Minimizing false collision avoidance warnings
A route learning system for a vehicle and a method of using the system is described. The method includes: in response to determining that a current location matches a historical location, retrieving from memory false alert geotag that includes historical path data; and based on determining that a currently-predicted path does not match the historical path, replacing the currently-predicted path with the historical path to mitigate a false warning to a driver of a host vehicle.
1. A method, comprising:
in response to determining that a current location matches a historical location, retrieving from memory false alert geotag that includes historical path data; and
based on determining that a currently-predicted path does not match the historical path, replacing the currently-predicted path with the historical path to mitigate a false warning to a driver of a host vehicle.
2. The method of claim 1 , wherein the geotag was stored previously in memory in response to:
receiving a collision avoidance alert; and
determining that an actual path of the vehicle, after receiving the alert, differed from a predicted path at a time thereof.
3. The method of claim 2 , wherein the alert is based at least partially on receiving a vehicle-to-vehicle communication from a target vehicle.
4. The method of claim 2 , wherein the actual path is determined using a plurality of path points.
5. The method of claim 4 , wherein each of the path points comprise a respective pair of x- and y-coordinates, wherein, in determining the actual path, a respective z-axis coordinate of each respective path point is ignored.
6. The method of claim 2 , further comprising: storing a first path point, then storing a second path point following a first interval, and then storing a third path point following a second interval.
7. The method of claim 1 , wherein determining that the currently-predicted path does not match the historical path further comprises comparing a predicted radius or predicted curvature of the currently-predicted path with a historical radius of the historical path or a corresponding historical curvature thereof.
8. The method of claim 7 , wherein determining that the currently-predicted path does not match the historical path further comprises comparing a predicted radius or predicted curvature of the currently-predicted path with a historical radius of the historical path or a corresponding historical curvature thereof.
9. The method of claim 1 , further comprising determining a range to a nearest starting point location from among a plurality of false alert geotags, and based on the determined range, delaying comparing current location with historical location data of the plurality.
10. The method of claim 1 , further comprising: replacing the currently-predicted path at a false alert detection system; and sending the replaced currently-predicted path from the false alert detection system to a collision avoidance system which generated an alert.
11. A system, comprising:
a processor; and
memory storing instructions executable by the processor, the instructions comprising, to:
in response to determining that a current location matches a historical location, retrieve from memory false alert geotag that includes historical path data; and
based on determining that a currently-predicted path does not match the historical path, replace the currently-predicted path with the historical path to mitigate a false warning to a driver of a host vehicle.
12. The system of claim 11 , wherein the geotag was stored previously in memory in response to instructions to:
receive a collision avoidance alert; and
determine that an actual path of the vehicle, after receiving the alert, differed from a predicted path at a time thereof.
13. The system of claim 12 , wherein the alert is based at least partially on receiving a vehicle-to-vehicle communication from a target vehicle.
14. The system of claim 12 , wherein the actual path is determined using a plurality of path points.
15. The system of claim 14 , wherein each of the path points comprise a respective pair of x- and y-coordinates, wherein, in determining the actual path, a respective z-axis coordinate of each respective path point is ignored.
16. The system of claim 12 , wherein the instructions further comprise, to: store a first path point, then store a second path point following a first interval, and then store a third path point following a second interval.
17. The system of claim 11 , wherein the instruction to determine that the currently-predicted path does not match the historical path further comprises an instruction to compare a predicted radius or predicted curvature of the currently-predicted path with a historical radius of the historical path or a corresponding historical curvature thereof.
18. The system of claim 17 , wherein the instruction to determine that the currently-predicted path does not match the historical path comprises an instruction to compare a predicted center of a circle that comprises the predicted radius or predicted curvature with a historical center location of a circle associated with the historical radius or a corresponding historical curvature thereof.
19. The system of claim 11 , further comprising determining a range to a nearest starting point location from among a plurality of false alert geotags, and based on the determined range, delaying comparing current location with historical location data of the plurality.
20. The system of claim 11 , wherein the instructions further comprise, to: replace the currently-predicted path at a false alert detection system; and send the replaced currently-predicted path from the false alert detection system to a collision avoidance system which generated an alert.