Robot Grip Point Memory for Continuous Object Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing handling systems for picking objects from one container to another suffer from downtime due to the need for repeated grip point determination, especially when robot dynamics are fast, leading to inefficiencies in gripping and transferring objects.
Innovation Solution
A handling system that uses a robot with an end effector and a detection device to image and determine grip points, storing these candidates for subsequent cycles, allowing the robot to access pre-determined grip points without waiting for new determinations, thus reducing downtime and improving efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the robot performs serial handling cycles with repeated grasp point determination, then the robot can accurately grasp and transfer objects, but the robot experiences downtime waiting for grasp point determination results
Solution Approach 1:
The system performs preliminary actions by capturing images of the workspace and pre-determining multiple grasp point candidates for multiple objects before the robot begins its handling cycle. This allows the robot to access pre-computed grasp points during execution, eliminating the need to wait for real-time grasp point determination and reducing robot downtime while maintaining accurate grasping.
2Speed
If the robot operates with fast dynamics, then the robot can quickly execute handling tasks, but the robot still experiences inefficiency due to waiting for grasp point determination
Solution Approach 1:
The system ensures continuous useful action by pre-determining grasp points for multiple objects in advance, allowing the robot to continuously execute handling tasks without interruption. The robot can seamlessly move from one object to the next using pre-computed grasp points, maintaining high speed operation and maximizing productivity without idle waiting time.
3Loss of information
If the system determines grasp points for all objects in each cycle, then complete object information is available, but the processing time increases
Solution Approach 1:
The system applies partial action by determining grasp points for only a subset of objects in each cycle rather than all objects. By selecting and processing a manageable number of grasp point candidates, the system maintains complete information availability for the objects being handled while reducing overall processing time and computational load.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
The invention relates to a method for handling objects (13) arranged in a work area (12) by means of a handling system (10), the method comprising performing several handling cycles successively, each handling cycle comprising capturing at least one image of the work area, determining, based on the at least one image, at least one grip point candidate at which a respective object can be gripped with the end effector, wherein the determined grip point candidates form a set Me of grip point candidates, selecting one grip point candidate as the target grip point for the end effector, and executing a handling task comprising moving the end effector to the target grip point, wherein at least a subset Mes of the set Me is stored in a grip point memory.wherein at least a subset Mtes of the grip point candidates Mes stored in the grip point memory remain stored at least until the next handling cycle, and wherein the target grip point is selected from a set Ms of grip point candidates stored in the grip point memory. The invention also relates to a handling system designed for this purpose.