Robot Picking Pose Normalization for Variable Package Dimensions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The reliability of automated picking processes by robots is compromised due to fluctuations in article parameters such as dimensions and weight, leading to incorrect pickups and reduced throughput, as existing methods struggle to accurately detect and adapt to variations in packaging and weight changes.
Innovation Solution
An optimization method that uses an opto-sensory preparation and analysis system to determine gripping surface size and pose, applying mathematical scattering measure functions to normalize dimensions and weights, and comparing them with stored ranges to ensure accurate picking, while also allowing for quick adaptation to changes in article parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual entry of article parameters is used at the article receipt area, then the system can store reference data in the warehouse management system, but the recorded parameters often lack the accuracy required for reliable robot manipulation
Solution Approach 1:
The patent replaces manual mechanical entry of article parameters with an automated optical measurement system. Image processing methods capture images of articles, and mathematical scattering measure functions automatically determine dimensions and weights, eliminating human error and improving both reliability and precision of parameter recording.
Solution Approach 2:
The system enables articles to self-identify their parameters through automated image capture and analysis. The scattering measure function automatically processes article images to extract dimensional and weight information without human intervention, making the parameter recording process self-service and highly accurate.
2Measurement precision
If image processing methods are used to identify article boundaries, then gripping positions can be determined, but boundary detection becomes difficult when articles are densely arranged
Solution Approach 1:
The patent transforms the boundary detection problem by changing parameters from direct edge detection to scattering measure analysis. By analyzing the scattering distribution of pixel intensities around potential boundaries, the system can reliably detect article boundaries even in densely arranged configurations where traditional edge detection fails.
Solution Approach 2:
The scattering measure function serves as an intermediary between the image data and boundary detection. Instead of directly detecting boundaries, the system uses scattering measures as an intermediate representation that makes boundary detection more reliable, especially for densely packed articles where direct edge detection is difficult.
3Productivity
If article parameters are manually recorded without verification, then the warehouse management system can store reference data, but parameter fluctuations cause malfunctions and reduced throughput
Solution Approach 1:
The patent implements feedback by continuously verifying article parameters against reference data during the picking process. The scattering measure function provides real-time parameter verification, and when deviations are detected, the system can trigger alerts or adjustments, ensuring both high reliability and maintained throughput.
Solution Approach 2:
The system performs preliminary verification of article parameters using the scattering measure function before the picking process begins. By pre-validating parameters and comparing them against reference data, the system prevents malfunctions before they occur, maintaining both reliability and throughput.
4Reliability
If the robot system uses fixed article parameters for picking, then the control process is simple, but parameter fluctuations lead to incorrect pickups and reduced reliability
Solution Approach 1:
The patent transforms fixed parameter usage into dynamic parameter verification by introducing scattering measure functions. These functions automatically adjust and verify parameters in real-time based on actual article measurements, improving reliability while the automation keeps complexity manageable.
Solution Approach 2:
The system performs self-verification of article parameters through automated scattering measure analysis. The robot system automatically compares measured parameters against reference data and adjusts accordingly, making the verification process self-service and reducing the perceived complexity for operators.
Data Source
AI summary
An optimization method improves article pickup and discharge reliability in a picking process using a robot. An article is picked-up from or out of a first load carrier and is placed in or on or dropped into or onto a second load carrier by a gripping unit on the robot head. In an image processing step, a gripping pose for the gripping unit is calculated for picking-up the article by determining at least one dimension from a captured image and by determining a range allocation by comparing with dimension ranges. Using a confidence value, a dimension value is determined, from stored article reference data or from a normalization value of the dimension range and allocated to the determined dimension. In a preparation step, a mathematical scattering measure function is applied for the determined dimension and dimension ranges, and normalization and confidence values of the dimension ranges are determined therefrom.