Localisation Reference Depth Maps for Sub-Meter Vehicle Positioning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing navigation systems lack the sub-meter accuracy required for highly and fully automated driving applications, as traditional positioning methods using navigation satellites or terrestrial beacons provide only 5-10 meter accuracy, which is insufficient for precise vehicle positioning on high-definition digital maps.

Innovation Solution

Generating localisation reference data in the form of depth maps projected onto reference planes defined by navigable elements, with each pixel representing the distance to environmental objects, and associating this data with digital maps to enhance positioning accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional positioning methods using navigation satellites or terrestrial beacons are used, then the system is simple and easy to operate, but the positioning accuracy is only 5-10 meters which is insufficient for automated driving

Engineering Contradiction:
Improvepositioning accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines multiple positioning approaches by integrating depth map-based relative positioning with traditional absolute positioning systems. The depth maps are generated from sensor data and correlated with pre-stored reference depth maps to determine precise vehicle position and orientation, while still utilizing GNSS and other traditional systems for coarse positioning and system redundancy.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent transitions from traditional 2D map matching to 3D depth map correlation for positioning. By capturing and processing depth information from multiple sensors (laser scanners, cameras, radar) to create three-dimensional representations of the environment, the system achieves sub-meter positioning accuracy through multi-dimensional spatial correlation.

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

2Measurement precision

If detailed three-dimensional vector models with separate lane representations are created for automated driving, then positioning accuracy improves, but the data quantity and processing complexity increase significantly

Engineering Contradiction:
Improvepositioning accuracyVSAvoiddata quantity
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential depth information needed for positioning from comprehensive sensor data. By focusing on depth maps that represent distance to environmental objects rather than storing complete three-dimensional models of all road features, the system reduces data quantity while maintaining positioning accuracy.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent pre-generates and stores reference depth maps along planned routes before the vehicle reaches them. This preliminary action allows the vehicle to quickly correlate current sensor data with pre-computed reference data, reducing real-time processing requirements and enabling faster positioning updates.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If real-time sensor data is continuously correlated with reference depth maps to maintain sub-meter accuracy, then positioning precision is maintained, but computational resources and processing time are consumed

Engineering Contradiction:
Improvepositioning accuracyVSAvoidprocessing efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent implements periodic correlation of sensor data with reference depth maps at strategically selected locations along the route, particularly at points where positioning accuracy is critical or where environmental features provide strong correlation signals. This periodic approach maintains accuracy while reducing continuous computational burden.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The system uses readily available sensor data from the vehicle's own sensors (laser scanners, cameras, radar) to generate depth maps for positioning, eliminating the need for external positioning infrastructure. The vehicle essentially positions itself by comparing its own sensor observations against pre-stored reference observations.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3998456B1Methods and systems for generating and using localisation reference data
Publication Date: 2026.01.28 TOMTOM GLOBAL CONTENT
  • EP3998456B1 patent drawingFigure 1
  • EP3998456B1 patent drawingFigure 2
  • EP3998456B1 patent drawingFigure 3~4

AI summary

Methods and systems for improved positioning accuracy relative to a digital map are disclosed, and which are preferably used for highly and fully automated driving applications, and which may use localisation reference data associated with a digital map. The invention further extends to methods and systems for the generation of localisation reference data associated with a digital map.