SYSTEM AND METHOD FOR LANE ASSOCIATION/TRANSITION ASSOCIATION WITH SPLINES

Abstract

A method for vehicle behavior prediction is described. The method includes detecting a vehicle entering an unmarked road segment. The method also includes determining a set of exit paths available for the detected vehicle to reach different exit lanes of the unmarked road segment. The method further includes predicting an exit path taken by the detected vehicle from the set of exit paths available for the detected vehicle to reach the different exit lanes of the unmarked road segment. The method also includes planning a trajectory of an ego vehicle according to the predicted exit path taken by the detected vehicle to reach an exit lane of the unmarked road segment.

Description

Claims

1. A method for vehicle behavior prediction, the method comprising: detecting a vehicle entering an unmarked road segment;determining a set of exit paths available for the detected vehicle to reach different exit lanes of the unmarked road segment;predicting an exit path taken by the detected vehicle from the set of exit paths available for the detected vehicle to reach the different exit lanes of the unmarked road segment; andplanning a trajectory of an ego vehicle according to the predicted exit path taken by the detected vehicle to reach an exit lane of the unmarked road segment.

2. The method of claim 1, in which detecting the vehicle comprises determining a location and a heading of the detected vehicle in response to the detected vehicle reaching an intersection.

3. The method of claim 1, in which determining the set of exit paths comprises: generating a birds-eye-view of the unmarked road segment; andgenerating the set of exit paths based on a determined location and a heading of the detected vehicle relative to the different exit lanes of the unmarked road segment.

4. The method of claim 1, in which predicting the exit path taken by the detected vehicle comprises; determining a curvature of the different exit lanes of the unmarked road segment in relation to a determined location and a heading of the detected vehicle; andinferring the predicted exit path taken by the detected vehicle as the exit lane having the least curvature.

5. The method of claim 1, in which predicting the exit path taken by the detected vehicle comprises: sensing a curvature of upcoming roads corresponding to the different exit lanes of the unmarked road segment; andranking the set of paths available for the detected vehicle to reach the different exit lanes of the unmarked road segment based off of the sensed curvatures of upcoming roads following the different exit lanes.

6. The method of claim 5, in which ranking the set of exit paths comprises: generating splines between intersection exits and a position of the detected vehicle; andusing a curvature of the splines to determine which path the detected vehicle is most likely to take.

7. The method of claim 1, further comprising training a model to predict the exit path taken by the detected vehicle to reach the exit lane of the unmarked road segment based on a curvature of the different exit lanes of the unmarked road segment in relation to the detected vehicle.

8. The method of claim 1, in which detecting comprises: identifying the vehicle entering an intersection; andsensing a curvature of upcoming roads connected to the different exit lanes of the intersection.

9. A non-transitory computer-readable medium having program code recorded thereon for vehicle behavior prediction, the program code being executed by a processor and comprising: program code to detect a vehicle entering an unmarked road segment;program code to determine a set of exit paths available for the detected vehicle to reach different exit lanes of the unmarked road segment;program code to predict an exit path taken by the vehicle from the set of exit paths available for the detected vehicle to reach the different exit lanes of the unmarked road segment; andprogram code to plan a trajectory of an ego vehicle according to the predicted exit path taken by the vehicle to reach a corresponding exit lane of the unmarked road segment.

10. The non-transitory computer-readable medium of claim 9, in which the program code to detect the vehicle comprises program code to determine a location and a heading of the detected vehicle in response to the detected vehicle reaching an intersection.

11. The non-transitory computer-readable medium of claim 9, in which the program code to determine the set of exit paths comprises: program code to generate a birds-eye-view of the unmarked road segment; andprogram code to generate the set of exit paths based on a determined location and a heading of the detected vehicle relative to the different exit lanes of the unmarked road segment.

12. The non-transitory computer-readable medium of claim 9, in which the program code to predict the exit path taken by the detected vehicle comprises; program code to determine a curvature of the different exit lanes of the unmarked road segment in relation to a determined location and a heading of the detected vehicle; andprogram code to infer the predicted exit path taken by the detected vehicle as an exit lane having the least curvature.

13. The non-transitory computer-readable medium of claim 9, in which the program code to predict the exit path taken by the detected vehicle comprises: program code to sense a curvature of upcoming roads corresponding to the different exit lanes of the unmarked road segment; andprogram code to rank the set of paths available for the detected vehicle to reach the different exit lanes of the unmarked road segment based off of the sensed curvatures of upcoming roads following the different exit lanes.

14. The non-transitory computer-readable medium of claim 13, in which the program code to rank the set of exit paths comprises: program code to generate splines between intersection exits and a position of the detected vehicle; andprogram code to use a curvature of the splines to determine which path the detected vehicle is most likely to take.

15. The non-transitory computer-readable medium of claim 9, further comprising program code to train a model to predict the exit path taken by the detected vehicle to reach an exit lane of the unmarked road segment based on a curvature of the different exit lanes of the unmarked road segment in relation to the detected vehicle.

16. The non-transitory computer-readable medium of claim 9, in which the program code to detect comprises: program code to identify the vehicle entering an intersection; andprogram code to sense a curvature of upcoming roads connected to the different exit lanes of the intersection.

17. A system for vehicle behavior prediction, the system comprising: a vehicle perception module to detect a vehicle entering an unmarked road segment;a vehicle paths determination module to determine a set of exit paths available for the detected vehicle to reach different exit lanes of the unmarked road segment;a vehicle path prediction module to predict an exit path taken by the vehicle from the set of exit paths available for the detected vehicle to reach the different exit lanes of the unmarked road segment; anda vehicle trajectory planner module to plan a trajectory of an ego vehicle according to the predicted exit path taken by the vehicle to reach a corresponding exit lane of the unmarked road segment.

18. The system of claim 17, in which the vehicle perception module is further to determine a location and a heading of the detected vehicle in response to the detected vehicle reaching an intersection.

19. The system of claim 17, in which the vehicle paths determination module is further to generate a birds-eye-view of the unmarked road segment, and to generate the set of exit paths based on a determined location and a heading of the detected vehicle relative to the different exit lanes of the unmarked road segment.

20. The system of claim 17, in which the vehicle path prediction module is further to determine a curvature of the different exit lanes of the unmarked road segment in relation to a determined location and a heading of the detected vehicle; and to infer the predicted exit path taken by the detected vehicle as an exit lane having the least curvature.