Grip Region Detection for Suction Gripping of Flexible Objects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robots struggle to reliably grip flexible objects such as packages of clothing due to their deformable nature, which can introduce non-smooth surfaces that interfere with adhesion by end effector apparatuses like suction cups.
Innovation Solution
A computing system identifies a sufficiently smooth and large grip region on the object's surface using image information from a camera, and determines a safety region surrounding it to reduce collision risks during motion planning, enabling reliable gripping and movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If robots use end effector apparatuses like suction cups to grip flexible objects, then the robot can handle and move the objects, but the deformable nature of flexible objects creates non-smooth surfaces that interfere with adhesion
Solution Approach 1:
The system performs preliminary detection of smooth grip regions on flexible objects using image processing before the robot attempts to grip the object. By identifying suitable grip regions in advance based on smoothness criteria, the system ensures reliable adhesion when the end effector contacts the object, resolving the contradiction between gripping capability and adhesion reliability.
2Productivity
If the robot performs motion planning without considering safety regions, then the motion planning is simpler and faster, but collision risks increase during robot movement
Solution Approach 1:
The system performs preliminary identification of safety regions surrounding grip regions before executing robot motion. By pre-defining these safety zones based on the detected grip regions, the motion planning process can efficiently operate within constrained boundaries, reducing collision risks while maintaining planning speed through the use of pre-established safety parameters.
3Measurement precision
If the system performs detailed image analysis to identify grip regions on flexible objects, then gripping accuracy improves, but processing time increases
Solution Approach 1:
The system applies local quality analysis by focusing image processing efforts only on potential grip regions rather than analyzing the entire object surface. By using smoothness criteria to identify and concentrate analysis on specific local areas that are likely to be suitable grip regions, the system achieves high identification accuracy while significantly reducing overall processing time compared to exhaustive full-surface analysis.
Data Source
AI summary
A method performed by a computing system is presented. The method may include the computing system receiving image information that represents an object surface associated with a flexible object, and identifying, as a grip region, a surface region of the object surface that satisfies a defined smoothness condition and has a region size that is larger than or equal to a defined region size threshold, wherein the grip region is identified based on the image information. The method may further include identifying, as a safety region, a three-dimensional (3D) region which surrounds the grip region in one or more horizontal dimensions, and which extends from the grip region along a vertical dimension that is perpendicular to the one or more horizontal dimensions. The method may further include performing robot motion planning based on the grip region and the safety region.