End Effector Holding Posture Selection for Shape Error Robustness
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional object holding techniques face issues such as time-consuming posture exploration, low robustness against shape errors, and inability to operate held objects, particularly when using finger tips.
Innovation Solution
An object holding method and program that determine the center of an object based on captured images, select a holding posture, and reduce portions with measurement errors by applying forces from a selected posture to stabilize the hold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the object shape is measured and a holdable posture is explored using conventional techniques, then the object can be held, but it becomes time consuming to explore the holdable posture
Solution Approach 1:
The system pre-calculates and stores multiple candidate holding postures along with their corresponding object centers before actual object manipulation. When an object needs to be held, the system only needs to match the measured object center with pre-computed candidate postures, avoiding time-consuming exploration during operation. This preliminary preparation of holding postures and centers resolves the contradiction by shifting computational work from runtime to setup phase.
2Reliability
If the object shape is measured and a holdable posture is explored using conventional techniques, then the object can be held, but the robustness against shape errors is low
Solution Approach 1:
Instead of relying on a single precise shape measurement, the system measures only the necessary portion of the object shape (e.g., center position) and uses pre-computed candidate postures that are robust to measurement variations. By measuring less but using pre-prepared multiple candidates, the system achieves higher robustness against measurement errors while maintaining holding capability.
3Force
If the object is held by using finger tips in conventional techniques, then the object can be grasped, but it cannot be operated
Solution Approach 1:
The system segments the holding function into two distinct phases: grasping (using finger tips for secure holding) and operating (using pre-determined postures that enable manipulation). By separating these functions and selecting appropriate postures from pre-computed candidates, the system achieves both secure grasping and ease of operation, resolving the contradiction between holding force and operability.
4Reliability
If a holding posture is selected based on measured object shape, then the object can be held, but measurement errors affect the holding accuracy
Solution Approach 1:
The system creates a simplified copy of the object's essential feature (center position) rather than relying on complete shape measurement. By matching the measured center with pre-computed candidate centers, the system achieves accurate holding while being insensitive to errors in detailed shape measurement. This copying approach resolves the contradiction by focusing on critical information only.
Data Source
AI summary
An object holding method includes: a step of determining a center of a first object assumed to be held by an end effector for a plurality of holding postures which the end effector is able to take; a step of measuring a shape of a second object based on an image in which the second object is captured from a viewpoint; a step of selecting a holding posture when the end effector holds the second object from the holding postures based on centers of the second object and the first object; and a step of reducing a portion of the shape of the second object in a case where the end effector holds the second object by using the selected holding posture.