Radar Route Clearance Classification for Long-Range Drivability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle sensors, particularly radar sensors, struggle to reliably determine the drivability of a route section in front of the vehicle due to signal distortions and multiple reflections, especially at long ranges, which affects autonomous and automated driving safety and accuracy.
Innovation Solution
A method using radar measurements to generate multiple sets of data, calculate a feature vector, and classify it with a trained classifier to determine drivability, combining raw data analysis with statistical significance to enhance accuracy and reliability, especially at long ranges, and validate with short-range measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Length of stationary object
If radar sensors are used to determine drivability at long range, then the detection range is extended, but the measurement precision deteriorates due to signal distortions and multiple reflections
Solution Approach 1:
The patent segments the measurement process into multiple stages: acquiring multiple radar measurements at different distances, identifying short-range measurements with high precision, and using these to validate or correct long-range measurements. This segmentation allows the system to leverage the high accuracy of short-range data while maintaining the extended detection capability of long-range radar.
Solution Approach 2:
The patent introduces an intermediary validation mechanism where short-range radar measurements act as a reference or mediator to assess the reliability of long-range measurements. By comparing long-range data against the more reliable short-range data, the system can filter out distorted measurements and improve overall measurement precision at long ranges.
2Measurement precision
If additional sensors or sensor types are used to improve measurement reliability, then the measurement precision improves, but the device complexity and cost increase
Solution Approach 1:
The patent makes the existing radar sensor multi-functional by using it for both long-range detection and short-range validation. Instead of adding separate sensors, the system utilizes the radar's capability across different distance ranges, with short-range measurements serving dual purposes of direct drivability assessment and reliability validation of long-range measurements.
Solution Approach 2:
The radar system performs self-validation by using its own short-range measurements to verify the accuracy of its long-range measurements. The system automatically identifies reliable measurements and uses them to correct or validate less reliable ones, eliminating the need for external validation sensors or complex additional hardware.
3Measurement precision
If multiple sets of measurement data are processed to improve reliability, then the measurement precision improves, but the loss of time increases due to additional processing
Solution Approach 1:
The patent applies partial processing by selectively validating only the critical measurements rather than processing all data equally. The system identifies and processes only those measurements that are necessary for drivability determination, using short-range data to validate long-range data when needed, rather than uniformly processing all measurement sets.
Solution Approach 2:
The system performs preliminary identification and classification of measurement reliability before full processing. By pre-identifying short-range measurements as high-reliability references, the system can quickly validate long-range measurements without extensive processing, reducing overall computation time while maintaining precision.
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
Enhances the reliability and accuracy of drivability determination, reducing reliance on costly additional sensors and minimizing installation space, while improving safety and efficiency in autonomous driving.
Implementation Method 1
Vehicles are known to have sensors, for example radar sensors, LIDAR, cameras and/or ultrasonic sensors, to detect static objects (and/or moving objects)
Implementation Method 2
Height determination and/or height measurement can be carried out along a vertical line
Data Source
AI summary
The present invention relates to a method for determining the drivability of a route section by a vehicle. The route section includes at least one object with an actual height, such as a roadway boundary, a tunnel ceiling or a bridge. The actual height of the object extends at least in sections along a vertical, the object is located at least in sections in front of the vehicle in the direction of travel.