Vehicle control method and device, vehicle and storage medium
By acquiring images of the relative positions of the vehicle and the target parking space, collision information is determined and control strategies are formulated, thus solving the problem of accurate alignment between the vehicle and the target parking space and avoiding collisions in automatic parking, thereby improving the accuracy and efficiency of automatic parking.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- XIAOMI EV TECH CO LTD
- Filing Date
- 2024-10-29
- Publication Date
- 2026-05-01
AI Technical Summary
During automatic parking, existing technologies struggle to improve the accuracy of 3D parking space perception while ensuring accurate alignment between the vehicle and the target parking space and avoiding collisions, especially given the decrease in accuracy caused by changes in camera position and angle after the vehicle has been in use for an extended period.
By acquiring images of the vehicle's surroundings that meet preset conditions based on the relative position of the vehicle and the target parking space, collision information is determined, and a vehicle control strategy is formulated based on the collision information to control the vehicle to park in the target parking space, including real-time monitoring and adjustment of the vehicle's position to avoid collisions.
It enables real-time determination of the relative position of the vehicle and the target parking space during automatic parking, improving the accuracy and efficiency of automatic parking and ensuring that the vehicle is accurately parked in the target parking space without scratches.
Smart Images
Figure CN121947466A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of autonomous driving technology, and in particular to a vehicle control method, device, vehicle, and storage medium. Background Technology
[0002] With the increasing popularity of automatic parking technology, people have higher and higher demands for the precision of automatic parking. For example, for parking spaces with obstacles at the edges (such as mechanical parking spaces), it is necessary to ensure that the vehicle is perfectly parked in the space and avoid vehicle scratches.
[0003] In related technologies, improving the accuracy of 3D parking space perception can enhance the accuracy of automatic parking. However, while improving the accuracy of 3D parking space perception, the requirements for the external parameters of camera calibration are also very high. But the tooling of actual production vehicles may be inconsistent, and the position and angle of the camera may also change after the vehicle has been used for a long time, which may seriously affect the accuracy of 3D parking space perception.
[0004] Therefore, how to accurately control the vehicle during automatic parking has become a key research direction. Summary of the Invention
[0005] To overcome the problems existing in related technologies, this disclosure provides a vehicle control method, device, vehicle, and storage medium.
[0006] According to a first aspect of the present disclosure, a vehicle control method is provided, including vehicle control...
[0007] If the relative position of the vehicle and the target parking space meets the preset conditions, acquire the vehicle's perimeter image at the current moment;
[0008] Based on the vehicle perimeter image, determine the collision information corresponding to the case where the vehicle parks in the target parking space based on the current driving direction;
[0009] Based on the collision information, a vehicle control strategy is determined;
[0010] Based on the vehicle control strategy, the vehicle is controlled to park in the target parking space.
[0011] According to a second aspect of the present disclosure, a vehicle control device is provided, comprising:
[0012] The acquisition module is used to acquire the vehicle's perimeter image at the current moment when the relative position of the vehicle and the target parking space meets preset conditions.
[0013] The first determining module is used to determine the collision information corresponding to the case where the vehicle parks in the target parking space based on the vehicle perimeter image;
[0014] The second determining module is used to determine a vehicle control strategy based on the collision information;
[0015] The control module is used to control the vehicle to park in the target parking space based on the vehicle control strategy.
[0016] According to a third aspect of the present disclosure, a vehicle is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: implement the steps of the vehicle control method as proposed in the first aspect of the present disclosure.
[0017] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein when instructions in the storage medium are executed by a processor of a mobile terminal, the steps of the vehicle control method as proposed in the first aspect of the present disclosure are implemented.
[0018] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects:
[0019] In this embodiment, when the relative position of the vehicle and the target parking space meets preset conditions, a vehicle perimeter image is acquired at the current moment. Then, based on the vehicle perimeter image, collision information is determined when the vehicle parks in the target parking space according to its current driving direction. Based on the collision information, a vehicle control strategy is determined, and finally, based on the vehicle control strategy, the vehicle is controlled to park in the target parking space. Therefore, during automatic parking, the relative position of the vehicle and the target parking space can be determined in real time. When the relative position meets preset conditions, collision detection is further performed based on the vehicle perimeter image. Based on the collision detection results, different control strategies are used to control the vehicle to park in the target parking space, thereby accurately controlling the vehicle to park in the target parking space during automatic parking and improving the accuracy of automatic parking.
[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0021] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure:
[0022] Figure 1 This is a schematic flowchart illustrating a vehicle control method according to some embodiments of this disclosure;
[0023] Figure 2 This is a schematic flowchart illustrating a vehicle control method according to some embodiments of this disclosure;
[0024] Figure 3 This is a schematic diagram of the structure of a vehicle control device according to some embodiments of this disclosure;
[0025] Figure 4 This is a functional block diagram of a vehicle illustrating an exemplary embodiment. Detailed Implementation
[0026] Some embodiments of this disclosure will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. Various changes, modifications, and equivalents of the methods, apparatus, and / or systems described herein will become apparent upon understanding this disclosure. For example, the order of operations described herein is merely illustrative and is not limited to those orders set forth herein, but can be changed as will become apparent upon understanding this disclosure, except for operations that must be performed in a particular order. Furthermore, for clarity and brevity, descriptions of features known in the art may be omitted.
[0027] The embodiments described in the following examples of this disclosure are not representative of all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.
[0028] Figure 1 This is a flowchart illustrating a vehicle control method according to some embodiments of the present disclosure, such as... Figure 1 As shown, it includes the following steps:
[0029] Step 101: If the relative position of the vehicle and the target parking space meets the preset conditions, obtain the vehicle's perimeter image at the current moment.
[0030] Among them, the vehicles can be autonomous vehicles, semi-autonomous vehicles, or other vehicles with automatic parking functions.
[0031] The target parking space can be the parking space where the vehicle is to be parked. In some embodiments, the target parking space can be selected by the driver of the vehicle, or it can be selected by the vehicle itself. This disclosure does not limit this.
[0032] In some embodiments, during the automatic parking process, the relative position of the vehicle and the target parking space can be monitored in real time to see if the preset conditions are met.
[0033] In some embodiments, when the vehicle is located outside the target parking space and the angle between the vehicle's driving direction and the long side of the target parking space is less than an angle threshold, the relative position between the vehicle and the target parking space is determined to meet a preset condition.
[0034] The vehicle's direction of travel can be the direction in which the vehicle is pointing towards the front of the vehicle.
[0035] The angle threshold can be 2°, 3°, etc. This disclosure does not limit it.
[0036] Among them, the vehicle perimeter image can be an image of the environment around the vehicle captured by the image sensors in the vehicle. The vehicle perimeter image may include the target storage location.
[0037] In some embodiments, the vehicle perimeter image may be acquired by an image sensor deployed at the rear of the vehicle. Alternatively, it may be acquired by an image sensor deployed at both the rear and sides of the vehicle. This disclosure does not limit the scope of the image acquisition.
[0038] Step 102: Based on the vehicle perimeter image, determine the collision information corresponding to the vehicle parking in the target parking space based on the current driving direction.
[0039] In some embodiments, collision information may include whether a vehicle has been involved in a collision or not. A collision may be a first side impact or a second side impact. The first side impact and the second side impact refer to the left and right sides of the vehicle, respectively.
[0040] Among these conditions, if no collision occurs, the vehicle can be parked in the target parking space in its current driving direction without crossing the edge line of the target parking space.
[0041] Among them, the first side collision of the vehicle can be caused by the vehicle entering the target parking space in the current driving direction, and the first side of the vehicle will press against the edge line of the target parking space, and may scrape against the obstacles on the side of the target parking space.
[0042] Among them, a collision on both sides of the vehicle can occur when the vehicle is parking in the target parking space in its current direction of travel. The second side of the vehicle will cross the edge line of the target parking space and may scrape against obstacles on the side of the target parking space.
[0043] In some embodiments, a mapping relationship between sample vehicle perimeter images and collision labels can be pre-built, and then collision information corresponding to the vehicle perimeter image at the current time can be queried based on the pre-built mapping relationship.
[0044] In some embodiments, vehicle perimeter images are input into a collision detection model to obtain collision information; wherein, the collision detection model is trained and generated based on sample vehicle perimeter images and corresponding collision labels.
[0045] Among them, the sample vehicle perimeter image can be the vehicle perimeter image collected by the image sensor in the sample vehicle when the relative position of the sample vehicle and the sample storage location meets the preset conditions.
[0046] Among them, the collision label can be the collision information corresponding to the sample vehicle obtained in the experiment when it is parked in the sample parking space based on the driving direction when the preset conditions are met.
[0047] In some embodiments, a classification model can be trained based on sample vehicle perimeter images and corresponding collision labels to obtain a collision detection model.
[0048] In some embodiments, the classification model can be a fully connected neural network (F-CNN), a convolutional neural network (CNN), a recurrent neural network (RNN), etc. This disclosure does not limit it.
[0049] Step 103: Determine the vehicle control strategy based on the collision information.
[0050] In some embodiments, when the collision information indicates no collision, the vehicle control strategy can be to control the vehicle to park in the target parking space in the current driving direction.
[0051] In some embodiments, when collision information indicates a collision, the vehicle control strategy can be as follows: control the vehicle to move away from the target parking space and replan the path to park in the target parking space. During the process of parking in the target parking space based on the new path, monitor in real time whether the relative position between the vehicle and the target parking space meets preset conditions. If the preset conditions are met, reacquire the vehicle's perimeter image at the current moment and determine the collision information corresponding to the vehicle parking in the target parking space based on the current driving direction. If the collision information still indicates a collision, control the vehicle to move away from the target parking space again until the collision information indicates no collision, and then control the vehicle to park in the target parking space in the current driving direction. This ensures that the vehicle does not cross the edge line of the target parking space when parking, avoiding scratches.
[0052] Step 104: Based on the vehicle control strategy, control the vehicle to park in the target parking space.
[0053] In some embodiments, if the collision information indicates no collision, the vehicle is controlled to park in the target parking space in the current driving direction.
[0054] In some embodiments, when the collision information indicates a collision, the vehicle is controlled to move away from the target parking space and a new path is planned to park in the target parking space. During the process of parking in the target parking space based on the new path, the relative position between the vehicle and the target parking space is monitored in real time to see if it meets the preset conditions. If the preset conditions are met, the vehicle's perimeter image at the current moment is reacquired, and the collision information corresponding to the vehicle parking in the target parking space based on the current driving direction is determined. If the collision information still indicates a collision, the vehicle is controlled to move away from the target parking space again until the collision information indicates no collision, and then the vehicle is controlled to park in the target parking space in the current driving direction.
[0055] In this embodiment, when the relative position between the vehicle and the target parking space meets preset conditions, a vehicle perimeter image is acquired at the current moment. Then, based on the perimeter image, collision information is determined when the vehicle parks in the target parking space according to its current driving direction. Based on the collision information, a vehicle control strategy is determined, and finally, based on the vehicle control strategy, the vehicle is controlled to park in the target parking space. Therefore, during automatic parking, the relative position between the vehicle and the target parking space can be determined in real time. If the relative position meets preset conditions, collision detection is further performed based on the perimeter image. Based on the collision detection results, different control strategies are used to control the vehicle to park in the target parking space, thereby accurately controlling the vehicle to park in the target parking space during automatic parking and improving the accuracy of automatic parking.
[0056] Figure 2 This is a flowchart illustrating a vehicle control method according to some embodiments of the present disclosure, such as... Figure 2 As shown, it includes the following steps:
[0057] Step 201: If the relative position of the vehicle and the target parking space meets the preset conditions, obtain the vehicle's perimeter image at the current moment.
[0058] Step 202: Based on the vehicle perimeter image, determine the collision information corresponding to the vehicle parking in the target parking space based on the current driving direction.
[0059] The specific implementation of steps 201 to 202 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.
[0060] Step 203: If the collision information is a first side collision or a second side collision, determine the target position based on the vehicle's initial position and collision information at the current moment.
[0061] In some embodiments, when the collision information indicates a collision with the first side of the vehicle, the initial position is moved a first distance in a first direction to obtain a target position, wherein the first direction is perpendicular to the vehicle's driving direction and points towards the second side of the vehicle.
[0062] It should be noted that if a collision occurs on the first side of the vehicle, it means that the first side of the vehicle is closer to the target parking space than the second side of the vehicle. Therefore, the first side of the vehicle needs to be moved away from the target parking space to avoid a collision.
[0063] In some embodiments, when the collision information indicates a collision with the second side of the vehicle, the initial position is moved a first distance in a second direction to obtain the target position, wherein the second direction is perpendicular to the vehicle's driving direction and points towards the first side of the vehicle.
[0064] It should be noted that if a collision occurs on the second side of the vehicle, it means that the second side of the vehicle is closer to the target parking space than the first side. Therefore, the second side of the vehicle needs to be moved away from the target parking space to avoid a collision.
[0065] In some embodiments, the first distance can be a fixed value, such as 3 centimeters, 2 centimeters, etc.
[0066] Step 204: Control the vehicle to drive to the target location, and return to perform the operation of determining collision information until the collision information is non-collision. Then, control the vehicle to park in the target parking space in the current driving direction. When the vehicle is at the target location, the relative position between the vehicle and the target parking space meets the preset conditions.
[0067] In some embodiments, the path of the vehicle to the target location can be replanned based on a path planning method, using the relative position of the vehicle to the target storage location when it is at the target location as a constraint. For example, the vehicle can first be controlled to travel 10 meters away from the target storage location. Then, based on the constraint that the relative position of the vehicle to the target storage location when it is at the target location meets a preset condition, the path of the vehicle to the target location can be replanned, and the vehicle can be controlled to travel to the target location, ensuring that the relative position of the vehicle to the target storage location when it is at the target location meets the preset condition.
[0068] In some embodiments, a first distance is determined based on the number of collision information points, wherein the number of collision information points is negatively correlated with the first distance. Therefore, during vehicle positioning, the distance decreases as the vehicle is moved, allowing for faster parking of the vehicle in the target parking space without collision.
[0069] In some embodiments, the first distance corresponding to the (i+1)th iteration is half the second distance corresponding to the i-th iteration.
[0070] For example, if the relative position of the vehicle and the target parking space meets preset conditions, the vehicle's perimeter image at the current moment is acquired; based on the perimeter image, collision information is determined for the first time; if the first determined collision information is a first side collision, the current initial position is moved 10 centimeters in the first direction to obtain the first determined target position; the vehicle is controlled to drive to the first determined target position, and collision information is determined for the second time; if the second determined collision information is a second side collision, the first determined target position is moved 5 centimeters in the second direction to obtain the second determined target position; the vehicle is controlled to drive to the second determined target position, and when collision information is determined for the third time, if the third determined collision information is a first side collision, the second determined target position is moved 2.5 centimeters in the second direction to obtain the third determined target position, until the collision information is confirmed as a collision.
[0071] In this embodiment, when the relative position of the vehicle and the target parking space meets preset conditions, a vehicle perimeter image is acquired at the current moment. Based on the perimeter image, collision information is determined when the vehicle parks in the target parking space based on its current driving direction. If the collision information indicates a first-side collision or a second-side collision, a target position is determined based on the vehicle's initial position and the collision information at the current moment. The vehicle is then controlled to drive to the target position and returns to execute the collision information determination operation until the collision information indicates no collision. At this point, the vehicle is controlled to park in the target parking space in its current driving direction. When the vehicle is at the target position, its relative position to the target parking space meets preset conditions. Therefore, even when the collision information indicates no collision, the vehicle's position can be adjusted based on the collision location to ensure that the collision information corresponding to the adjusted position is no collision. This improves the accuracy of automatic parking while maintaining its efficiency.
[0072] To implement the above embodiments, this disclosure also proposes a vehicle control device.
[0073] Figure 3 This is a block diagram of a vehicle control device illustrated according to some embodiments of this disclosure. (Refer to...) Figure 3 The device includes:
[0074] The acquisition module 301 is used to acquire the vehicle perimeter image at the current moment when the relative position of the vehicle and the target storage location meets the preset conditions.
[0075] The first determining module 302 is used to determine the collision information corresponding to the case where the vehicle parks in the target parking space based on the vehicle perimeter image;
[0076] The second determining module 303 is used to determine the vehicle control strategy based on the collision information;
[0077] The control module 304 is used to control the vehicle to park in the target parking space based on the vehicle control strategy.
[0078] In some embodiments, the control module 304 is configured to:
[0079] In cases where the collision information indicates a first-side collision or a second-side collision, the target location is determined based on the vehicle's initial position and the collision information at the current moment.
[0080] Control the vehicle to drive to the target location, and return to perform the operation of determining collision information until the collision information is non-collision. Then control the vehicle to park in the target parking space in the current driving direction. When the vehicle is at the target location, the relative position between the vehicle and the target parking space meets the preset conditions.
[0081] In some embodiments, the control module 304 is configured to:
[0082] In the case of a collision with the vehicle's first side, the initial position is moved a first distance in a first direction to obtain the target position, where the first direction is perpendicular to the vehicle's direction of travel and points towards the vehicle's second side; or...
[0083] In the case of a collision with the second side of the vehicle, the initial position is moved a first distance in the second direction to obtain the target position, wherein the second direction is perpendicular to the vehicle's driving direction and points towards the first side of the vehicle.
[0084] In some embodiments, a third determining module is further included, configured to:
[0085] The first distance is determined based on the number of collisions identified, and the number of collisions is negatively correlated with the first distance.
[0086] In some embodiments, the control module 304 is configured to:
[0087] If the collision information indicates no collision, control the vehicle to park in the target parking space in the current driving direction.
[0088] In some embodiments, the first determining module 302 is configured to:
[0089] The vehicle perimeter image is input into the collision detection model to obtain collision information; the collision detection model is generated by training based on the sample vehicle perimeter image and the corresponding collision label.
[0090] In some embodiments, a fourth determining module is further included, configured to:
[0091] If the vehicle is located outside the target storage space and the angle between the vehicle's driving direction and the long side of the target storage space is less than the angle threshold, the relative position of the vehicle and the target storage space is determined to meet the preset conditions.
[0092] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0093] The vehicle control device of this embodiment acquires a vehicle perimeter image at the current moment when the relative position between the vehicle and the target parking space meets preset conditions. Then, based on the perimeter image, it determines the collision information corresponding to the vehicle parking in the target parking space based on its current driving direction. Based on the collision information, it determines a vehicle control strategy and finally controls the vehicle to park in the target parking space based on the vehicle control strategy. Therefore, during automatic parking, the relative position between the vehicle and the target parking space can be determined in real time. If the relative position meets preset conditions, collision detection is further performed based on the perimeter image. Based on the collision detection results, different control strategies are used to control the vehicle to park in the target parking space, thereby accurately controlling the vehicle to park in the target parking space during automatic parking and improving the accuracy of automatic parking.
[0094] Figure 4 This is a block diagram illustrating a vehicle 400 according to an exemplary embodiment. For example, vehicle 400 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicle. Vehicle 400 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.
[0095] Reference Figure 4 The vehicle 400 may include various subsystems, such as an infotainment system 410, a perception system 420, a decision control system 430, a drive system 440, and a computing platform 450. The vehicle 400 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and component of the vehicle 400 can be interconnected via wired or wireless means.
[0096] In some embodiments, the infotainment system 410 may include a communication system, an entertainment system, and a navigation system, etc. The perception system 420 may include several sensors for sensing information about the environment surrounding the vehicle 400. For example, the perception system 420 may include a global positioning system (which may be GPS, BeiDou, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.
[0097] The decision control system 430 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system. The drive system 440 may include components that provide power to the vehicle 400. In one embodiment, the drive system 440 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.
[0098] Some or all of the functions of the vehicle 400 are controlled by a computing platform 450. The computing platform 450 may include at least one processor 451 and a memory 452, the processor 451 being able to execute instructions 453 stored in the memory 452.
[0099] Processor 451 can be any conventional processor, such as a commercially available CPU. The processor may also include, for example, a Graphics Processing Unit (GPU), a Field Programmable Gate Array (FPGA), a System on Chip (SOC), an Application Specific Integrated Circuit (ASIC), or a combination thereof.
[0100] The memory 452 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.
[0101] In addition to instruction 453, memory 452 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 452 can be used by computing platform 450. In this embodiment of the present disclosure, processor 451 can execute instruction 453 to complete all or part of the steps of the above-described vehicle control method.
[0102] This disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the vehicle control method provided in this disclosure.
[0103] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims are generally understood to mean “one or more.”
[0104] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding the specification and drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although specific features of this disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term “including.”
[0105] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.
[0106] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. A vehicle control method, characterized in that, include: If the relative position of the vehicle and the target parking space meets the preset conditions, acquire the vehicle's perimeter image at the current moment; Based on the vehicle perimeter image, determine the collision information corresponding to the case where the vehicle parks in the target parking space based on the current driving direction; Based on the collision information, a vehicle control strategy is determined; Based on the vehicle control strategy, the vehicle is controlled to park in the target parking space.
2. The method according to claim 1, characterized in that, The step of controlling the vehicle to park in the target parking space based on the vehicle control strategy includes: In the case where the collision information is a first side collision or a second side collision of the vehicle, the target position is determined based on the vehicle's initial position at the current moment and the collision information; The vehicle is controlled to drive to the target location, and then returns to perform the operation of determining collision information until the collision information is non-collision. Then, the vehicle is controlled to park in the target parking space in the current driving direction, wherein the relative position of the vehicle and the target parking space at the target location meets the preset conditions.
3. The method according to claim 2, characterized in that, Determining the target location based on the vehicle's initial position at the current moment and the collision information includes: In the case where the collision information indicates a collision with the first side of the vehicle, the initial position is moved a first distance in a first direction to obtain the target position, wherein the first direction is perpendicular to the vehicle's direction of travel and points towards the second side of the vehicle; or... In the case where the collision information indicates a collision with the second side of the vehicle, the initial position is moved a first distance in a second direction to obtain the target position, wherein the second direction is perpendicular to the vehicle's driving direction and points towards the first side of the vehicle.
4. The method according to claim 3, characterized in that, The method further includes: The first distance is determined based on the number of times the collision information is determined, wherein the number of times the collision information is determined is negatively correlated with the first distance.
5. The method according to claim 1, characterized in that, The step of controlling the vehicle to park in the target parking space based on the vehicle control strategy includes: If the collision information indicates no collision, control the vehicle to park in the target parking space in the current driving direction.
6. The method according to claim 1, characterized in that, The step of determining the collision information corresponding to the situation where the vehicle parks in the target parking space based on the vehicle perimeter image includes: The vehicle perimeter image is input into the collision detection model to obtain the collision information; wherein, the collision detection model is trained and generated based on the sample vehicle perimeter image and the corresponding collision label.
7. The method according to claim 1, characterized in that, The method further includes: If the vehicle is located outside the target storage location and the angle between the vehicle's driving direction and the long side of the target storage location is less than an angle threshold, the relative position of the vehicle and the target storage location is determined to meet the preset conditions.
8. A vehicle control method apparatus, characterized in that, The device includes: The acquisition module is used to acquire the vehicle's perimeter image at the current moment when the relative position of the vehicle and the target parking space meets preset conditions. The first determining module is used to determine the collision information corresponding to the case where the vehicle parks in the target parking space based on the vehicle perimeter image; The second determining module is used to determine a vehicle control strategy based on the collision information; The control module is used to control the vehicle to park in the target parking space based on the vehicle control strategy.
9. A vehicle, characterized in that, include: processor; A memory for storing processor-executable instructions; wherein the processor is configured to implement the steps of the method according to any one of claims 1-7.
10. A non-transitory computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of a mobile terminal, implement the steps of the method according to any one of claims 1-7.