Robotic Package Registration Using Minimum Viable Grip Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robotic systems for de-palletizing packages often rely on human intervention or fail to accurately identify physical characteristics, leading to mishandling and inefficiencies, especially when packages are heavy or irregularly shaped.
Innovation Solution
A robotic system equipped with a package registration mechanism that includes a de-palletizing platform, a receiving platform, a robotic arm, an image system, a registration data source, and a force-torque sensor, which captures images, determines registration status, and calculates a minimum viable region to safely grip and lift unregistered packages.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If human workers perform de-palletizing operations, then flexibility and adaptability to different packages are maintained, but labor costs increase and risk of bodily injuries occurs
Solution Approach 1:
The robotic system performs self-registration by capturing images of packages, automatically comparing them with registered images in the database, and identifying physical characteristics without human intervention. This self-service capability allows the system to adapt to different package types while eliminating the need for human workers who would otherwise be exposed to injury risks
Solution Approach 2:
The patent replaces the mechanical human worker system with an automated robotic system equipped with imaging devices and processing algorithms. The robotic arm with gripper substitutes human hands, while the image capture and comparison system substitutes human visual inspection and decision-making, thereby eliminating bodily injury risks while maintaining adaptability
2Extent of automation
If automated robotic systems are used for de-palletizing, then labor costs are reduced and safety is improved, but accuracy in identifying physical characteristics of unregistered packages deteriorates
Solution Approach 1:
The system performs preliminary registration by capturing images of packages and comparing them with registered images in the database before the robotic arm attempts to grasp and manipulate them. This preliminary identification action ensures that physical characteristics such as weight, dimensions, and center of mass are accurately determined in advance, enabling the automated system to handle unregistered packages with the same precision as registered ones
Solution Approach 2:
The system uses feedback from image comparison results to adjust its handling approach. By continuously comparing captured package images with registered images and using the match results to inform grasping and manipulation decisions, the system maintains high measurement precision throughout the automated de-palletizing process
3Productivity
If the system relies on registered images for package identification, then handling efficiency is improved, but the system fails when packages are unregistered or have unclear edges
Solution Approach 1:
The system performs preliminary registration operations by capturing images of all packages and comparing them with the registered image database before the robotic arm begins manipulation. This preliminary action ensures that even unregistered or irregularly shaped packages are identified and characterized in advance, allowing the system to maintain high reliability and productivity when encountering packages that do not match existing registrations
Data Source
AI summary
A method of operating a robotic system includes: receiving first image data representative of a package surface; identifying a pair of edges based on the first image data; determining a minimum viable region based on the pair of edges; receiving second image data representative of the package after the lift; and creating registration data based on the first and second image data.