Indoor UE Localization Using HMM for Signal Ambiguity

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for indoor localization, such as GPS and RSRP-based trilateration, struggle to accurately determine the location of user equipment (UE) in environments with obstacles like remote radio heads and leaky cables due to signal ambiguity and difficulty in distinguishing between multiple potential sources.

Innovation Solution

A method utilizing MR/XDR measurements and Hidden Markov Models (HMM) to analyze signal sequences, incorporating transition, emission, and initial state probability matrices, to determine the most likely location and route of the UE by partitioning the venue into sections and accounting for signal uncertainty.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If GPS or RSRP-based trilateration is used for indoor localization, then outdoor positioning capability is provided, but positioning accuracy deteriorates due to signal obstacles and ambiguity in indoor environments

Engineering Contradiction:

Improvepositioning capabilityVSAvoidpositioning accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The venue is divided into multiple discrete sections, with measurement points distributed within each section. This segmentation allows the system to handle signal ambiguity by confining the search space to local sections rather than the entire venue, thereby improving positioning accuracy in indoor environments with obstacles

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

A probabilistic model based on Hidden Markov Models is introduced as an intermediary between signal measurements and location determination. The model uses transition probability matrices, emission probability matrices, and initial state probability matrices to resolve signal ambiguity and compute the most likely location, transforming unreliable direct measurements into accurate position estimates

Inventive Principle:

Principle #24Intermediary (Mediator)

2Device complexity

If signal characteristics are compared directly to determine location, then computational simplicity is maintained, but positioning accuracy deteriorates due to signal ambiguity from multiple potential sources

Engineering Contradiction:

Improvecomputational complexityVSAvoidlocation determination accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

Probability matrices (transition, emission, and initial state) are pre-computed and stored before actual positioning operations. During runtime, the system only needs to perform matrix multiplications and comparisons rather than complex optimization calculations, maintaining computational efficiency while improving accuracy through the probabilistic framework

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically updates the most likely location by sequentially processing signal measurements and updating probability distributions. The Hidden Markov Model allows the location estimate to evolve over time based on new measurements, adapting to changing signal conditions while resolving ambiguity through temporal dynamics

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS12513652B2Method, apparatus and computer program product

Publication Date: 2025.12.30 NOKIA SOLUTIONS & NETWORKS OY

AI summary

There is provided a method comprising receiving at least one measured signal characteristic from a user equipment, the user equipment being located at a user equipment location; comparing the at least one measured signal characteristic to at least one of a plurality of signal characteristics, each signal characteristic being associated with a respective measurement point; and determining, based on the comparing, a probability that the user equipment location is a first location.