Sensor Data Reliability Verification via Database Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for autonomous vehicle control rely on sensor data processing, but lack a method to assess the reliability of object recognition, which is crucial for ensuring driving safety, especially in conditions like rain, fog, or sensor malfunctions.
Innovation Solution
A method and apparatus that compare sensor-generated object data with quality-assured scene data from a database to assess the reliability of sensor detection, data processing, and object recognition, using features like feature vectors and a degree of conformity to determine the reliability level, allowing for safe vehicle control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If sensor data processing is used for autonomous vehicle control, then automation extent is improved, but reliability of object recognition deteriorates due to lack of verification method
Solution Approach 1:
The patent implements feedback by comparing sensor-generated object data with database-stored reference data, and using the comparison results to assess and verify the reliability of object recognition in real-time, creating a closed-loop verification system
Solution Approach 2:
The patent applies preliminary action by pre-storing quality-assured reference data about objects in the database before vehicle operation, enabling subsequent reliability assessment without requiring additional external verification resources during autonomous driving
2Productivity
If sensor detection is performed in adverse conditions like rain or fog, then detection capability is maintained, but measurement precision deteriorates
Solution Approach 1:
The patent applies beforehand cushioning by pre-storing accurate reference object data in the database that serves as a truth benchmark, which cushions against measurement precision deterioration in adverse conditions by providing a reliable comparison standard for verification
3Productivity
If more sensor data is processed to improve object recognition, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent introduces an intermediary verification mechanism using pre-stored reference data in the database as a mediator between sensor data processing and reliability assessment, simplifying the verification process by providing expected outcomes for comparison rather than requiring complex analytical verification
Data Source
AI summary
A method and a device for processing sensor data in a vehicle, and a vehicle. A scene from the surroundings of the vehicle is detected by sensors, and corresponding sensor data are generated. Objects in the scene are recognized as a result of processing the sensor data, and corresponding object data are generated which characterize the recognized objects. In order to be able to reliably assess the reliability of the scene recognition by sensors, the processing of the sensor data, the object recognition and/or the database, the generated object data are compared with quality-assured scene data which are stored in a database and which characterize objects in the scene.