Infrastructure Sensor Localization via Vehicle Data Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for determining the location of infrastructure sensors on a map require specific hardware, such as GPS systems, and struggle to fuse data from various sources for autonomous and semiautonomous vehicle operations effectively.
Innovation Solution
A system that uses a computer with executable instructions to identify the location and orientation of a vehicle on a map, determining the infrastructure sensor's location based on vehicle and infrastructure sensor data, including point-cloud data, without requiring specific hardware like GPS, and enables data fusion for navigation and control in autonomous and semiautonomous modes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS hardware is used to determine infrastructure sensor location, then location accuracy is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces GPS hardware-based location determination with a computational method that uses sensor data fusion and coordinate transformations. Instead of relying on dedicated positioning hardware, the system uses existing sensor data (IMU, camera, radar) combined with map data to calculate infrastructure sensor locations through mathematical transformations between coordinate systems.
Solution Approach 2:
The patent introduces map data and coordinate transformation algorithms as intermediaries to bridge the gap between vehicle sensor data and infrastructure sensor location determination. The map serves as a reference framework, and coordinate transformations act as mathematical mediators to convert sensor measurements into accurate location information without requiring direct GPS hardware at the infrastructure sensor.
2Reliability
If multiple data sources are fused for location determination, then reliability is improved, but computational complexity increases
Solution Approach 1:
The patent segments the data fusion process into distinct coordinate transformation steps: first transforming vehicle sensor data into vehicle coordinate system, then transforming to map coordinate system using map data. This segmentation allows each transformation to be handled independently with appropriate algorithms, reducing overall computational complexity while maintaining reliability through systematic multi-source data integration.
Data Source
AI summary
A system includes a computer including a processor and a memory storing instructions executable by the processor to identify a location and an orientation of a vehicle on a map. The instructions include instructions to determine a location of an infrastructure sensor on the map based on the location and the orientation of the vehicle, data from a vehicle sensor, and data from the infrastructure sensor.