Vehicle Radar Positioning Using Map-Matched Sensor Samples
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle positioning and motion determination methods, such as GPS, radar, and LiDAR, face challenges in accuracy and reliability, particularly in environments with weak or no satellite signals, and require significant processing resources for radar data analysis.
Innovation Solution
A method that directly matches radar sensor data samples with a transformed map of static landmarks using influence parameters to control the matching process, reducing processing effort while maintaining accuracy by utilizing ground-truth data and avoiding the creation of full spatial representations like point clouds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If GPS is used for vehicle positioning, then position data can be determined with fair degree of accuracy, but the method fails in environments with weak or no satellite signals such as tunnels and enclosed areas
Solution Approach 1:
The patent segments the positioning problem into two parts: using GPS when available and using radar-based matching when GPS is unavailable. The system divides the operating environments into GPS-available zones and GPS-denied zones, applying different positioning methods appropriately to ensure continuous reliable positioning.
Solution Approach 2:
The patent introduces radar scans and map data as an intermediary positioning method between GPS and dead reckoning. When GPS signals are unavailable, the system uses radar to capture environmental features and matches them against pre-stored map data to determine position, serving as a bridge that maintains positioning reliability without continuous GPS dependency.
2Reliability
If radar sensors are used for position determination, then positioning can work without GPS signals, but significant processing resources are required for analyzing raw sensor data
Solution Approach 1:
The patent applies preliminary action by pre-processing and storing map data in advance. The offline map data is prepared beforehand with extracted geometric features and stored in a database. During runtime, the system only needs to perform matching operations rather than full data processing, significantly reducing computational resources and energy consumption while maintaining reliable positioning.
Solution Approach 2:
The patent extracts only the essential geometric features from raw radar data and map data for matching purposes. Instead of processing complete point clouds or raw sensor data, the system extracts key geometric characteristics such as distances, angles, and relative positions of detected objects, reducing the data volume and processing requirements while preserving positioning accuracy.
3Loss of information
If full spatial representations like point clouds are created from sensor data, then comprehensive environmental information is obtained, but computational overhead increases significantly
Solution Approach 1:
The patent extracts only the necessary geometric information from sensor data for positioning purposes. Instead of creating and processing complete point clouds, the system extracts key features such as distances to detected objects, angular positions, and relative geometries. This selective extraction maintains sufficient environmental information for accurate positioning while dramatically reducing computational complexity and memory requirements.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach allows for precise and reliable determination of vehicle position and motion data with reduced computational overhead, even in challenging environments, using simplified sensor data representations and influence parameters to enhance accuracy.
Implementation Method 1
the radar system includes at least one radar sensor adapted to receive radar signals emitted from at least one radar emitter of the radar system and reflected in a vicinity of the vehicle towards the radar sensor
Implementation Method 2
The raw sensor data is usually given as sensor data samples with a radial distance component and a rate of change of the distance (velocity in the radial distance direction). Such sensor data can be denoted as Doppler-sensor data or range-Doppler data delivered by a Doppler sensor
Implementation Method 3
Modern vehicles, for example upper-class cars, are equipped with radar and/or LiDAR (light detection and ranging) systems
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A computer-implemented method for determining a position of a vehicle is disclosed, wherein the vehicle is equipped with a sensor for capturing scans of a vicinity of the vehicle, wherein the method comprises at least the following steps carried out by computer-hardware components: capturing at least one scan by means of the sensor with a plurality of sensor data samples given in a sensor data representation; determining, from a database, a predefined map with at least one element is given in a map data representation; determining a transformed map by transforming the at least one element of the predefined map from the map data representation into the sensor data representation; matching at least a subset of the sensor data samples of the at least one scan and the at least one element of the transformed map; and determining the position of the vehicle based on the matching.