Method and apparatus for determining automatic parking strategy

1. A method for determining an automatic parking strategy, comprising:

determining, according to an automatic parking strategy, a target parking action corresponding to a current parking stage, wherein the current parking stage is one of a plurality of parking stages comprised in a parking process of a vehicle, wherein the automatic parking strategy is determining, as the target parking action, a parking action with a highest value in a plurality of parking actions corresponding to the current parking stage;

performing the target parking action;

obtaining feedback information, wherein the feedback information is used to indicates whether a result of performing the target parking action reaches a predetermined objective, and the predetermined objective is a predetermined position of the vehicle relative to a target parking spot, and/or the predetermined objective is a status of the vehicle in the parking process; and

updating the automatic parking strategy based on the feedback information, where when the feedback information is θ t and θ t−1 , and |θ t |<|θ t−1 |, increasing the value of the target parking action based on θ t and θ t−1 , wherein θ t and θ t−1 are the included angles at the two adjacent moments, θ t ≠ 0 , and the value of the target parking action is proportional to



θ

t

-

1





θ

t



.

2. The method according to claim 1 , wherein before the determining, according to an automatic parking strategy, a target parking action corresponding to a current parking stage, the method further comprises:

determining the current parking stage based on an included angle between a current preset direction of the vehicle and a reference direction, wherein there is a preset correspondence between the current parking stage and the included angle.

3. The method according to claim 2 , wherein the preset direction of the vehicle is a longitudinal axis direction of the vehicle, the reference direction is a longitudinal axis direction of the target parking spot, and the included angle is an acute angle or a right angle.

4. The method according to claim 3 , wherein the determining the current parking stage based on an included angle between a current preset direction of the vehicle and a reference direction comprises:

when the included angle is greater than or equal to a first included angle threshold, determining that the current parking stage is an initial stage, wherein the first included angle threshold is less than 90 degrees.

5. The method according to claim 4 , wherein

the target parking action is driving into the target parking spot at a first steering angle, wherein the first steering angle is less than a maximum steering angle of the vehicle; and

the predetermined objective is that the included angle is less than or equal to the first included angle threshold and the vehicle enters the target parking spot.

6. The method according to claim 4 , wherein the automatic parking strategy comprises determining, as the target parking action, a parking action with a highest value in a plurality of parking actions corresponding to the current parking stage; and

the updating the automatic parking strategy based on the feedback information comprises:

when the feedback information comprises the included angles at two adjacent moments during the target parking action, and an absolute value of a difference between the included angles at the two adjacent moments is greater than a preset included angle threshold, reducing a value of the target parking action.

7. The method according to claim 3 , wherein the determining the current parking stage based on an included angle between a current preset direction of the vehicle and a reference direction comprises:

when the included angle is greater than a second included angle threshold and less than the first included angle threshold, determining that the current parking stage is a transition stage, wherein both the first included angle threshold and the second included angle threshold are less than 90 degrees, and the second included angle threshold is less than the first included angle threshold.

8. The method according to claim 7 , wherein

the target parking action is driving to the target parking spot at a second steering angle, wherein the second steering angle is equal to the maximum steering angle of the vehicle; and

the predetermined objective is that the included angle is less than or equal to the second included angle threshold and the vehicle enters the target parking spot.

9. The method according to claim 3 , wherein the determining the current parking stage based on an included angle between a current preset direction of the vehicle and a reference direction comprises:

when the included angle is less than or equal to the second included angle threshold, determining that the current parking stage is a fine-tuning stage, wherein the second included angle threshold is less than 90 degrees.

10. An apparatus for determining an automatic parking strategy, comprising:

at least one processor;

a non-transitory computer-readable storage medium coupled to the at least one processor and storing programming instructions for execution by the at least one processor, the programming instructions instruct the at least one processor to perform the following operations:

determining, according to an automatic parking strategy, a target parking action corresponding to a current parking stage, wherein the current parking stage is one of a plurality of parking stages comprised in a parking process of a vehicle, wherein the automatic parking strategy is determining, as the target parking action, a parking action with a highest value in a plurality of parking actions corresponding to the current parking stage;

performing the target parking action;

obtaining feedback information, wherein the feedback information indicates whether a result of performing the target parking action reaches a predetermined objective, and the predetermined objective is a predetermined position of the vehicle relative to a target parking spot, and/or the predetermined objective is a status of the vehicle in the parking process; and

updating the automatic parking strategy based on the feedback information, where when the feedback information is θ t and θ t−1 , and |θ t |<|θ t−1 |, increasing the value of the target parking action based on θ t and θ t−1 , wherein θ t and θ t−1 are the included angles at the two adjacent moments, |θ t |≠ 0 , and the value of the target parking action is proportional



θ

t

-

1





θ

t



.

11. The apparatus according to claim 10 , wherein before determining, according to the automatic parking strategy, the target parking action corresponding to the current parking stage, the programming instructions instruct the at least one processor to perform:

determining the current parking stage based on an included angle between a current preset direction of the vehicle and a reference direction, wherein there is a preset correspondence between the current parking stage and the included angle.

12. The apparatus according to claim 11 , wherein the preset direction of the vehicle is a longitudinal axis direction of the vehicle, the reference direction is a longitudinal axis direction of the target parking spot, and the included angle is an acute angle or a right angle.

13. The apparatus according to claim 12 , wherein the programming instructions instruct the at least one processor to perform:

determining, when the included angle is greater than or equal to a first included angle threshold, the current parking stage is an initial stage, wherein the first included angle threshold is less than 90 degrees.

14. The apparatus according to claim 13 , wherein the programming instructions instruct the at least one processor to perform:

driving the target parking action into the target parking spot at a first steering angle, wherein the first steering angle is less than a maximum steering angle of the vehicle; and

the predetermined objective is that the included angle is less than or equal to the first included angle threshold and the vehicle enters the target parking spot.

15. The apparatus according to claim 14 , wherein the programming instructions instruct the at least one processor to perform:

determining the automatic parking strategy, as the target parking action, a parking action with a highest value in a plurality of parking actions corresponding to the current parking stage;

reducing a value of the target parking action when the feedback information comprising the included angles at two adjacent moments during the target parking action, and an absolute value of a difference between the included angles at the two adjacent moments is greater than a preset included angle threshold.

16. The apparatus according to claim 15 , wherein the programming instructions instruct the at least one processor to perform:

determining the current parking stage is a transition stage when the included angle is greater than a second included angle threshold and less than the first included angle threshold, wherein both the first included angle threshold and the second included angle threshold are less than 90 degrees, and the second included angle threshold is less than the first included angle threshold.

17. The apparatus according to claim 16 , wherein the programming instructions instruct the at least one processor to perform:

driving the target parking action to the target parking spot at a second steering angle, wherein the second steering angle is equal to the maximum steering angle of the vehicle; and

the predetermined objective is that the included angle is less than or equal to the second included angle threshold and the vehicle enters the target parking spot.

18. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program enables a computer to perform a method comprising:

determining, according to an automatic parking strategy, a target parking action corresponding to a current parking stage, wherein the current parking stage is one of a plurality of parking stages comprised in a parking process of a vehicle, wherein the automatic parking strategy is determining, as the target parking action, a parking action with a highest value in a plurality of parking actions corresponding to the current parking stage;

performing the target parking action;

obtaining feedback information, wherein the feedback information indicates whether a result of performing the target parking action reaches a predetermined objective, and the predetermined objective is a predetermined position of the vehicle relative to a target parking spot, and/or the predetermined objective is a status of the vehicle in the parking process; and

updating the automatic parking strategy based on the feedback information, where when the feedback information is θ t and θ t−1 , and |θ t |<|θ t−1 |, increasing the value of the target parking action based on θ t and θ t−1 , wherein θ t and θ t−1 are the included angles at the two adjacent moments, |θ t |≠0, and the value of the target parking action is proportional to



θ

t

-

1





θ

t



.