Indoor Mapping via Crowdsourced RF Data Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining the location of a user indoors is challenging due to the unreliability of GPS receivers, which hinders the provision of high-quality location-based services.
Innovation Solution
A method and system that utilize radio frequency (RF) data from communication devices to determine segments, extract RF features, form clusters, and generate routes for indoor mapping, leveraging pedestrian dead reckoning (PDR) and RF data such as Wi-Fi and magnetic field data to create accurate indoor maps without user intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS receivers are used for location determination, then outdoor location accuracy is improved, but indoor location determination becomes unreliable or inoperable
Solution Approach 1:
The patent introduces RF data (Wi-Fi signals, magnetic field data) as an intermediary measurement source to bridge the gap when GPS is unavailable indoors. These intermediate signals serve as proxies for location determination in environments where direct satellite signals cannot penetrate, allowing the system to maintain location capabilities across both indoor and outdoor settings.
Solution Approach 2:
The system transitions from relying on GPS satellite signal parameters to utilizing RF signal parameters (signal strength, magnetic field characteristics) for location determination. This parameter substitution enables the system to adapt to different environmental conditions, particularly indoor settings where GPS parameters are unavailable but RF parameters remain measurable.
2Measurement precision
If crowdsourced RF data is collected from multiple communication devices, then indoor mapping accuracy is improved, but data processing complexity increases
Solution Approach 1:
The patent merges RF data from multiple communication devices to create a collective dataset for indoor mapping. By combining signals from multiple sources, the system achieves more accurate and robust indoor location information while distributing the data collection burden across many devices rather than requiring a single complex system.
Solution Approach 2:
Communication devices perform self-service by automatically collecting and contributing their own RF data to the crowdsourced dataset. Each device independently measures RF parameters and contributes to the collective mapping effort, reducing the need for centralized data collection infrastructure and simplifying the overall system architecture.
3Ease of operation
If clusters of RF data segments are formed to generate indoor routes, then location-based service quality is improved, but computational requirements increase
Solution Approach 1:
The patent segments the continuous RF trajectory data into discrete segments that can be clustered and processed independently. This segmentation allows the system to manage computational requirements by processing smaller, manageable units of data rather than attempting to analyze entire trajectories at once, while still maintaining the ability to generate accurate indoor routes through cluster formation.
Data Source
AI summary
Mapping through crowdsourcing includes determining, using a processor, segments for a plurality of trajectories, wherein each trajectory includes radio frequency (RF) data from a communication device, determining, using the processor, RF features for the segments, and forming, using the processor, clusters of the segments according to the RF features. One or more routes of a map are generated from the clusters using the processor.