Vehicle Positioning via Ground Feature Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for determining a vehicle's position, such as GPS and mobile phone networks, provide insufficient accuracy for highly automated driving functions, which require more precise location data.
Innovation Solution
A method and system that record and process sensor data, including camera images, to extract ground characteristics and determine the vehicle's position using a characteristic map, achieving positional accuracy of up to less than 10 cm by comparing extracted features with a global map.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional GPS and mobile phone network methods are used for position determination, then the system complexity remains low and ease of operation is maintained, but the measurement precision of vehicle position is insufficient (only 5-50m accuracy)
Solution Approach 1:
The patent combines multiple positioning techniques (GPS, mobile phone networks, and image recognition-based visual odometry) into a unified hybrid positioning system. The GPS receiver, mobile communication unit, and camera system work together, with each component contributing to the overall position determination, thereby achieving high precision (less than 10 cm) while distributing system complexity across multiple subsystems
Solution Approach 2:
The patent introduces an image processing system as an intermediary between the vehicle and the positioning infrastructure. By capturing images of ground characteristics and comparing them with pre-stored map data, the system creates an intermediate reference framework that enables precise position determination without requiring direct dependence on any single positioning infrastructure
2Measurement precision
If GPS and mobile phone networks are used for position determination, then the ease of operation is maintained, but the position accuracy deteriorates to only 5-50m resolution which is insufficient for highly automated driving
Solution Approach 1:
The patent segments the positioning task into multiple independent components: GPS provides coarse position, mobile phone networks provide cellular tower triangulation, and the image recognition system provides fine-positioning through ground characteristic matching. Each segment operates independently and contributes to the final integrated position, maintaining operational simplicity while achieving high precision
Data Source
AI summary
A method and a device for determining the position of a vehicle, said method comprising the steps: recording sensor data from the ground over which the vehicle travels; extracting ground characteristics of the ground over which the vehicle travels from the recorded sensor data or from occupancy grids which are calculated on the basis of the sensor data; determining the current position of the vehicle on the basis of the extracted ground characteristics using a characteristic map.