Indoor Positioning Using Machine Learning Signal Mapping

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional indoor positioning methods using angle-detection units like WiFi or Bluetooth devices are costly and consume excessive battery power, especially when covering large areas.

Innovation Solution

A method and system for indoor positioning that employs a processing unit to listen to broadcast signals from reference nodes, obtain signal measurements, and update a Machine Learning Model (MLM) describing a linear function between signal measurements and distances, allowing for efficient deployment and reduced power consumption without the need for expensive angle-detection units.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If angle-detection units (WiFi or Bluetooth devices) are deployed to achieve high precision indoor positioning, then positioning precision is improved, but deployment cost and battery power consumption increase

Engineering Contradiction:

Improvepositioning precisionVSAvoidbattery power consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent extracts the angle-detection functionality from the positioning system and replaces it with signal strength-based measurement. Instead of requiring expensive angle-detection units at each reference node, the system uses standard WiFi or Bluetooth devices that measure signal strength (RSSI) to estimate distances, thereby eliminating the need for specialized hardware while maintaining positioning capability

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces expensive angle-detection units with inexpensive standard wireless communication devices. By using widely available WiFi or Bluetooth modules that can be found in most smartphones and computers, the system achieves cost-effective deployment across large areas without requiring specialized expensive hardware at each reference node

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

2Area of stationary object

If angle-detection units are deployed to cover a wide range of space, then positioning coverage is improved, but deployment cost increases

Engineering Contradiction:

Improvepositioning coverageVSAvoiddeployment cost

Core Design Contradiction:

Area of stationary objectVSEase of manufacture

Solution Approach 1:

The patent makes the reference nodes universal by using standard wireless communication devices that serve multiple purposes. These devices can function as reference nodes for positioning, broadcast their location information, and communicate with mobile devices, eliminating the need for specialized single-function angle-detection units and reducing overall system cost

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent employs inexpensive standard wireless devices instead of expensive specialized angle-detection units. This allows for economical deployment across large areas, as the low cost of each reference node enables denser placement and wider coverage without proportionally increasing the budget

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

3Measurement precision

If angle-detection units are used for indoor positioning, then positioning precision is improved, but device complexity increases

Engineering Contradiction:

Improvepositioning precisionVSAvoiddevice complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical/optical angle-detection system with an electromagnetic signal-based system. Instead of using physical angle-detection units that require complex hardware, the system uses signal strength measurements (RSSI) from standard wireless communications to infer distance and position, significantly simplifying the device requirements

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent removes the angle-detection component from the positioning system entirely and extracts only the essential function of distance measurement. By using signal strength to estimate distance without requiring angle detection, the system achieves positioning with simpler devices that lack complex angle-detection hardware

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS9995816B2Methods for indoor positioning and apparatuses using the same

Publication Date: 2018.06.12 WISTRON CORP

AI summary

The invention introduces a method for indoor positioning, executed by a processing unit of a first reference node, which contains at least the following steps. Broadcast signals of second reference nodes are listened. Signal measurements of the broadcast signals are obtained. Identification information is obtained from broadcast messages sent by the second reference nodes. A distance associated with each identification information is obtained. A MLM (Machine Learning Model) is updated according to the signal measurements and the distances, where the MLM describes a linear function between signal measurements and distances.