High-Resolution Digital Map Layers for Sensor Model Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional maps lack sufficient resolution and information for fully automated vehicles, especially in urban areas, and there are no recognized quality criteria for evaluating and validating sensor models, making real vehicle tests economically infeasible and simulation-based validation challenging.
Innovation Solution
A high-resolution digital map is enhanced with sensor-specific confidence layers containing detection indicators from real sensor data during test drives, allowing for the validation and improvement of sensor models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional maps are used, then the map structure is simple and easy to manage, but the resolution and information content are insufficient for fully automated vehicles
Solution Approach 1:
The patent segments the map into multiple layers (base layer for road network, additional layers for traffic signs, static objects, and sensor confidence indicators). This segmentation allows the map to organize complex information hierarchically, improving resolution and information content while maintaining manageable structure through layered architecture.
Solution Approach 2:
The patent adds a new dimension to the traditional map structure by incorporating sensor confidence indicators as an additional layer. This dimensional extension enables the map to not only store spatial and object information but also to encode validation quality metrics, transforming the map from a static structural representation to a multi-dimensional data structure that supports sensor model validation.
2Reliability
If real vehicle tests are conducted to validate sensor models, then validation accuracy is improved, but the cost and complexity increase significantly
Solution Approach 1:
The patent creates a virtual copy of the validation process by embedding sensor confidence indicators directly into the digital map. Instead of requiring physical real-world tests, the system uses the map itself as a reference framework that contains validated sensor performance data, allowing virtual validation through simulation while maintaining the reliability of real-world testing.
Solution Approach 2:
The sensor confidence indicator layer acts as an intermediary between real sensor data and simulation models. It provides a bridge that allows validation results from real tests to be encoded in the map and subsequently used to validate sensor models in simulation, reducing the need for repeated real-world testing while maintaining validation accuracy.
3Ease of manufacture
If simulation-based validation is used, then cost is reduced, but the quality and accuracy of validation are compromised without recognized quality criteria
Solution Approach 1:
The patent introduces new parameters (sensor confidence indicators) that quantify validation quality in the digital map. These parameters transform the validation process by providing measurable criteria for assessing sensor model performance in simulation, enabling cost-effective validation while maintaining or improving validation quality through quantifiable metrics.
4Loss of information
If additional sensor data layers are added to the digital map, then information content and resolution are improved, but the data volume and processing complexity increase
Solution Approach 1:
The patent applies local quality by adding sensor confidence indicators only at specific locations where objects were detected, rather than uniformly across the entire map. This selective enrichment maintains high information content and resolution where needed while minimizing unnecessary data processing complexity in areas without detected objects.
Data Source
AI summary
A method for providing a high-resolution digital map includes locating a device and providing sensor data at a located position during a test drive of the located device. The method further includes ascertaining detection indicators for at least one object detected based on the provided sensor data at the located position, and adding at least one additional layer to the high-resolution digital map. The at least one additional layer includes the ascertained detection indicators for the at least one detected object.