify their grasp strategy based on real-time sensor feedback about item characteristics. The robot can dynamically change its approach when encountering difficult-to-grasp items in the cluttered mix, making the system flexible enough to handle varying item configurations
3Productivity
If multiple robots are used to increase throughput, then productivity improves, but collision risk between robots increases
Solution Approach 1:
The system uses real-time feedback from sensors to monitor the positions and movements of multiple robots. The centralized controller continuously receives feedback about robot states and adjusts their trajectories and timing to prevent collisions, enabling safe operation of multiple robots working in parallel to increase throughput
Solution Approach 2:
The system performs preliminary planning of robot trajectories and schedules before execution. The centralized controller pre-coordinates the paths and timing of multiple robots, identifying and resolving potential collision scenarios in advance, which allows multiple robots to operate simultaneously at high throughput without collisions
Data Source
AI summary
A robotic singulation system is disclosed. In various embodiments, sensor data including data associated with an item present in a workspace is received. The sensor data is used to determine and implement a plan to autonomously operate a robotic structure to move and place the item singly in a corresponding location in a singulation conveyance structure. The plan takes into consideration an attribute of the item determined based at least in part on the sensor data.