Robot Grasping Control Using Under-Gripper Contact Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robot grasping systems struggle to accurately determine the specified amount of flexible grasping objects, such as prepared foods, due to limitations in recognizing internal states from imaging information captured by units positioned on the upper part of the object.
Innovation Solution
A grasping device with a grasping part module, an arm part, and an imaging unit that captures images from a position moving with the grasping part, allowing the control unit to adjust the grasping based on contact state information, including ratios of object to background and luminance changes, to accurately grasp a specified amount.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If an imaging unit is provided on the upper part of the grasping object to capture image information, then the grasping system can obtain visual feedback, but the internal state of the flexible grasping object cannot be recognized and the specified amount cannot be estimated accurately
Solution Approach 1:
The imaging unit is inverted from the conventional upper position to the lower position, allowing it to capture images from underneath the grasping object. This inversion enables the detection of contact states between the grasping object and the grasping part, providing visual feedback that reveals the internal state and specified amount of flexible objects that cannot be observed from above.
Solution Approach 2:
The imaging unit acts as an intermediary between the grasping part and the control unit, capturing contact state information and transmitting it to the control unit. This intermediary provides the missing visual feedback about the internal state of flexible grasping objects, enabling accurate specified amount estimation without direct physical sensors on the grasping object itself.
2Measurement precision
If the imaging unit is positioned on the upper part of the grasping object, then the system structure is simple, but the contact state information required for accurate grasping control cannot be captured
Solution Approach 1:
The imaging unit is positioned on the lower side of the grasping part, inverted from the conventional upper position. This inversion allows the imaging unit to capture contact state images directly between the grasping object and the grasping part, providing the necessary visual feedback for accurate grasping control while maintaining a relatively simple system structure.
3Productivity
If the grasping part module grasps flexible objects, then the specified amount can be controlled, but the variability in shape and compression makes accurate amount determination difficult
Solution Approach 1:
The imaging unit captures contact state images during grasping, and the control unit uses this visual feedback to determine the specified amount of flexible objects. This feedback mechanism compensates for the variability in shape and compression of flexible objects, enabling accurate amount determination while maintaining automated high-speed grasping operations.
Solution Approach 2:
The patent replaces mechanical sensors or direct physical measurement methods with an optical imaging system. The imaging unit captures visual information about the contact state, and the control unit processes this optical data to determine the specified amount, substituting mechanical measurement approaches with optical-field methods that are better suited for flexible, deformable objects.
Data Source
AI summary
A grasping device includes: a grasping part module including a first surface and a second surface and configured to grasp an object between the first surface and the second surface; an arm part configured to change a position of the grasping part module; an imaging unit provided at a position that moves together with the grasping part module and configured to capture an image of at least a part of the object; and a control unit configured to control, based on specified amount information indicating a contact state in a case where a specified amount of the object and the first surface are in contact with each other, and information indicating a contact state captured by the imaging unit, at least one of the grasping part module and the arm part such that an amount of the object that is grasped approaches the specified amount.


