Gripping Point Localization via 3D Sensor and Camera Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for localizing gripping points on closely arranged objects are inefficient and costly due to the limited resolution of laser scanners, making it difficult to distinguish individual objects and determine accurate gripping points for robots in material flow and automation technology.
Innovation Solution
A method using a combination of a 3D sensor, a camera, and illumination units to determine the spatial position and boundaries of objects, allowing for the reliable distinction of individual objects by fusing distance information from the 3D sensor with two-dimensional images from the camera, and improving distinguishability through controlled illumination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a high-resolution laser scanner is used to distinguish closely arranged objects, then measurement precision is improved, but device cost and complexity increase
Solution Approach 1:
The patent combines a standard-resolution laser scanner with a camera system to achieve high measurement precision for closely arranged objects. The laser scanner provides depth information while the camera provides visual information, and their data are fused to enable accurate object distinction without requiring an expensive high-resolution laser scanner alone.
Solution Approach 2:
The patent introduces a camera system as an intermediary component that works together with the laser scanner. The camera captures visual information that complements the depth data from the laser scanner, enabling accurate object distinction using standard-resolution scanning equipment rather than requiring high-resolution scanning alone.
2Ease of manufacture
If standard components are used for object detection, then device cost is reduced, but measurement precision for closely arranged objects deteriorates
Solution Approach 1:
The patent merges the capabilities of a standard-resolution laser scanner and a camera system to achieve measurement precision comparable to high-resolution scanners, while using only standard, cost-effective components. The combination allows accurate object boundary detection and gripping point localization without the high cost of premium equipment.
Solution Approach 2:
The patent makes the laser scanner and camera serve multiple functions: the laser scanner provides both depth information and object positioning, while the camera provides visual verification and boundary detection. This multi-functionality allows standard components to achieve precision typically requiring specialized equipment.
3Productivity
If objects are arranged closely next to one another, then productivity is improved, but object distinction capability deteriorates
Solution Approach 1:
The patent combines depth information from the laser scanner with visual information from the camera to maintain accurate object distinction even when objects are closely arranged. This fusion of data sources enables the system to handle high-density material flow while preserving the ability to identify and process individual objects separately.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables secure, economic, and precise determination of gripping points for closely arranged objects, reducing the need for high-resolution laser scanners and enhancing object recognition, thereby improving handling accuracy and efficiency in automation systems.
Implementation Method 1
The 3D sensor used in the method can in particular be a conventional laser scanner which detects additional distance information or depth information, for example via a time-of-flight measurement.
Implementation Method 2
The two-dimensional image generated by the camera can thus in particular be utilized e.g. to recognize edges of the objects by means of shadows cast in the direction of illumination.
Data Source
AI summary
The invention relates to a method for the localization of gripping points of objects, wherein the objects are scanned by means of a 3D sensor and the objects are illuminated by means of at least one first illumination unit while the objects are detected by means of a camera, wherein the relative positions of the 3D sensor, of the first illumination unit and of the camera with respect to one another are known and the 3D sensor, the first illumination unit and the camera are arranged in a fixed position with respect to one another. In this respect, the boundary of the objects is determined from a two-dimensional image generated by the camera, a spatial position is determined from detected distance information of the 3D sensor and of the two-dimensional image and the gripping points for the objects are determined from the boundaries and from the spatial position of the objects.