Vehicle track prediction method and device, storage medium and terminal device
A vehicle track prediction method and device, a storage medium and a terminal device are provided. The method includes: determining an obstacle vehicle entering a junction region in a case that an autonomous vehicle enters the junction region; acquiring historical traveling data of the obstacle vehicle in the junction region; predicting a potential track of the obstacle vehicle according to the historical traveling data and a current traveling state of the obstacle vehicle; and predicting a track of the autonomous vehicle in the junction region according to the potential track of the obstacle vehicle and a current traveling state of the autonomous vehicle. A decision making accuracy in self-driving may be effectively improved, and a driving risk may be reduced.
1. A vehicle track prediction method, comprising:
determining an obstacle vehicle entering a junction region in a case that an autonomous vehicle enters the junction region, wherein the junction region is a region enclosed by exits and entrances of an intersection;
acquiring historical travelling data of the obstacle vehicle in the junction region;
predicting a potential track of the obstacle vehicle in the junction region according to the historical travelling data of the obstacle vehicle in the junction region and a current travelling state of the obstacle vehicle; and
predicting a track of the autonomous vehicle in the junction region according to the potential track of the obstacle vehicle in the junction region and a current travelling state of the autonomous vehicle.
2. The vehicle track prediction method of claim 1 , wherein the predicting the potential track of the obstacle vehicle in the junction region according to the historical travelling data of the obstacle vehicle in the junction region and the current travelling state of the obstacle vehicle comprises:
determining a selectable exit for the obstacle vehicle in the junction region according to an entrance at which the obstacle vehicle enters the junction region and a current travelling direction of the obstacle vehicle;
if at least two selectable exits are determined, determining probabilities of selectable exits being selected by the obstacle vehicle according to the historical travelling data of the obstacle vehicle in the junction region;
determining an exit by which the obstacle vehicle travels away from the junction region, according to the probabilities of selectable exits selected by the obstacle vehicle; and
predicting the potential track of the obstacle vehicle according to the determined exit and the current travelling state of the obstacle vehicle.
3. The vehicle track prediction method of claim 2 , further comprising:
if only one selectable exit is determined, predicting the potential track of the obstacle vehicle according to the one selectable exit and the current travelling state of the obstacle vehicle.
4. The vehicle track prediction method of claim 1 , wherein the acquiring historical travelling data of the obstacle vehicle in the junction region comprises:
according to an entrance at which the obstacle vehicle enters the junction region, acquiring a lane line coinciding with the entrance in the junction region;
determining whether the obstacle vehicle travels along the lane line, according to the entrance and a current travelling direction of the obstacle vehicle; and
if the obstacle vehicle does not travel along the lane line, acquiring the historical travelling data of the obstacle vehicle in the junction region.
5. The vehicle track prediction method of claim 4 , wherein if the obstacle vehicle travels along the lane line, the potential track of the obstacle vehicle is determined according to the lane line and the current travelling state of the obstacle vehicle.
6. A vehicle track prediction device, comprising:
one or more processors; and
a storage device configured for storing one or more programs, wherein
the one or more programs are executed by the one or more processors to enable the one or more processors to:
determine an obstacle vehicle entering a junction region in a case that an autonomous vehicle enters the junction region, wherein the junction region is a region enclosed by exits and entrances of an intersection;
acquire historical travelling data of the obstacle vehicle in the junction region;
predict a potential track of the obstacle vehicle in the junction region according to the historical travelling data of the obstacle vehicle in the junction region and a current travelling state of the obstacle vehicle; and
predict a track of the autonomous vehicle in the junction region according to the potential track of the obstacle vehicle in the junction region and a current travelling state of the autonomous vehicle.
7. The vehicle track prediction device of claim 6 , wherein the one or more programs are executed by the one or more processors to enable the one or more processors further to:
determine a selectable exit for the obstacle vehicle in the junction region according to an entrance at which the obstacle vehicle enters the junction region and a current travelling direction of the obstacle vehicle;
if at least two selectable exits are determined, determine probabilities of selectable exits being selected by the obstacle vehicle according to the historical travelling data of the obstacle vehicle in the junction region;
determine an exit by which the obstacle vehicle travels away from the junction region according to the probabilities of selectable exits selected by the obstacle vehicle; and
predict the potential track of the obstacle vehicle according to the determined exit and the current travelling state of the obstacle vehicle.
8. The vehicle track prediction device of claim 7 , wherein the one or more programs are executed by the one or more processors to enable the one or more processors further to:
if only one selectable exit is determined, predict the potential track of the obstacle vehicle according to the one selectable exit and the current travelling state of the obstacle vehicle.
9. The vehicle track prediction device of claim 6 , wherein the one or more programs are executed by the one or more processors to enable the one or more processors further to:
according to an entrance at which the obstacle vehicle enters the junction region, acquire a lane line coinciding with the entrance in the junction region;
determine whether the obstacle vehicle travels along the lane line, according to the entrance and a current travelling direction of the obstacle vehicle; and
if the obstacle vehicle does not travel along the lane line, acquire the historical travelling data of the obstacle vehicle in the junction region.
10. The vehicle track prediction device of claim 9 , wherein the one or more programs are executed by the one or more processors to enable the one or more processors further to: if the obstacle vehicle travels along the lane line, determine the potential track of the obstacle vehicle according to the lane line and the current travelling state of the obstacle vehicle.
11. A non-transitory computer-readable storage medium, storing computer executable instructions stored thereon, that when executed by a processor cause the processor to perform operations comprising:
determining an obstacle vehicle entering a junction region in a case that an autonomous vehicle enters the junction region, wherein the junction region is a region enclosed by exits and entrances of an intersection;
acquiring historical travelling data of the obstacle vehicle in the junction region;
predicting a potential track of the obstacle vehicle in the junction region according to the historical travelling data of the obstacle vehicle in the junction region and a current travelling state of the obstacle vehicle; and
predicting a track of the autonomous vehicle in the junction region according to the potential track of the obstacle vehicle in the junction region and a current travelling state of the autonomous vehicle.
12. The non-transitory computer-readable storage medium of claim 11 , wherein the computer executable instructions, when executed by a processor, cause the processor to perform further operations comprising:
determining a selectable exit for the obstacle vehicle in the junction region according to an entrance at which the obstacle vehicle enters the junction region and a current travelling direction of the obstacle vehicle;
if at least two selectable exits are determined, determining probabilities of selectable exits being selected by the obstacle vehicle according to the historical travelling data of the obstacle vehicle in the junction region;
determining an exit by which the obstacle vehicle travels away from the junction region, according to the probabilities of selectable exits selected by the obstacle vehicle; and
predicting the potential track of the obstacle vehicle according to the determined exit and the current travelling state of the obstacle vehicle.
13. The non-transitory computer-readable storage medium of claim 12 , wherein the computer executable instructions, when executed by a processor, cause the processor to perform further operations comprising:
if only one selectable exit is determined, predicting the potential track of the obstacle vehicle according to the one selectable exit and the current travelling state of the obstacle vehicle.
14. The non-transitory computer-readable storage medium of claim 11 , wherein the computer executable instructions, when executed by a processor, cause the processor to perform further operations comprising:
according to an entrance at which the obstacle vehicle enters the junction region, acquiring a lane line coinciding with the entrance in the junction region;
determining whether the obstacle vehicle travels along the lane line, according to the entrance and a current travelling direction of the obstacle vehicle; and
if the obstacle vehicle does not travel along the lane line, acquiring the historical travelling data of the obstacle vehicle in the junction region.
15. The non-transitory computer-readable storage medium of claim 14 , wherein if the obstacle vehicle travels along the lane line, the potential track of the obstacle vehicle is determined according to the lane line and the current travelling state of the obstacle vehicle.