Driving Automation Restriction Layers for ODD-Aware Vehicle Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated driving systems face challenges in determining Operational Design Domains (ODDs) due to the complexity of processing separate rules and map data from different providers, which can lead to increased computational intensity and difficulties in ensuring safety and designing AD system functionality.
Innovation Solution
The method involves providing map data with a driving automation restriction layer that includes attributes associated with specific road network segments, reducing vehicle-side processing by integrating ODD-related rules directly into the map data, thereby simplifying the determination of ODD compliance and enhancing safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If separate rules and map data are provided from different providers, then the AD system can access comprehensive operational constraints and geographic information, but the vehicle-side processing complexity increases substantially
Solution Approach 1:
The patent merges separate rules data and map data into a single integrated data structure where operational constraints are embedded within geographic features. This combination eliminates the need for separate processing of rules and map data at the vehicle, reducing computational complexity while maintaining comprehensive operational coverage.
Solution Approach 2:
The rules are pre-associated with their corresponding geographic features during data preparation, rather than requiring runtime matching at the vehicle. This preliminary association of constraints with locations simplifies the vehicle-side processing by eliminating complex spatial queries and rule matching operations.
2Adaptability or versatility
If rules are provided separately from map data, then the system can maintain independent update cycles for each data type, but the association and integration of rules with geographic features becomes difficult
Solution Approach 1:
The patent segments the integrated data into modular geographic features, each containing embedded rules. This segmentation allows independent updates of specific geographic features and their associated rules without requiring updates to the entire dataset, while maintaining clear associations through the hierarchical structure.
3Adaptability or versatility
If map data and rules are provided in different formats without common geographical frame of reference, then the system can accommodate diverse data sources, but the integration and processing at the vehicle becomes substantially more difficult
Solution Approach 1:
The patent enforces a homogeneous data structure where all rules are embedded within standardized geographic feature objects. This uniform structure provides a common geographical frame of reference that simplifies processing while allowing diverse data sources to be ingested through standardized import and conversion processes.
Data Source
AI summary
A method for providing data to one or more vehicles for controlling respective automated driving systems of the one or more vehicles, the method comprising: receiving an indication of a vehicle fleet; obtaining, from a restriction repository storing restriction data that indicates one or more location-dependent driving automation restrictions for automated driving systems, restriction data that corresponds to a portion of a road network and that is applicable to the indicated vehicle fleet; generating, or performing an update process for, a driving automation restriction layer for an amount of map data that corresponds to the portion of the road network based on the obtained restriction data; and providing the amount of map data, with the driving automation restriction layer, to one or more vehicles in the vehicle fleet.