Ultrasonic Sensor Object Identification via Second Echo Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driver assistance systems using ultrasonic sensors for identifying objects around a vehicle are not reliable in distinguishing between different objects, such as parked vehicles and kerbs, due to the complexity of echo signals and varying distances.
Innovation Solution
A method that involves clustering features from successive measurement cycles based on position values and the presence of second echoes within a predetermined time frame, allowing for accurate identification and classification of objects by determining the presence of second echoes in a window of features, and associating these with specific objects based on their geometric arrangement and minimum dimensions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If ultrasonic sensors are used to transmit signals and evaluate echo signals for object identification, then object detection capability is provided, but reliability in distinguishing between different objects (such as parked vehicles and kerbs) deteriorates due to complexity of echo signals and varying distances
Solution Approach 1:
The patent segments the echo signal evaluation into multiple distinct features: position value from first echo, presence of second echo within predetermined time period, and clustering of features from successive measurement cycles. This segmentation transforms the complex echo signal analysis into manageable discrete features that can be reliably evaluated independently and combined for object identification.
Solution Approach 2:
The patent introduces temporal dimension by performing multiple measurement cycles at successive times and clustering features based on their consistency across time. Additionally, it uses the time interval between first and second echoes as an additional dimension for differentiation, enabling reliable distinction between object types (parked vehicles vs. kerbs) that cannot be distinguished by position alone.
2Measurement precision
If multiple measurement cycles are performed at successive times with ultrasonic signals, then measurement data quantity increases, but processing complexity and time consumption increase
Solution Approach 1:
The patent extracts only the essential features from each measurement cycle: position value from first echo and presence of second echo. By extracting only these critical features rather than processing all raw signal data, the system achieves accurate object identification while minimizing processing time and computational resources required for each measurement cycle.
Solution Approach 2:
The patent merges multiple measurement cycles by clustering features from successive measurements. This combining approach allows the system to accumulate precision from multiple measurements while processing them efficiently as grouped clusters, reducing overall processing time compared to evaluating each measurement cycle independently.
3Reliability
If features are clustered based on position values and second echo presence, then object identification accuracy improves, but system complexity increases
Solution Approach 1:
The patent applies different evaluation criteria to different features: position value is used for spatial clustering, while second echo presence is used for temporal/functional clustering. This local quality approach assigns specific processing rules to specific feature types, improving object classification accuracy while maintaining systematic and manageable processing complexity through feature-specific handling.
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 enhances the reliability of object identification by accurately distinguishing between different objects, improving the accuracy of parking maneuvers and reducing errors in determining the presence and type of objects around the vehicle.
Implementation Method 1
Each measurement cycle involves an ultrasonic sensor of the motor vehicle being used to transmit an ultrasonic signal. In addition, on the basis of a first received echo of the ultrasonic signal, a position value is ascertained that describes a position of the at least one object
Data Source
AI summary
The invention relates to a method for identifying at least one object (9, 10) in a surrounding area (7) of a motor vehicle (1), in which the motor vehicle (1) is moved relative to at least one object (9, 10) and, while the motor vehicle (1) is moved relative to the at least one object (9, 10), a measurement cycle is performed at each of a plurality of successive times, wherein each measurement cycle involves an ultrasonic sensor (4) of the motor vehicle (1) being used to transmit an ultrasonic signal, and a feature (14) being determined that describes a position value, which describes a position of the at least one object (9, 10) and which is ascertained on the basis of a first received echo of the ultrasonic signal, and a presence of a second echo of the ultrasonic signal that is received within a predetermined period of time after the first echo, wherein the respective features (14) are associated with a cluster (13) on the basis of their position value, and the features (14) of the cluster (13) are signalled as belonging to the at least one object (9, 10) on the basis of the presence of the second echo.