Modulation Symbol Mapping for Low-Latency Remote Localization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current wireless communication systems face inefficiencies in transmitting and receiving data for localization services, particularly in optimizing communication resources to achieve accurate location estimation and low latency, especially in scenarios like 6G networks and metaverse applications, where redundant information is generated and computational costs are high.

Innovation Solution

The implementation of a machine learning-based approach that jointly optimizes the control system (CTRL) and communication system (COMM) using an encoder and decoder to map image-based and sensor-based input data into encoded modulation symbols, adding a reference signal for adaptive communication, and bypassing physical layer decoding to improve localization accuracy and latency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional physical layer decoding and demodulation are used for localization services, then communication reliability is maintained, but computational costs are high and latency increases

Engineering Contradiction:
Improvelocalization service efficiencyVSAvoidprocessing latency
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent extracts and removes the physical layer decoding and demodulation steps from the traditional communication pipeline. By directly mapping sensor data to modulation symbols at the application layer, the system eliminates redundant processing steps while maintaining communication reliability, thereby reducing computational costs and processing latency

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of following the conventional approach of encoding data then decoding and demodulating it through multiple layers, the patent inverts the process by directly mapping sensor measurements to modulation symbols. This reverse engineering of the communication pipeline achieves the same reliability with significantly reduced computational complexity

Inventive Principle:
Principle #13The other way round (Inversion)

2Measurement precision

If redundant information is transmitted for accurate localization, then measurement precision improves, but communication resource efficiency deteriorates

Engineering Contradiction:
Improvelocation estimation accuracyVSAvoidcommunication resource efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent changes the parameter representation by directly mapping sensor data parameters to modulation symbol parameters through machine learning models. This parameter transformation eliminates redundant information while preserving the essential localization data, achieving both accuracy and efficiency simultaneously

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system applies local quality optimization by transmitting only the specific features and parameters that are locally relevant to localization accuracy. Rather than transmitting all sensor data uniformly, the patent selectively encodes only the necessary information at each processing stage, improving communication efficiency without sacrificing measurement precision

Inventive Principle:
Principle #3Local quality

3Measurement precision

If complex machine learning models are used for end-to-end optimization, then localization accuracy improves, but device complexity increases

Engineering Contradiction:
Improvelocalization accuracyVSAvoidencoder-decoder system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the complex machine learning system into distinct functional modules: sensor data acquisition, feature extraction, machine learning-based mapping, and modulation symbol generation. This segmentation allows each component to be optimized independently, reducing overall device complexity while maintaining high localization accuracy

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The encoder-decoder system is designed with multi-functionality to handle various sensor types and localization scenarios using the same core machine learning framework. This universal approach reduces device complexity by avoiding the need for separate specialized systems for different applications

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4456461A1Mapping of image data and motion sensor data into modulation symbols for remote localization services
Publication Date: 2024.10.30 NOKIA SOLUTIONS & NETWORKS OY
  • EP4456461A1 patent drawingFigure 1
  • EP4456461A1 patent drawingFigure 2A
  • EP4456461A1 patent drawingFigure 2B

AI summary

Disclosed is a method comprising obtaining first input data, that is image-based input data, and second input data, that is sensor-based input data, providing the first input data and the second input data to an encoder, wherein the encoder uses a machine learning model for mapping the first and second input data to encoded modulation symbols, adding a reference signal to the encoded modulation symbols, allocating transmission time interval resource units to the encoded modulation symbols with the reference signal, and transmitting the symbols with the refence signal to a transmission channel.