Asset Location Using Machine Learning Zone Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for locating assets in indoor environments, such as GPS and RF technologies, face challenges due to low accuracy and high costs, especially in environments with obstacles that cause multipath interference, leading to inefficient asset location.
Innovation Solution
A method for training a machine learning model using data from multiple receivers and tags in an environment to determine the zone location of an asset, reducing the impact of multipath interference by leveraging previous data collected from the environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If GPS tracking is used to locate assets, then live tracking capability is provided, but location accuracy deteriorates to >6m in indoor environments
Solution Approach 1:
The environment is divided into multiple zones, and the system determines which zone an asset is in rather than providing continuous precise positioning. This segmentation approach achieves reliable asset tracking while accepting coarser location granularity.
Solution Approach 2:
The system creates a simplified digital representation of the physical environment as a zone map, which is then used for location determination. This copying approach enables efficient tracking without requiring high-precision continuous positioning data.
2Ease of manufacture
If RF technology with trilateration is used to locate assets, then cost is reduced compared to GPS, but location accuracy deteriorates to 5-10m due to multipath interference
Solution Approach 1:
The system accepts multipath interference as an unavoidable environmental characteristic and uses machine learning to adapt to it. Rather than trying to eliminate the interference, the system learns to operate effectively despite its presence, converting the harmful effect into a manageable condition.
Solution Approach 2:
The system changes the approach from precise coordinate-based positioning to zone-based location determination. This parameter change in the measurement scale allows RF technology to achieve sufficient accuracy for indoor environments without being constrained by multipath interference.
3Measurement precision
If the number of receivers is increased to improve location accuracy, then measurement precision improves, but device complexity and deployment cost increase
Solution Approach 1:
The system uses a limited number of receivers strategically positioned to cover zones, rather than deploying excessive receivers throughout the environment. Machine learning enables accurate location determination with this partial deployment approach.
Solution Approach 2:
The machine learning model acts as an intermediary that processes receiver data and translates it into accurate zone location determinations. This intermediary enables the system to achieve high measurement precision without requiring a proportional increase in the number of receivers.
4Device complexity
If manual searching is used to locate assets, then no additional equipment is needed, but productivity deteriorates due to labor-intensive searching
Solution Approach 1:
The system enables automated asset location determination without requiring manual searching. Assets essentially locate themselves by transmitting signals that are processed by the machine learning model, eliminating the need for human searchers while maintaining simplicity in asset-side equipment.
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
The trained machine learning model enables precise location of assets within a zone, improving accuracy and efficiency in locating assets in environments like warehouses, reducing the need for extensive receiver deployment and minimizing the impact of environmental obstacles.
Implementation Method 1
Multipath interference occurs when an RF signal arrives at a receiver via two or more routes. This results in the total length of each signal path, and thus the time delay and phase of each received signal, to be different.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for training a machine learning model for locating an asset in an environment when the machine learning model is executed on a computer system. The method comprises receiving data corresponding to a plurality of training signals. The plurality of training signals are received at a plurality of receivers from a plurality of training tags located in the environment. The environment has a plurality of zones, and each of the training tags is associated with a zone in which it is located. The method further comprises generating training data for a first zone of the plurality of zones, wherein the training data for the first zone includes values of the training signals received from training tags located in the first zone, each value associated with the receiver at which a respective training signal was received. The method further comprises generating training data for a second zone of the plurality of zones, wherein the training data for the second zone includes values of the training signals received from training tags located in the second zone, each value associated with the receiver at which a respective training signal was received. The method further comprises training, using the training data for the first zone and the training data for the second zone, a machine learning model to output a zone as a determined location of an asset in the environment based on an input which includes data corresponding to one or more signals received at one or more receivers from a tag associated with the asset.