High-Precision Map Generation via Vehicle and Infrastructure Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing maps used for vehicle navigation are often incomplete or outdated, lacking accurate representation of traffic infrastructure and surroundings, which can compromise safety and efficiency, especially for automated vehicles.
Innovation Solution
A method and device that integrate first surroundings data from vehicle sensors and second surroundings data from traffic infrastructure sensors to generate and provide a highly accurate map, ensuring completeness and updates based on predefined criteria, enhancing the accuracy and safety of vehicle operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing maps are used for vehicle navigation, then the navigation system can operate with simple infrastructure, but the map completeness and update accuracy deteriorate
Solution Approach 1:
The patent combines vehicle-mounted sensors (cameras, radar, LIDAR) with traffic infrastructure sensors (roadside cameras, sensors) to create a unified map generation system. This merging allows the system to achieve high map accuracy by integrating multiple data sources while distributing the complexity across different components rather than concentrating it in a single system.
Solution Approach 2:
The map generation device is designed to process and integrate data from multiple types of sensors and multiple vehicles simultaneously. It serves multiple functions: generating maps from individual vehicle data, combining data from multiple vehicles, incorporating infrastructure sensor data, and providing maps to multiple vehicles. This multi-functionality achieves high map accuracy without proportionally increasing system complexity.
2Reliability
If multiple sensor data sources are integrated to improve map accuracy, then the map quality improves, but the data processing complexity increases
Solution Approach 1:
The patent segments the map generation process into distinct modules: receiving data from vehicle sensors, receiving data from infrastructure sensors, processing individual vehicle data, processing combined vehicle data, and integrating infrastructure data. This segmentation allows each module to handle specific tasks independently, improving map reliability through systematic processing while managing complexity through modular architecture.
Solution Approach 2:
The system incorporates feedback mechanisms where the map generation device continuously receives data from multiple vehicles and infrastructure sensors, processes this information, generates updated maps, and provides these maps back to vehicles. This closed-loop feedback ensures map reliability by continuously validating and updating map data against real-time sensor inputs from multiple sources.
Data Source
AI summary
In a method and a device for preparing and providing a highly accurate map, steps are performed which include receiving first surroundings data values that represent first surroundings of at least one vehicle and that are detected using a surroundings sensor system of the at least one vehicle; receiving second surroundings data values that represent second surroundings of at least one traffic infrastructure area and that are detected using at least one traffic infrastructure sensor; generating the highly accurate map based on the first and second surroundings data values, and outputting the highly accurate map.