CN115042823A - Passenger-riding parking method and device, electronic equipment and storage medium - Google Patents

Abstract

Translated fromChinese

本申请实施例提供一种代客泊车方法、装置、电子设备及存储介质，具体的，响应于智能驾驶车辆的自动巡航，获取智能驾驶车辆所处泊车环境中，各个移动目标各自的目标位移信息，并基于对应于车辆所处泊车环境设定的移动规则以及移动模型，对各个目标位移信息进行分析，获得各个移动目标各自的目标预测轨迹，进一步的，基于预设的评价模型，对各个目标预测轨迹进行分析并生成相应的控制指令，以使智能驾驶车辆能够基于控制指令，对泊车环境中的各个移动目标进行避让，进而有效提升了智能驾驶车辆在代客泊车中的行驶安全性，并确保了智能驾驶车辆内部乘车人员的驾乘体验。

The embodiments of the present application provide a valet parking method, device, electronic device, and storage medium. Specifically, in response to the automatic cruise of the intelligent driving vehicle, the respective targets of each moving target in the parking environment where the intelligent driving vehicle is located are obtained. Displacement information, and based on the movement rules and movement models set corresponding to the parking environment where the vehicle is located, analyze the displacement information of each target to obtain the target predicted trajectory of each moving target. Further, based on the preset evaluation model, Analyze the predicted trajectory of each target and generate corresponding control instructions, so that the intelligent driving vehicle can avoid each moving target in the parking environment based on the control instructions, thereby effectively improving the intelligent driving vehicle in valet parking. Driving safety and ensuring the driving experience of the occupants inside the intelligent driving vehicle.

Description

Passenger-riding parking method and device, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of intelligent driving, in particular to a passenger-riding parking method and device, electronic equipment and a storage medium.

Background

The Valet Parking (Valet Parking) technology is an intelligent driving assistance technology for realizing automatic cruise and automatic Parking of an intelligent driving vehicle based on driving units such as a vehicle-mounted camera, a laser radar, an Inertial-Time Kinematic (RTK) positioning Unit, an Inertial Measurement Unit (IMU) and the like.

Specifically, in the related art, a global path of an intelligent driving vehicle to be parked may be planned based on a global map of a parking environment (e.g., an indoor parking lot) in which the vehicle is located and the collected free parking space information, and an automatic cruise of the intelligent driving vehicle may be started according to the planned global path, so as to ensure that the vehicle cruises to a specified target parking space, and further automatic parking may be performed here.

However, since a parking environment in which a vehicle is located usually has a large number of moving objects (e.g., pedestrians and other vehicles) in actual situations, a safety accident may occur between an intelligent driving vehicle in automatic cruising or automatic parking and the moving objects in the parking environment.

For example, in an indoor parking lot, there may be a case where a certain moving pedestrian approaches an intelligent driving vehicle in automatic cruise, and in this case, the intelligent driving vehicle cruising according to the global route easily collides with the moving pedestrian, so that the driving safety of the intelligent driving vehicle in the valet parking in the related art is not high.

Disclosure of Invention

The embodiment of the application provides a passenger-riding parking method and device, electronic equipment and a storage medium, which are used for improving the driving safety of an intelligent driving vehicle in passenger-riding parking.

In a first aspect, an embodiment of the present application provides a method for parking a car in a passenger car, including:

and responding to the automatic cruising of the intelligent driving vehicle, and acquiring the target displacement information of each moving target in the parking environment of the intelligent driving vehicle.

And respectively analyzing the target displacement information based on a movement rule and a movement model set corresponding to the parking environment to obtain respective target prediction tracks of the moving targets.

And analyzing each target prediction track based on a preset evaluation model, and generating a control instruction for the intelligent driving vehicle based on an analysis result.

And controlling the intelligent driving vehicle by adopting the control command, and triggering the intelligent driving vehicle to park when the intelligent driving vehicle is determined to reach the target position.

In a second aspect, an embodiment of the present application provides a valet parking device, including:

the obtaining module is used for responding to automatic cruising of the intelligent driving vehicle and obtaining target displacement information of each moving target in a parking environment where the intelligent driving vehicle is located.

And the prediction module is used for analyzing the displacement information of each target respectively based on a movement rule and a movement model which are set corresponding to the parking environment to obtain the target prediction track of each moving target.

And the evaluation module is used for analyzing each target prediction track based on a preset evaluation model and generating a control instruction for the intelligent driving vehicle based on an analysis result.

And the control module is used for controlling the intelligent driving vehicle by adopting the control command and triggering the intelligent driving vehicle to park when the intelligent driving vehicle is determined to reach the target position.

In an optional embodiment, the obtaining module is specifically configured to obtain target displacement information of each moving target in a parking environment of the intelligently driven vehicle, and the obtaining module is configured to:

obtaining respective perception information of at least one obstacle object in the parking environment, wherein each perception information at least comprises: a perceived image acquired for an obstacle.

And respectively carrying out feature extraction on the obtained perception information to obtain respective perception features of the at least one obstacle object, wherein each perception feature is used for representing the object attribute of the corresponding obstacle object.

And taking each obstacle with corresponding perception characteristics meeting preset conditions in the at least one obstacle as a moving target corresponding to the parking environment, and tracking each moving target to obtain target displacement information of each moving target.

In an optional embodiment, the analyzing, based on a movement rule and a movement model set corresponding to the parking environment, the target displacement information of each of the moving targets to obtain a target predicted trajectory of each of the moving targets, where the predicting module is specifically configured to:

acquiring an environmental road condition corresponding to the parking environment, wherein the environmental road condition at least comprises: a road damage condition of the parking environment.

And analyzing the environmental road condition based on the movement rule set corresponding to the parking environment to obtain target feasible road sections corresponding to the moving targets in the parking environment.

And respectively analyzing the target displacement information of each moving target in each target feasible section based on a moving model set corresponding to the parking environment to obtain the target prediction track of each moving target.

In an optional embodiment, the target predicted trajectory is analyzed based on a preset evaluation model, and a control command for the smart driving vehicle is generated based on an analysis result, where the evaluation module is specifically configured to:

and respectively analyzing the target prediction tracks based on a preset evaluation model to obtain the risk rating determined for each moving target.

And respectively obtaining the risk control strategies associated with the risk ratings from a preset control strategy set, and generating a control instruction for the intelligent driving vehicle based on the obtained risk control strategies.

In a third aspect, an electronic device is provided, which includes a processor and a memory, wherein the memory stores program code, and when the program code is executed by the processor, the processor executes the steps of the valet parking method according to the first aspect.

In a fourth aspect, a computer-readable storage medium is provided, which includes program code for causing an electronic device to perform the steps of the valet parking method of the first aspect when the program code runs on the electronic device.

The embodiment of the application provides a passenger-replacing parking method, a passenger-replacing parking device, an electronic device and a storage medium, particularly, the parking environment of an intelligent driving vehicle is obtained in response to the automatic cruise of the intelligent driving vehicle, the target displacement information of each moving target is based on the moving rule and the moving model which are set corresponding to the parking environment of the vehicle, analyzing the displacement information of each target to obtain the target prediction track of each moving target, and further, based on a preset evaluation model, analyzing each target predicted track and generating corresponding control instructions, so that the intelligent driving vehicle can drive the vehicle according to the control instructions, each moving target in the parking environment is avoided, so that the driving safety of the intelligent driving vehicle in the passenger-riding parking is effectively improved, and the driving experience of passengers in the intelligent driving vehicle is ensured.

Drawings

Fig. 1 is a schematic diagram of an application scenario provided in an embodiment of the present application;

FIG. 2 is a schematic view of a valet parking system according to an embodiment of the present disclosure;

fig. 3 is a flowchart of a method for parking a car as a passenger in an embodiment of the present application;

FIG. 4 is a schematic diagram of a target predicted trajectory according to an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of a risk rating provided by an embodiment of the present application;

fig. 6 is a schematic flow chart of a complete passenger-assistant parking method according to an embodiment of the present application;

FIG. 7 is a schematic view of a valet parking apparatus according to an embodiment of the present application;

fig. 8 is a schematic view of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the drawings in the embodiments of the present invention, and it is obvious that the embodiments described are only some embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that in the description of the present application, the directions or positional relationships indicated by "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. are based on the directions or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and thus, cannot be construed as limiting the present application.

Further, "a plurality" is understood to mean "at least two" in the description of the present application. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. A is connected with B and can represent: a and B are directly connected and A and B are connected through C. In addition, in the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not intended to indicate or imply relative importance nor order to be construed.

The design idea of the embodiment of the application is as follows:

in the related art, the automatic cruising and automatic parking of the smart driving vehicle are started in response to the global path planning of the smart driving vehicle, which easily causes the driving safety of the smart driving vehicle in the automatic cruising and automatic parking to be low due to a large number of moving objects (such as pedestrians, other vehicles, and the like) existing in the parking environment where the vehicle is located.

For example, in an indoor parking lot, if there is a possibility that a moving pedestrian approaches an intelligent vehicle in automatic cruise, in such a situation, the intelligent vehicle cruising along the global route is likely to collide with the moving pedestrian.

In order to improve the driving safety of an intelligent driving vehicle in automatic cruising or automatic parking, embodiments of the present application provide a passenger-replacing parking method, apparatus, electronic device, and storage medium, specifically, in response to automatic cruising of an intelligent driving vehicle, obtain respective target displacement information of each moving target in a parking environment where the intelligent driving vehicle is located, analyze the respective target displacement information based on a movement rule and a movement model set corresponding to the parking environment where the vehicle is located, obtain respective target predicted trajectories of each moving target, further, analyze the respective target predicted trajectories based on a preset evaluation model, and generate corresponding control instructions, so that the intelligent driving vehicle can avoid the respective moving targets in the parking environment based on the control instructions, thereby effectively improving the driving safety of the intelligent driving vehicle in passenger-replacing parking, and the driving experience of passengers in the intelligent driving vehicle is ensured.

Referring to fig. 1, a schematic diagram of a possible application scenario provided in the embodiment of the present application is shown, where the application scenario includes: asmart driving vehicle 101, a movingtarget 102a, a movingtarget 102b, an environmental sensor 103, and a server 104, wherein the smartdriving vehicle 101 may be in an auto cruise in a smart driving mode.

As shown in fig. 2, thesmart driving vehicle 101 may be equipped with avalet parking system 20, and when thevalet parking system 20 is activated, thesmart driving vehicle 101 may be instructed to enter into automatic cruise, and more specifically, in the embodiment of the present invention, thevalet parking system 20 may include asensing sensor 201, aparking controller 202, a high-precision positioning module 203, an associatedsystem signal module 204, and a vehiclebody control module 205, and functions of each module are as follows.

Theperception sensor 201 is a physical sensor for detecting and tracking a moving target in a parking environment in which thesmart driving vehicle 101 is located, and includes: any one or combination of environment perception related physical sensors such as a vision sensor, a millimeter wave radar, an ultrasonic radar and a laser radar.

For example, theperception sensor 201 may include any visual sensor having an image capturing and/or video capturing function, such as a Camera, an infrared Camera, a video Camera, a Digital Still Camera (DSC), a Single Lens Reflex Camera (SLRC), and the like, and the visual sensor may be mounted outside the compartment of theintelligent driving vehicle 101, so that in the automatic cruise of theintelligent driving vehicle 101, image data including a moving object in the parking environment where the intelligent driving vehicle is located may be captured based on the mounted visual sensor.

Further, theperception sensor 201 may further include a radio positioning device having a target detection function and a spatial position finding function, such as a millimeter wave radar, an ultrasonic radar, and a laser radar. For example, in the embodiment of the present application, theperception sensor 201 may further include a laser radar, and the laser radar may be configured to reflect a laser signal to a moving target in a parking environment where the smartdriving vehicle 101 is located, and analyze and obtain displacement data, such as a moving speed, a moving position, and the like of the moving target relative to thesmart driving vehicle 101 according to the received corresponding reflected signal.

In an alternative embodiment, thesensing sensor 201 may be connected to theparking controller 202 of thevalet parking system 20 in a wired connection manner and/or a wireless connection manner, so that thesensing sensor 201 transmits the acquired data to theparking controller 202, where the wired connection manner and/or the wireless connection manner include: data line connections, cellular mobile communication connections, Wireless Fidelity (Wi-Fi) connections, etc., which are not limited in this application.

Theparking controller 202 is an electronic device for performing data storage and data analysis functions, and theparking controller 202 may store a movement rule and a movement model set corresponding to the parking environment, and when theparking controller 202 receives target displacement information related to the parking environment, may analyze a target prediction trajectory of a corresponding moving target based on the stored movement rule and movement model.

For example, in the embodiment of the present application, theparking controller 202 implements the functions related to the parking obstacle avoidance method according to the embodiment of the present application through an internal processor, where the internal processor includes a Central Processing Unit (CPU) or other devices or computing units having data processing functions.

In an alternative embodiment, theparking controller 202 may also be connected to the high-precision positioning module 203, the associatedsystem signal module 204, and the vehiclebody control module 205 of thevalet parking system 20 in a wired connection manner and/or a wireless connection manner, which are not described herein again.

The high-precision positioning module 203 is an electronic device for accurately positioning a moving target in theintelligent driving vehicle 101 and its parking environment, and includes: any one or combination of accurate positioning equipment such as an inertial navigation positioning unit (RTK), an Inertial Measurement Unit (IMU), a Global Navigation Satellite System (GNSS) and the like.

For example, in the embodiment of the present application, the high-precision positioning module 203 may be an inertial navigation positioning unit RTK and an inertial measurement unit IMU, which may perform precise positioning on the moving target in theintelligent driving vehicle 101 and its parking environment in the automatic cruising or automatic parking of theintelligent driving vehicle 101.

The associatedsystem signal module 204 and the vehiclebody control module 205 may be connected to a control panel and electronic controls such as vehicle-mounted devices in thesmart driving vehicle 101. For example, in the embodiment of the present application, the associationsystem signal module 204 and the vehiclebody control module 205 may implement a user control and a vehicle driving function related to valet parking based on connected electronic controls.

Further, in the above application scenario, one or more environment sensors 103 may be deployed in a parking environment where thesmart vehicle 101 is located, and are configured to detect an environment road condition in the parking environment and a movement condition of each moving object existing therein in real time, where the environment sensors 103 may include: any one or combination of electronic devices with detection and positioning functions, such as a camera, an infrared camera, a video camera, a Digital Still Camera (DSC), a millimeter wave radar, an ultrasonic radar, and a laser radar, which is not limited in this application.

For example, in the embodiment of the present application, it is assumed that thesmart driving vehicle 101 is in an indoor parking lot for passenger-substitute parking, and the indoor parking lot may be disposed with one or more environmental sensors 103, for example, the environmental sensors 103 disposed at each turning position in the indoor parking lot, in a subsequent process, data of a moving speed, a moving position, and the like of each moving target (e.g., a pedestrian, a vehicle, and the like) in the indoor parking lot may be detected in real time through the disposed environmental sensors 103, so as to assist thesmart driving vehicle 101 to obtain more accurate target displacement information based on the collected data.

Further, in the embodiment of the present application, theintelligent driving vehicle 101 may perform information interaction with the environmental sensor 103 and the server 104 deployed in the parking environment through a communication network, where the server 104 may be configured to obtain and store the data acquired by the environmental sensor 103 in real time, and when it is determined that theintelligent driving vehicle 101 enters the automatic cruise, issue the data to theintelligent driving vehicle 101.

In an optional embodiment, the server 104 may further store a movement rule and a movement model set corresponding to the parking environment, and analyze a target prediction trajectory of each movement target included in the environment by using the movement rule and the movement model; further, the server 104 may further generate a control instruction that conforms to the analyzed target predicted trajectory, so as to control theintelligent driving vehicle 101 to avoid an obstacle through the created information interaction when theintelligent driving vehicle 101 is in the automatic cruise, thereby reducing the instruction analysis time of thevalet parking system 20, and further improving the user experience.

It is understood that, in practical situations, the above application scenarios are only examples, and the number of the smart driving vehicles, the moving targets, the environmental sensors, and the servers that can be included in the above application scenarios may also be any number specified, which is not limited in this application.

Further, referring to fig. 3, based on the application scenario, an embodiment of the present application provides a method for parking a valet, where the method may be applied to theintelligent driving vehicle 101 and/or the server 104, and theintelligent driving vehicle 101 is taken as an example for description, and the method specifically includes:

s301: and responding to the automatic cruising of the intelligent driving vehicle, and acquiring the target displacement information of each moving target in the parking environment of the intelligent driving vehicle.

Specifically, the valet parking system may automatically instruct the intelligent driving vehicle to enter into automatic cruising when the intelligent driving vehicle is at a starting position for valet parking, for example, when the intelligent driving vehicle is at an entrance of a parking lot.

For example, the user may manually instruct the smart driving vehicle to enter into the automatic cruise mode, for example, by means of an on-board display screen, a terminal client, an on-board remote controller, and the like.

For example, when the smart driving vehicle navigates to a parking position indicated by a certain instruction, if the parking position does not meet a preset parking condition, the current position of the smart driving vehicle may also be used as the start position of the valet parking, so that when the valet parking system is at the start position, the smart driving vehicle is instructed to enter into the auto cruise.

Further, responding to the automatic cruising of the intelligent driving vehicle, and acquiring target displacement information of each moving target in the parking environment of the intelligent driving vehicle; specifically, the moving objects may be any obstacle in the parking environment, such as a person, a vehicle, an animal, and the like, and in the embodiment of the present application, for each moving object existing in the environment, the object displacement information of each moving object may be obtained by a sensing sensor mounted on the smart driving vehicle and/or an environment sensor configured in the parking environment.

Specifically, in an alternative embodiment, when obtaining the target displacement information of each moving target through a perception sensor mounted on the intelligent driving vehicle and/or an environment sensor configured in a parking environment, the following steps may be performed:

s3011: acquiring respective perception information of at least one obstacle in a parking environment, wherein each perception information at least comprises: a perceived image acquired for an obstacle.

Specifically, when the intelligent driving vehicle automatically navigates, the sensing sensor mounted inside the vehicle or the environmental sensor mounted in the parking environment where the intelligent driving vehicle is located can be used for detecting each obstacle object with the corresponding entity outline in the current parking environment in real time, and obtaining the respective sensing information of each obstacle object.

For example, in an alternative embodiment, the intelligent driving vehicle may acquire image data of a front position or a peripheral position of the intelligent driving vehicle in real time through a visual sensor mounted inside the intelligent driving vehicle during an automatic cruising process of the intelligent driving vehicle, and when acquiring a perception image of a certain obstacle, the perception image is used as perception information of the obstacle.

For example, in another optional embodiment, the intelligent driving vehicle may further receive, in real time, a perception image issued by the server to the intelligent driving vehicle through a communication connection with the server corresponding to the current parking environment; specifically, the perception image may be acquired by an environment sensor mounted in the current parking environment, and the perception image may include at least one obstacle object in the current parking environment, so that when the smart driving vehicle receives the perception image, the perception image may be used as target perception data of a corresponding moving target.

S3012: and respectively carrying out feature extraction on the obtained perception information to obtain respective perception features of at least one obstacle object.

Specifically, in an actual situation, obstacle objects in a parking environment where the vehicle is located may be fixed, such as roadblocks, fences, and the like, in order to improve analysis efficiency of a target predicted trajectory, in the embodiment of the present application, for respective perception information of each obstacle object in the current parking environment, feature extraction may be performed on the obtained respective perception information, so that each moving target to be analyzed is selected from the extracted respective perception features.

For example, in an alternative embodiment, feature extraction may be performed on the perception information respectively acquired by each obstacle through a preset Convolutional Neural Network (CNN), so that, based on the perception features respectively extracted by each obstacle, a corresponding moving object, such as a "person", "a vehicle", and the like, meeting a preset condition is selected from the perception features.

S3013: and respectively taking each obstacle with corresponding perception characteristics meeting preset conditions in at least one obstacle as a moving target in the parking environment, tracking each moving target, and obtaining target displacement information of each moving target.

Specifically, based on the extracted sensing features, the obstacle objects in the parking environment, the corresponding sensing features of which meet preset conditions, are used as moving targets to be analyzed, and the sensing sensors carried by the vehicle and/or the environment sensors arranged in the parking environment are/is adopted to track the determined moving targets, so that the target displacement information of each moving target is obtained.

For example, in this embodiment of the application, based on the extracted sensing features, the corresponding sensing features in the parking environment may be characterized as obstacle objects of a "person" or a "vehicle" as moving targets to be analyzed, and target displacement information of each moving target may be obtained through a detection and positioning device such as a laser radar mounted in the vehicle and/or the parking environment, where the target displacement information may include a moving direction, a moving distance, a moving speed, and the like, which is not limited in this application.

It is worth further explaining that, in an actual situation, data fusion can be performed on the collected corresponding perception data of different perception sensors carried in the vehicle and/or the parking environment, so as to obtain more accurate target displacement information for the detected moving target.

For example, in an actual application scenario, a visual sensor mounted in a vehicle and/or a parking environment may be used to perform feature extraction and target tracking on a detected moving target, so as to obtain first displacement data of the moving target, such as a target type and a moving distance, and a laser radar mounted in the vehicle and/or the parking environment is used to perform time synchronization on point cloud data and an acquired image corresponding to a current parking environment, and then second displacement data of the moving target, such as a moving speed and a moving direction, is obtained based on a determined target type and coordinate transformation of the laser radar, in this embodiment of the present application, data fusion may be performed on the first displacement data and the second displacement data respectively acquired by the visual sensor and the laser radar, so that while data accuracy of corresponding sensing data acquired by each sensing sensor is ensured, the accuracy of target displacement information obtained by fusion is further improved.

S302: and respectively analyzing the displacement information of each target based on a movement rule and a movement model set corresponding to the parking environment to obtain the target prediction track of each moving target.

Furthermore, in order to ensure the driving safety of the intelligent driving vehicle in the process of passenger-assistant parking, the target prediction tracks of the moving targets in the current parking environment are analyzed based on the obtained displacement information of the targets.

In an optional embodiment, based on the obtained displacement information of each target, a movement path of each moving target in the current parking environment may be predicted through a movement rule and a movement model set corresponding to the parking environment, and then a target prediction track corresponding to each moving target is determined according to a prediction result, specifically, the method includes the following steps:

s3021: and acquiring an environmental road condition corresponding to the parking environment.

S3022: and analyzing the environmental road condition based on the movement rule set corresponding to the parking environment to obtain a target feasible road section corresponding to each moving target in the parking environment.

Specifically, in an actual situation, in order to ensure the accuracy of the target predicted trajectory obtained through analysis, a target feasible road section of each moving target in the current parking environment is determined according to the environmental road condition of the parking environment where the intelligent driving vehicle is located and the moving rule set for the parking environment.

For example, the environmental road condition may be a road damage condition of a parking environment in which the intelligent driving vehicle is located, or a congestion condition of each road included in the parking environment.

For example, the movement rule may be a traffic rule adopted in a parking environment in an actual situation, or may be a traffic rule specially instructed by a relevant person for each moving target in the parking environment, which is not limited in the present application.

S3033: and respectively analyzing the target displacement information of each moving target in each target feasible section based on a moving model set corresponding to the parking environment to obtain the target prediction track of each moving target.

Further, based on a movement model set corresponding to the parking environment, in each target feasible section, target displacement information of a corresponding moving target is analyzed, and a respective target prediction track of each moving target is obtained.

For example, the movement model may be a movement model for a corresponding moving object obtained by statistics in an actual situation according to a movement speed of the moving object such as a pedestrian or a vehicle, or may be manually specified by a relevant person according to an average movement speed of each moving object based on a parking environment, which is not limited in the present application.

Referring to fig. 4, based on the above manner, by combining the environmental road condition of the parking environment where the intelligent driving vehicle is located, the preset movement rule and the movement model, the target prediction trajectory of each moving target in S301 is analyzed, and taking the movingtarget 102a and the movingtarget 102b in the application scene as an example, the target prediction trajectory of each moving target is shown in the figure.

S303: and analyzing each target predicted track based on a preset evaluation model, and generating a control instruction for the intelligent driving vehicle based on an analysis result.

Further, each obtained target prediction track is analyzed based on a preset evaluation model, and a control command for the intelligent driving vehicle is generated corresponding to each moving target in the current parking environment based on the analysis result.

For example, in an optional embodiment, the analyzing each target predicted trajectory based on the preset evaluation model specifically includes the following steps:

s3011: and respectively analyzing the predicted track of each target based on a preset evaluation model to obtain the risk rating determined for each moving target.

Specifically, for each obtained target prediction track, the risk rating corresponding to the current position from the corresponding moving target to the intelligent driving vehicle can be evaluated respectively, so that different risk control strategies for the intelligent driving vehicle are adopted according to different risk ratings, and the user experience is further improved.

For example, in an alternative embodiment, a preset evaluation model may be adopted, and based on given respective movement indexes, the respective target predicted trajectories of the respective movement targets are evaluated, so as to obtain respective risk ratings of the respective movement targets under the current condition.

For example, the movement index may be determined according to a traffic rule adopted by the current parking environment, for example, a target speed limit, a target driving direction, a lane where a target predicted trajectory is located, and the like, which are respectively set for different moving targets by the current parking environment, may be adopted as the movement index; alternatively, the driving intention of the corresponding moving object under the actual condition may be considered and used as the moving index mentioned above, which is specifically as follows.

Referring to table 1 below, in an alternative embodiment, for a "pedestrian" related moving object, the corresponding risk rating for that type of moving object may be obtained in the following manner.

TABLE 1

Specifically, for a moving object related to "pedestrian", the evaluation results shown in table 1 above may be used to determine the risk rating to which each of the respective moving objects belongs.

For example, assume that in the application scenario shown in fig. 1, the evaluation result of determining the predicted trajectory of the corresponding target of the movingtarget 102a is "not meeting the target speed limit; there is a road traversing intention; without noticing a specified one or combination of the smart driving vehicles ", the risk rating attributed to the movingtarget 102a may be determined to be" high risk ".

Further, in an alternative embodiment, for a moving object related to a "vehicle", the risk rating corresponding to the moving object can be obtained in the following manner, as shown in table 2 below.

TABLE 2

Specifically, for a moving object related to "vehicle", the evaluation results shown in table 2 above may be used to determine the risk rating to which each of the respective moving objects belongs.

For example, assume that in the application scenario shown in fig. 1, the evaluation result of determining the target predicted trajectory corresponding to the movingtarget 102b is "meeting the target speed limit; the target driving direction is met; the risk rank attributed to the movingtarget 102b may be determined to be "low risk" at the time of a specified one or combination of self-lane driving ".

It should be noted that, in the evaluation results shown in tables 1 and 2, the driving intention such as "not paying attention to the smart vehicle" may be obtained by analyzing the target predicted trajectory of the corresponding moving target, or may be obtained by analyzing the target behavior detected for the moving target.

For example, when it is detected that the moving target related to the "pedestrian" has target behaviors such as "head down", "head turning", and the like, it may be determined that the moving target may have the driving intention of the "not paying attention to the intelligent driving vehicle", and in an actual situation, the evaluation result corresponding to the moving target may be manually specified according to real-time observation of a related technician, which is not described herein again.

S3012: and respectively obtaining the risk control strategies associated with the risk ratings from a preset control strategy set, and generating a control instruction for the intelligent driving vehicle based on the obtained risk control strategies.

Further, in order to improve the user experience of the intelligent driving vehicle, for each obtained risk rating, a respective corresponding risk control strategy may be determined, so as to generate a control instruction for the intelligent driving vehicle according to each determined risk control strategy.

For example, referring to table 3 below, in the embodiment of the present application, different control strategies may be respectively set based on the obtained risk ratings, including:

TABLE 3

Based on the manner, the intelligent driving vehicle can obtain each risk control strategy aiming at each moving target in the parking environment from the preset control strategy set corresponding to the predicted different risk grades of different moving targets, and generate corresponding control instructions by adopting each obtained risk control strategy.

Illustratively, referring to fig. 5, taking the target predicted trajectories of the movingtarget 102a and the movingtarget 102b shown in fig. 4 as an example, it is assumed that in the embodiment of the present application, the respective risk ratings of the movingtarget 102a and the movingtarget 102b are respectively 'high risk' and 'low risk' by adopting a preset evaluation model, then, for movingtargets 102a, 102b,smart driving vehicle 101 may obtain the risk control strategy corresponding to its risk rating respectively, thereby, based on the obtained risk control strategy, instructing thesmart driving vehicle 101 to prepare the movingtarget 102a in the parking environment for early deceleration and/or parking avoidance, and to indicate that theintelligent driving vehicle 101 can take a passing round and/or keep running at the original speed, the moving target 120b is avoided, and the driving safety of theintelligent driving vehicle 101 is ensured.

S304: and controlling the intelligent driving vehicle by adopting the control command, and triggering the intelligent driving vehicle to park when the intelligent driving vehicle is determined to reach the target position.

Furthermore, in the embodiment of the application, the control instruction is adopted to control the intelligent driving vehicle to avoid each moving target in the parking environment in advance, and therefore the driving safety of the vehicle is ensured in the automatic cruise of the intelligent driving vehicle.

It can be understood that, in an actual situation, an internal driver of the intelligent driving vehicle can also manually control the intelligent driving vehicle in the driving process through a control panel, voice communication and the like, so that when the driver takes over the intelligent driving vehicle, a passenger-assistant parking system in the intelligent driving vehicle can be interrupted, and when the driving environment of the vehicle is detected to meet preset conditions again, the intelligent driving vehicle is continuously controlled to perform corresponding automatic cruising or automatic parking.

For example, in the embodiment of the present application, theintelligent driving vehicle 101 may perform automatic cruise by using the generated control instruction, or may perform manual control on the intelligent driving vehicle by an internal driver of the intelligent driving vehicle when the intelligent driving vehicle needs to take over, so that theintelligent driving vehicle 101 is effectively ensured to avoid each moving target in the parking environment based on the above manner. Further, when it is determined that the intelligent driving vehicle reaches the target position, thevalet parking system 20 may also trigger the intelligent driving vehicle to perform automatic parking in response to the current target position; optionally, the driver may take over the parking control system to trigger the intelligent driving vehicle to park manually, so as to ensure that the intelligent driving vehicle is parked completely.

Referring to fig. 6, a complete flow diagram of the valet parking method is shown, based on the above manner, the embodiment of the application can adopt the analyzed target prediction tracks to control the intelligent driving vehicle in valet parking to avoid each moving target in the parking environment in advance, so that the safety and stability of the intelligent driving vehicle in the valet parking driving process are effectively improved.

Referring to fig. 7, in order to improve the driving safety of the intelligent driving vehicle in the process of passenger car parking, an embodiment of the present application further provides a passenger car parking apparatus, which includes an obtainingmodule 701, a predictingmodule 702, an evaluatingmodule 703, and acontrol module 704, where:

the obtainingmodule 701 is configured to obtain, in response to automatic cruising of an intelligent driving vehicle, target displacement information of each moving target in a parking environment where the intelligent driving vehicle is located.

A predictingmodule 702, configured to analyze the target displacement information respectively based on a movement rule and a movement model set in correspondence to the parking environment, and obtain a target predicted trajectory of each moving target.

And theevaluation module 703 is configured to analyze each target predicted trajectory based on a preset evaluation model, and generate a control instruction for the intelligent driving vehicle based on an analysis result.

And thecontrol module 704 is configured to control the intelligent driving vehicle by using the control instruction, and trigger the intelligent driving vehicle to park when it is determined that the intelligent driving vehicle reaches the target position.

In an optional embodiment, in the acquiring target displacement information of each moving target in a parking environment where the intelligent driving vehicle is located, the acquiringmodule 701 is specifically configured to:

obtaining respective perception information of at least one obstacle object in the parking environment, wherein each perception information at least comprises: a perceived image acquired for an obstacle.

And respectively carrying out feature extraction on the obtained perception information to obtain respective perception features of the at least one obstacle object, wherein each perception feature is used for representing the object attribute of the corresponding obstacle object.

And taking each obstacle with corresponding perception characteristics meeting preset conditions in the at least one obstacle as a moving target corresponding to the parking environment, and tracking each moving target to obtain target displacement information of each moving target.

In an optional embodiment, in the analyzing each target displacement information based on the movement rule and the movement model set corresponding to the parking environment to obtain the target predicted trajectory of each moving target, the predictingmodule 702 is specifically configured to:

acquiring an environmental road condition corresponding to the parking environment, wherein the environmental road condition at least comprises: a road damage condition of the parking environment.

And analyzing the environmental road condition based on the movement rule set corresponding to the parking environment to obtain target feasible road sections corresponding to the moving targets in the parking environment.

And respectively analyzing the target displacement information of each moving target in each target feasible section based on a moving model set corresponding to the parking environment to obtain the target prediction track of each moving target.

In an optional embodiment, the target predicted tracks are analyzed based on a preset evaluation model, and a control instruction for the smart driving vehicle is generated based on an analysis result, where theevaluation module 703 is specifically configured to:

and respectively analyzing the target prediction tracks based on a preset evaluation model to obtain the risk rating determined for each moving target.

And respectively obtaining the risk control strategies associated with the risk ratings from a preset control strategy set, and generating a control command for the intelligent driving vehicle based on the obtained risk control strategies.

Based on the same inventive concept as the above-mentioned application embodiments, the embodiment of the present application further provides an electronic device, and the electronic device may be used for passenger-riding parking. In one embodiment, the electronic device may be a server, a terminal device, or other electronic device. In this embodiment, the electronic device may be configured as shown in FIG. 8, and include amemory 801, acommunication interface 803, and one ormore processors 802.

Amemory 801 for storing computer programs executed by theprocessor 802. Thememory 801 may mainly include a program storage area and a data storage area, where the program storage area may store an operating system, programs required for running an instant messaging function, and the like; the storage data area can store various instant messaging information, operation instruction sets and the like.

Thememory 801 may be a volatile memory (volatile memory), such as a random-access memory (RAM); thememory 801 may also be a non-volatile memory (non-volatile memory) such as, but not limited to, a read-only memory (rom), a flash memory (flash memory), a Hard Disk Drive (HDD) or a solid-state drive (SSD), or thememory 801 may be any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Thememory 801 may be a combination of the above memories.

Theprocessor 802 may include one or more Central Processing Units (CPUs), or be a digital Processing Unit, etc. Theprocessor 802 is configured to implement the above-described valet parking method when a computer program stored in thememory 801 is called.

Thecommunication interface 803 is used for communication with terminal devices and other servers.

The specific connection medium among thememory 801, thecommunication interface 803 and theprocessor 802 is not limited in the embodiments of the present application. In the embodiment of the present application, thememory 801 and theprocessor 802 are connected by a bus 804 in fig. 8, the bus 804 is represented by a thick line in fig. 8, and the connection manner between other components is merely illustrative and is not limited. The bus 804 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 8, but this is not intended to represent only one bus or type of bus.

According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to cause the computer device to execute any one of the above-described embodiments of the method for valet parking. The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, 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.

The embodiment of the application provides a passenger-replacing parking method, a passenger-replacing parking device, an electronic device and a storage medium, particularly, the parking environment of an intelligent driving vehicle is obtained in response to the automatic cruise of the intelligent driving vehicle, the target displacement information of each moving target is based on the moving rule and the moving model which are set corresponding to the parking environment of the vehicle, analyzing the displacement information of each target to obtain the target prediction track of each moving target, and further, based on a preset evaluation model, analyzing each target predicted track and generating corresponding control instructions, so that the intelligent driving vehicle can drive the vehicle according to the control instructions, each moving target in the parking environment is avoided, so that the driving safety of the intelligent driving vehicle in the passenger-riding parking is effectively improved, and the driving experience of passengers in the intelligent driving vehicle is ensured.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims (10)

Translated fromChinese

1.一种代客泊车方法，其特征在于，包括：1. a valet parking method, is characterized in that, comprises:响应于智能驾驶车辆的自动巡航，获取所述智能驾驶车辆所处泊车环境中，各个移动目标各自的目标位移信息；In response to the automatic cruise of the intelligent driving vehicle, acquiring the respective target displacement information of each moving target in the parking environment where the intelligent driving vehicle is located;基于对应于所述泊车环境设定的移动规则以及移动模型，分别对各个所述目标位移信息进行分析，获得所述各个移动目标各自的目标预测轨迹；Based on the movement rules and movement models set corresponding to the parking environment, analyze the displacement information of each of the targets respectively, and obtain the target predicted trajectory of each of the moving targets;基于预设的评价模型，对各个所述目标预测轨迹进行分析，并基于分析结果，生成针对所述智能驾驶车辆的控制指令；Based on a preset evaluation model, analyze each of the target predicted trajectories, and generate control instructions for the intelligent driving vehicle based on the analysis results;采用所述控制指令控制所述智能驾驶车辆，并在确定所述智能驾驶车辆抵达目标位置时，触发所述智能驾驶车辆进行泊车。The intelligent driving vehicle is controlled by using the control instruction, and when it is determined that the intelligent driving vehicle reaches the target position, the intelligent driving vehicle is triggered to park.2.如权利要求1所述的方法，其特征在于，所述获取所述智能驾驶车辆所处泊车环境中，各个移动目标各自的目标位移信息，包括：2 . The method according to claim 1 , wherein acquiring the respective target displacement information of each moving target in the parking environment where the intelligent driving vehicle is located comprises: 2 .获取所述泊车环境中，至少一个障碍物体各自的感知信息，其中，每个感知信息至少包括：针对一个障碍物体采集到的感知图像；Acquiring respective perception information of at least one obstacle object in the parking environment, wherein each perception information at least includes: a perception image collected for one obstacle object;分别对获得的各个感知信息进行特征提取，获得所述至少一个障碍物体各自的感知特征，其中，每个感知特征用于表征相应障碍物体的物体属性；Respectively perform feature extraction on the acquired perceptual information to obtain the respective perceptual features of the at least one obstacle object, wherein each perceptual feature is used to represent the object attribute of the corresponding obstacle object;将所述至少一个障碍物体中，相应感知特征满足预设条件的各个障碍物体，分别作为所述泊车环境对应的移动目标，并对各个移动目标进行跟踪，获得所述各个移动目标各自的目标位移信息。In the at least one obstacle object, each obstacle object whose corresponding perception characteristic satisfies the preset condition is regarded as the moving target corresponding to the parking environment, and each moving target is tracked to obtain the respective target of each moving target. displacement information.3.如权利要求1或2所述的方法，其特征在于，所述基于对应于所述泊车环境设定的移动规则以及移动模型，对各个所述目标位移信息进行分析，获得所述各个移动目标各自的目标预测轨迹，包括：3. The method according to claim 1 or 2, characterized in that, based on the movement rules and movement models set corresponding to the parking environment, each of the target displacement information is analyzed to obtain the each of the target displacements. The respective target predicted trajectories of the moving targets, including:获取所述泊车环境对应的环境路况，其中，所述环境路况中至少包括：所述泊车环境的道路损坏情况；Acquiring environmental road conditions corresponding to the parking environment, wherein the environmental road conditions at least include: road damage conditions of the parking environment;基于对应于所述泊车环境设定的移动规则，对所述环境路况进行分析，获得所述泊车环境中，所述各个移动目标各自对应的目标可行路段；Analyzing the environmental road conditions based on the movement rules set corresponding to the parking environment, and obtaining target feasible road sections corresponding to the respective moving targets in the parking environment;基于对应于所述泊车环境设定的移动模型，在各个所述目标可行路段中，分别对所述各个移动目标各自的目标位移信息进行分析，获得所述各个移动目标各自的目标预测轨迹。Based on the movement model set corresponding to the parking environment, in each of the target feasible sections, the respective target displacement information of the respective moving targets is analyzed to obtain the respective target predicted trajectories of the respective moving targets.4.如权利要求1或2所述的方法，其特征在于，所述基于预设的评价模型，对各个所述目标预测轨迹进行分析，并基于分析结果，生成针对所述智能驾驶车辆的控制指令，包括：4. The method according to claim 1 or 2, wherein, based on a preset evaluation model, each of the target predicted trajectories is analyzed, and based on the analysis results, a control for the intelligent driving vehicle is generated Instructions, including:基于预设的评价模型，分别对各个所述目标预测轨迹进行分析，获得针对所述各个移动目标各自确定的风险评级；Based on a preset evaluation model, analyze each of the target predicted trajectories, and obtain a risk rating determined for each of the moving targets;从预设的控制策略集合中，分别获得各个所述风险评级各自关联的风险控制策略，并基于获得的各个风险控制策略，生成针对所述智能驾驶车辆的控制指令。From the preset control strategy set, respective risk control strategies associated with each of the risk ratings are obtained, and based on the obtained risk control strategies, a control instruction for the intelligent driving vehicle is generated.5.一种代客泊车装置，其特征在于，包括：5. A valet parking device, characterized in that, comprising:获取模块，用于响应于智能驾驶车辆的自动巡航，获取所述智能驾驶车辆所处泊车环境中，各个移动目标各自的目标位移信息；an acquisition module, configured to acquire the respective target displacement information of each moving target in the parking environment where the intelligent driving vehicle is located in response to the automatic cruise of the intelligent driving vehicle;预测模块，用于基于对应于所述泊车环境设定的移动规则以及移动模型，分别对各个所述目标位移信息进行分析，获得所述各个移动目标各自的目标预测轨迹；a prediction module, configured to analyze the displacement information of each of the targets respectively based on the movement rules and the movement model set corresponding to the parking environment, and obtain the target predicted trajectories of the respective moving targets;评价模块，用于基于预设的评价模型，对各个所述目标预测轨迹进行分析，并基于分析结果，生成针对所述智能驾驶车辆的控制指令；an evaluation module, configured to analyze each of the target predicted trajectories based on a preset evaluation model, and generate control instructions for the intelligent driving vehicle based on the analysis results;控制模块，用于采用所述控制指令控制所述智能驾驶车辆，并在确定所述智能驾驶车辆抵达目标位置时，触发所述智能驾驶车辆进行泊车。The control module is configured to use the control instruction to control the intelligent driving vehicle, and when it is determined that the intelligent driving vehicle reaches a target position, trigger the intelligent driving vehicle to park.6.如权利要求5所述的装置，其特征在于，所述获取所述智能驾驶车辆所处泊车环境中，各个移动目标各自的目标位移信息，所述获取模块具体用于：6. The device according to claim 5, wherein the acquiring the respective target displacement information of each moving target in the parking environment where the intelligent driving vehicle is located, the acquiring module is specifically used for:获取所述泊车环境中，至少一个障碍物体各自的感知信息，其中，每个感知信息至少包括：针对一个障碍物体采集到的感知图像；Acquiring respective perception information of at least one obstacle object in the parking environment, wherein each perception information at least includes: a perception image collected for one obstacle object;分别对获得的各个感知信息进行特征提取，获得所述至少一个障碍物体各自的感知特征，其中，每个感知特征用于表征相应障碍物体的物体属性；Respectively perform feature extraction on the acquired perceptual information to obtain the respective perceptual features of the at least one obstacle object, wherein each perceptual feature is used to represent the object attribute of the corresponding obstacle object;将所述至少一个障碍物体中，相应感知特征满足预设条件的各个障碍物体，分别作为所述泊车环境对应的移动目标，并对各个移动目标进行跟踪，获得所述各个移动目标各自的目标位移信息。In the at least one obstacle object, each obstacle object whose corresponding perception characteristic satisfies the preset condition is regarded as the moving target corresponding to the parking environment, and each moving target is tracked to obtain the respective target of each moving target. displacement information.7.如权利要求5或6所述的装置，其特征在于，所述基于对应于所述泊车环境设定的移动规则以及移动模型，对各个所述目标位移信息进行分析，获得所述各个移动目标各自的目标预测轨迹，所述预测模块具体用于：7. The device according to claim 5 or 6, wherein the target displacement information is analyzed based on a movement rule and a movement model set corresponding to the parking environment to obtain the respective target displacement information. The respective target prediction trajectories of the moving targets, and the prediction module is specifically used for:获取所述泊车环境对应的环境路况，其中，所述环境路况中至少包括：所述泊车环境的道路损坏情况；Acquiring environmental road conditions corresponding to the parking environment, wherein the environmental road conditions at least include: road damage conditions of the parking environment;基于对应于所述泊车环境设定的移动规则，对所述环境路况进行分析，获得所述泊车环境中，所述各个移动目标各自对应的目标可行路段；Analyzing the environmental road conditions based on the movement rules set corresponding to the parking environment, and obtaining target feasible road sections corresponding to the respective moving targets in the parking environment;基于对应于所述泊车环境设定的移动模型，在各个所述目标可行路段中，分别对所述各个移动目标各自的目标位移信息进行分析，获得所述各个移动目标各自的目标预测轨迹。Based on the movement model set corresponding to the parking environment, in each of the target feasible sections, the respective target displacement information of the respective moving targets is analyzed to obtain the respective target predicted trajectories of the respective moving targets.8.如权利要求5或6所述的装置，其特征在于，所述基于预设的评价模型，对各个所述目标预测轨迹进行分析，并基于分析结果，生成针对所述智能驾驶车辆的控制指令，所述评价模块具体用于：8. The device according to claim 5 or 6, wherein, based on a preset evaluation model, each of the target predicted trajectories is analyzed, and based on the analysis results, a control for the intelligent driving vehicle is generated instruction, the evaluation module is specifically used for:基于预设的评价模型，分别对各个所述目标预测轨迹进行分析，获得针对所述各个移动目标各自确定的风险评级；Based on a preset evaluation model, analyze each of the target predicted trajectories, and obtain a risk rating determined for each of the moving targets;从预设的控制策略集合中，分别获得各个所述风险评级各自关联的风险控制策略，并基于获得的各个风险控制策略，生成针对所述智能驾驶车辆的控制指令。From the preset control strategy set, respective risk control strategies associated with each of the risk ratings are obtained, and based on the obtained risk control strategies, a control instruction for the intelligent driving vehicle is generated.9.一种电子设备，包括存储器，处理器及存储在存储器上并可在处理器运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1-4中任一项所述的代客泊车方法。9. An electronic device comprising a memory, a processor and a computer program that is stored on the memory and can run on the processor, wherein the processor implements any one of claims 1-4 when the processor executes the computer program. A method of valet parking as described.10.一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1-4中任一所述方法的步骤。10. A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1-4 are implemented.

Images