In-vehicle traffic assist
A system, comprising a processor and a memory, the memory including instructions to be executed by the processor to pilot a vehicle based on determining first and second lane markers, where lane markers are mathematical descriptions of roadway lane markers applied to a roadway to mark traffic lanes, determine a missing first or second lane marker, and pilot the vehicle for a determined period of time based on a remaining first or second lane marker.
1. A method, comprising:
controlling a vehicle according to a steerable path polynomial that extends for a distance D 1 from a current point P 0 of the vehicle on a roadway to a point P 1 on the roadway, and that is determined based on determining first and second lane markers;
determining that one of the first or second lane markers has become a missing lane marker;
determining, based on the steerable path polynomial, vehicle acceleration data, and a steerable path polynomial confidence exceeding a threshold when the steerable path polynomial is extended for a distance D 2 , an extension to the steerable path polynomial for the distance D 2 from the point P 1 to a point P 2 on the roadway, wherein the distance D 2 extends past at least a part of the missing lane marker; and
controlling the vehicle based on the steerable path polynomial extension, wherein the steerable path polynomial confidence is based on a remaining first or second lane marker and a probability of accuracy of a lane model that includes the steerable path polynomial extension.
2. The method of claim 1 , further comprising determining that the missing lane marker is missing because of a roadway entrance or exit ramp.
3. The method of claim 1 , wherein determining the first and second lane markers includes processing one or more acquired images with Hough transforms to determine lane marker confidence.
4. The method of claim 3 , further comprising determining the steerable path polynomial confidence based on the lane marker confidence, determining a position of the vehicle with respect to the steerable path polynomial, determining the steerable path polynomial curvature, and determining inertial navigation data.
5. The method of claim 4 , further comprising determining the steerable path polynomial confidence based on determining the position of the vehicle with respect to the steerable path polynomial, determining the inertial navigation data, and determining the steerable path polynomial curvature.
6. The method of claim 5 , wherein the position of the vehicle is determined based on the inertial navigation data.
7. The method of claim 6 , wherein determining the steerable path polynomial curvature is based on the remaining first or second lane marker, the position of the vehicle and the inertial navigation data.
8. The method of claim 7 , wherein the distance D 2 is based on the steerable path polynomial curvature and the lane marker confidence.
9. The method of claim 8 , further comprising determining the distance D 2 based on the steerable path polynomial and vehicle speed or a predetermined time.
10. The method of claim 9 , wherein the vehicle speed is based on the inertial navigation data.
11. A system, comprising a processor; and
a memory, the memory including instructions to be executed by the processor to:
control a vehicle according to a steerable path polynomial that extends for a distance D 1 from a current point P 0 of the vehicle on a roadway to a point P 1 on the roadway, and that is determined based on determining first and second lane markers;
determine that one of the first or second lane markers has become a missing lane marker;
determine, based on the steerable path polynomial, vehicle acceleration data, and a steerable path polynomial confidence exceeding a threshold when the path polynomial is extended for a distance D 2 , an extension to the steerable path polynomial for the distance D 2 from the point P 1 to a point P 2 on the roadway, wherein the distance D 2 extends past at least a part of the missing lane marker; and
control the vehicle based on the path polynomial extension, wherein the steerable path polynomial confidence is based on a remaining first or second lane marker and a probability of accuracy of a lane model that includes the steerable path polynomial extension.
12. The system of claim 11 , further programmed to determine the missing lane marker is missing because of a roadway entrance or exit ramp.
13. The system of claim 11 , further programmed to determine the first or second lane markers by processing one or more acquired images with Hough transforms to determine lane marker confidence.
14. The system of claim 13 , further programmed to determine the steerable path polynomial confidence based on the lane marker confidence, determining a position of the vehicle with respect to the steerable path polynomial, determining the steerable path polynomial curvature, and determining inertial navigation data.
15. The system of claim 14 , further programmed to determine the steerable path polynomial confidence based on determining the position of the vehicle with respect to the steerable path polynomial, determining the inertial navigation data, and determining the steerable path polynomial curvature.
16. The system of claim 15 , further programmed to determine the position of the vehicle based on the inertial navigation data.
17. The system of claim 16 , further programmed to determine the steerable path polynomial curvature is based on the remaining first or second lane marker, the position of the vehicle and the inertial navigation data.
18. The system of claim 17 , further programmed to determine the distance D 2 is based on the steerable path polynomial curvature and the lane marker confidence.
19. The system of claim 18 , further programmed to determine the distance D 2 based on the steerable path polynomial and vehicle speed or a predetermined time.
20. The system of claim 19 , further programmed to determine the vehicle speed based on the inertial navigation data.