Machine-Vision Pick-and-Place for Flexible Workpiece Transfer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated workpiece transfer systems are costly and time-consuming to deploy due to their customization to specific workpiece types, shapes, and sizes, and they have limited processing rates and require significant manual reconfiguration for different tasks.
Innovation Solution
An automated system using an imaging device and a machine-learning model to identify pickable workpieces, an autonomous pick-and-place robot, and a processor to define operating parameters for the robot's end-of-arm-tooling component to retrieve and transfer workpieces based on position, orientation, and other features, enabling efficient and flexible handling of various workpieces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing automated workpiece transfer systems are customized to specific workpiece types, shapes, and sizes, then they can handle specific tasks reliably, but deployment costs and time increase significantly
Solution Approach 1:
The system uses a universal pick-and-place robot with customizable end-of-arm tooling that can handle multiple workpiece types through software configuration rather than hardware redesign. The imaging device and machine learning model provide universal workpiece identification capabilities across different geometries, eliminating the need for task-specific customization while maintaining reliable operation.
Solution Approach 2:
The system changes operational parameters (grip force, speed, position) dynamically based on workpiece characteristics identified by the machine learning model, rather than requiring physical reconfiguration. This allows the same hardware to adapt to different workpieces by adjusting software-controlled parameters, reducing deployment complexity while maintaining task reliability.
2Manufacturing precision
If existing automated workpiece transfer systems are customized for specific tasks, then they achieve accurate positioning and orientation, but significant manual reconfiguration is required for different tasks
Solution Approach 1:
The system replaces manual mechanical reconfiguration with an automated imaging and machine learning-based identification system. The imaging device captures workpiece characteristics, and the machine learning model automatically determines positioning parameters, eliminating the need for manual measurement and setup while maintaining high positioning precision across different workpiece types.
Solution Approach 2:
The system performs self-configuration by automatically identifying workpiece characteristics through imaging and machine learning, then autonomously determining the appropriate positioning and orientation parameters. This self-service capability eliminates manual reconfiguration efforts while maintaining manufacturing precision, as the system adapts to each workpiece type independently.
3Productivity
If traditional feeders are used to transfer workpieces, then they maintain steady processing rates, but they require significant space and have limited flexibility
Solution Approach 1:
The system uses a dynamic pick-and-place robot instead of a static traditional feeder, allowing flexible adjustment of processing parameters and workpiece handling approaches. The robot can adapt its motion paths, speeds, and gripping strategies dynamically based on workpiece characteristics identified by the machine learning model, maintaining high processing rates while providing superior versatility.
Solution Approach 2:
The system adds the dimension of intelligent decision-making through machine learning to the workpiece transfer process. Rather than relying solely on mechanical design for flexibility, the system uses software-based adaptation that allows high processing rates to be maintained while achieving unlimited versatility across different workpiece types and configurations.
4Measurement precision
If more imaging and processing power is added to identify workpieces accurately, then workpiece identification precision improves, but system cost and complexity increase
Solution Approach 1:
The system introduces a machine learning model as an intermediary between the imaging device and the pick-and-place robot. The imaging device captures workpiece characteristics, the machine learning model processes this information to identify workpiece types and determine positioning parameters, and the robot executes the transfer. This intermediary layer achieves high identification precision while keeping the overall system complexity manageable through software-based processing rather than complex hardware.
Data Source
AI summary
Automated workpiece transfer systems and methods of implementing thereof are disclosed. The system can include an imaging device operable to capture an initial image of workpieces loaded onto a loading area; an autonomous pick-and-place robot, and a processor in communication with the imaging device and the pick-and-place robot. The autonomous pick-and-place robot can include an end-of-arm-tooling component operable to retrieve pickable workpieces from the loading area and transfer the pickable workpieces to a receiving area according to a set of operating parameters. The processor can be operable to apply a machine-learning model to the initial image to identify pickable workpieces; identify a region of interest within the initial image; and based on the initial image, define the set of operating parameters for operating the end-of-arm-tooling component to retrieve the one or more pickable workpieces.