Gripping Control Data Using Stable Object Poses
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining grasp poses for gripping arbitrary objects are time-consuming and prone to errors, as they require user input and assessment.
Innovation Solution
A method that captures an object's image, determines object parameters, and ascertains control data for gripping by assuming stable poses, reducing analysis complexity and automating the process using information about possible stable poses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all possible orientations of the object are taken into account during image analysis, then the completeness of object identification is improved, but the analysis complexity increases significantly
Solution Approach 1:
The patent segments the continuous space of all possible object orientations into discrete stable poses. By identifying and analyzing only these discrete stable configurations (where objects naturally rest on surfaces), the system reduces the infinite complexity of all possible orientations to a manageable set of specific poses, thereby reducing analysis complexity while maintaining identification reliability.
Solution Approach 2:
The patent applies partial action by focusing analysis only on stable poses rather than all possible orientations. This selective approach analyzes only the subset of orientations that are physically relevant (stable poses), eliminating unnecessary computational effort for unstable orientations that would not occur in practice, thus reducing complexity without sacrificing identification completeness.
2Measurement precision
If user assessment is used to determine grasp poses, then the accuracy of gripping determination is improved, but the time consumption increases
Solution Approach 1:
The system performs self-service by automatically determining stable poses and gripping points through algorithmic analysis of object geometry and physics principles, eliminating the need for manual user assessment. The computer vision system and physics engine work autonomously to identify stable configurations and calculate optimal gripping points, maintaining accuracy while dramatically reducing time consumption.
Solution Approach 2:
The patent replaces the mechanical/manual process of user assessment with an automated computational system. Instead of relying on human users to visually assess and determine grasp poses, the system uses computer vision, 3D modeling, and physics-based simulations to automatically calculate stable poses and gripping points, substituting human cognitive processes with automated computational mechanisms.
3Reliability
If manual determination of gripping points is performed, then the reliability of gripping is improved, but the automation level decreases
Solution Approach 1:
The system performs preliminary action by pre-calculating stable poses and gripping points through automated analysis of object geometry and physics principles before the actual gripping operation. The computer vision system captures object images, determines 3D models, identifies stable poses, and calculates optimal gripping points in advance, enabling fully automated gripping execution without manual intervention while maintaining high reliability.
Solution Approach 2:
The patent changes the parameters of the gripping system from manual control to automated computational determination. By transforming the determination of gripping points from a manual task to an automated process based on object geometry parameters, stable pose parameters, and physics-based calculations, the system achieves both high automation level and maintained reliability through systematic parameter analysis.
Data Source
AI summary
A method for ascertaining control data for a gripping device for gripping an object includes capturing an image of the object, determining at least one object parameter of the captured object, and ascertaining control data for a gripping device to grip the object at at least one gripping point, where ascertaining the at least one gripping point of the object is performed using information relating to at least one possible stable position of the object, and the possible stable position of the object is established such that all of the position data of the object that can be converted into one another via a movement and/or rotation about a surface normal of a support surface on which the object lies are assigned to the possible stable position.