CN114291100B

CN114291100B - Parking method and device for automatically driving vehicle

Info

Publication number: CN114291100B
Application number: CN202210035054.6A
Authority: CN
Inventors: 谭益农; 李旭健; 郭鼎峰; 朱振广
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2020-03-03
Filing date: 2020-03-03
Publication date: 2024-05-31
Anticipated expiration: 2040-03-03
Also published as: CN111301432A; CN114291099B; CN114291100A; CN114291098A; CN114291098B; CN114291099A; CN111301432B

Abstract

The embodiment of the application discloses a parking method and device for an automatic driving vehicle. One embodiment of the method comprises the following steps: in response to determining that the autonomous vehicle meets a preset parking condition, performing the following parking control steps: determining a variance of a continuous plurality of actual accelerations of the autonomous vehicle; determining an acceleration to be employed by the autonomous vehicle based on the variance; based on the acceleration to be employed, a travel instruction is generated and output. In the scheme provided by the embodiment of the application, the obtained variance of the actual acceleration can represent the reliability degree of the obtained actual acceleration, so that based on the reliability degree, an appropriate parking strategy can be determined to obtain the acceleration required by appropriate parking. Therefore, the embodiment of the application is beneficial to avoiding the problems of improper first acceleration and low smoothness to be adopted, which are determined because the obtained actual acceleration is not credible, and further avoiding the problem of the sense of taking advantage of the object.

Description

Parking method and device for automatically driving vehicle

The application is a divisional application of a Chinese patent application No. 202010139229.9, the application number of the original application is: 202010139229.9, the application date is: 2020.03.03, titled: a parking method and apparatus for automatically driving a vehicle.

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to the technical field of Internet, and particularly relates to a parking method and device for an automatic driving vehicle.

Background

An automatic driving vehicle (also called an unmanned vehicle) can cooperate by means of artificial intelligence, visual calculation, radar, a monitoring device and the like, so that a vehicle-mounted computer can automatically and safely control the automatic driving vehicle without any human operation. In the course of driving an autonomous vehicle, there is a large difference between the parking phase and the general driving phase. The space for parking is often relatively narrow, so that the control accuracy of the automatic driving vehicle in the parking stage is required to be high.

In the related art, a general vehicle control method in a driving stage is generally applied directly to a parking stage of an automatically driven vehicle.

Disclosure of Invention

The embodiment of the application provides a parking method and device for an automatic driving vehicle.

In a first aspect, an embodiment of the present application provides a parking method for an automatically driven vehicle, including: in response to determining that the running state of the automatically driven vehicle meets the preset parking condition, performing the following parking control step: determining a variance of a plurality of actual accelerations of the autonomous vehicle over a plurality of consecutive preset periods; determining a first acceleration to be employed by the autonomous vehicle based on variances of the plurality of actual accelerations; a travel instruction is generated and output based on the first acceleration to be employed.

In some embodiments, determining a first acceleration to be employed by the autonomous vehicle based on a variance of a plurality of actual accelerations includes: determining a first acceleration to be employed by the autonomous vehicle based on a current speed of the autonomous vehicle and a distance from the target parking location in response to determining that the variance is below a preset variance threshold; and generating and outputting a travel instruction based on the first acceleration to be employed, including: a travel instruction for instructing the acceleration of the automatically driven vehicle to be increased from the current actual acceleration to the first acceleration to be employed is generated.

In some embodiments, the direction of the first acceleration to be employed is the direction of the braking force; determining a first acceleration to be employed by the autonomous vehicle based on a current speed of the autonomous vehicle and a distance from a target parking location, comprising: determining a delay time for braking of a braking device of the autonomous vehicle; determining the speed of the automatic driving vehicle and the distance from the target parking position after the delay time is elapsed, wherein the speed and the distance are respectively the target speed and the target distance; a first acceleration to be employed by the autonomous vehicle is determined based on a ratio between a square of the target speed and the target distance.

In some embodiments, determining a first acceleration to be employed by the autonomous vehicle based on a variance of a plurality of actual accelerations includes: in response to determining that the variance of the plurality of actual accelerations is not below the preset variance threshold, a first acceleration to be employed by the autonomous vehicle is determined based on a deviation of a current position of the autonomous vehicle from the planned position.

In some embodiments, determining a first acceleration to be employed by the autonomous vehicle based on a deviation of a current position of the autonomous vehicle from a planned position includes: determining the deviation between the current position and the planned position of the automatic driving vehicle as a first deviation; determining a speed difference value between the current speed and the reference speed of the automatic driving vehicle, and determining a position deviation caused by the speed difference value in a preset period; and determining the sum of the first deviation and the position deviation, and inputting the sum into a designated controller to obtain the first acceleration to be adopted by the automatic driving vehicle.

In some embodiments, in response to determining that the autonomous vehicle meets a preset parking condition, performing a parking control step comprising: in response to a judgment that the running state of the automatically driven vehicle meets various preset parking conditions in a plurality of continuous preset periods, executing the following parking control steps; wherein each preset parking condition comprises at least two of the following: the distance between the target parking position and the target parking position is smaller than a first preset distance; the current speed is less than a first preset speed; the current reference acceleration is smaller than a preset acceleration threshold value; the method further comprises the following steps: and stopping the parking control step in response to determining that the running state of the autonomous vehicle does not meet any one or more of the preset parking conditions for a plurality of consecutive preset periods.

In some embodiments, the parking control step further comprises: and determining a second acceleration to be applied to the autonomous vehicle in the current preset period based on the acceleration to be applied determined in the previous preset period in response to determining that the distance between the autonomous vehicle and the target parking position is less than a second preset distance, the second preset speed is less than the first preset speed, and the direction of the second acceleration to be applied is the direction of the braking force.

In some embodiments, determining a second acceleration to be applied by the autonomous vehicle during the current preset period based on the acceleration to be applied determined during the previous preset period includes: in response to determining that the acceleration to be adopted, which is determined in the last preset period, is within one of at least two preset numerical ranges, determining a preset increment value corresponding to the one of the preset numerical ranges, wherein the preset increment value is the product of a preset multiple corresponding to the one of the preset numerical ranges and a specified numerical value; and determining the sum of the preset increment value and the acceleration to be adopted determined in the last preset period as a second acceleration to be adopted, wherein the preset increment value corresponding to the preset numeric range with larger numeric value in at least two preset numeric ranges is smaller than the preset increment value corresponding to the preset numeric range with smaller numeric value.

In some embodiments, in response to determining that the driving state of the autonomous vehicle meets the preset parking condition, the following parking control step is performed, including: determining a third acceleration to be adopted by the automatic driving vehicle by utilizing a preset acceleration determining rule in response to judging that the automatic driving vehicle meets a preset parking condition, and judging whether the third acceleration to be adopted is above a preset sudden braking acceleration value, wherein the direction of the third acceleration to be adopted is the braking force direction; if the third acceleration to be adopted is not above the sudden braking acceleration value, executing a parking control step; and outputting an instruction comprising the sudden braking acceleration value if the third acceleration to be adopted is above the sudden braking acceleration value.

In some embodiments, the direction of the first acceleration to be employed is the direction of the braking force; the parking control step further includes: in response to determining that the autonomous vehicle is currently ascending, reducing a first acceleration to be employed by the autonomous vehicle; in response to determining that the autonomous vehicle is currently downhill, a first acceleration to be employed by the autonomous vehicle is increased.

In a second aspect, an embodiment of the present application provides a parking apparatus for an automatically driven vehicle, including: a judging unit configured to judge whether the automatically driven vehicle meets a preset parking condition; a parking control unit configured to perform the following parking control step in response to determining that the running state of the automatically driven vehicle meets a preset parking condition: determining a variance of a plurality of actual accelerations of the autonomous vehicle over a plurality of consecutive preset periods; determining a first acceleration to be employed by the autonomous vehicle based on variances of the plurality of actual accelerations; a travel instruction is generated and output based on the first acceleration to be employed.

In some embodiments, the parking control unit is further configured to determine a first acceleration to be employed by the autonomous vehicle based on variances of the plurality of actual accelerations as follows: determining a first acceleration to be employed by the autonomous vehicle based on a current speed of the autonomous vehicle and a distance from the target parking location in response to determining that the variance is below a preset variance threshold; and a parking control unit further configured to generate and output a travel instruction based on the first acceleration to be employed, as follows: a travel instruction for instructing the acceleration of the automatically driven vehicle to be increased from the current actual acceleration to the first acceleration to be employed is generated.

In some embodiments, the direction of the first acceleration to be employed is the direction of the braking force; a parking control unit further configured to perform determining a first acceleration to be employed by the autonomous vehicle based on a current speed of the autonomous vehicle and a distance from a target parking position in the following manner: determining a delay time for braking of a braking device of the autonomous vehicle; determining the speed of the automatic driving vehicle and the distance from the target parking position after the delay time is elapsed, wherein the speed and the distance are respectively the target speed and the target distance; a first acceleration to be employed by the autonomous vehicle is determined based on a ratio between a square of the target speed and the target distance.

In some embodiments, the parking control unit is further configured to determine a first acceleration to be employed by the autonomous vehicle based on variances of the plurality of actual accelerations as follows: in response to determining that the variance of the plurality of actual accelerations is not below the preset variance threshold, a first acceleration to be employed by the autonomous vehicle is determined based on a deviation of a current position of the autonomous vehicle from the planned position.

In some embodiments, the parking control unit is further configured to perform determining a first acceleration to be employed by the autonomous vehicle based on a deviation of a current position of the autonomous vehicle from the planned position in the following manner: determining the deviation between the current position and the planned position of the automatic driving vehicle as a first deviation; determining a speed difference value between the current speed and the reference speed of the automatic driving vehicle, and determining a position deviation caused by the speed difference value in a preset period; and determining the sum of the first deviation and the position deviation, and inputting the sum into a designated controller to obtain the first acceleration to be adopted by the automatic driving vehicle.

In some embodiments, the parking control unit is further configured to perform the following parking control step in response to determining that the running state of the autonomous vehicle meets the preset parking condition, in the following manner: in response to a judgment that the running state of the automatically driven vehicle meets various preset parking conditions in a plurality of continuous preset periods, executing the following parking control steps; wherein each preset parking condition comprises at least two of the following: the distance between the target parking position and the target parking position is smaller than a first preset distance; the current speed is less than a first preset speed; the current reference acceleration is smaller than a preset acceleration threshold value; the apparatus further comprises: and an exit unit configured to stop executing the parking control step in response to determining that the running state of the automatically driven vehicle does not conform to any one or more of the respective preset parking conditions for a plurality of consecutive preset periods.

In some embodiments, determining the second acceleration to be applied by the autonomous vehicle in the current preset period based on the acceleration to be applied determined in the parking control step in the previous preset period includes: in response to determining that the acceleration to be adopted, which is determined in the last preset period, is within one of at least two preset numerical ranges, determining a preset increment value corresponding to the one of the preset numerical ranges, wherein the preset increment value is the product of a preset multiple corresponding to the one of the preset numerical ranges and a specified numerical value; and determining the sum of the preset increment value and the acceleration to be adopted determined in the last preset period as a second acceleration to be adopted, wherein the preset increment value corresponding to the preset numeric range with larger numeric value in at least two preset numeric ranges is smaller than the preset increment value corresponding to the preset numeric range with smaller numeric value.

In some embodiments, the parking control unit is further configured to perform the following parking control step in response to determining that the running state of the autonomous vehicle meets the preset parking condition, in the following manner: determining a third acceleration to be adopted by the automatic driving vehicle by utilizing a preset acceleration determining rule in response to judging that the automatic driving vehicle meets a preset parking condition, and judging whether the third acceleration to be adopted is above a preset sudden braking acceleration value, wherein the direction of the third acceleration to be adopted is the braking force direction; if the third acceleration to be adopted is not above the sudden braking acceleration value, executing a parking control step; and outputting an instruction comprising the sudden braking acceleration value if the third acceleration to be adopted is above the sudden braking acceleration value.

In some embodiments, the direction of the first acceleration to be employed by the autonomous vehicle is the direction of the braking force; the parking control step further includes: in response to determining that the autonomous vehicle is currently ascending, reducing a first acceleration to be employed by the autonomous vehicle; in response to determining that the autonomous vehicle is currently downhill, a first acceleration to be employed by the autonomous vehicle is increased.

In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; and a storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement a method as in any of the embodiments of the parking method for an autonomous vehicle.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which when executed by a processor performs a method as in any of the embodiments of a parking method for an autonomous vehicle.

The parking scheme for the automatic driving vehicle provided by the embodiment of the application firstly, in response to judging that the running state of the automatic driving vehicle meets the preset parking condition, the following parking control steps are executed: a variance of a plurality of actual accelerations of the autonomous vehicle over a plurality of consecutive preset periods is determined. Thereafter, a first acceleration to be employed by the autonomous vehicle is determined based on the variances of the plurality of actual accelerations. Then, a travel instruction is generated and output based on the first acceleration to be employed. In the scheme provided by the embodiment of the application, the obtained variance of the actual acceleration can represent the reliability degree of the obtained actual acceleration, so that based on the reliability degree, an appropriate parking strategy can be determined to obtain the acceleration required by appropriate parking. Therefore, the embodiment of the application is beneficial to avoiding the problems of improper first acceleration and low smoothness to be adopted, which are determined because the obtained actual acceleration is not credible, and further avoiding the problem of the sense of taking advantage of the object.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:

FIG. 1 is an exemplary system architecture diagram in which some embodiments of the present application may be applied;

FIG. 2 is a flow chart of one embodiment of a parking method for an autonomous vehicle according to the present application;

FIG. 3 is a schematic illustration of one application scenario of a parking method for an autonomous vehicle according to the present application;

FIG. 4 is a flow chart of yet another embodiment of a parking method for an autonomous vehicle according to the present application;

FIG. 5 is a schematic structural view of one embodiment of a parking apparatus for an autonomous vehicle according to the present application;

FIG. 6 is a schematic diagram of a computer system suitable for use in implementing some embodiments of the application.

Detailed Description

The application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be noted that, for convenience of description, only the portions related to the present application are shown in the drawings.

It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

Fig. 1 shows an exemplary system architecture 100 to which an embodiment of a data processing method for an autonomous vehicle or a data processing device for an autonomous vehicle of the present application may be applied.

As shown in fig. 1, the system architecture 100 may include an onboard system (i.e., onboard brain or onboard computer) 101, a network 102, and a server 103. Network 102 is the medium used to provide communication links between in-vehicle system 101 and server 103. Network 102 may include various connection types such as wired, wireless communication links, or fiber optic cables, among others.

A user may interact with server 103 via network 102 using on-board system 101 to receive or send messages, etc. Various communication client applications may be installed on the in-vehicle system 101.

The server 103 may be a server that provides various services, such as a background server that provides support for the in-vehicle system 101. The background server may analyze data such as actual acceleration of the autonomous vehicle, and may feed back the processing result (e.g., generate and output a travel command) to the vehicle-mounted system.

It should be noted that, the data processing method for an autopilot vehicle provided in the embodiment of the present application may be executed by the vehicle-mounted system 101, and accordingly, the data processing device for an autopilot vehicle may be disposed in the vehicle-mounted system 101.

It should be understood that the number of in-vehicle systems, networks, and servers in fig. 1 are merely illustrative. There may be any number of in-vehicle systems, networks, and servers, as desired for implementation.

With continued reference to FIG. 2, a flow 200 of one embodiment of a method for parking an autonomous vehicle according to the present application is shown. The parking method for an automatically driven vehicle includes the steps of:

in step 201, in response to determining that the running state of the automatically driven vehicle meets the preset parking condition, the following parking control step is performed.

In this embodiment, an executing body (for example, the on-board brain shown in fig. 1) of the parking method for the autonomous vehicle may determine whether the autonomous vehicle meets a preset parking condition, and if it is determined that the driving state of the autonomous vehicle meets the preset parking condition, the executing body may execute the parking control step (for example, steps 202 to 204). In practice, the preset parking condition may be various conditions preset for the running state of the autonomous vehicle. The running state of the autonomous vehicle refers to a state of the autonomous vehicle during running. For example, the driving state may be a distance from the target parking position, and accordingly, the driving state meeting the preset parking condition may be a distance between the autonomous vehicle and the target parking position, that is, the parking spot, being smaller than the preset distance. The running state of the autonomous vehicle may be changed along with the running of the autonomous vehicle.

In some alternative implementations of the present embodiment, step 201 may include: in response to determining that the running state of the automatically driven vehicle meets each preset parking condition in a plurality of continuous preset periods, executing the following parking control steps; wherein each preset parking condition comprises at least two of the following: the distance between the automatic driving vehicle and the target parking position is smaller than a first preset distance; the current speed of the automatic driving vehicle is smaller than a first preset speed; the current reference acceleration of the automatic driving vehicle is smaller than a preset acceleration threshold value; the method further comprises the following steps: and stopping the parking control step in response to determining that the running state of the autonomous vehicle does not meet any one or more of the preset parking conditions for a plurality of consecutive preset periods.

In these alternative implementations, the preset parking conditions may include each of at least two preset parking conditions if the autonomous vehicle is relatively close to the target parking location. The execution body may execute the parking control step in a case where a running state of the automatically driven vehicle meets each of the preset parking conditions. The preset cycle is a cycle of the acquisition and calculation of the execution subject, such as a cycle of calculating the acceleration, the speed, etc. of the vehicle, and the execution subject may determine whether the automated driving vehicle meets each preset parking condition in each cycle. The executing body executes the parking control step, namely, enters the parking logic, and then, if the executing body detects that the automatic driving vehicle does not meet any one or more preset parking conditions in a plurality of continuous periods, the executing body can exit the parking logic, namely, stops executing the parking control step.

Specifically, the above-described execution body may execute the parking control step in a case where it is determined that the distance of the automatically driven vehicle from the target parking position is small, the speed of the automatically driven vehicle is small, and the reference acceleration of the automatically driven vehicle is small. The reference acceleration, that is, the pre-aiming acceleration, is the acceleration for reference determined by the execution body according to a preset rule, and corresponds to the reference line. The reference line is generated by the execution subject (or the server in fig. 1) based on the road information segment. For example, the reference line may be a center line of the lane. The reference line or the smoothed result of the reference line may be used to plan a travel path, i.e., a travel track, of the vehicle.

The executing body in the implementation manner can execute the parking control step only when the automatic driving vehicle is judged to meet various preset parking conditions in a plurality of continuous preset periods, so that the condition that whether the automatic driving vehicle is parked or not and whether the parking control step is executed or not is avoided, and the command confusion is caused. In addition, the execution main body can comprehensively judge whether to park according to the distance, the speed and the acceleration, so that the judging result is more accurate.

In some optional application scenarios of these implementations, the parking control step may further include: and determining a second acceleration to be applied to the autonomous vehicle in the current preset period based on the acceleration to be applied determined in the previous preset period in response to determining that the distance between the autonomous vehicle and the target parking position is less than a second preset distance, the second preset speed is less than the first preset speed, and the direction of the second acceleration to be applied is the direction of the braking force.

In these optional application scenarios, if the executing body determines that the autonomous vehicle is very close to the target parking position, that is, the distance between the autonomous vehicle and the target parking position is smaller than the second preset distance, and the executing body determines that the current speed of the autonomous vehicle is smaller than the second preset speed, the executing body may determine the acceleration to be adopted by the autonomous vehicle in the current preset period, that is, the second acceleration to be adopted by the autonomous vehicle based on the acceleration determined in the previous preset period.

In practice, the above-described execution subject may determine the second acceleration to be applied by the autonomous vehicle in the present preset period based on the acceleration to be applied determined in the last preset period in various manners. For example, the executing body may input the acceleration to be adopted determined in the previous preset period into a preset function or model, so as to obtain the second acceleration to be adopted determined in the current preset period. The function or model herein may be used to characterize the correspondence between the acceleration to be applied determined in the last preset period and the second acceleration to be applied in the current preset period.

These application scenarios may be based on the acceleration to be employed determined in the last preset period, thereby improving the accuracy of determining the acceleration to be utilized by the autonomous vehicle based on the acceleration already employed.

Optionally, determining the second acceleration to be applied to the autonomous vehicle in the current preset period based on the acceleration to be applied determined in the previous preset period in the application scenario may include: in response to determining that the acceleration to be adopted, which is determined in the last preset period, is within one of at least two preset numerical ranges, determining a preset increment value corresponding to the one of the preset numerical ranges, wherein the preset increment value is the product of a preset multiple corresponding to the one of the preset numerical ranges and a specified numerical value; and determining the sum of the preset increment value and the acceleration to be adopted determined in the last preset period as a second acceleration to be adopted, wherein the preset increment value corresponding to the preset numeric range with larger numeric value in at least two preset numeric ranges is smaller than the preset increment value corresponding to the preset numeric range with smaller numeric value.

Specifically, the execution body may set at least two preset numerical ranges for the acceleration to be adopted determined in the last preset period. The different preset value ranges correspond to different preset increment values, so that if the acceleration to be adopted determined in the last preset period is in the different preset value ranges, the corresponding preset increment values are different. The preset increment value is a value to be incremented from the acceleration to be adopted determined in the last preset period to the second acceleration to be adopted in the current preset period. In this application scenario, the executing body may continue to increase the braking force (i.e., increase the acceleration to be employed by the autonomous vehicle) until the vehicle is completely stopped or the braking force increases to a preset braking force maximum value.

For example, the preset period is 1 second, and if the acceleration to be adopted is determined to be-0.15 m/s ² in the previous 1 second, the preset value range of the acceleration is 0 to-0.2 m/s ², and the preset increment value corresponding to the range is-0.25 m/s ². The preset multiple corresponding to the preset numerical range is 5, the preset multiple 5 is multiplied by a specified numerical value of-0.05 m/s ² to obtain the preset added value of-0.25 m/s ², and then the second acceleration to be adopted is determined to be-0.15 m/s ²+(-0.25m/s² within the current 1 second. If the acceleration to be adopted is determined to be-0.35 m/s ² within the previous 1 second, the preset value range of the acceleration is-0.2 m/s ² to-0.4 m/s ², and the preset increment value corresponding to the range is-0.2 m/s ². The preset multiple corresponding to the preset numerical range is 4, the preset multiple 4 is multiplied by a specified numerical value of-0.05 m/s ² to obtain the preset added value of-0.2 m/s ², and the second acceleration to be adopted is determined to be-0.35 m/s ²+(-0.2m/s² in the current 1 second. The negative sign here indicates that the direction of the acceleration is the direction of the braking force.

The increase in the acceleration of the present application means an increase in the absolute value of the acceleration, regardless of whether the direction of the acceleration of the present application is the direction of the traction force or the direction of the braking force.

Under the condition that the acceleration adopted by the automatic driving vehicle is small, the vehicle is stopped in time by adopting larger acceleration and braking force.

Step 202, determining a variance of a plurality of actual accelerations of the autonomous vehicle over a plurality of consecutive preset periods.

In the present embodiment, the execution subject may determine a variance of an actual acceleration of the autonomous vehicle. Specifically, the actual acceleration may include the historical actual acceleration of the above-described autonomous vehicle, and may also include the current actual acceleration of the above-described autonomous vehicle. The actual acceleration refers to the actual acceleration of the autonomous vehicle. In general, the above-described execution subject may employ a plurality of actual accelerations continuously detected for the autonomous vehicle (at a plurality of preset periods in succession). Typically, each preset period corresponds to an actual acceleration.

Step 203 determines a first acceleration to be applied by the autonomous vehicle based on the variance of the plurality of actual accelerations.

In this embodiment, the execution subject may determine the acceleration to be employed by the autonomous vehicle, that is, the first acceleration to be employed, based on the determined variance. Specifically, an acceleration may be used for each preset period, where the acceleration is issued by the execution body and may deviate from the actual acceleration. The first acceleration to be employed determined here may be an acceleration to be employed in a preset future period of time, for example, may be an acceleration to be employed in the next preset period.

In practice, the above-described execution subject may determine the acceleration to be employed based on the variance in various ways. For example, the execution subject may input the variance into a preset model, and obtain the acceleration to be employed output from the preset model. The preset model is used for representing the corresponding relation between the variances of the actual accelerations and the accelerations to be adopted.

In some alternative implementations of the present embodiment, step 203 may include: in response to determining that the variance of the plurality of actual accelerations is not below the preset variance threshold, a first acceleration to be employed by the autonomous vehicle is determined based on a deviation of a current position of the autonomous vehicle from the planned position.

In these alternative implementations, the execution body may determine whether the variance is small, i.e., below a preset variance threshold. If the variance is not small, the value of the acceleration is not credible, and the execution body can park in a position tracking mode. Specifically, the execution subject may determine the first acceleration to be employed based on a deviation of a position between a current position of the autonomous vehicle and the planned position. The planned position is here the pre-aiming position, which is the position in the planned path planned with the reference line. The time corresponding to the current position and the planned position participating in determining the deviation is the current time, namely, the planned position is the position planned by the current time in the planned path.

In practice, the above-described execution subject may determine the first acceleration to be employed based on the above-described deviation (deviation of the current position from the planned position) in various ways. For example, the executing body may acquire a correspondence between the deviation and the first acceleration to be employed, and directly find the first acceleration to be employed corresponding to the deviation of the autonomous vehicle.

The implementation methods can determine the first acceleration to be adopted by the automatic driving vehicle based on the position under the condition that the obtained actual acceleration is not credible, so that the fact that the determined first acceleration to be adopted is improper due to data failure of the actual acceleration is avoided.

In some optional application scenarios of these implementations, determining the acceleration to be employed by the autonomous vehicle based on the deviation of the current position of the autonomous vehicle from the planned position may include: determining the deviation between the current position and the planned position of the automatic driving vehicle as a first deviation; determining a speed difference value between the current speed and the reference speed of the automatic driving vehicle, and determining a position deviation caused by the speed difference value in a preset period; and determining the sum of the first deviation and the position deviation, and inputting the sum into a designated controller to obtain the first acceleration to be adopted by the automatic driving vehicle.

In these alternative application scenarios, the current position and current speed refer to the actual position and speed of the autonomous vehicle. The first deviation herein and the deviation between positions in the positional deviation may refer to distances between positions. Specifically, the reference speed may refer to a speed for reference obtained using a preset determination rule, corresponding to a reference line. The positional deviation may be a product of the above-described speed difference value and a time corresponding to a preset period.

In practice, the above-specified controller may be a proportional-integral-derivative (PID) controller or a proportional-integral (PI) controller. After the execution body inputs the sum of the first deviation and the position deviation into the specified controller, the execution body can obtain the acceleration output by the specified controller, namely the first acceleration to be adopted by the automatic driving vehicle.

These implementations may utilize the positional deviation and the designated control to accurately determine a first acceleration to be employed by the autonomous vehicle.

Step 204, based on the first acceleration to be employed, a travel instruction is generated and output.

In this embodiment, the execution subject may generate a running instruction based on the determined first acceleration to be employed and output the running instruction. Specifically, the execution subject may generate the travel instruction in various ways. For example, the execution body may directly output a travel instruction including the first acceleration to be employed, and in addition, the execution body may determine a difference between the current actual acceleration and the first acceleration to be employed, and increase the acceleration of the automated driving vehicle from the current actual acceleration to the acceleration to be employed by using a gradient change (an incremental or decremental change), the value of the changed acceleration being the difference. Thus, the output travel instruction is an instruction indicating a change in acceleration gradient. In this case, the direction of the first acceleration to be employed is the direction of the braking force. For another example, the execution body may add the difference to the last travel instruction for controlling acceleration, thereby generating a travel instruction indicating the acceleration to be employed.

In the solution provided in this embodiment, the variance of the obtained actual acceleration may represent the confidence level of the obtained actual acceleration, so that based on the confidence level, an appropriate parking policy may be determined to obtain the acceleration to be used for appropriate parking. Therefore, the present embodiment helps to avoid the problems of improper first acceleration and low smoothness to be adopted, which are determined because the obtained actual acceleration is not reliable, and further avoid the problem of creating a passenger feel frustration.

In some alternative implementations of the present embodiment, step 201 may include: determining a third acceleration to be adopted by the automatic driving vehicle by utilizing a preset acceleration determining rule in response to judging that the automatic driving vehicle meets a preset parking condition, and judging whether the third acceleration to be adopted is above a preset sudden braking acceleration value, wherein the direction of the third acceleration to be adopted is the braking force direction; if the third acceleration to be adopted is not above the sudden braking acceleration value, executing a parking control step; and outputting an instruction comprising the sudden braking acceleration value if the third acceleration to be adopted is above the sudden braking acceleration value.

In these alternative implementations, the executing body may determine, according to a preset acceleration determination rule, an acceleration to be used by the autonomous vehicle, that is, a third acceleration to be used by the autonomous vehicle, if it is determined that the autonomous vehicle meets a preset parking condition. There may be a difference in the value of the third acceleration to be employed here from the first acceleration to be employed determined in step 203. Specifically, the preset acceleration determination rule may be an acceleration determination rule adopted by an automatically driven vehicle when a general driving phase of the parking logic is not entered. The sudden braking acceleration value is an acceleration value used when the vehicle is automatically driven to define a sudden braking.

In addition, if the acceleration to be adopted determined by these implementations is greater than the sudden braking acceleration, that is, the determined braking force is very large, the execution body may directly adopt the sudden braking acceleration value as the acceleration, and issue the sudden braking acceleration value to the vehicle chassis.

These implementations can set an upper limit on the acceleration to the braking force that does not cause damage to the vehicle body and possible passengers, thereby avoiding the problem of excessive braking force output. And under the condition that the determined acceleration is large, the emergency stop strategy is adopted to stop the vehicle in an emergency, so that the problem that traffic accidents are caused by untimely braking of the vehicle is avoided.

In some optional implementations of this embodiment, the parking control step may further include: and determining a second acceleration to be adopted by the automatic driving vehicle based on a change value of the acceleration adopted by the automatic driving vehicle in unit time in response to the fact that the distance between the automatic driving vehicle and the target parking position is smaller than a second preset distance and the current speed is smaller than a second preset speed, wherein the second preset distance is smaller than the first preset speed, and the direction of the second acceleration to be adopted is the direction of the braking force.

In some alternative implementations of the present embodiment, the direction of the first acceleration to be employed by the autonomous vehicle is the direction of the braking force; the above parking control step may further include: in response to determining that the autonomous vehicle is currently ascending, reducing a first braking force of the autonomous vehicle; in response to determining that the autonomous vehicle is currently downhill, a first braking force of the autonomous vehicle is increased.

In these alternative implementations, the executing body may perform gradient compensation for the first acceleration to be employed. During the automatic driving of the vehicle uphill, the acceleration, i.e. the braking force, is increased. While during the downhill of the autonomous vehicle, the acceleration, i.e. the braking force, is reduced. Thus, the situation that the automatic driving vehicle slides can be effectively avoided.

In practice, the gradient compensation may also be performed for the second acceleration to be employed, that is, the above-described parking control step may further include: responsive to determining that the autonomous vehicle is currently ascending, reducing a second acceleration to be employed by the autonomous vehicle; in response to determining that the autonomous vehicle is currently downhill, a second acceleration to be employed by the autonomous vehicle is increased.

With continued reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of the parking method for the autonomous vehicle according to the present embodiment. In the application scenario of fig. 3, the execution subject 301 may execute the following parking control step in response to determining that the running state of the autonomous vehicle meets the preset parking condition: a variance 302 of historical acceleration of the autonomous vehicle over a plurality of consecutive preset periods is determined. Based on the variance 302, the acceleration 303 to be employed by the autonomous vehicle is determined. Based on the first acceleration 303 to be employed, a travel instruction 304 is generated and output.

With further reference to fig. 4, a flow 400 of yet another embodiment of a parking method for an autonomous vehicle is shown. The flow 400 of the parking method for an autonomous vehicle includes the steps of:

in step 401, in response to determining that the running state of the automatically driven vehicle meets the preset parking condition, the following parking control step is performed.

In this embodiment, an executing body (for example, the on-board brain shown in fig. 1) of the parking method for the autonomous vehicle may determine whether the autonomous vehicle meets a preset parking condition, and if it is determined that the driving state of the autonomous vehicle meets the preset parking condition, the executing body may execute the parking control step (for example, steps 402 to 404). In practice, the preset parking condition may be various conditions preset for the running state of the autonomous vehicle. The running state of the autonomous vehicle refers to a state of the autonomous vehicle during running.

Step 402 determines a variance of a plurality of actual accelerations of the autonomous vehicle over a plurality of consecutive preset periods.

In the present embodiment, the execution subject may determine a variance of an actual acceleration of the autonomous vehicle. Specifically, the actual acceleration may include the historical actual acceleration of the above-described autonomous vehicle, and may also include the current actual acceleration of the above-described autonomous vehicle. The actual acceleration refers to the actual acceleration of the autonomous vehicle. In general, the above-described execution subject may employ a plurality of actual accelerations continuously detected for the autonomous vehicle (at a plurality of preset periods in succession).

In response to determining that the variance of the plurality of actual accelerations is not below the preset variance threshold, a first acceleration to be employed by the autonomous vehicle is determined based on a deviation of the current position of the autonomous vehicle from the planned position, step 403.

In this embodiment, the execution body may determine whether the variance is small, that is, below a preset variance threshold. The small variance indicates that the value of the acceleration is reliable, and the executing body can stop by adopting an acceleration tracking mode, namely, on the basis of the current actual acceleration, the gradient increases the difference value between the acceleration to be adopted and the current actual acceleration. Specifically, the execution subject may determine the first acceleration to be employed by the autonomous vehicle based on the current speed of the autonomous vehicle and the distance of the autonomous vehicle from the target parking position.

The execution subject may instruct the acceleration of the autonomous vehicle to gradually increase from the current actual acceleration to the first acceleration to be employed determined by the parking control step. Specifically, the gradient increase means a gradual increase, and may be a uniform increase or a non-uniform increase. For example, the specified number to be added is 6, which can be added in three times, each time the increase is 2, the increase can be divided into 2 times, and the increase is 2.5 and 1.5 respectively.

In practice, the above-described executing body may determine the first acceleration to be employed by the vehicle based on the current speed and distance in various ways. For example, the executing body may acquire a preset correspondence between the current speed and the distance and the first acceleration to be adopted, so that the first acceleration to be adopted corresponding to the current speed and the distance is directly determined in the correspondence.

In some alternative implementations of the present embodiment, the direction of the first acceleration to be employed is the direction of the braking force; determining the acceleration to be taken by the autonomous vehicle based on the current speed of the autonomous vehicle and the distance from the target parking location in step 403 may include: determining a delay time for braking of a braking device of the autonomous vehicle; determining the speed of the automatic driving vehicle and the distance from the target parking position after the delay time is elapsed, wherein the speed and the distance are respectively the target speed and the target distance; a first acceleration to be employed by the autonomous vehicle is determined based on a ratio between a square of the target speed and the target distance.

In these alternative implementations, the sum of the boost time and the depressurization time of the brake device of the autonomous vehicle is the delay time described above. The execution body may determine the first acceleration to be employed based on the ratio in various manners, for example, the execution body may perform a predetermined process on the ratio, for example, multiply the ratio by a predetermined coefficient, thereby obtaining the first acceleration to be employed. Further, the above-described execution subject may determine the first acceleration to be employed based on a ratio between the square of the target speed and twice the target distance.

In practice, the current speed of the autonomous vehicle may be set to v, after a delay time, v+at, where a is the current acceleration of the vehicle and the direction of a is the same as the direction of the braking force. The current distance of the autonomous vehicle from the target parking position is s, and the distance of the autonomous vehicle from the target parking position after the delay time is s-vt-0.5at ². The general formula of the first acceleration a _d to be used is a _d＝v²/2 s, so the formula of the first acceleration to be used after the delay may be:

A _d in this formula takes the opposite number, indicating that the direction of the first acceleration to be taken is the same as the direction of the braking force. In addition, the equation may also be utilized to determine the second acceleration to be employed as described above.

Step 404, a travel instruction for instructing the acceleration of the autonomous vehicle to increment from the current actual acceleration to a first acceleration to be employed is generated.

In this embodiment, the execution subject may generate a running instruction based on the determined first acceleration to be employed and output the running instruction. Specifically, the running instruction instructs the acceleration of the automatically driven vehicle to be changed by a prescribed value from the current actual acceleration gradient, the prescribed value being the difference between the first acceleration to be employed determined in the parking control step and the current actual acceleration.

The embodiment can accurately estimate the acceleration to be employed based on the speed of the vehicle and the distance from the parking position in the case where the value of the actual acceleration is more reliable.

With further reference to fig. 5, as an implementation of the method shown in the above figures, the present application provides an embodiment of a parking apparatus for an autonomous vehicle, which apparatus embodiment corresponds to the method embodiment shown in fig. 2, and which apparatus embodiment may include the same or corresponding features or effects as the method embodiment shown in fig. 2, except for the features described below. The device can be applied to various electronic equipment.

As shown in fig. 5, a parking apparatus 500 for an automatically driven vehicle of the present embodiment includes: a judging unit 501 and a parking control unit 502. Wherein the judging unit 501 is configured to judge whether the automatic driving vehicle meets a preset parking condition; a parking control unit 502 configured to perform the following parking control steps in response to determining that the running state of the automatically driven vehicle meets a preset parking condition: determining a variance of a plurality of actual accelerations of the autonomous vehicle over a plurality of consecutive preset periods; determining a first acceleration to be employed by the autonomous vehicle based on variances of the plurality of actual accelerations; a travel instruction is generated and output based on the first acceleration to be employed.

In this embodiment, the specific processes of the judging unit 501 and the parking control unit 502 of the parking device 500 for automatically driving the vehicle and the technical effects thereof can be respectively referred to the relevant descriptions of step 201, step 202, step 203 and step 204 in the corresponding embodiment of fig. 2, and are not repeated here.

In some optional implementations of this embodiment, the parking control unit is further configured to determine a first acceleration to be employed by the autonomous vehicle based on variances of the plurality of actual accelerations, as follows: determining a first acceleration to be employed by the autonomous vehicle based on a current speed of the autonomous vehicle and a distance from the target parking location in response to determining that the variance is below a preset variance threshold; and a parking control unit further configured to generate and output a travel instruction based on the first acceleration to be employed, as follows: a travel instruction for instructing the acceleration of the automatically driven vehicle to be increased from the current actual acceleration to the first acceleration to be employed is generated.

In some alternative implementations of the present embodiment, the direction of the first acceleration to be employed is the direction of the braking force; a parking control unit further configured to perform determining a first acceleration to be employed by the autonomous vehicle based on a current speed of the autonomous vehicle and a distance from a target parking position in the following manner: determining a delay time for braking of a braking device of the autonomous vehicle; determining the speed of the automatic driving vehicle and the distance from the target parking position after the delay time is elapsed, wherein the speed and the distance are respectively the target speed and the target distance; a first acceleration to be employed by the autonomous vehicle is determined based on a ratio between a square of the target speed and the target distance.

In some optional implementations of this embodiment, the parking control unit is further configured to determine a first acceleration to be employed by the autonomous vehicle based on variances of the plurality of actual accelerations, as follows: in response to determining that the variance of the plurality of actual accelerations is not below the preset variance threshold, a first acceleration to be employed by the autonomous vehicle is determined based on a deviation of a current position of the autonomous vehicle from the planned position.

In some optional implementations of this embodiment, the parking control unit is further configured to determine the first acceleration to be employed by the autonomous vehicle based on a deviation of the current position of the autonomous vehicle from the planned position, as follows: determining the deviation between the current position and the planned position of the automatic driving vehicle as a first deviation; determining a speed difference value between the current speed and the reference speed of the automatic driving vehicle, and determining a position deviation caused by the speed difference value in a preset period; and determining the sum of the first deviation and the position deviation, and inputting the sum into a designated controller to obtain the first acceleration to be adopted by the automatic driving vehicle.

In some optional implementations of this embodiment, the parking control unit is further configured to perform the following parking control step in response to determining that the running state of the autonomous vehicle meets the preset parking condition, in the following manner: in response to a judgment that the running state of the automatically driven vehicle meets various preset parking conditions in a plurality of continuous preset periods, executing the following parking control steps; wherein each preset parking condition comprises at least two of the following: the distance between the target parking position and the target parking position is smaller than a first preset distance; the current speed is less than a first preset speed; the current reference acceleration is smaller than a preset acceleration threshold value; the apparatus further comprises: and an exit unit configured to stop executing the parking control step in response to determining that the running state of the automatically driven vehicle does not conform to any one or more of the respective preset parking conditions for a plurality of consecutive preset periods.

In some optional implementations of this embodiment, the parking control step further includes: and determining a second acceleration to be applied to the autonomous vehicle in the current preset period based on the acceleration to be applied determined in the previous preset period in response to determining that the distance between the autonomous vehicle and the target parking position is less than a second preset distance, the second preset speed is less than the first preset speed, and the direction of the second acceleration to be applied is the direction of the braking force.

In some optional implementations of this embodiment, determining the second acceleration to be applied by the autonomous vehicle in the parking control step based on the acceleration to be applied determined in the previous preset period includes: in response to determining that the acceleration to be adopted, which is determined in the last preset period, is within one of at least two preset numerical ranges, determining a preset increment value corresponding to the one of the preset numerical ranges, wherein the preset increment value is the product of a preset multiple corresponding to the one of the preset numerical ranges and a specified numerical value; and determining the sum of the preset increment value and the acceleration to be adopted determined in the last preset period as a second acceleration to be adopted, wherein the preset increment value corresponding to the preset numeric range with larger numeric value in at least two preset numeric ranges is smaller than the preset increment value corresponding to the preset numeric range with smaller numeric value.

In some optional implementations of this embodiment, the parking control unit is further configured to perform the following parking control step in response to determining that the running state of the autonomous vehicle meets the preset parking condition, in the following manner: determining a third acceleration to be adopted by the automatic driving vehicle by utilizing a preset acceleration determining rule in response to judging that the automatic driving vehicle meets a preset parking condition, and judging whether the third acceleration to be adopted is above a preset sudden braking acceleration value, wherein the direction of the third acceleration to be adopted is the braking force direction; if the third acceleration to be adopted is not above the sudden braking acceleration value, executing a parking control step; and outputting an instruction comprising the sudden braking acceleration value if the third acceleration to be adopted is above the sudden braking acceleration value.

In some alternative implementations of the present embodiment, the direction of the first acceleration to be employed by the autonomous vehicle is the direction of the braking force; the parking control step further includes: in response to determining that the autonomous vehicle is currently ascending, reducing a first acceleration to be employed by the autonomous vehicle; in response to determining that the autonomous vehicle is currently downhill, a first acceleration to be employed by the autonomous vehicle is increased.

As shown in fig. 6, the electronic device 600 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data required for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

In general, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, magnetic tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 shows an electronic device 600 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 6 may represent one device or a plurality of devices as needed.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication means 609, or from storage means 608, or from ROM 602. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing means 601. It should be noted that the computer readable medium of the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In an embodiment of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. Whereas in embodiments of the present disclosure, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present application may be implemented in software or in hardware. The described units may also be provided in a processor, for example, described as: a processor includes a judging unit and a parking control unit. The names of these units do not constitute a limitation on the unit itself in some cases, and for example, the judgment unit may also be described as "a unit that judges whether or not the automated driving vehicle meets the preset parking condition".

As another aspect, the present application also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: in response to determining that the running state of the automatically driven vehicle meets the preset parking condition, performing the following parking control step: determining a variance of a plurality of actual accelerations of the autonomous vehicle over a plurality of consecutive preset periods; determining a first acceleration to be employed by the autonomous vehicle based on variances of the plurality of actual accelerations; a travel instruction is generated and output based on the first acceleration to be employed.

The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the application referred to in the present application is not limited to the specific combinations of the technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the inventive concept described above. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.

Claims

1. A parking method for an autonomous vehicle, the method comprising:

Determining a third acceleration to be adopted by the automatic driving vehicle by utilizing a preset acceleration determining rule in response to judging that the running state of the automatic driving vehicle meets a preset stopping condition, wherein the direction of the third acceleration to be adopted is the direction of a braking force;

Judging whether the third acceleration to be adopted is above a preset sudden braking acceleration value or not;

Executing a parking control step in response to the third acceleration to be employed not being above the sudden braking acceleration value;

Outputting an instruction comprising the sudden braking acceleration value in response to the third acceleration to be adopted being above the sudden braking acceleration value;

The parking control step includes:

determining a variance of a plurality of actual accelerations of the autonomous vehicle over a plurality of consecutive preset periods;

Determining a first acceleration to be employed by the autonomous vehicle based on a variance of the plurality of actual accelerations;

and generating and outputting a driving instruction based on the first acceleration to be adopted.

2. The method of claim 1, wherein the determining a first acceleration to be employed by the autonomous vehicle based on the variance of the plurality of actual accelerations comprises:

In response to determining that the variance of the plurality of actual accelerations is not below a preset variance threshold, determining a first acceleration to be employed by the autonomous vehicle based on a deviation of a current position of the autonomous vehicle from a planned position.

3. The method of claim 1, wherein the responsive to determining that the autonomous vehicle meets a preset parking condition, performing a parking control step comprises:

in response to determining that the running state of the autonomous vehicle meets each preset parking condition in a plurality of continuous preset periods, executing the following parking control step, wherein each preset parking condition comprises at least two of the following: the distance between the target parking position and the target parking position is smaller than a first preset distance; the current speed is less than a first preset speed; the current reference acceleration is smaller than a preset acceleration threshold value; and

The method further comprises the steps of:

and stopping executing the parking control step in response to determining that the running state of the autonomous vehicle does not meet any one or more of the preset parking conditions for a plurality of consecutive preset periods.

4. A method according to claim 3, wherein the parking control step further comprises:

And determining a second acceleration to be adopted by the automatic driving vehicle in the current preset period based on the acceleration to be adopted determined in the last preset period in response to the fact that the distance between the automatic driving vehicle and the target parking position is smaller than a second preset distance and the current speed is smaller than a second preset speed, wherein the second preset distance is smaller than the first preset distance, the second preset speed is smaller than the first preset speed, and the direction of the second acceleration to be adopted is the direction of braking force.

5. The method of claim 4, wherein the determining a second acceleration to be applied by the autonomous vehicle for a current preset period based on the acceleration to be applied determined for the previous preset period comprises:

Determining a preset increment value corresponding to one of at least two preset numerical ranges in response to determining that the acceleration to be adopted, which is determined in the last preset period, is in one of the preset numerical ranges, wherein the preset increment value is the product of a preset multiple corresponding to the one of the preset numerical ranges and a designated numerical value;

and determining the sum of the preset increment value and the acceleration to be adopted determined in the last preset period as the second acceleration to be adopted, wherein the preset increment value corresponding to the preset numeric value range with larger numeric value in the at least two preset numeric value ranges is smaller than the preset increment value corresponding to the preset numeric value range with smaller numeric value.

6. The method of claim 1, wherein the direction of the first acceleration to be employed is the direction of braking force; the parking control step further includes:

In response to determining that the autonomous vehicle is currently ascending, reducing a first acceleration to be employed by the autonomous vehicle;

In response to determining that the autonomous vehicle is currently downhill, a first acceleration to be employed by the autonomous vehicle is increased.

7. A parking apparatus for automatically driving a vehicle, the apparatus comprising:

A judging unit configured to determine a third acceleration to be employed by the autonomous vehicle using a preset acceleration determination rule in response to a judgment that a running state of the autonomous vehicle meets a preset parking condition, wherein a direction of the third acceleration to be employed is a direction of a braking force; judging whether the third acceleration to be adopted is above a preset sudden braking acceleration value or not;

A parking control unit configured to perform a parking control step in response to the third acceleration to be employed not being above the sudden braking acceleration value; outputting an instruction comprising the sudden braking acceleration value in response to the third acceleration to be adopted being above the sudden braking acceleration value; the parking control step includes: determining a variance of a plurality of actual accelerations of the autonomous vehicle over a plurality of consecutive preset periods; determining a first acceleration to be employed by the autonomous vehicle based on a variance of the plurality of actual accelerations; and generating and outputting a driving instruction based on the first acceleration to be adopted.

8. The apparatus of claim 7, wherein the parking control unit is further configured to perform the determining a first acceleration to be employed by the autonomous vehicle based on the variance of the plurality of actual accelerations in a manner that:

9. The apparatus according to claim 7, wherein the parking control unit is further configured to perform the following parking control step in response to determining that the running state of the autonomous vehicle meets a preset parking condition, as follows:

In response to a judgment that the running state of the automatically driven vehicle meets various preset parking conditions in a plurality of continuous preset periods, executing the following parking control steps;

wherein, each preset parking condition comprises at least two of the following: the distance between the target parking position and the target parking position is smaller than a first preset distance; the current speed is less than a first preset speed; the current reference acceleration is smaller than a preset acceleration threshold value; and

The apparatus further comprises:

and an exit unit configured to stop executing the parking control step in response to determining that the running state of the automatically driven vehicle does not conform to any one or more of the plurality of preset parking conditions for a plurality of consecutive preset periods.

10. The apparatus of claim 9, wherein the parking control step further comprises:

11. The apparatus according to claim 10, wherein the determining of the second acceleration to be applied to the autonomous vehicle in the present preset period based on the acceleration to be applied determined in the previous preset period in the parking control step includes:

12. The apparatus of claim 7, wherein a direction of the first acceleration to be employed by the autonomous vehicle is a direction of braking force; the parking control step further includes:

13. An electronic device, comprising:

One or more processors;

Storage means for storing one or more programs,

When executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-6.

14. A computer readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements the method of any of claims 1-6.