Sensor Data Ambiguity Resolution via Reference Object Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current environmental sensors, such as radar and LIDAR sensors, often produce erroneous results like false positives and false negatives when detecting dynamic and static objects, which can lead to unsafe automated driving responses due to ambiguities and ghost targets.
Innovation Solution
A method using a control device to receive data from multiple sensors, forming object hypotheses and using a reference object from a second sensor to eliminate ambiguities by rejecting incorrect hypotheses, thereby reducing false-positive and false-negative rates and ensuring accurate object detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If environmental sensors (radar, LIDAR) are used for object detection in automated driving, then detection capability is improved, but sensor errors such as false positives and false negatives occur due to ambiguities and ghost targets
Solution Approach 1:
The patent introduces a reference object detected by a second sensor as an intermediary to resolve ambiguities in angle measurements from the first sensor. The reference object serves as a mediator that helps identify the correct object hypothesis among multiple ambiguous possibilities by comparing detection results across different sensors, thereby improving measurement precision without sacrificing detection reliability
Solution Approach 2:
The system implements feedback by comparing object hypotheses from the first sensor with reference object data from the second sensor. This feedback mechanism allows the system to validate or reject object hypotheses based on consistency across sensors, reducing false positives and false negatives while maintaining reliable detection capability
2Reliability
If multiple object hypotheses are formed from sensor measurement data, then detection completeness is improved, but false-positive results increase due to ambiguities
Solution Approach 1:
The reference object from the second sensor acts as an intermediary validation mechanism. By comparing object hypotheses against reference object data, the system can identify which hypotheses correspond to actual objects and which are false positives, thereby maintaining detection completeness while reducing harmful false-positive results
Solution Approach 2:
The patent converts the potentially harmful effect of multiple ambiguous object hypotheses into a benefit by using the second sensor as a discriminator. The ambiguities generated by the first sensor are resolved through comparison with the second sensor's reference object data, transforming the problem of multiple hypotheses into an opportunity for cross-validation and error reduction
Data Source
AI summary
A method for eliminating sensor errors, in particular ambiguities when detecting dynamic objects, by a control device, is provide. Measurement data are received from at least one first sensor and object hypotheses are formed from the received measurement data. Data of at least one reference object, which is detected based on measurement data from at least one second sensor, are received. The formed object hypotheses are compared with the at least one detected reference object. Object hypotheses that do not match the detected reference object are rejected. A method for eliminating sensor errors, in particular ambiguities when detecting static objects is also provided.