Augmenting Standard Definition Maps with High-Definition Layers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional electronic maps lack sufficient granularity and accuracy to support advanced and safety-critical applications such as autonomous navigation, particularly for higher levels of autonomous driving functionality, due to the expense and complexity of generating high-definition map data using traditional methods.
Innovation Solution
The generation of high-definition map data from a combination of disparate sources like aerial imagery, vehicle object detections, and telemetry data, without requiring specialized and expensive technologies like LiDAR, by detecting map objects within aerial imagery and clustering vehicle object detections to enhance lower definition map data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods using LiDAR are used to generate high-definition map data, then measurement precision and manufacturing precision are improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent combines multiple disparate data sources (aerial imagery, vehicle object detections, telemetry data) into a unified high-definition map representation. By merging these different data types through a common processing framework, the system achieves LiDAR-level precision without requiring LiDAR hardware, thus resolving the contradiction between measurement precision and device complexity
Solution Approach 2:
The patent introduces an intermediary processing layer that transforms raw data from multiple sources into standardized map features. This intermediary layer includes object detection modules, clustering algorithms, and data fusion mechanisms that bridge the gap between low-cost data sources and high-precision map requirements, eliminating the need for expensive LiDAR while maintaining measurement precision
2Device complexity
If conventional electronic maps are used, then device complexity is reduced, but measurement precision and accuracy are insufficient for autonomous navigation
Solution Approach 1:
The patent segments the map data into multiple layers with different levels of detail and precision. The base layer contains standard definition map data for general navigation, while additional layers contain high-definition data for autonomous navigation features. This segmentation allows the system to maintain simplicity for general use while providing high precision when needed for autonomous driving, resolving the contradiction between device complexity and measurement precision
Solution Approach 2:
The patent adds a new dimension to map data by introducing multiple resolution levels and data types that can be selectively activated. Instead of a single monolithic map structure, the system provides a dimensional hierarchy where standard definition maps form the base and high-definition augmentations form additional dimensions, enabling the system to maintain simplicity while achieving high precision through dimensional expansion
3Measurement precision
If high-definition map data is generated using specialized data sources, then measurement precision is improved, but cost increases
Solution Approach 1:
The patent creates copies of high-precision map features by deriving them from multiple low-cost data sources through computational processing. Instead of directly capturing data with expensive LiDAR, the system copies and reconstructs high-precision map representations by fusing aerial imagery, vehicle sensor data, and telemetry information, thus achieving high measurement precision at reduced cost
Solution Approach 2:
The patent changes the parameters of data collection by using multiple low-cost sensors and data types instead of a single expensive LiDAR system. By varying the data sources (aerial imagery, camera feeds, GPS telemetry) and processing parameters, the system achieves cost-effective high-definition map generation that matches the precision of expensive traditional methods
Data Source
AI summary
High-definition map data is generated from a combination of disparate data sources, such as aerial imagery, vehicle object detections, and/or vehicle telemetry data. The resulting high-definition map is sufficiently granular to support higher levels of autonomous driving systems, such as L2 and L3. In particular, specialized, expensive data sources such as LiDAR are not required for the generation of the high-definition map. Map objects are detected within aerial imagery, and vehicle object detections are clustered to filter spurious detections. The resulting detected objects are used to generate HD layers on top of other map data.