Multisensory Location Fingerprinting Map for Indoor Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a need for highly accurate positioning information in indoor spaces where GPS-based navigation is either impossible or exhibits unacceptably low granularity, as existing technologies like inertial navigation systems suffer from accuracy drift and require frequent calibration.
Innovation Solution
A method and system that utilize a multisensory location fingerprinting approach, where multiple mobile devices collect and correlate data vectors including electromagnetic signals, accelerometer readings, and internal navigation estimates to create a location fingerprinting map, which is updated periodically to maintain accuracy and correct for inertial navigation drift, enabling precise indoor positioning and navigation without additional hardware.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS-based navigation is used for indoor positioning, then outdoor positioning accuracy is achieved, but indoor positioning accuracy deteriorates due to signal unavailability
Solution Approach 1:
The patent introduces an intermediary location fingerprinting map that mediates between GPS signals and indoor positioning requirements. The map stores pre-collected electromagnetic environment characteristics (WiFi, cellular, Bluetooth signals) at various locations, which serve as intermediary data to determine position when GPS is unavailable. The system compares real-time sensor readings against this fingerprinting map to achieve accurate indoor positioning without direct GPS signals.
Solution Approach 2:
The patent replaces the GPS satellite-based electromagnetic system with a local electromagnetic sensing system. Instead of relying on satellite signals that penetrate poorly through buildings, the system uses local electromagnetic signatures (WiFi access points, cellular towers, Bluetooth devices) that are abundant indoors. This substitution enables continuous positioning both outdoors and indoors using appropriate signal sources.
2Reliability
If inertial navigation systems are used for indoor positioning, then positioning functionality is maintained without GPS, but accuracy deteriorates over time due to drift
Solution Approach 1:
The patent implements feedback by continuously comparing inertial navigation system (INS) position estimates against the location fingerprinting map. When the device moves through the indoor space, the system periodically checks whether the INS-estimated position corresponds to a location with a stored fingerprint. This feedback mechanism detects and corrects INS drift by anchoring the position estimate to known locations identified through electromagnetic signature matching.
Solution Approach 2:
The patent merges two positioning approaches: inertial navigation system (INS) for continuous position tracking and location fingerprinting for periodic correction. The INS provides short-term positioning continuity while the fingerprinting map provides long-term accuracy reference points. By combining these methods, the system achieves both continuous availability and sustained accuracy without GPS.
3Measurement precision
If traditional location fingerprinting calibration is performed, then positioning accuracy is achieved, but time and resource consumption increases due to manual calibration requirements
Solution Approach 1:
The patent enables self-service calibration where the system automatically collects electromagnetic environment data from multiple users' mobile devices as they move through the indoor space. Instead of requiring manual calibration teams to systematically visit every location, the system leverages crowd-sourced data from normal device usage. Multiple devices independently collect and contribute fingerprinting data, which is then aggregated to build the complete location map automatically.
Solution Approach 2:
The patent performs preliminary data collection in parallel across multiple devices and locations rather than sequentially through manual calibration. While users naturally move through the space using their devices, the system pre-collects electromagnetic signatures at numerous locations simultaneously. This preliminary action populates the fingerprinting map in advance, enabling accurate positioning from the first use without requiring dedicated calibration time.
4Measurement precision
If multiple sensors are integrated for multisensory fingerprinting, then positioning accuracy is improved, but device complexity increases
Solution Approach 1:
The patent applies multi-functionality by using a single mobile device to perform multiple roles: GPS reception, inertial navigation, electromagnetic signal sensing (WiFi, cellular, Bluetooth), and location fingerprinting data collection. The same device that users carry for general use becomes a multi-functional positioning instrument, eliminating the need for separate specialized hardware for each sensing function and reducing overall system complexity.
Data Source
AI summary
The present invention discloses, inter alia, a computerized system for building a multisensory location map, the system comprising an interface for receiving multiple multisensory data vectors acquired by multiple mobile devices at multiple locations and accelerometer readings obtained upon movement of at least one device carried by at least one user between the multiple locations; at least a portion of said movement being walking; at least a majority of the multiple locations are located within an area in which an accuracy of global positioning system (GPS) based navigation is below an allowable threshold; and a processor, interconnected with said interface, with accelerometers, a magnetometer and a map calculator, configured for: extracting, out of accelerometer readings, accelerometer information related to multiple walking phases of the walking; for at least two of said multiple walking phases, real-time correcting a currently measured Z vector, and a pitch angle and a roll angle thereof, thereby compensating for horizontal accelerations, thereby obtaining a Z vector pointing toward Earth's center; calculating, from said Z vector pointing toward earth's center, a surface parallel to Earth's face (perpendicular to said Z vector pointing toward earth's center); estimating, from said surface parallel to Earth's face and from a magnetic north measured by at least one built-in magnetometer in said at least one device, an offset selected from a group consisting of: an azimuth offset from magnetic north and a heading offset from geometric north; processing the accelerometer information related to said at least two of said multiple walking phases to determine a direction of propagation of the at least one user and correcting said direction of propagation based on said offset; and estimating, from said corrected direction of propagation, at least one location of said at least one user; and the map calculator calculating, in response to the multiple multisensory data vectors and said at least one estimated location, a location fingerprinting map that comprises multiple grid points; each of the multiple grid points comprising a multisensory grid point fingerprint and grid point location information derivable from said at least one estimated location.