Robotic Arm Handling Using Object Property-Based Grip Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic systems struggle to handle objects that are not previously identified or known, often leading to damage due to improper gripping or handling, and require complex identification processes.
Innovation Solution
A method involving object detection, measurement of properties using sensors, querying a database or statistical model to determine handling properties, and creating control data for robotic arms to handle objects without prior identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the robot uses a gripping force adapted to previously identified objects, then the object handling is reliable and damage-free, but the system cannot handle unidentified or unknown objects
Solution Approach 1:
The system changes the parameter of object recognition from requiring full identification to using only physical property measurements (mass, dimensions, shape). By changing what parameters are used for object characterization, the system can handle both known and unknown objects reliably using the same physical property-based approach.
2Measurement precision
If the system implements complex object identification processes, then handling parameters can be precisely determined, but the system becomes more complex and time-consuming
Solution Approach 1:
The system extracts only the essential physical properties (mass, dimensions, shape) needed for handling from the object, ignoring all other identification aspects. This extraction approach provides sufficient precision for determining handling parameters while keeping the system simple and fast.
Solution Approach 2:
The system replaces complex mechanical identification processes with sensor-based physical property measurements. Using sensors to measure mass, dimensions, and shape substitutes for more complex identification mechanisms, achieving the same goal with simpler technology.
3Force
If the system uses strong gripping force to ensure secure handling, then the object is held firmly, but the object may be damaged by crushing
Solution Approach 1:
The system determines local quality characteristics of the object (shape, dimensions, mass distribution) and uses this information to adapt the gripping force locally. By knowing the object's physical properties, the robot can apply just the right amount of force at the right locations to hold the object securely without causing damage.
4Manufacturing precision
If the system measures multiple object properties to determine handling parameters, then the handling accuracy improves, but the measurement time and processing complexity increase
Solution Approach 1:
The system performs partial measurement by focusing only on the essential physical properties needed for handling (mass, dimensions, shape) rather than measuring all possible object properties. This partial action approach achieves sufficient handling accuracy while minimizing measurement and processing time.
Data Source
AI summary
The invention relates to a method for handling an object (20) by means of a robotic arm (10), the method comprising the following steps:a. detecting at least one object (20) and measuring at least one measurement value of at least one object property of the object (20) by means of at least one sensor (31, 32);b. determining at least one handling property by querying the measurement value in a database and/or by inference with a statistical model involving entering the measurement value;c. creating a set of control data for the robotic arm (10) based on the handling property; andd. handling the object (20) by means of the robotic arm (10) according to the set of control data.Furthermore, the invention relates to a device for handling objects (20), the device comprising a robotic arm (10), at least one sensor (31, 32), and a computer system (40).