System and method for detecting and addressing errors in a vehicle localization
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.
1. A method for addressing an error in a localization system, the method comprising:
monitoring a plurality of sensors of a driver assistance system in real-time, each sensor generating a data stream;
identifying a sensor of the plurality of sensors having an anomalous data stream;
calculating a primary localization from the respective data streams, including the anomalous data stream, from the plurality of sensors;
calculating a backup localization from a subset of the respective data streams that does not include the anomalous data stream;
determining an error estimate based on a difference between the primary localization and the backup localization; and
executing an action when the error estimate of the backup localization exceeds a threshold.
2. The method of claim 1 , wherein the step of identifying the sensor having the anomalous data stream includes using at least one of an ensemble voting scheme or a recurrent neural network.
3. The method of claim 1 , wherein the action includes removing the anomalous data stream of the sensor so that it is not used by the driver assistance system.
4. The method of claim 1 , wherein the action includes displaying a notification when the anomalous data stream is detected.
5. The method of claim 1 , wherein at least one sensor of the plurality of sensors is located on a vehicle.
6. The method of claim 1 , further comprising:
tracking the anomalous data stream of the sensor; and
adding the anomalous data stream of each of the sensors for use by the driver assistance system when the anomalous data stream is below the threshold.
7. The method of claim 1 , wherein determining the difference between the primary localization and the backup localization includes retrieving primary localization data from a lookup table.
8. The method of claim 1 , wherein the step of calculating the backup localization is based on a subset of the plurality of sensors without the sensor having the anomalous data stream.
9. The method of claim 1 , wherein calculating the primary localization is based on data from the anomalous data stream of the sensor, wherein the data is retrieved prior to detection of the anomalous data stream.
10. A driver assistance system comprising:
a plurality of sensors, each sensor generating a data stream; and
a processor that executes instructions stored in memory, wherein execution of the instructions by the processor:
monitors a plurality of sensors of the driver assistance system in real-time, each sensor generating a data stream;
identifies a sensor of the plurality of sensors having an anomalous data stream;
calculates a primary localization from the respective data streams, including the anomalous data stream, from the plurality of sensors, the primary localization calculation including the anomalous data stream;
calculates a backup localization calculation from a subset of the respective data streams not including the anomalous data stream;
determines an error estimate based on a difference between the primary localization and the backup localization; and
executes an action when the error estimate of the backup localization exceeds a threshold.
11. The system of claim 10 , wherein the processor identifies the sensor having an anomalous data stream includes using at least one of an ensemble voting scheme or a recurrent neural network.
12. The system of claim 10 , wherein the action includes removing the anomalous data stream of the sensor from use by the driver assistance system.
13. The system of claim 10 , wherein the action includes displaying a notification when the anomalous data stream is detected.
14. The system of claim 10 , wherein at least one sensor of the plurality of sensors is located on a vehicle.
15. The system of claim 10 , wherein execution of instructions by the processor:
tracks the anomalous data stream of the sensor; and
adds the anomalous data stream of each of the sensors for use by the driver assistance system when the anomalous data stream is below the threshold.
16. The system of claim 10 , wherein execution of the instructions by the processor to determine a difference between the primary localization and the backup localization includes further execution of the instructions by the processor to retrieve backup localization data from a lookup table.
17. The system of claim 10 , wherein calculating the backup localization is based on a subset of the plurality of sensors without the sensor having the anomalous data stream.
18. The system of claim 10 , wherein calculating the primary localization is based on data from the anomalous data stream of the sensor, wherein the data is retrieved prior to detection of the anomalous data stream.