Graph-Based Indoor Positioning Using Sensor Trajectories
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing indoor positioning systems face challenges with high computational costs, energy consumption, and the need for high-precision sensor data, particularly when GPS data is unavailable, leading to inefficiencies and potential security issues with remote server processing and sensitive information leakage.
Innovation Solution
A computer-implemented method using a graph model with feature functions that determines a mobile device's position within an indoor area by constructing a graph from a map, incorporating observations from sensors like accelerometers and magnetometers, and optimizing trajectories without relying on GPS data, allowing for efficient computation and flexible sensor data integration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If recursive Bayesian filters (particle/Kalman filters, HMMs) are used for map matching, then positioning accuracy is improved, but computational cost increases significantly
Solution Approach 1:
The patent segments the positioning problem into discrete graph vertices representing spatial locations and edges representing possible transitions. This discretization transforms the continuous state space problem into a discrete optimization problem that can be solved more efficiently using dynamic programming on the graph structure, reducing computational complexity while maintaining positioning accuracy.
Solution Approach 2:
The patent uses a pre-constructed graph model that copies the spatial structure of the environment. This graph model serves as a simplified representation that can be processed efficiently without requiring complex real-time calculations, allowing the system to achieve accurate positioning through graph-based optimization rather than computationally intensive filtering.
2Measurement precision
If map matching is performed on a remote server via Internet, then positioning accuracy is improved, but service availability decreases and security risks increase
Solution Approach 1:
The patent enables the mobile device to perform map matching locally using its own sensors and the graph model stored on the device. This self-service approach eliminates dependency on remote servers and Internet connectivity, ensuring positioning service availability even in offline conditions while maintaining security by keeping sensor data on the device.
Solution Approach 2:
The graph model is pre-constructed and stored on the mobile device before positioning is needed. This preliminary preparation allows the device to perform real-time map matching locally without requiring server communication during actual positioning operations, improving both availability and response time.
3Measurement precision
If high-precision sensor data is required for accurate map matching, then positioning accuracy is improved, but energy consumption increases
Solution Approach 1:
The patent uses a graph-based approach that processes sensor data in a simplified manner by mapping observations to discrete graph vertices and edges. This partial processing approach achieves sufficient positioning accuracy without requiring the full computational power needed for high-precision filtering, thereby reducing energy consumption while maintaining acceptable positioning performance.
Data Source
Figure 1
Figure 2a~2b
Figure 2c~2d
AI summary
A method of determining the position of a mobile device using a model. The model comprises a graph comprising a set of vertices and a set of edges between the vertices, and one or more feature functions that take as input one or more vertices of the graph and a set of observations for the device, and return a feature value. The model is constructed by obtaining a map of the geographical area, constructing the graph using the map, wherein the vertices of the graph correspond to areas of the map, and two vertices are joined by an edge when the areas corresponding to the vertices are adjacent and can be travelled between by a device, and building the one or more feature functions using the graph, wherein the feature value of the one or more feature functions indicates the extent to which the observations support the device being positioned in the areas corresponding to the one or more vertices of the graph. The method then comprises the steps of: obtaining a set of observations from the sensors of the device; determining the trajectory for the device that optimises the values given by the feature functions given for the set of observations; and determining the position of the device to be the end point of the trajectory.