Vehicle Localization Backup Logic for Sensor Spoofing Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advanced Driver Assistance Systems (ADAS) in vehicles are vulnerable to spoofing attacks, which can compromise the accuracy of sensor data streams, posing risks to vehicle safety and user security.
Innovation Solution
A method that monitors sensor data streams in real-time, identifies anomalous data, calculates primary and backup localizations, and executes actions when error estimates exceed thresholds, including removing anomalous data streams and providing user notifications to ensure safe vehicle recovery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system uses multiple sensors for localization, then the reliability of localization is improved, but the complexity of detecting and measuring anomalies increases
Solution Approach 1:
The system segments the localization task by calculating multiple independent localization estimates using different sensor subsets. Each sensor or sensor combination produces a separate localization estimate, allowing the system to compare results and identify anomalies without requiring complex analysis of individual sensor data streams.
Solution Approach 2:
The system implements feedback by continuously comparing primary and backup localization estimates and using the discrepancy to detect anomalies. When the difference between localization estimates exceeds a threshold, the system triggers anomaly detection and takes corrective actions, creating a closed-loop feedback mechanism that improves reliability.
2Measurement precision
If the system calculates multiple localization estimates, then the measurement precision of localization is improved, but the device complexity increases
Solution Approach 1:
The system divides the localization computation into separate primary and backup estimates calculated independently using different sensor combinations. This segmentation allows for precise measurement through comparison while keeping each individual calculation relatively simple and manageable.
Solution Approach 2:
The system changes parameters by using different sensor subsets for primary versus backup localization calculations. By varying which sensors are included in each calculation, the system achieves multiple precise estimates without requiring a completely complex system architecture.
3Reliability
If the system removes anomalous data streams, then the reliability of the driver assistance system is improved, but the loss of information increases
Solution Approach 1:
The system extracts and removes only the identified anomalous data streams from the sensor input, rather than discarding entire sensors or data streams. This selective extraction maintains reliability by eliminating harmful data while preserving useful information from the same sensor source when possible.
Solution Approach 2:
The system temporarily discards anomalous data streams when reliability is compromised but recovers them when they return to normal operation. This approach minimizes information loss while maintaining system reliability during anomaly periods, allowing the system to reuse valid data streams when they become reliable again.
Data Source
AI summary
The present disclosure relates to a system and a method for addressing an error in a localization system that includes monitoring a plurality of sensors of a driver assistance system in real-time, with each sensor generating a data stream. The method further includes identifying a sensor having an anomalous data stream and calculating a primary localization and a backup localization. The primary localization calculation includes the anomalous data stream and the backup localization calculation does not include the anomalous data stream. Further, the method includes executing an action when the backup localization error estimate exceeds a threshold.