Measuring Device Positioning via Neural Network Prognosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the position and orientation of measuring devices, such as total stations, are prone to errors and require experienced operators to set up control points, which increases the time and complexity of the measurement process.
Innovation Solution
A method utilizing a trained artificial neural network to assess the need for further measurements and the suitability of measuring positions, allowing the device to automatically adjust or cancel measurements based on a probability grid, reducing the need for manual control points and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If control points are provided and measured in the measuring environment using known methods, then the position and orientation of the measuring device can be determined, but the process is susceptible to errors and requires experienced operators
Solution Approach 1:
The measuring device determines its own position and orientation by capturing images of the measuring environment and processing them through neural networks and probability grids, eliminating the need for external control points and experienced operators to set them up
Solution Approach 2:
The patent replaces the mechanical/manual process of setting and measuring control points with an automated image processing system using neural networks and probability grids to determine device position and orientation
2Measurement precision
If control points are provided and measured in the measuring environment, then the position and orientation of the measuring device can be determined, but the time required for the measurement process increases
Solution Approach 1:
The neural network is pre-trained with simulated measuring environments and images before actual use, enabling it to quickly assess measuring position suitability and determine device orientation without requiring time-consuming control point measurements during the actual measurement process
Solution Approach 2:
The system automatically processes images and updates probability grids without requiring experienced operators to manually set up and measure control points, significantly reducing the time required for position and orientation determination
3Measurement precision
If multiple measurements are taken to improve accuracy of position and orientation determination, then the precision improves, but the time required and complexity of the process increases
Solution Approach 1:
The system uses feedback from image analysis and neural network assessments to determine whether the current measuring position is suitable, updating the probability grid accordingly and deciding whether further measurements are needed, thereby optimizing the number of measurements taken
Solution Approach 2:
The neural network assesses the suitability of the current measuring position and determines if further measurements are necessary, allowing the system to take only the necessary number of measurements rather than always taking multiple measurements, thus improving efficiency while maintaining accuracy
Data Source
AI summary
A method for determining a position and/or orientation of a measuring device in a measuring environment which is mapped in a geometry model by a trained artificial neural network that has been trained by known measuring environments to give a prognosis of the need for a further measurement by the measuring device and, if necessary, a prognosis of the suitability of a measuring position of the measuring device.