Autonomous Vehicle Sensor Cross-Validation for Fault Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges with sensor failures or inaccurate readings, which compromise their ability to navigate environments confidently and precisely.
Innovation Solution
The system employs cross-validation of sensors by using a reference sensor to evaluate the accuracy of a second sensor by comparing object parameter values or object labels from both sensors, determining deviation values, and applying thresholds to identify and address sensor issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple sensors are used to detect objects in the driving environment, then the reliability of object detection is improved, but the device complexity increases
Solution Approach 1:
The system implements cross-validation by comparing object parameter values from multiple sensors against each other and against stored map information. This feedback mechanism allows the system to identify and correct sensor errors by detecting deviations beyond acceptable thresholds, thereby improving detection reliability while managing the complexity of having multiple sensors through systematic comparison and validation protocols
Solution Approach 2:
The patent introduces map information as an intermediary reference that mediates between multiple sensor readings. By comparing sensor data against the stored electronic representation of the environment, the system can validate sensor accuracy and identify failures without requiring direct comparison between all sensor pairs, thus managing complexity while maintaining reliability
2Measurement precision
If sensor data is cross-validated against map information, then measurement precision is improved, but the loss of time increases due to additional processing
Solution Approach 1:
The system performs preliminary actions by storing detailed map information about the driving environment in advance. This pre-stored reference data enables rapid validation of sensor readings during operation, as the system only needs to compare current sensor data against the pre-existing map rather than performing complex real-time analysis, thus improving precision while minimizing time loss
3Reliability
If deviation thresholds are applied to identify sensor problems, then the reliability of sensor monitoring is improved, but the device complexity increases due to additional processing requirements
Solution Approach 1:
The system employs parameter changes by establishing deviation thresholds that define acceptable ranges for object parameter values. When sensor readings deviate beyond these thresholds, the system identifies potential sensor failures. This approach improves reliability by providing clear criteria for fault detection while managing processing complexity through standardized threshold-based comparison rather than requiring complex diagnostic algorithms
Data Source
AI summary
Methods and systems are disclosed for cross-validating a second sensor with a first sensor. Cross-validating the second sensor may include obtaining sensor readings from the first sensor and comparing the sensor readings from the first sensor with sensor readings obtained from the second sensor. In particular, the comparison of the sensor readings may include comparing state information about a vehicle detected by the first sensor and the second sensor. In addition, comparing the sensor readings may include obtaining a first image from the first sensor, obtaining a second image from the second sensor, and then comparing various characteristics of the images. One characteristic that may be compared are object labels applied to the vehicle detected by the first and second sensor. The first and second sensors may be different types of sensors.