Indoor Location Model Using Crowd-Sourced Inertial Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current indoor location determination methods for mobile devices rely on site surveys of wireless access points, which are time-consuming and become stale over time due to changes in access point locations, leading to inaccurate models.
Innovation Solution
A scalable method using crowd-sourced inertial navigation system (INS) signals from multiple client devices to create and maintain an accurate model of wireless access points by tracking user trajectories and scoring routes to identify frequently traveled areas and wireless signal signatures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional site surveys are conducted to build indoor location databases, then initial model accuracy is improved, but the time and resources required increase significantly
Solution Approach 1:
The system enables users to passively contribute location data through their mobile devices as they naturally move through indoor spaces. The crowd-sourced data collection mechanism eliminates the need for dedicated surveyors to manually visit each location, allowing the database to build and update itself through aggregated user trajectories and wireless signal measurements.
Solution Approach 2:
Mobile devices serve multiple functions: they act as both the user's personal device and as survey instruments for collecting location data. The same device used for communication and entertainment also captures wireless signal strengths, determines device positions through inertial sensors, and contributes to building the indoor location database, eliminating the need for specialized surveying equipment.
2Area of stationary object
If comprehensive site surveys are performed to cover tens of thousands of buildings, then database coverage is improved, but the complexity and cost of maintenance increase
Solution Approach 1:
The system automatically collects and processes location data from numerous user devices across multiple buildings simultaneously. Each device independently contributes data as it moves through indoor spaces, and the server automatically aggregates, validates, and updates the database without requiring coordinated survey efforts across thousands of locations.
Solution Approach 2:
The large-scale survey problem is divided into numerous small, independent data collection tasks performed by individual mobile devices. Each device independently maps its local environment and contributes trajectory data, which the server then integrates into the overall database. This segmentation allows parallel data collection across many buildings without increasing overall system complexity.
3Stability of the object's composition
If static databases are created through one-time surveys, then initial data consistency is improved, but the data becomes stale and inaccurate over time due to access point changes
Solution Approach 1:
The system transitions from static, one-time surveys to dynamic, continuous data collection. User devices continuously measure wireless signal strengths and update their position estimates as they move through indoor spaces, allowing the database to automatically adapt to changes in access point locations, additions, or removals without requiring re-surveying.
Solution Approach 2:
Instead of performing discrete, periodic re-surveys, the system maintains continuous data collection through ongoing user device usage. As long as users move through the covered areas, new data is continuously gathered and the database is incrementally updated, ensuring persistent accuracy without interruption to normal operations.
4Measurement precision
If extensive site surveys are conducted to ensure accurate location modeling, then measurement precision is improved, but productivity of database creation decreases
Solution Approach 1:
The database creation process is transformed from an active surveying operation into a passive self-building process. Rather than surveyors actively collecting data point-by-point, the system passively accumulates location data from user devices as they naturally use their mobile phones for other purposes, dramatically accelerating database creation without sacrificing accuracy.
Solution Approach 2:
The system merges the database creation function with normal mobile device usage. Users continue their regular activities with their devices while simultaneously contributing location data, combining two separate processes (daily device use and surveying) into one unified operation that achieves both productivity and accuracy goals.
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
This approach enables a passive and efficient site survey that maintains an up-to-date database of access points, improving accuracy and reducing the need for extensive site surveys, while ensuring user privacy through anonymization and aggregation of data.
Implementation Method 1
the inertial navigation signals may include one of: accelerometer data, gyroscope data, and compass data
Implementation Method 2
the inertial navigation signals may include one of: accelerometer data, gyroscope data, and compass data
Implementation Method 3
the inertial navigation signals may include one of: accelerometer data, gyroscope data, and compass data
Implementation Method 4
Current techniques to determine indoor locations of mobile devices are based on interior scans of wireless access points. The scans may be used to build a database that can model an indoor space by determining locations of the access points and their corresponding signal strengths at those locations
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Aspects of the present disclosure provide techniques for constructing a scalable model of an indoor space using crowd-sourced inertial navigation system (INS) signals from mobile devices. By tracking INS signals from a number of participating users, the user's trajectories can be estimated as they move their mobile devices indoors. The estimated trajectories can be scored against similar routes taken by other users. Routes with the highest scores are then laid out over a map of the indoor space to identify areas most often traveled to and from landmarks and distances between the landmarks.