Indoor Localization via Wireless Signal Maps and Voting Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigation systems face challenges in providing accurate indoor localization due to the lack of GPS satellite signals, making it difficult to offer advanced navigation features such as finding specific locations within buildings or malls.
Innovation Solution
The method involves generating signal maps by collecting wireless network access point identifiers and signal strengths, using voting models or rectangular models to predict the location of a client device within an indoor space, and combining this data with motion models to identify the current location based on received signals and sensor inputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS satellite signals are used for localization, then outdoor navigation accuracy is improved, but indoor localization capability deteriorates due to signal blockage
Solution Approach 1:
The patent introduces wireless network access points as intermediary objects to enable indoor localization. Instead of relying on GPS satellites that cannot penetrate buildings, the system uses locally deployed access points that emit wireless signals detectable indoors. These access points serve as mediators between the mobile device and the indoor environment, allowing location determination without direct GPS signal access.
Solution Approach 2:
The patent replaces the GPS satellite-based electromagnetic positioning system with a wireless network-based localization system. Instead of using satellite signals that require line-of-sight reception, the system substitutes a ground-based wireless infrastructure using access points and mobile devices with wireless network cards, enabling localization through wireless signal strength measurements rather than satellite signal triangulation.
2Measurement precision
If detailed signal map data is collected for accurate indoor localization, then location prediction accuracy is improved, but network bandwidth consumption and device resource usage increase
Solution Approach 1:
The patent extracts only the essential elements needed for localization from the wireless environment - specifically access point identifiers (MAC addresses) and signal strength values. Rather than transmitting complete signal maps or detailed environmental data, the system extracts and transmits only these critical parameters that are sufficient for location determination, significantly reducing data volume while maintaining localization accuracy.
Solution Approach 2:
The patent changes the parameters being transmitted from detailed signal characteristics to simplified identification parameters. Instead of sending raw signal waveforms or comprehensive environmental data, the system transforms the data into discrete access point identifiers and quantized signal strength levels, reducing data complexity and transmission requirements while preserving the information needed for location prediction.
Data Source
AI summary
Aspects of this disclosure provide systems and methods for generating models of a wireless network environment in an indoor space which may be used to predict an indoor location. The disclosure relates to collecting wireless network access point identifier information and power level observed at various locations are collected to generate various signal maps. The signal maps may be used to generate models of the indoor space. In one example, a voting model may use a probability distribution of a plurality of signal maps in order to identify a location with a highest probability of overlap with current signals received at a client device. Once a location has been identified, it may be used to assist with any number of navigational functions, such as providing turn by turn directions to another indoor location, for example, a conference room or exit, or simply providing information about the current location.