Automatic parking method and device, electronic equipment and computer readable storage medium

Abstract

The application relates to the Internet of Vehicles technology field and provides an automatic parking method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: when it is determined that an automatic parking mode of a vehicle is started, a data packet is requested from a cloud platform, the data packet comprises a parking neural network model which is updated based on historical parking data recorded according to a driver parking operation; the current environment image, the current distance set and the current position of the vehicle are continuously acquired and input to the current parking neural network model, so that the output signal of the parking neural network model is used to control the vehicle to perform an automatic parking operation. The automatic parking method provided by the application can perform an automatic parking operation simulating the driver parking operation according to the parking neural network model which is updated based on the historical parking data recorded according to the driver parking operation, the current position, the current environment image and the current distance set, so that the automatic parking operation is closer to the driver parking operation, and a more intelligent automatic parking mode is provided for the driver.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet of Vehicles, and particularly to an automatic parking method and device, an electronic device, and a computer readable storage medium. BACKGROUND

[0002] In the prior art, an automatic parking model is a standardized artificial intelligence trained by a vehicle manufacturer. However, the automatic parking mode corresponding to the automatic parking model trained in this way lacks a certain accuracy and is too mechanical in actual application. The driver needs to pay attention to the automatic parking process in the case that the automatic parking mode is turned on, so as to avoid the mechanical automatic parking mode from causing inconvenience to the driver due to not considering the scene during automatic parking, the parking preference of the driver, and the like. SUMMARY

[0003] Therefore, the embodiments of the present application provide an automatic parking method, device, electronic device, and computer readable storage medium to solve the problem that the automatic parking in the prior art cannot meet the parking preference and scene of the driver.

[0004] In a first aspect, the embodiments of the present application provide an automatic parking method, comprising:

[0005] When it is determined that the automatic parking mode of the vehicle is turned on, a data packet is requested from a cloud platform, and the data packet includes a parking neural network model updated based on historical parking data recorded by the driver parking operation;

[0006] The environment image of the current vehicle, the current distance set, and the current position are continuously acquired, and the distance set includes the closest distance from each obstacle in each direction of the vehicle to the vehicle;

[0007] The current environment image, the current distance set, and the current position are input into the current parking neural network model, so as to control the vehicle to perform automatic parking operation by using the output signal of the parking neural network model.

[0008] In a second aspect, the embodiments of the present application provide an automatic parking device, comprising:

[0009] The request module is configured to request a data packet from a cloud platform when it is determined that the automatic parking mode of the vehicle is turned on, and the data packet includes a parking neural network model updated based on historical parking data recorded by the driver parking operation;

[0010] The acquisition module is configured to continuously acquire the environment image of the current vehicle, the current distance set, and the current position, and the distance set includes the closest distance from each obstacle in each direction of the vehicle to the vehicle;

[0011] The control module is configured to input the current environment image, the current distance set and the current position into the current parking neural network model, so as to control the vehicle to perform the automatic parking operation by using an output signal of the parking neural network model.

[0012] In a third aspect, the embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above method when executing the computer program.

[0013] In a fourth aspect, the embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0014] Compared with the prior art, the embodiment of the present application has the beneficial effects that when it is determined that the automatic parking mode of the vehicle is started, a data packet is requested from a cloud platform, and the data packet includes a parking neural network model updated based on historical parking data recorded by a driver's parking operation; the current environment image, the current distance set and the current position of the vehicle are continuously acquired, and the distance set includes the closest distances from the vehicle to obstacles in each direction of the vehicle; the current environment image, the current distance set and the current position are input into the current parking neural network model, so as to control the vehicle to perform the automatic parking operation by using an output signal of the parking neural network model. The automatic parking method provided by the present application can learn or train according to the driver's parking operation, so that when the automatic parking mode is started, the automatic parking operation simulating the driver's parking operation can be performed by using the parking neural network model updated based on the historical parking data recorded by the driver's parking operation, the current position, the current environment image and the current distance set, so that the automatic parking scene is better combined, the driver's parking operation is closer, and a more intelligent and accurate automatic parking mode is provided for the driver. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0016] Figure 1 is a scene schematic diagram of an application scenario of the embodiment of the present application;

[0017] Figure 2 is an architecture diagram of an automatic parking method provided by the embodiment of the present application;

[0018] Figure 3is a flowchart of an automatic parking method provided by an embodiment of the present application;

[0019] Figure 4 is a schematic diagram of an automatic parking device provided by an embodiment of the present application;

[0020] Figure 5 is a schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0021] In the following description, specific details are set forth in order to provide a thorough understanding of embodiments of the present application. However, persons having ordinary skill in the art will readily understand that embodiments of the present application can be practiced without these specific details, and that the present application is not limited to the embodiments described. In other instances, detailed descriptions of well-known systems, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0022] An automatic parking method and device according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 is a schematic diagram of an application scenario of an embodiment of the present application. The application scenario can include a first terminal device 101, a second terminal device 102, a server 103, and a network 104.

[0024] The first terminal device 101 can be hardware or software. When the first terminal device 101 is hardware, it can be various electronic devices with a display screen and supporting communication with the server 103, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like; when the first terminal device 101 is software, it can be installed in an electronic device as described above. The first terminal device 101 can be implemented as a plurality of software or software modules, or as a single software or software module, and the present application is not limited thereto. Further, the first terminal device 101 can have various applications installed thereon, such as a data processing application, an instant messaging tool, a social platform software, a search application, a shopping application, and the like.

[0025] The second terminal device 102 can be hardware or software. When the second terminal device 102 is hardware, it can be various electronic devices with a display screen and supporting communication with the server 103, including but not limited to a vehicle-mounted computer, a vehicle controller, and the like; when the second terminal device 102 is software, it can be installed in the electronic device as described above. The second terminal device 102 can be implemented as multiple software or software modules, or as a single software or software module, and the embodiments of the present application do not limit this. Further, the second terminal device 102 can have various applications installed thereon, such as a data processing application, an instant messaging tool, a social platform software, a search application, a shopping application, a vehicle control application, and the like.

[0026] The server 103 can be a server that provides various services, for example, a background server that receives a request sent by a terminal device that establishes a communication connection therewith. The background server can receive and analyze the request sent by the terminal device, and generate a processing result. The server 103 can be a single server, a server cluster composed of several servers, or a cloud computing service center, and the embodiments of the present application do not limit this.

[0027] It should be noted that the server 103 can be hardware or software. When the server 103 is hardware, it can be various electronic devices that provide various services for the first terminal device 101 and the second terminal device 102. When the server 103 is software, it can be multiple software or software modules that provide various services for the first terminal device 101 and the second terminal device 102, or a single software or software module that provides various services for the first terminal device 101 and the second terminal device 102, and the embodiments of the present application do not limit this.

[0028] The network 104 can be a wired network connected by coaxial cables, twisted pairs, and optical fibers, or a wireless network that can realize interconnection of various communication devices without wiring, for example, Bluetooth, Near Field Communication (NFC), Infrared, and the like, and the embodiments of the present application do not limit this.

[0029] It should be noted that the specific types, quantities, and combinations of the first terminal device 101, the second terminal device 102, the server 103, and the network 104 can be adjusted according to the actual needs of the application scenario, and the embodiments of the present application do not limit this.

[0030] Figure 2 is an architecture diagram of an automatic parking method provided by an embodiment of the present application, as shown in Figure 2As shown, the vehicle control system includes a vehicle controller, a cloud platform, a parking data recording device, a parking data acquisition device and a control device. The vehicle controller controls the vehicle to perform automatic parking operation corresponding to the automatic parking mode. The parking data recording device includes a driving path recording device, a steering wheel angle calculation and steering recording device and a vehicle control recording device. The parking data acquisition device and the control device include a vehicle control device, a networking device, an image acquisition sensor, an ultrasonic radar sensor and a positioning device (such as Beidou system, global positioning system, etc.).

[0031] The parking data acquisition device and the control device acquire the related parking data of the vehicle, and transmit the data to the parking data recording device for recording. When a parking is completed, the parking data recording device uploads all the parking data recorded during the parking to the cloud platform. The cloud platform processes the parking data, and when the vehicle controller requests the related parking data from the cloud platform, the cloud platform sends the parking data to the vehicle controller.

[0032] Figure 3 is a flowchart of an automatic parking method provided by an embodiment of the present application. As shown in Figure 3 , the automatic parking method includes the following steps:

[0033] S301, when it is determined that the automatic parking mode of the vehicle is started, a data packet is requested from the cloud platform, and the data packet includes a parking neural network model updated based on historical parking data recorded according to driver parking operation;

[0034] S302, continuously acquiring an environment image of the current vehicle, a current distance set and a current position;

[0035] S303, inputting the current environment image, the current distance set and the current position into the current parking neural network model, so as to control the vehicle to perform automatic parking operation by using the output signal of the parking neural network model.

[0036] The distance set includes the nearest distance from the vehicle to each obstacle in each direction of the vehicle.

[0037] Figure 3 The automatic parking method can be executed by the second terminal device 102. Figure 1

[0038] In some embodiments, when the vehicle is in the automatic parking mode, i.e. the automatic parking mode of the vehicle is started, a data packet is requested from the cloud platform, and the data packet includes a parking neural network model updated according to historical parking data recorded according to driver parking operation.

[0039] ​When the vehicle starts the automatic parking mode, the image acquisition sensor is controlled to continuously acquire the environment image of the vehicle, the ultrasonic radar sensor is controlled to continuously acquire the distance set of the vehicle, and the positioning device is controlled to continuously acquire the position of the vehicle, wherein the distance set includes the closest distance from the vehicle to each obstacle in each direction of the vehicle.

[0040] The current environment image, the current distance set and the current position are input into the parking neural network model issued according to the starting of the automatic parking mode, to obtain an output signal of the parking neural network model, and the vehicle is controlled to perform the automatic parking operation according to the output signal. It can be understood that the action of inputting the current environment image, the current distance set and the current position into the parking neural network model is continuous, and the output signal will also be continuously output.

[0041] According to the technical scheme provided in the embodiments of the present application, the automatic parking can be performed in combination with the current environment image, the distance set and the position of the vehicle, so that the automatic parking operation and the route of the automatic parking are more in line with the needs of the user, and the safety and trust of the user when using the automatic parking mode are improved.

[0042] In some embodiments, the process of updating the parking neural network model based on the historical parking data recorded by the driver parking operation includes:

[0043] receiving a training start instruction;

[0044] Based on the training start instruction, the historical parking data of the vehicle in the training automatic parking state is continuously recorded at a preset period until the training stop instruction is received, and the historical parking data includes the position, the driving path, the steering wheel angle and the steering, the motion state, the environment image and the distance set of the vehicle.

[0045] All the recorded historical parking data is uploaded to the cloud platform, and the historical parking data is used to update the parking neural network model.

[0046] The training start instruction can be a training start instruction sent by the driver through the function control interface of the vehicle, or a training start instruction sent by the driver through the terminal device. When it is determined that the vehicle is in the training automatic parking state and the training start instruction is received, the historical parking data of the vehicle is continuously recorded at a preset period until the training stop instruction is received.

[0047] The historical parking data includes the position, the driving path, the steering wheel angle and the steering, the motion state, the environment image and the distance set of the vehicle. The motion state includes the motion state of the accelerator, the brake, the hand brake / electronic brake and other devices that control the motion state of the vehicle to change.

[0048] The position of the vehicle is continuously acquired by a positioning device, the driving path is continuously recorded by a driving path recording device, the steering wheel angle and the steering are recorded by a steering wheel angle calculation and steering recording device, the motion state is acquired by a vehicle control device and recorded by a vehicle control recording device, the environment image is acquired by an image acquisition sensor, and the distance set is acquired by an ultrasonic radar sensor.

[0049] The preset period is a time period divided according to a preset time interval, for example, 1 second can be set as a period, and the time point when the training start instruction is received and the vehicle is in the automatic parking state is taken as an initial period. The historical parking data of the current driver performing automatic parking operation is recorded every 1 second, until the training stop instruction is received. The historical parking data recorded according to each preset period is uploaded to the cloud platform, so as to update the parking neural network model by using the historical parking data.

[0050] In an example embodiment of the present application, the driver sends a training start instruction by starting a button, and the vehicle is in an automatic parking state. An example is described as follows:

[0051] When the training start instruction is received, the driving path recording device is controlled to acquire and record the vehicle trajectory Z0, the positioning device (such as Beidou system, global positioning system, etc.) acquires the current position L0 of the vehicle, the image acquisition sensor acquires the images P0 of the objects around the vehicle, the ultrasonic radar analyzes the closest distances between the obstacles in each direction and the vehicle to obtain the distance set A0, wherein the distance set A0 includes the closest distances between the obstacles in each direction and the vehicle. The above data and the data recorded by the vehicle control recording device and the data recorded by the steering wheel angle calculation and steering recording device are taken as the starting data corresponding to the starting point in the historical parking data, that is, the historical parking data of the t0 period.

[0052] According to the preset period, the historical parking data corresponding to each preset period is recorded, which is recorded as the historical parking data of the t1, t2, …… tn periods. When the training stop instruction is received, the historical parking data corresponding to the time when the training stop instruction is received is recorded as the historical parking data of the tk period, and the tk period is after the tn period. The historical parking data from the t0 period to the tk period is uploaded to the cloud platform. When the parking neural network model of the cloud platform is updated, the driver is prompted that the automatic parking learning of the vehicle in the position and the scene has been completed.

[0053] According to the technical scheme provided in the embodiments of the present application, the data of the driver performing parking operation can be recorded to update the parking neural network model, so that the automatic parking by the parking neural network model can be more in line with the parking habits of the driver, and the intelligence of the parking neural network model is improved.

[0054] In some embodiments, further comprising:

[0055] The verification data is determined based on historical parking data, and the verification data includes a position, an environmental image and a distance set in the historical parking data recorded in each preset period;

[0056] The verification data is uploaded to a cloud platform, and the cloud platform is requested to update the verification data based on multiple historical parking data;

[0057] The verification data further includes a position, an environmental image and a distance set corresponding to a first inclination and a first return of a steering wheel of the vehicle in the historical parking data.

[0058] The verification data is filtered from the historical parking data of t0, t1, t2, …, tn, …, tk periods, and the verification data includes a position, an environmental image and a distance set recorded in each preset period, and further includes a position, an environmental image and a distance set corresponding to a first inclination and a first return of a steering wheel of the vehicle in the historical parking data in the current training automatic parking process. The verification data is uploaded to a cloud platform, and the cloud platform is requested to update the verification data according to multiple uploaded historical parking data, and the data of each point in the verification data is converged to a range threshold, so that the automatic parking can be more intelligent.

[0059] According to the technical scheme provided by the embodiments of the present application, the verification data is updated according to multiple uploaded historical parking data, so that the verification data is more intelligent and more in line with human driving habits, thereby improving the intelligence of the automatic parking method.

[0060] In some embodiments, before determining that the automatic parking mode of the vehicle is started, comprising:

[0061] Continuously acquiring the speed of the current vehicle;

[0062] When it is detected that the current position and the current speed satisfy the starting condition, a prompt information is sent;

[0063] Receiving prompt feedback information of the prompt information, and determining whether to start the automatic parking mode based on the prompt feedback information;

[0064] If yes, the prompt feedback information is taken as a mode starting instruction, and it is determined that the automatic parking mode of the vehicle is started.

[0065] The starting condition includes a position starting condition and a speed starting condition, the position starting condition is that the current position is within a starting position range, and the speed starting condition is that the current speed is less than a preset starting speed, and the starting position range is determined by a starting position recorded in the historical parking data, i.e. the position in the historical parking data recorded in the t0 period.

[0066] When the positioning device detects that the current position of the vehicle is within the starting position range and the speed of the vehicle is less than the preset starting speed, a prompt message is sent to prompt whether to start the automatic parking, and prompt feedback information of the prompt message is received, if the prompt feedback information is to start the automatic parking mode, the prompt feedback information is taken as a mode starting instruction to control the vehicle to start the automatic parking mode, and if the prompt feedback information is not to start the automatic parking mode, the vehicle is kept in the current state.

[0067] When the cloud platform receives historical parking data multiple times, the starting position range can be updated according to the historical parking data multiple times.

[0068] According to the technical scheme provided by the embodiment of the application, when the vehicle meets the starting condition, a prompt message is sent to inquire whether the driver needs automatic parking, so that the automatic parking mode is more intelligent and humanized.

[0069] In some embodiments, the current environment image and the current distance set are input into the current parking neural network model to control the vehicle to perform automatic parking operation by using the output signal of the parking neural network model, including:

[0070] It is judged whether the current environment image, the current distance set and the current position match the verification data;

[0071] If not, it is judged whether there is a risk in the next preset period of performing automatic parking operation according to the parking neural network based on the current distance set;

[0072] If matched, the automatic parking operation is continued according to the parking neural network;

[0073] The step of judging whether the current environment image, the current distance set and the current position match the verification data is repeated until it is detected that the automatic parking operation is completed, and the automatic parking mode is exited.

[0074] The data packet sent by the cloud platform further includes verification data.

[0075] When the vehicle starts the automatic parking mode, the vehicle control device will control the vehicle according to the historical parking data recorded in the preset period, that is, t0, t1, t2, …, tn, …, tk, at the same time, the positioning device is controlled to obtain the current position, the image sensor is controlled to collect the environment image, and the ultrasonic radar is controlled to collect the distance set, which are compared with the verification data to synchronously verify the current environment image, the distance set and the position, and it is judged whether the corresponding data recorded in the preset period matches the parking historical data recorded by the driver, if matched, the next period of automatic parking operation is performed according to the parking neural network model, until the automatic parking operation is completed, the automatic parking mode is exited and the gear position of the vehicle is in the parking gear.

[0076] According to the above example, if the match fails, it is determined whether there is a risk of collision in the next period of performing the automatic parking operation according to the parking neural network model based on the current distance set. If there is a risk, an alarm information is sent and the automatic parking mode is exited. If there is no risk, an automatic parking request is sent and a request feedback information of the automatic parking request is received, and the automatic parking mode is adjusted according to the request feedback information.

[0077] The request feedback information includes a keep mode instruction or an exit mode instruction. The keep mode instruction is used to control the vehicle to keep in the automatic parking mode. The keep mode instruction can be realized by sliding or long-pressing an icon on the central control system of the vehicle or an application program of the terminal device. When the vehicle completes the automatic parking operation, the vehicle is exited from the automatic parking mode and the gear position of the vehicle is set to the parking gear. The exit mode instruction is used to exit the automatic parking mode. The exit mode instruction can be realized by clicking on the central control system of the vehicle or the application program of the terminal device. When it is determined to exit the automatic parking mode, the gear position of the vehicle is set to the parking gear.

[0078] According to the technical scheme provided in the embodiments of the present application, the driver's control can be received in each stage of the automatic parking, and the degree of control of the driver on the automatic parking mode is improved, and the flexibility of the automatic parking mode is also improved.

[0079] In some embodiments, the current environment image, the current distance set and the current position are input into the current parking neural network model, so as to control the vehicle to perform the automatic parking operation by using the output signal of the parking neural network model. The method further includes:

[0080] The current parking data is recorded.

[0081] The current parking data is uploaded to the cloud platform, so as to update the parking neural network model.

[0082] When the vehicle is in the automatic parking state, the current parking data is recorded according to a preset period, and the current parking data is uploaded to the cloud platform as the historical parking data, so as to update the parking neural network model, thereby making the parking neural network model more intelligent.

[0083] In an example embodiment of the present application, the vehicle function control interface displays an option of "whether to record the position". If the driver selects "yes", the position is recorded, and the historical parking data of the vehicle is uploaded to the cloud platform, so as to prompt the user to perform the automatic parking when the vehicle is detected to travel to the position and the corresponding historical parking data condition and the starting condition are met. Subsequently, when the vehicle is detected to travel to the position and to park or to perform the automatic parking, the corresponding historical parking data is uploaded to the data set corresponding to the position stored in the cloud platform, so that the parking neural network model is intelligently learned.

[0084] The automatic parking method provided by the application can be applied to a scene in which a wall or other obstacles exist on the side of the cockpit door, causing the driver to be inconvenient to get off the vehicle. The recording and learning of the driver's parking are completed through the historical parking data recording device and the control device, so that when the driver gets off the vehicle and controls the vehicle to automatically park, the vehicle can simulate the driver to park according to the learning result of the parking neural network model.

[0085] All the optional technical solutions described above can be combined to form optional embodiments of the application, which will not be described one by one here.

[0086] The following is an embodiment of the device of the application, which can be used to execute the method embodiments of the application. For details not disclosed in the device embodiments of the application, please refer to the method embodiments of the application.

[0087] Figure 4 is a schematic diagram of an automatic parking device provided by an embodiment of the application. As shown in Figure 4 The automatic parking device includes a request module 401, an acquisition module 402 and a control module 403.

[0088] The request module 401 is configured to request a data packet from a cloud platform when it is determined that the automatic parking mode of the vehicle is turned on, and the data packet includes a parking neural network model updated based on historical parking data recorded based on a driver's parking operation;

[0089] The acquisition module 402 is configured to continuously acquire a current environment image, a current distance set and a current position, and the distance set includes the closest distances from the vehicle to obstacles in each direction of the vehicle;

[0090] The control module 403 is configured to input the current environment image, the current distance set and the current position into the current parking neural network model, so as to control the vehicle to perform an automatic parking operation by using the output signal of the parking neural network model.

[0091] In some embodiments, the process of updating the parking neural network model based on the historical parking data recorded based on the driver's parking operation includes:

[0092] receiving a training start instruction;

[0093] Based on the training start instruction, continuously record the historical parking data of the vehicle in the training automatic parking state according to a preset period until a training stop instruction is received, and the historical parking data includes the position, driving path, steering wheel angle and steering, motion state, environment image and distance set of the vehicle;

[0094] Upload all the recorded historical parking data to the cloud platform, and update the parking neural network model by using the historical parking data.

[0095] In some embodiments, the request module 401 is further configured to:

[0096] determine the verification data based on the historical parking data, the verification data comprising a position, an environmental image and a distance set in the historical parking data recorded in each preset period;

[0097] upload the verification data to a cloud platform, and request the cloud platform to update the verification data based on multiple historical parking data;

[0098] the verification data further comprises a position, an environmental image and a distance set in the historical parking data corresponding to a first inclination of a steering wheel of the vehicle and a first return to zero.

[0099] In some embodiments, the request module 401 is configured to, before the automatic parking mode of the vehicle is determined to be turned on, be configured to:

[0100] continuously obtain a current speed of the vehicle;

[0101] when it is detected that the current position and the current speed satisfy an opening condition, send a prompt information, the opening condition comprising a position opening condition and a speed opening condition, the position opening condition being that the current position is within an opening position range, the speed opening condition being that the current speed is less than a preset opening speed, and the opening position range being determined by an opening position recorded in the historical parking data;

[0102] accept a prompt feedback information of the prompt information, and determine whether to turn on the automatic parking mode based on the prompt feedback information;

[0103] if yes, take the prompt feedback information as a mode opening instruction, and determine that the automatic parking mode of the vehicle is turned on.

[0104] In some embodiments, the control module 403 is configured to input the current environmental image and the current distance set into the current parking neural network model, so as to control the vehicle to perform the automatic parking operation by using an output signal of the parking neural network model, and the data packet further comprises the verification data, for:

[0105] determining whether the current environmental image, the current distance set and the current position match the verification data;

[0106] if not, determining whether there is a collision risk in the next preset period of performing the automatic parking operation according to the parking neural network based on the current distance set;

[0107] if yes, continue to perform the automatic parking operation according to the parking neural network model;

[0108] repeat the step of determining whether the current environmental image, the current distance set and the current position match the verification data until it is detected that the automatic parking operation has been completed, and the automatic parking mode is exited.

[0109] In some embodiments, the control module 403 is configured to determine, based on the current distance set, whether there is a collision risk in the next preset cycle of performing automatic parking operation according to the parking neural network, for the purpose of:

[0110] If present, an alarm message will be sent and the automatic parking mode will be exited. The alarm message is used to indicate that there is a risk of collision during the automatic parking operation.

[0111] If it does not exist, send an automatic parking request and receive the request feedback information. Adjust the automatic parking mode according to the request feedback information, which includes a hold mode command or an exit mode command.

[0112] In some embodiments, the control module 403 is configured to input the current environmental image, the current distance set, and the current position into the current parking neural network model, so as to control the vehicle to perform automatic parking operations using the output signal of the parking neural network model, and is further configured to:

[0113] Record current parking data;

[0114] The current parking data is uploaded to the cloud platform to update the parking neural network model.

[0115] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0116] Figure 5 This is a schematic diagram of the electronic device 5 provided in an embodiment of this application. Figure 5 As shown, the electronic device 5 of this embodiment includes: a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, it implements the steps in the various method embodiments described above. Alternatively, when the processor 501 executes the computer program 503, it implements the functions of each module / unit in the various device embodiments described above.

[0117] Electronic device 5 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 5 may include, but is not limited to, processor 501 and memory 502. Those skilled in the art will understand that... Figure 5 This is merely an example of electronic device 5 and does not constitute a limitation on electronic device 5. It may include more or fewer components than shown, or different components.

[0118] The processor 501 can be a central processing unit (CPU), or other general purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc.

[0119] The memory 502 can be an internal storage unit of the electronic device 5, for example, a hard disk or a memory of the electronic device 5. The memory 502 can also be an external storage device of the electronic device 5, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 5. The memory 502 can also include both the internal storage unit and the external storage device of the electronic device 5. The memory 502 is used to store computer programs and other programs and data required by the electronic device.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of functional units and modules is taken as an example, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above described functions. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0121] The integrated modules / units, if implemented in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can be executed by a processor to implement the steps of the above-mentioned various method embodiments. The computer program can include computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electric carrier signals and telecommunication signals.

[0122] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. An automatic parking method characterized by, The method comprises the following steps: When it is determined that the automatic parking mode of the vehicle is started, a data packet is requested from a cloud platform, wherein the data packet comprises a parking neural network model updated based on historical parking data recorded by a driver parking operation; Current environmental images of the vehicle, a current distance set and a current position of the vehicle are continuously obtained, wherein the distance set comprises the closest distances from the vehicle to obstacles in each direction of the vehicle; The current environmental images, the current distance set and the current position are input into the current parking neural network model to control the vehicle to perform an automatic parking operation by using output signals of the parking neural network model; The process of updating the parking neural network model based on the historical parking data recorded by the driver parking operation comprises the following steps: A training start instruction is received; Based on the training start instruction, the historical parking data of the vehicle in a training automatic parking state is continuously recorded at a preset period until a training stop instruction is received, wherein the historical parking data comprises the position, driving path, steering wheel angle and steering, motion state, environmental image and distance set of the vehicle; All the recorded historical parking data is uploaded to the cloud platform, and the parking neural network model is updated by using the historical parking data; The method further comprises the following steps: Based on the historical parking data, verification data is determined, wherein the verification data comprises the position, environmental image and distance set in the historical parking data recorded in each preset period, and further comprises the position, environmental image and distance set in the historical parking data corresponding to the first inclination and first return of the steering wheel in the current training automatic parking process; The verification data is uploaded to the cloud platform, and the cloud platform is requested to update the verification data based on multiple historical parking data.

2. The method of claim 1, wherein, Before it is determined that the automatic parking mode of the vehicle is started, the method comprises the following steps: The current speed of the vehicle is continuously obtained; When it is detected that the current position and the current speed satisfy a start condition, a prompt information is sent, wherein the start condition comprises a position start condition and a speed start condition, the position start condition is that the current position is within a start position range, and the speed start condition is that the current speed is less than a preset start speed, and the start position range is determined by a start position recorded in the historical parking data; Prompt feedback information of the prompt information is accepted, and whether the automatic parking mode is started is determined based on the prompt feedback information; If yes, the prompt feedback information is taken as the mode start instruction, and it is determined that the automatic parking mode of the vehicle is started.

3. The method of claim 1, wherein, The data packet further comprises verification data, and the current environmental images and the current distance set are input into the current parking neural network model to control the vehicle to perform an automatic parking operation by using output signals of the parking neural network model, which comprises the following steps: It is determined whether the current environmental images, the current distance set and the current position match the verification data; If not, it is determined whether there is a collision risk in the next preset period of performing the automatic parking operation according to the parking neural network based on the current distance set; If matched, the automatic parking operation is continued according to the parking neural network model; The step of judging whether the current environment image, the current distance set and the current position match the verification data is repeatedly performed until it is detected that the automatic parking operation is completed, and the automatic parking mode is exited.

4. The method of claim 3, wherein, Based on the current distance set, it is judged whether there is a collision risk in the next preset period of the automatic parking operation according to the parking neural network, including: If there is, an alarm information is sent and the automatic parking mode is exited, and the alarm information is used to prompt that there is a collision risk in the automatic parking operation; If not, an automatic parking request is sent and request feedback information of the automatic parking request is received, and the automatic parking mode is adjusted according to the request feedback information, and the request feedback information includes a keep mode instruction or an exit mode instruction.

5. The method according to any one of claims 1 to 4, characterized in that, The current environment image, the current distance set and the current position are input into the current parking neural network model, so as to control the vehicle to perform automatic parking operation by using the output signal of the parking neural network model, and the process further includes: Recording current parking data; Uploading the current parking data to the cloud platform to update the parking neural network model.

6. An automatic parking apparatus characterized by comprising: Including: The request module is configured to request a data packet from the cloud platform when it is determined that the automatic parking mode of the vehicle is started, and the data packet includes a parking neural network model updated based on historical parking data recorded by a driver parking operation; The acquisition module is configured to continuously acquire an environment image of the current vehicle, a current distance set and a current position, and the distance set includes the closest distance from the vehicle to each obstacle in each direction of the vehicle; The control module is configured to input the current environment image, the current distance set and the current position into the current parking neural network model, so as to control the vehicle to perform automatic parking operation by using the output signal of the parking neural network model; The process of updating the parking neural network model based on the historical parking data recorded by the driver parking operation includes: Receiving a training start instruction; Based on the training start instruction, the historical parking data of the vehicle in the training automatic parking state is continuously recorded at a preset period until a training stop instruction is received, and the historical parking data includes the position, driving path, steering wheel angle and steering, motion state, environment image and distance set of the vehicle; All the recorded historical parking data is uploaded to the cloud platform, and the parking neural network model is updated by using the historical parking data; Further including: Based on the historical parking data, verification data is determined, and the verification data includes the position, environment image and distance set in the historical parking data recorded in each preset period, and further includes the position, environment image and distance set in the historical parking data corresponding to the first inclination and first return of the steering wheel in the current training automatic parking process; uploading the verification data to the cloud platform, and requesting the cloud platform to update the verification data based on the historical parking data.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

Images