Geographic Segmentation for Automated Driving Environment Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for creating environment models in infrastructure-based automated driving systems face challenges in distributing sensor data processing across multiple instances, especially in large service areas, due to state-related processing requirements that are difficult to manage, leading to potential overload and increased costs.
Innovation Solution
The method involves dividing a service area into geographic segments, assigning sensor data with coordinates to specific process instances, and computing partial environment models for each segment, allowing for dynamic adaptation of segment size and number based on expected objects, enabling efficient distribution and scaling of processing load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If sensor data processing is centralized in a single process instance, then the environment model computation is simplified, but the system cannot handle large service areas and becomes overloaded
Solution Approach 1:
The service area is divided into multiple geographic segments, each assigned to a separate process instance. This segmentation allows the system to distribute the processing load across multiple instances, preventing any single instance from becoming overloaded while maintaining the ability to compute environment models for large service areas.
2Area of stationary object
If multiple process instances are used for large service areas, then the system can handle larger areas, but state-related processing becomes difficult to distribute
Solution Approach 1:
The patent extracts the geographic segment identification and filtering logic from the centralized processing and implements it in each distributed process instance. Each instance independently identifies sensor data belonging to its assigned geographic segment using geographic coordinates, eliminating the need for complex state distribution while enabling scalable processing across large service areas.
3Productivity
If processing instances are dynamically created based on load, then system efficiency is improved, but additional reliability gains require more instances which increases costs
Solution Approach 1:
The system dynamically adapts the number and distribution of process instances based on the service area size and expected processing load. Geographic segments are dynamically assigned to process instances, allowing the system to scale processing capacity according to实际需求 while maintaining cost efficiency by only creating instances when needed.
Data Source
AI summary
A method for creating an environment model for a service area, wherein within the service area, a service for the infrastructure-based support of an at least partially automated networked motor vehicle is provided. The method includes: dividing the service area into multiple geographic segments; receiving sensor data, which are attributed with geographic coordinates, and assigning the sensor data to at least one geographic segment as a function of the geographic coordinates; assigning a geographic segment to a selected process instance; computing a respective partial environment model for each geographic segment by the process instance assigned to the geographic segment on the basis of the received sensor data (fusion of the sensor data).