Crowdsourced RF Ranging Map for Localization Accuracy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing RF ranging-based localization systems face challenges in accuracy and scalability due to sparse and inaccurate target detection, multipath issues, and the difficulty in reproducing consistent target detection outputs across varying sensor positions.

Innovation Solution

The proposed solution involves a crowdsourced RF ranging map generation method, where user equipment (UE) obtains RF ranging data and pose information, and transmits this data to a server to create a global RF ranging map. This map is then used by other vehicles for localization, with semantic information distinguishing static, temporary-static, and dynamic objects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If RF ranging data is collected from individual vehicles for localization, then localization capability is provided, but accuracy is insufficient due to sparse and inaccurate target detection

Engineering Contradiction:

Improvelocalization accuracyVSAvoidtarget detection consistency

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent combines RF ranging data from multiple vehicles to create a crowdsourced map, merging sparse individual detections into a dense collective dataset that improves both accuracy and reliability of target detection

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system performs preliminary RF ranging measurements and map construction in advance, building a comprehensive crowdsourced map before actual localization is needed, so that individual vehicles can achieve high accuracy without needing dense real-time targets

Inventive Principle:

Principle #10Preliminary action

2Loss of information

If camera-based systems are used for localization, then detailed environmental information is obtained, but privacy concerns arise and costs increase

Engineering Contradiction:

Improveenvironmental information qualityVSAvoidprivacy concerns

Core Design Contradiction:

Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent replaces camera-based optical sensing with RF ranging-based electromagnetic sensing, achieving environmental mapping through radio wave reflections rather than visual capture, thereby eliminating privacy concerns while maintaining localization capability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates an RF-based virtual copy of the physical environment through crowdsourced ranging data, producing a functional equivalent to camera-based visual maps without capturing actual visual information that would raise privacy issues

Inventive Principle:

Principle #26Copying

3Measurement precision

If LIDAR or camera imaging technologies are used, then high localization accuracy is achieved, but system costs increase significantly

Engineering Contradiction:

Improvelocalization accuracyVSAvoidsystem cost

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent uses inexpensive RF ranging sensors instead of costly LIDAR or camera systems, accepting that individual vehicle data is sparse but compensating through crowdsourcing from many vehicles to achieve comparable localization accuracy at lower cost

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

Solution Approach 2:

The RF ranging system serves multiple functions including localization, mapping, and environmental characterization using a single sensor type, eliminating the need for separate expensive LIDAR or camera subsystems

Inventive Principle:

Principle #6Universality (Multi-functionality)

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 enhances localization accuracy and scalability by leveraging crowdsourced data, improves privacy compared to camera-based systems, and provides robustness in challenging weather conditions, while reducing costs compared to LIDAR and camera imaging technologies.

Implementation Method 1

RF ranging may contemplate or include RF ranging and bearing techniques such that a relative distance (range) and relative bearing (angular position) may be determined based on a received RF beam's timing and angular/spatial characteristics

Methodology Applied

Scientific EffectTime of flight: Time of Flight

Implementation Method 2

The semantic information may include doppler-based information indicating a probability that a target object is static or dynamic

Methodology Applied

Scientific EffectDoppler effect: Doppler Effect

Data Source

PatentUS12332362B2Systems and methods for radio frequency (RF) ranging-aided localization and map generation

Publication Date: 2025.06.17 QUALCOMM INC

AI summary

Systems, methods, and devices for radio frequency (RF) ranging-aided localization and crowdsourced mapping are provided. In one aspect, a method performed by a user equipment (UE) includes obtaining sensor data comprising first radio frequency (RF) ranging data and imaging data. The method further includes tagging the first RF ranging data with location information and semantic information, wherein the semantic information is based on the imaging data, and wherein the semantic information indicates a first portion of the RF ranging data is associated with a static object type and a second portion of the RF ranging data is associated with a temporary-static object type different from the static object type. The method further includes transmitting, to a RF ranging assistance server, the first RF ranging data tagged with the location information and the semantic information.