Radio Environment Grid Representation for Scalable QoS Prediction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing predictive quality of service (QoS) systems for radio environments in cooperative driving scenarios are limited by their inability to handle varying numbers of surrounding vehicles and applications, which restricts their applicability in real-life scenarios.

Innovation Solution

A method for determining a representation of a radio environment using a spatial grid of cells, where information on active transceivers is summarized per cell, allowing for efficient representation and prediction of future QoS.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If statistical models use a fixed number of inputs (e.g., fixed-size vector in linear regression, fixed feature space in SVM or MLP), then the model structure is simple and well-defined, but the model cannot handle varying numbers of surrounding vehicles and applications in real-life scenarios

Engineering Contradiction:
Improveadaptability to varying numbers of vehicles and applicationsVSAvoidmodel structure complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the radio environment into a spatial grid of cells, where each cell independently represents a region with aggregated transceiver activities. This segmentation allows the system to handle varying numbers of vehicles by mapping them to grid cells rather than processing each vehicle individually, thus improving adaptability while maintaining a fixed-size grid representation for the model input.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a spatial dimension by creating a grid structure over the radio environment. Instead of using a fixed-size vector of vehicle parameters, the system represents the environment as a 2D spatial grid where each cell contains aggregated information. This dimensional transformation allows the model to capture spatial distribution patterns while maintaining a consistent input structure.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Loss of information

If information on each individual vehicle and application is tracked separately, then detailed information is available, but the amount of information to be processed and transmitted increases significantly

Engineering Contradiction:
Improveinformation detail preservationVSAvoidamount of information to be processed
Core Design Contradiction:
Loss of informationVSQuantity of substance

Solution Approach 1:

The patent merges information from multiple transceivers within the same grid cell by aggregating their activities. Instead of processing each vehicle's information separately, the system combines data from all transceivers in a cell to create a unified representation of that cell's radio environment status, thus reducing the total information volume while preserving essential spatial patterns.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent creates a simplified copy of the radio environment in the form of a grid representation. Rather than transmitting and processing detailed information about each individual vehicle, the system uses the grid structure as an abstracted copy that captures the essential spatial distribution and density of transceiver activities, significantly reducing information processing requirements.

Inventive Principle:
Principle #26Copying

3Measurement precision

If the spatial distribution of vehicles is considered in detail, then accurate QoS prediction is achieved, but some ordering or abstraction is required which increases processing complexity

Engineering Contradiction:
ImproveQoS prediction accuracyVSAvoidprocessing complexity for ordering and abstraction
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the continuous spatial environment into discrete grid cells, providing a natural ordering structure. This segmentation captures the spatial distribution of vehicles by assigning them to specific cells, maintaining prediction accuracy through spatial resolution while avoiding the complexity of continuous coordinate processing and ordering.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the parameter representation from continuous vehicle coordinates to discrete grid cell indices. By transforming spatial information into grid-based parameters, the system maintains the ability to capture spatial distribution patterns while simplifying the data structure and reducing processing complexity for ordering and abstraction operations.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3796685B1A method, a computer program, an apparatus, and a vehicle for determining a representation of a radio environment of a mobile transceiver
Publication Date: 2025.04.23 VOLKSWAGEN AG
  • EP3796685B1 patent drawingFigure 1
  • EP3796685B1 patent drawingFigure 2
  • EP3796685B1 patent drawingFigure 3

AI summary

Embodiments provide a method, a computer program, an apparatus, and a vehicle for determining a representation of a radio environment of a mobile transceiver. The method (10) for determining a representation of a radio environment of a mobile transceiver (200) comprises determining (12) information on one or more active transceivers in the environment of the mobile transceiver and generating (14) a grid of the radio environment of the mobile transceiver, the grid comprising a plurality of adjoining cells. The method (10) further comprises indicating (16) an activity of the one or more active transceivers per cell in the grid.