Vehicle Localization Fusion for Map-Based High-Accuracy Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining a vehicle's position are plagued by uncertainty, which can compromise the safety and reliability of automated vehicle operations, especially in varying environmental conditions.
Innovation Solution
A method that combines multiple localization techniques to establish an initial position with reduced uncertainty, followed by the use of a highly accurate map for comparison with sensed environmental data to determine the vehicle's precise location, utilizing a system that includes sensors like video, radar, lidar, and ultrasonic sensors, and a computing unit for data processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple localization methods are performed to determine initial position with reduced uncertainty, then reliability of vehicle position determination is improved, but computational effort and processing time increase
Solution Approach 1:
The patent applies preliminary action by performing multiple localization methods (GNSS, GSM, WLAN, map-based) to determine an initial position with reduced uncertainty before proceeding to the computationally intensive comparison of environmental data values with map data. This preliminary positioning reduces the search space and computational burden for subsequent high-precision localization, achieving reliable position determination while managing computational effort.
2Measurement precision
If multiple localization methods are used to reduce uncertainty to about 10 centimeters, then measurement precision of vehicle position is improved, but device complexity increases
Solution Approach 1:
The patent merges multiple localization methods (GNSS, GSM, WLAN, map-based localization) into a unified positioning system. Each method contributes its strengths to achieve an initial position with reduced uncertainty, which is then refined through comparison with environmental sensor data and map information. This combination achieves high measurement precision (about 10 centimeters) while distributing the complexity across multiple complementary techniques rather than relying on a single complex system.
3Measurement precision
If environmental data values are compared to a detailed map for high accuracy positioning, then position accuracy is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary localization using multiple methods to establish an initial position with reduced uncertainty before conducting the detailed comparison of environmental data values with map information. This preliminary step constrains the search space and allows the subsequent high-precision comparison to focus on a limited area, thereby reducing processing time while maintaining high position accuracy.
4Reliability
If maximum uncertainty is reduced to ensure safe automated operation, then safety of automated vehicle is improved, but system complexity increases
Solution Approach 1:
The patent combines multiple localization methods and sensor systems (video, radar, lidar, ultrasonic sensors) to achieve maximum uncertainty reduction for safe automated operation. By merging these complementary systems, the patent ensures high reliability and safety for automated vehicles while distributing the complexity across multiple independent but coordinated subsystems, making the overall system more robust and manageable.
Data Source
AI summary
A method and a first apparatus for determining a highly accurate position of a vehicle. In the method, several localization methods for determining an initial position are performed, wherein each localization method is designed to determine a position of the vehicle with a particular uncertainty, depending on the respective localization method. A comparison of the respectively determined positions with their uncertainties is performed and the initial position is determined depending thereon. Starting from the initial position, a map is subsequently provided, which at least partially represents an environment of the vehicle. Environmental data values are sensed by means of an environmental sensor system of the vehicle. The highly accurate position of the vehicle is determined by a comparison of the sensed environmental data values to the map.