Machine Learning Device Localization from Distance Measurements
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the location of smart devices in a network are time-consuming and inefficient, especially when hundreds of devices need to be installed, as manual recording of device locations is impractical.
Innovation Solution
A method using machine learning to determine device locations by generating synthetic distance measurements between candidate locations, training a model with these measurements, and inputting measured distance data to predict actual device locations, which is robust to measurement errors through random variations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual recording of device locations is used, then location data can be obtained, but the process becomes unacceptably time-consuming and inefficient when hundreds of devices need to be installed
Solution Approach 1:
The patent replaces the manual mechanical process of recording device locations with an automated electronic system. The system uses distance measurements between devices to automatically determine and record locations through machine learning algorithms, eliminating the need for manual note-taking and significantly reducing installation time while maintaining location accuracy
Solution Approach 2:
The system enables devices to self-locate by automatically performing distance measurements with other devices and using these measurements to determine their own positions. The machine learning model processes the distance data and outputs location information without human intervention, allowing the installation system to serve itself
2Loss of information
If manual identification of device locations is performed by turning on devices one by one, then location information can be obtained, but the process becomes very time-consuming
Solution Approach 1:
The patent replaces the manual process of individually activating and identifying devices with an automated system that uses distance measurements between all devices. The machine learning model processes these measurements to simultaneously determine the locations of all devices in the network, completing the task in a fraction of the time required for manual identification
Solution Approach 2:
The system performs multiple functions simultaneously: it measures distances between all device pairs, processes this data through the machine learning model, and determines locations for all devices in a single integrated process. This multi-functional approach replaces the sequential manual process of individually identifying each device
Data Source
AI summary
A method of determining device locations includes receiving a set of candidate locations in an environment and generating training data representing synthetic distance measurements between pairs of the candidate locations. The synthetic distance measurements are generated by applying random variations to the geometric distances between the candidate locations. The training data and candidate locations are used to train a machine learning model. A set of measured distances between devices are input to the trained learning model, which is used to determine a respective location in the environment of each of the devices.