Method, device and apparatus for generating a defensive driving strategy, and storage medium
A method, a device and an apparatus for generating a defensive driving strategy and a storage medium are provided. The method includes: detecting a type of each obstacle of a plurality of obstacles in a sensible range of an autonomous vehicle; determining whether there is a collision risk of the autonomous vehicle with the obstacle by using a collision risk detection method corresponding to the type; and determining the defensive driving strategy for the autonomous vehicle when the obstacle has a collision risk with the autonomous vehicle in the sensible range. According to the embodiments, an occurrence probability of a dangerous condition on a road may be reduced.
1. A method for generating a defensive driving strategy, comprising:
detecting, by one or more processors, a type of each obstacle of a plurality of obstacles in a sensible range of an autonomous vehicle;
determining, by the one or more processors, whether there is a collision risk of the autonomous vehicle with the obstacle by using a collision risk detection method corresponding to the type; and
reducing, by the one or more processors, a travelling speed of the autonomous vehicle or changing, by the one or more processors, a planned track of the autonomous vehicle when the obstacle has a collision risk with the autonomous vehicle in the sensible range,
wherein in response to detecting the obstacle is of a first type, determining whether there is the collision risk of the autonomous vehicle with the obstacle, by using a first collision risk detection method corresponding to the first type, comprises:
acquiring a planned track of the autonomous vehicle in a preset period;
determining a predicted track of the obstacle in the preset period; and
determining whether there is an intersection of the planned track with the predicted track, and determining that there is the collision risk of the autonomous vehicle with the obstacle if there is the intersection, and
wherein in response to detecting the obstacle is of a second type, determining whether there is the collision risk of the autonomous vehicle with the obstacle, by using a second collision risk detection method corresponding to the second type, comprises:
determining a stopping distance of the autonomous vehicle; and
determining whether the obstacle is located at a current lane of the autonomous vehicle or a lane adjacent to the current lane, and is located in front of the autonomous vehicle;
if the obstacle is located at the current lane or the lane adjacent to the current lane, and is located in front of the vehicle, determining whether a distance in a longitudinal direction between the obstacle and the autonomous vehicle is shorter than the stopping distance; and
if the distance is shorter than the stopping distance, determining that there is the collision risk of the autonomous vehicle with the obstacle, wherein the longitudinal direction is a travelling direction of the autonomous vehicle, and
wherein the obstacle of the first type is a motor vehicle with four or more wheels, and the obstacle of the second type is a bicycle, a Pedestrian, or a vehicle other than the obstacle of the first type.
2. The method of claim 1 , wherein the determining a predicted track of the obstacle in the preset period comprises: determining the predicted track of the obstacle in the preset period according to a current speed and a current travelling direction of the obstacle.
3. The method of claim 1 , wherein the determining the stopping distance of the autonomous vehicle comprises: determining the stopping distance of the autonomous vehicle according to a current speed of the autonomous vehicle and a road condition.
4. A device for generating a defensive driving strategy, 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:
detect a type of each obstacle of a plurality of obstacles in a sensible range of an autonomous vehicle;
determine whether there is a collision risk of the autonomous vehicle with the obstacle by using a collision risk detection method corresponding to the type; and
reduce a travelling speed of the autonomous vehicle or change a planned track of the autonomous vehicle when the obstacle has a collision risk with the autonomous vehicle in the sensible range,
wherein in response to detecting the obstacle is of a first type, the one or more programs are executed by the one or more processors to enable the one or more processors further to:
acquire a planned track of the autonomous vehicle in a preset period;
determine a predicted track of the obstacle in the preset period; and
determine whether there is an intersection of the planned track with the predicted track, and determine that there is the collision risk of the autonomous vehicle with the obstacle if there is the intersection, and
wherein in response to detecting the obstacle is of a second type, the one or more programs are executed by the one or more processors to enable the one or more processors further to:
determine a stopping distance of the autonomous vehicle; and
determine whether the obstacle is located at a current lane of the autonomous vehicle or a lane adjacent to the current lane, and is located in front of the autonomous vehicle;
if the obstacle is located at the current lane or the lane adjacent to the current lane, and is located in front of the vehicle, determine whether a distance in a longitudinal direction between the obstacle and the autonomous vehicle is shorter than the stopping distance; and
if the distance is shorter than the stopping distance, determine that there is the collision risk of the autonomous vehicle with the obstacle, wherein the longitudinal direction is a travelling direction of the autonomous vehicle, and
wherein the obstacle of the first type is a motor vehicle with four or more wheels, and the obstacle of the second type is a bicycle, a pedestrian, or a vehicle other than the obstacle of the first type.
5. The device of claim 4 , wherein the one or more programs are executed by the one or more processors to enable the one or more processors further to: determine the predicted track of the obstacle in the preset period according to a current speed and a current travelling direction of the obstacle.
6. The device of claim 4 , wherein the one or more programs are executed by the one or more processors to enable the one or more processors further to: determine the stopping distance of the autonomous vehicle according to a current speed of the autonomous vehicle and a road condition.
7. 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:
detecting a type of each obstacle of a plurality of obstacles in a sensible range of an autonomous vehicle;
determining whether there is a collision risk of the autonomous vehicle with the obstacle by using a collision risk detection method corresponding to the type; and
reducing a travelling speed of the autonomous vehicle or changing a planned track of the autonomous vehicle when the obstacle has a collision risk with the autonomous vehicle in the sensible range,
wherein in response to detecting the obstacle is of a first type, the computer executable instructions, when executed by a processor, cause the processor to perform further operations comprising:
acquiring a planned track of the autonomous vehicle in a preset period;
determining a predicted track of the obstacle in the preset period; and
determining whether there is an intersection of the planned track with the predicted track, and determining that there is the collision risk of the autonomous vehicle with the obstacle if there is the intersection, and
wherein in response to detecting the obstacle is of a second type, the computer executable instructions, when executed by a processor, cause the processor to perform further operations comprising:
determining a stopping distance of the autonomous vehicle; and
determining whether the obstacle is located at a current lane of the autonomous vehicle or a lane adjacent to the current lane, and is located in front of the autonomous vehicle;
if the obstacle is located at the current lane or the lane adjacent to the current lane, and is located in front of the vehicle, determining whether a distance in a longitudinal direction between the obstacle and the autonomous vehicle is shorter than the stopping distance; and
if the distance is shorter than the stopping distance, determining that there is the collision risk of the autonomous vehicle with the obstacle, wherein the longitudinal direction is a travelling direction of the autonomous vehicle, and
wherein the obstacle of the first type is a motor vehicle with four or more wheels, and the obstacle of the second type is a bicycle, a pedestrian, or a vehicle other than the obstacle of the first type.
8. The non-transitory computer-readable storage medium of claim 7 , wherein the computer executable instructions, when executed by a processor, cause the processor to perform further operations comprising: determining the predicted track of the obstacle in the preset period according to a current speed and a current travelling direction of the obstacle.
9. The non-transitory computer-readable storage medium of claim 7 , wherein the computer executable instructions, when executed by a processor, cause the processor to perform further operations comprising: determining the stopping distance of the autonomous vehicle according to a current speed of the autonomous vehicle and a road condition.