Mobile Tag Location Estimation Using Weighted Likelihood Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current intelligent building control systems lack an effective method for accurately predicting the location of mobile tags within a structure, which hinders precise environmental and logistical control based on occupant or asset behavior.
Innovation Solution
A building control system that employs a combination of first and second sensors to generate weighted likelihood maps of a mobile tag's location using grid points, combining sensed conditions such as motion and RF signals to estimate the tag's position, and utilizing convex shapes to improve processing efficiency and navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensor types are used to improve location estimation accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The sensor system is segmented into multiple functional groups (first sensors for first conditions, second sensors for second conditions) that independently sense different physical parameters. Each sensor type is optimized for its specific measurement task, and the results are integrated through the controller to achieve comprehensive location estimation without requiring every sensor to perform all functions.
Solution Approach 2:
The controller serves as a multi-functional unit that receives data from diverse sensor types, generates weighted likelihoods for multiple sensor inputs, combines these likelihoods, and produces location estimates. This universal processing approach allows the system to handle various sensor types uniformly while achieving improved measurement precision through data fusion.
2Measurement precision
If weighted likelihoods from multiple sensors are combined to improve location accuracy, then measurement precision is improved, but processing time increases
Solution Approach 1:
The controller pre-establishes the framework for combining weighted likelihoods and uses efficient algorithms to process sensor data. By structuring the combination process in advance and using optimized computational approaches, the system reduces real-time processing delays while maintaining high location estimation accuracy through comprehensive data fusion.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Apparatuses, methods, and systems for estimating a location of a tag are disclosed. One method includes sensing a first condition of a structure, sensing a second condition of the structure, generating a first set of weighted likelihoods based on the first sensed condition of the structure, wherein the first set of weighted likelihoods includes a weighted likelihood of the tag being at each one of a plurality of grid points within the structure, generating a second set of weighted likelihoods based on the second sensed condition of the structure, wherein the second set of weighted likelihoods includes a weighted likelihood of the tag being at each one of the plurality of grid points, generating a combined set of likelihoods based on the first set of weighted likelihoods and the second set of weighted likelihoods, and estimating a location of the tag based on the combined set of likelihoods.