Vehicle control method and device, electronic device, vehicle and storage medium

Abstract

The invention discloses a vehicle control method, and the method comprises the steps: obtaining first driving environment information, and controlling the vehicle to run according to a second underwater image under the condition that the type of a vehicle driving road section is determined to be a wading road section according to the first driving environment information. Therefore, according to the embodiment of the invention, the vehicle can obtain the first driving environment information according to the pre-installed vehicle sound wave detection unit, namely the information obtained by sending sound waves outwards through the vehicle sound wave detection unit for detection; and under the condition that the vehicle driving road section type is determined to be a wading road section according to the first driving environment information, corresponding operations such as obstacle avoidance operation and the like are executed through a second underwater image obtained by the first underwater image and a predetermined generative adversarial network, so that the vehicle driving operation can be executed based on the second underwater image, and the vehicle driving efficiency is improved. And the safety and the stability of the vehicle driving on the wading road section are improved to a certain extent.

Description

Technical Field

[0001] The present application relates to the technical field of vehicles, and particularly relates to a control method, a control device, an electronic device, a vehicle and a computer-readable storage medium for a vehicle. Background Art

[0002] During the driving process of a vehicle, the grip of the wheels is related to the current driving section. For example, the grip of the wheels is relatively low when the section is a wading section, or the grip of the wheels is relatively low when the section is a dry asphalt section. Therefore, detecting the current driving section of the vehicle has become an urgent problem to be solved. Summary of the Invention

[0003] The present application provides a control method, a control device, an electronic device, a vehicle and a computer-readable storage medium for a vehicle.

[0004] An embodiment of the present application provides a control method for a vehicle, including:

[0005] Obtaining first driving environment information, where the first driving environment information is obtained through a vehicle sound wave detection unit;

[0006] When it is confirmed according to the first driving environment information that the driving section type of the vehicle is a wading section, controlling the vehicle to drive according to a second underwater image, where the second underwater image is obtained according to a first underwater image and a pre-determined generative adversarial network, and the first underwater image is obtained by the vehicle sound wave detection unit when the driving section type of the vehicle is a wading section.

[0007] In the control method for a vehicle provided by the embodiment of the present application, the vehicle can perform sound wave detection through the vehicle sound wave detection unit to obtain first driving environment information, and when it is confirmed according to the first driving environment information that the driving section type of the vehicle is a wading section, control the vehicle to drive according to the second underwater image obtained from the first underwater image obtained by the vehicle sound wave detection unit when the driving section type of the vehicle is a wading section and a pre-determined generative adversarial network.

[0008] In this way, the embodiment of the present application enables the vehicle to obtain first driving environment information according to a pre-installed vehicle sound wave detection unit, that is, the information obtained by the vehicle sound wave detection unit sending out sound waves for detection, and when it is confirmed according to the first driving environment information that the driving section type of the vehicle is a wading section, perform corresponding operations such as obstacle avoidance operations through the second underwater image obtained from the first underwater image and a pre-determined generative adversarial network, so that the vehicle driving operation can be performed based on the second underwater image, which improves the safety and stability of the vehicle driving in the wading section to a certain extent.

[0009] In some embodiments, the method further includes:

[0010] When the type of the vehicle driving section is a wading section, determining an image encoding result according to the first underwater image and the encoding sub-network of the generative adversarial network, and determining the second underwater image according to the image encoding result and the decoding sub-network of the generative adversarial network.

[0011] In this way, in the process of the vehicle determining the second underwater image according to the first underwater image in the embodiments of the present application, the encoding sub-network of the generative adversarial network can encode the first underwater image to obtain an image encoding result, and the decoding sub-network of the generative adversarial network can decode the image encoding result to obtain the second underwater image, so that the image quality of the second underwater image is guaranteed to a certain extent.

[0012] In some embodiments, the encoding sub-network includes a convolutional neural network, and the decoding sub-network includes a transposed convolutional neural network.

[0013] In this way, in the embodiments of the present application, based on the encoding sub-network composed of a convolutional neural network and the decoding sub-network composed of a transposed convolutional neural network, the encoding sub-network can reliably encode the first underwater image to obtain an image encoding result, and the decoding sub-network can reliably decode the image encoding result to obtain the second underwater image, thereby guaranteeing the image quality of the second underwater image to a certain extent.

[0014] In some embodiments, the vehicle acoustic wave detection unit is installed outside the vehicle cockpit, and the vehicle acoustic wave detection unit is configured to be able to scan the underwater environment by acoustic waves to generate the first underwater image when submerged in water.

[0015] In some embodiments, when it is confirmed according to the first driving environment information that the type of the vehicle driving section is a wading section, controlling the vehicle to drive according to the second underwater image includes:

[0016] When it is confirmed according to the first driving environment information that the type of the vehicle driving section is a wading section, displaying the second underwater image.

[0017] In this way, in the embodiments of the present application, when the current driving section of the vehicle is a wading section, the second underwater image is displayed, so that the user can know the underwater environment according to the second underwater image, thereby performing corresponding driving operations, and further enabling the vehicle to drive stably on the wading section, and the safety of the vehicle and the users in the vehicle is guaranteed to a certain extent.

[0018] In some embodiments, the method further includes:

[0019] When it is confirmed according to the first driving environment information that the type of the road section where the vehicle is traveling is a wading section, the vehicle is controlled to avoid the target obstacle according to the position of the target obstacle in the first water body image, where the position of the target obstacle is determined according to the first water body image and a pre-determined image recognition model.

[0020] In this way, the embodiment of the present application enables the vehicle to perform obstacle avoidance according to the position of the target obstacle in the first underwater image, so that the vehicle can drive stably. The position of the target obstacle obtained by the embodiment of the present application is determined according to a pre-trained image recognition model, so the credibility of the obtained position of the target obstacle is guaranteed to a certain extent.

[0021] In some embodiments, the obtaining of the first driving environment information includes:

[0022] When it is confirmed according to the second driving environment information that the type of the road section where the vehicle is traveling is a wading section, the first driving environment information is obtained, where the second driving environment information is obtained by a vehicle radar.

[0023] In this way, the embodiment of the present application enables the vehicle to obtain the second driving environment information through the vehicle radar, and when it is confirmed by the second driving environment information that the type of the road section where the vehicle is traveling is a wading section, or rather, when it is determined by the vehicle radar that the vehicle is suspected of traveling in a wading section, the first driving environment information is obtained through the vehicle acoustic wave detection unit to reconfirm the type of the road section where the vehicle is traveling, so as to avoid the situation that the vehicle acoustic wave detection unit needs to continuously collect or generate the first driving environment information after the vehicle is powered on, and the vehicle power consumption caused by the vehicle acoustic wave detection unit is reduced to a certain extent.

[0024] In some embodiments, the vehicle radar is installed outside the vehicle cockpit, and the second driving environment information includes the distance information of the vehicle radar relative to the road surface deposits; when the distance information is that the distance of the vehicle radar relative to the road surface deposits is less than a preset distance, the type of the road section where the vehicle is traveling is confirmed as a wading section, and / or, when the distance information is that the distance of the vehicle radar relative to the road surface deposits is higher than the preset distance, the type of the road section where the vehicle is traveling is confirmed as a non-wading section.

[0025] Thus, the embodiment of the present application enables the vehicle to determine the type of the vehicle driving section according to the distance information of the vehicle radar relative to the road deposits in the second driving environment information collected or generated by the vehicle radar. For example, when the distance information indicates that the distance between the vehicle radar and the road deposits is less than a preset distance, it is confirmed that the type of the vehicle driving section is a wading section, and / or when the distance information indicates that the distance between the vehicle radar and the road deposits is higher than the preset distance, it is confirmed that the type of the vehicle driving section is a non-wading section. Furthermore, the credibility of the type of the vehicle driving section confirmed by the first driving environment information is improved to a certain extent.

[0026] In some embodiments, the vehicle acoustic detection unit is installed outside the vehicle cockpit. The first driving environment information includes the reception time of the echo corresponding to the acoustic wave emitted by the vehicle acoustic detection unit. When the reception time is less than a preset time, the type of the vehicle driving section is confirmed as a wading section, and / or when the reception time is higher than the preset time, the type of the vehicle driving section is confirmed as a non-wading section.

[0027] Thus, the embodiment of the present application enables the vehicle to determine, according to the vehicle acoustic detection unit installed outside the vehicle cockpit, the reception time of the echo corresponding to the acoustic wave emitted by the vehicle acoustic detection unit in the first driving environment information obtained by acoustic detection, and then determine the type of the vehicle driving section according to the reception time of the echo. That is, when the reception time is less than the time, the type of the vehicle driving section is confirmed as a wading section, and / or when the reception time is higher than the preset time, the type of the vehicle driving section is confirmed as a non-wading section. Thereby, the credibility of the type of the vehicle driving section determined by the first driving environment information is improved or guaranteed to a certain extent.

[0028] In some embodiments, the method further includes:

[0029] When it is confirmed, according to the first driving environment information, that the type of the vehicle driving section is a wading section, the vehicle is controlled to enter a preset working mode, wherein when the vehicle changes from a state of not being in the preset working mode to a state of being in the preset working mode, the maximum driving force that the vehicle can generate decreases.

[0030] Thus, the embodiment of the present application enables the vehicle to reduce the maximum driving force that the vehicle can generate based on the entry into the preset working mode. Furthermore, the probability that the vehicle may get out of control due to accelerating in the wading section can be reduced to a certain extent, and the safety of the vehicle and the users in the vehicle is guaranteed to a certain extent.

[0031] The embodiment of the present application provides a control device, including:

[0032] A transceiver unit, configured to obtain first driving environment information, where the first driving environment information is obtained by a vehicle acoustic wave detection unit;

[0033] A processing unit, configured to control the vehicle to travel according to a second underwater image when it is confirmed according to the first driving environment information that the type of the vehicle driving section is a wading section, where the second underwater image is obtained according to a first underwater image and a pre-determined generative adversarial network, and the first underwater image is obtained by the vehicle acoustic wave detection unit when the type of the vehicle driving section is a wading section.

[0034] An embodiment of the present application provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and when the computer program is executed by the processor, the above-mentioned vehicle control method is implemented.

[0035] An embodiment of the present application provides a vehicle, including the above-mentioned control device or including the above-mentioned electronic device.

[0036] An embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by one or more processors, the above-mentioned vehicle control method is implemented.

[0037] The control device, electronic device, vehicle and computer-readable storage medium provided by the embodiments of the present application can obtain first driving environment information according to a pre-installed vehicle acoustic wave detection unit, that is, information obtained by the vehicle acoustic wave detection unit sending out acoustic waves for detection, and when it is confirmed according to the first driving environment information that the type of the vehicle driving section is a wading section, perform corresponding operations such as obstacle avoidance operations through a second underwater image obtained from a first underwater image and a pre-determined generative adversarial network, so that the vehicle driving operation can be performed based on the second underwater image, which improves the safety and stability of the vehicle driving in a wading section to a certain extent.

[0038] Additional aspects and advantages of the embodiments of the present application will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the accompanying drawings, where:

[0040] Figure 1 is a schematic flowchart of a vehicle control method in some embodiments of the present application;

[0041] Figure 2Schematic diagram of a vehicle in some embodiments of the present application;

[0042] Figure 3 Schematic diagram of a vehicle in some embodiments of the present application;

[0043] Figure 4 Schematic diagram of the vehicle acoustic wave detection unit in some embodiments of the present application;

[0044] Figure 5 Simulation schematic diagram of the total reflection phenomenon of ultrasonic waves;

[0045] Figure 6 Simulation schematic diagram of the total reflection phenomenon of ultrasonic waves;

[0046] Figure 7 Schematic diagram of a vehicle in some embodiments of the present application;

[0047] Figure 8 Schematic diagram of the vehicle operation process in some embodiments of the present application. Specific embodiments

[0048] The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, in which the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the embodiments of the present application and should not be construed as a limitation of the embodiments of the present application.

[0049] When the vehicle is driving on a section with accumulated water, that is, when the vehicle is driving on a wading section, the grip of the wheels decreases, the wheels may slip, the braking distance of the vehicle increases, the braking performance of the vehicle decreases, and the probability of vehicle out of control increases. Therefore, when the user drives the vehicle on a wading section, the vehicle speed or gear usually needs to be reduced to maintain a safe distance, and to avoid the situation where the vehicle is out of control due to wheel slip when the vehicle is driving at high speed.

[0050] Therefore, some vehicles can be equipped with an assisted driving function for wading sections. That is, when it is determined that the vehicle is driving on a wading section, the maximum driving speed of the vehicle can be limited. For example, the vehicle is limited to a maximum speed of 60 mph on the wading section, thereby avoiding the safety risks brought by too high a vehicle speed.

[0051] However, the aforementioned assisted driving function for wading sections may need to be manually activated by the user. For example, when the user observes that the current driving section of the vehicle is a wading section, the aforementioned assisted driving function for wading sections can be activated through the central control display screen. However, when the user observes that the current driving section of the vehicle is a wading section, the user may forget to activate the assisted driving function for the vehicle wading section, resulting in the safety of the vehicle and the users in the vehicle being difficult to guarantee.

[0052] Based on the above possible problems, refer to Figure 1 , an embodiment of the present application provides a control method for a vehicle, including:

[0053] 01: Obtain first driving environment information, where the first driving environment information is obtained through a vehicle acoustic wave detection unit;

[0054] 02: When it is confirmed according to the first driving environment information that the driving road section type of the vehicle is a wading road section, control the vehicle to drive according to a second underwater image, where the second underwater image is obtained according to a first underwater image and a pre-determined generative adversarial network, and the first underwater image is obtained through the vehicle acoustic wave detection unit when the driving road section type of the vehicle is a wading road section.

[0055] An embodiment of the present application provides a control device. The vehicle control method of the embodiment of the present application can be implemented by the control device of the embodiment of the present application. Specifically, the control device includes a transceiver unit and a processing unit. The transceiver unit is used to obtain first driving environment information, where the first driving environment information is obtained through a vehicle acoustic wave detection unit. The processing unit is used to control the vehicle to drive according to a second underwater image when it is confirmed according to the first driving environment information that the driving road section type of the vehicle is a wading road section, where the second underwater image is obtained according to a first underwater image and a pre-determined generative adversarial network, and the first underwater image is obtained through the vehicle acoustic wave detection unit when the driving road section type of the vehicle is a wading road section.

[0056] An embodiment of the present application further provides an electronic device, which includes a memory and a processor. The vehicle control method of the embodiment of the present application can be implemented by the vehicle of the embodiment of the present application. Specifically, a computer program is stored in the memory, and the processor is used to obtain first driving environment information, where the first driving environment information is obtained through a vehicle acoustic wave detection unit; when it is confirmed according to the first driving environment information that the driving road section type of the vehicle is a wading road section, control the vehicle to drive according to a second underwater image, where the second underwater image is obtained according to a first underwater image and a pre-determined generative adversarial network, and the first underwater image is obtained through the vehicle acoustic wave detection unit when the driving road section type of the vehicle is a wading road section.

[0057] That is, the vehicle (or the vehicle's controller / processor) according to the embodiment of the present application can send out sound waves to the outside world through a pre-installed vehicle sound wave detection unit to detect the vehicle driving environment, so as to obtain the first driving environment information. When the first driving environment information is obtained and it is confirmed according to the first driving environment information that the vehicle driving road section type is a wading road section, based on the first underwater image obtained by the vehicle sound wave detection unit detecting the underwater environment when the vehicle driving road section type is a wading road section, and a pre-determined generative adversarial network, a second underwater image is determined, and thus the vehicle driving is controlled according to the second underwater image.

[0058] It should be understood that the vehicle sound wave detection unit in the embodiment of the present application can be understood as a device or equipment installed on the vehicle that can perform detection or environment detection through sound waves. It can be understood that the specific model, type, structure and other factors of the vehicle sound wave detection unit are all contents that can be set according to the actual situation.

[0059] For example, in some embodiments, the vehicle sound wave detection unit is a sonar. Similarly, in some other embodiments, the vehicle sound wave detection unit is a sound wave detector set based on any one of the sound sources of an electric spark source, a BOOMER source, and an air gun source. And in some embodiments where the distance of the vehicle sound wave detection unit relative to the "contact surface between the vehicle and the ground" is 0.5 meters, the vehicle sound wave detection unit can be a sound wave detector with an accuracy meeting 0.5 meters, including but not limited to sonar.

[0060] It should also be understood that the first driving environment information obtained by the vehicle sound wave detection unit in the embodiment of the present application refers to the information that can be obtained through sound wave detection, such as the position of an object outside the vehicle obtained through sound wave detection, or the sound wave return time, etc.

[0061] In addition, it should be noted that, compared with the air medium, water has a lower absorption rate of sound waves, and the loss and attenuation of sound waves during propagation in water are smaller. Therefore, when the vehicle sound wave detection unit sends out sound waves to the outside world, if the sound waves propagate in water, after the sound waves propagate and are reflected in water, the surrounding environment can be effectively detected through the reflected sound waves. In contrast, if the sound waves propagate in air, due to the higher attenuation and loss of sound waves in air, the emitted sound waves may not be reflected back to the vehicle sound wave detection unit. Furthermore, it is difficult to detect the specific situation of the surrounding environment through sound waves, or even impossible to detect the surrounding environment.

[0062] Therefore, in the embodiments of the present application, the vehicle acoustic wave detection unit can reliably detect the underwater environment through acoustic waves, but it is difficult to detect the air environment through acoustic waves. Therefore, based on the first driving environment information collected by the vehicle acoustic wave detection unit, the working environment or working effect of the vehicle acoustic wave detection unit is determined, so as to determine whether the vehicle acoustic wave detection unit is working underwater or in the air, and further determine whether the vehicle is driving on a wading section.

[0063] For example, when the first driving environment information detected or collected by the vehicle acoustic wave detection unit by transmitting and receiving acoustic waves can characterize information such as the positions of objects around the vehicle, or in other words, when the first driving environment information is relatively clear or has less noise information, it indicates that the vehicle acoustic wave detection unit is submerged in water (or the acoustic wave transceiver component in the vehicle acoustic wave detection unit is submerged in water). That is, it can be considered that the type of the vehicle driving section is a wading section.

[0064] On the contrary, when the first driving environment information fails to characterize information such as the positions of objects around the vehicle, or in other words, when the first driving environment information is relatively blurred or has more noise information, it indicates that the vehicle acoustic wave detection unit is not submerged in water (or the acoustic wave transceiver component in the vehicle acoustic wave detection unit is not submerged in water). That is, it can be considered that the type of the vehicle driving section is a non-wading section.

[0065] In addition, it should be noted that the step of determining the type of the vehicle driving section based on the first driving environment information can be executed by the vehicle itself, or by other devices or components outside the vehicle. That is, in some embodiments, after obtaining the first driving environment information, the vehicle can determine the type of the vehicle driving section by using the first driving environment information according to the pre-set program and / or hardware unit. In other embodiments, after obtaining the first driving environment information, the vehicle can send the first driving environment information to an electronic device such as a cloud server that does not belong to the vehicle. The electronic device receives the first driving environment information, determines the type of the vehicle driving section by using the first driving environment information according to the pre-set program and / or hardware unit, and then feeds back the type of the vehicle driving section to the vehicle.

[0066] It should also be clear that when it is confirmed that the type of the vehicle driving section is a wading section based on the first driving environment information, since the propagation effect of acoustic waves in the water medium is relatively high, the vehicle acoustic wave detection unit can detect the underwater environment through acoustic waves and generate a corresponding first underwater image. It can be understood that when the vehicle acoustic wave detection unit is in a land environment, or in other words, when the vehicle acoustic wave detection unit is not in an underwater environment, since the propagation effect of acoustic waves in a non-water medium is relatively poor (such as obvious attenuation), when it is confirmed that the type of the vehicle driving section is a non-wading section based on the first driving environment information, the vehicle acoustic wave detection unit may not form a first underwater image through acoustic waves.

[0067] That is to say, when it is confirmed that the type of the vehicle driving section is a non-wading section, since the vehicle driving section is a non-wading section, the vehicle acoustic detection unit fails to detect water, resulting in poor quality of the first underwater image generated by the vehicle acoustic detection unit through acoustic detection. Therefore, the vehicle according to the embodiment of the present application may not perform the step of obtaining the second underwater image based on the first underwater image when it is confirmed that the type of the vehicle driving section is a non-wading section.

[0068] It is also clear that the function or role of the generative adversarial network in the embodiment of the present application is content that can be set according to the actual situation.

[0069] For example, to ensure that the user can clearly know the obstacles in the water environment where the vehicle is located, in some embodiments of the present application, the generative adversarial network can be used to generate an image in which specific objects (such as objects with a sharp shape) in the first underwater image are highlighted based on the first underwater image, that is, the second underwater image. In other embodiments, the generative adversarial network in the embodiment of the present application can be used to generate a second underwater image with higher image quality or higher image resolution based on the first underwater image.

[0070] It can be understood that when specific objects (such as objects with a sharp shape) in the first underwater image are highlighted to obtain the second underwater image, or when the second underwater image with higher image quality is obtained from the first underwater image with lower image quality, the user or the vehicle can determine the obstacles in the second underwater image based on the highlighted objects in the second underwater image or based on the second underwater image with higher image quality, so as to know the underwater environment and drive to avoid obstacles.

[0071] In summary, the embodiment of the present application enables the vehicle to obtain the first driving environment information according to the pre-installed vehicle acoustic detection unit, that is, the information obtained by the vehicle acoustic detection unit by sending acoustic waves outward for detection, and when it is confirmed that the type of the vehicle driving section is a wading section according to the first driving environment information, perform corresponding operations such as obstacle avoidance operations based on the second underwater image obtained from the first underwater image and the pre-determined generative adversarial network, so that the vehicle driving operation can be performed based on the second underwater image, which improves the safety and stability of the vehicle driving in the wading section to a certain extent.

[0072] In addition, it can be understood that the generative adversarial network of the embodiment of the present application can be carried on the vehicle or on a remote electronic device such as a cloud server. When the generative adversarial network is carried on the vehicle, the vehicle can input the first underwater image into the generative adversarial network after obtaining the first underwater image to obtain the corresponding second underwater image to ensure the efficient generation of the second underwater image.

[0073] When the generative adversarial network is carried on a remote electronic device such as a cloud server, the vehicle can send the first underwater image to the remote electronic device such as the cloud server, so that the remote electronic device such as the cloud server can generate a second underwater image corresponding to the first underwater image through the generative adversarial network carried on itself, and feed back the second underwater image to the vehicle, thereby avoiding the vehicle having to bear the computing power required for the operation of the generative adversarial network, and reducing the vehicle's computing power or load.

[0074] In addition, during the training process of the generative adversarial network, the training sample set may include multiple sample groups, and each sample group includes a first underwater image sample with a low image resolution generated by the vehicle's acoustic detection unit, and a second underwater image sample with a high image resolution that highlights or enriches the image details in the first underwater image.

[0075] Moreover, through the training of the generative adversarial network based on multiple sample groups, the generator in the generative adversarial network can generate a generated image highly similar to the second underwater image sample in a certain sample group according to the first underwater image sample in the sample group, and after receiving the "generated image output by the generator" and the "second underwater image sample in the sample group", the discriminator in the generative adversarial network cannot reliably determine the "true image that is not the output of the generator" from the two images.

[0076] In some embodiments of the present application, the control method further includes:

[0077] When the vehicle driving section type is a wading section, determining an image encoding result according to the first underwater image and the encoding sub-network of the generative adversarial network, and determining a second underwater image according to the image encoding result and the decoding sub-network of the generative adversarial network.

[0078] The processing unit according to the embodiment of the present application is further configured to, when the vehicle driving section type is a wading section, determine an image encoding result according to the first underwater image and the encoding sub-network of the generative adversarial network, and determine a second underwater image according to the image encoding result and the decoding sub-network of the generative adversarial network.

[0079] The processor according to the embodiment of the present application is further configured to, when the vehicle driving section type is a wading section, determine an image encoding result according to the first underwater image and the encoding sub-network of the generative adversarial network, and determine a second underwater image according to the image encoding result and the decoding sub-network of the generative adversarial network.

[0080] That is, the generative adversarial network according to the embodiment of the present application includes an encoding sub-network and a decoding sub-network. Furthermore, the first underwater image can be converted into a corresponding image encoding result based on the encoding of the encoding sub-network. Then, the decoding sub-network decodes the image encoding result to obtain the second underwater image.

[0081] It can be understood that the encoding process of the decoding sub-network can be regarded as downsampling. Furthermore, the process of obtaining the image encoding result can be understood as downsampling the first underwater image to achieve feature extraction, and the feature extraction result is the aforementioned image encoding result.

[0082] Relatively speaking, the decoding process of the decoding sub-network can be regarded as upsampling. Furthermore, the process of obtaining the image encoding result can be understood as upsampling the first underwater image to achieve feature restoration, and the feature restoration result is the second underwater image.

[0083] It can also be understood that the encoding process of the decoding sub-network can be used to extract important feature information in the first underwater image, and the decoding process of the decoding sub-network can be used to restore the aforementioned important feature information to the second underwater image. Therefore, based on the extraction and restoration of important feature information, the vehicle can ignore unimportant feature information during the process of generating the first underwater image and ensure that the important feature information can be used for the generation of the second underwater image.

[0084] In this way, in the process of the vehicle determining the second underwater image according to the first underwater image in the embodiments of the present application, the encoding sub-network of the generative adversarial network can be used to encode the first underwater image to obtain an image encoding result, and the decoding sub-network of the generative adversarial network can be used to decode the image encoding result to obtain the second underwater image, so that the image quality of the second underwater image is guaranteed to a certain extent.

[0085] In some embodiments of the present application, the encoding sub-network includes a convolutional neural network, and the decoding sub-network includes a deconvolutional neural network.

[0086] That is to say, the encoding sub-network in the generative adversarial network of the embodiments of the present application can be constructed based on a convolutional neural network (Convolutional Neural Networks, CNN), and the decoding sub-network can be constructed based on a deconvolutional neural network (Deconvolutional Neural Networks, DNN).

[0087] It can be understood that the convolutional neural network has strong image extraction ability. Therefore, when encoding the first underwater image through the convolutional neural network, it can ensure to a certain extent that the important features in the first underwater image are extracted.

[0088] Relatively speaking, the deconvolutional neural network can perform deconvolution on the image encoding result output by the encoding sub-network, that is, upsampling, or decoding, so as to ensure that the image encoding result can be reliably converted into the second underwater image.

[0089] Thus, the embodiment of the present application is based on an encoding sub-network composed of a convolutional neural network and a decoding sub-network composed of a transposed convolutional neural network, enabling the encoding sub-network to reliably encode the first underwater image to obtain an image encoding result, and enabling the decoding sub-network to reliably decode the image encoding result to obtain a second underwater image, thereby ensuring the image quality of the second underwater image to a certain extent.

[0090] In some embodiments of the present application, the vehicle acoustic wave detection unit is installed outside the vehicle cockpit and is configured to be able to scan the underwater environment by acoustic waves to generate a first underwater image when submerged in water.

[0091] That is, the vehicle according to the embodiment of the present application can generate a first underwater image by acoustic wave scanning of the underwater environment through the vehicle acoustic wave detection unit installed outside the vehicle cockpit when submerged in water.

[0092] For a clearer description of the embodiments of the present application, please refer to Figure 2 and Figure 3 , the vehicle acoustic wave detection unit 210 can be installed on the vehicle chassis. At the same time, the vehicle acoustic wave detection unit 210 can scan the underwater environment by waves such as electromagnetic waves or ultrasonic waves (corresponding to the cone directly below the vehicle acoustic wave detection unit 210 in Figure 3 ) when submerged in water (corresponding to Figure 2 or Figure 3 ) to obtain a first underwater image.

[0093] In some embodiments of the present application, step 02 includes:

[0094] When it is confirmed according to the first driving environment information that the vehicle driving section type is a wading section, display the second underwater image.

[0095] The processing unit of the embodiment of the present application is further configured to display the second underwater image when it is confirmed according to the first driving environment information that the vehicle driving section type is a wading section.

[0096] The processor of the embodiment of the present application is further configured to display the second underwater image when it is confirmed according to the first driving environment information that the vehicle driving section type is a wading section.

[0097] That is, the vehicle according to the embodiment of the present application can display the second underwater image on the vehicle display component such as the central control display screen. Furthermore, when the user, such as the vehicle driver, can determine the road conditions ahead or under the vehicle through the second underwater image displayed on the vehicle, corresponding driving operations can be performed.

[0098] It can be understood that in some embodiments where the vehicle acoustic wave detection unit can detect the underwater environment through acoustic waves to generate a first underwater image, the acoustic wave emission angle of the acoustic wave transmitter (or transducer) of the vehicle acoustic wave detection unit can be set according to the actual situation. For example, in some embodiments, the angle between the acoustic wave emission angle and the direction of gravity (or the vertically downward direction) is 30° to 60°. At the same time, the acoustic wave transmitter can also rotate at an angular step value of 1° to 2°, so as to ensure that the first underwater image can detect the underwater environment more comprehensively.

[0099] Furthermore, to meet the above requirements, the sensitivity of the acoustic wave transmitter can be 200 dBre1V / uPa, the frequency response can be within 700 Hz to 10 kHz, and the fluctuation within the frequency band range can be 2 dB. Also, the supply current of the acoustic wave transmitter can be 2 mA to 10 mA, the supply voltage can be 24 V or 12 V, the horizontal directivity and omnidirectionality of the acoustic wave transmitter can be + / −2 dB@10 kHz, the vertical directivity can be 60°, and the maximum tolerable static pressure can be 6 MPa.

[0100] In addition, it should also be understood that when acoustic waves propagate in an aqueous medium, after losses such as attenuation, scattering, refraction, and transmission, some acoustic waves will be reflected back to the vehicle acoustic wave detection unit (or the acoustic wave receiving unit of the vehicle acoustic wave detection unit, such as a hydrophone). However, due to the complexity of the water environment, the echo signal received at this time may be at the mV level, and the echo signal can be understood as a mixed signal, mixed with multipath reflection signals and environmental noise, etc.

[0101] Therefore, to ensure that the vehicle acoustic wave detection unit can reliably complete underwater detection through acoustic waves and the echoes of acoustic waves, in some embodiments of the present application, specific reference can be made to Figure 4 , Figure 4 which is a schematic diagram of the vehicle acoustic wave detection unit in some embodiments of the present application. That is, after the acoustic wave emission end sends out acoustic waves based on the acoustic wave transmitter, the transmitting end signal amplifier, the oscillator, the threshold unit, the pulse shaper, the pulse repetition generator, and the time base signal generator, after the acoustic wave receiving end receives the echo based on the hydrophone, it performs one or more of high-pass filtering, low-pass filtering, and band-pass filtering based on the filter, and then performs signal amplification (such as amplifying the signal amplitude by 100 times) based on the receiving end signal amplifier, and then can be further processed through analog-to-digital conversion, differential input circuits, etc., so as to ensure that the echo signal can be reliably used to generate the first underwater image.

[0102] And, it can be understood that in the vehicle acoustic wave detection unit as shown in Figure 4 , the numerical value and sampling rate of the power supply of the vehicle acoustic wave detection unit may be different from those of other components in the vehicle, and thus the power supply of the vehicle acoustic wave detection unit may need to be set separately.

[0103] It can also be understood that the vehicle acoustic wave detection unit according to the embodiment of the present application can satisfy the following equation, that is:

[0104] DT = SL - 2*TL - NL + TS + DI

[0105] In the formula, DT is the intensity of the echo signal, SL is the intensity of the signal source, TL is the propagation loss during transmission. Since it includes the round trip of transmission and reception, the propagation loss needs to be multiplied by 2. NL is the noise level during propagation, TS is the intensity of the source signal reaching the target area after propagation loss and noise influence, and DI can be understood as the directivity index.

[0106] It can be understood that the embodiment of the present application can determine the parameter performance index of the vehicle acoustic wave detection unit according to the above equation, so as to provide a data basis for the hardware design and subsequent algorithm design of the vehicle acoustic wave detection unit.

[0107] In this way, when the vehicle is in a wading section on the current driving section according to the embodiment of the present application, a second underwater image is displayed, so that the user can know the underwater environment according to the second underwater image, and then perform corresponding driving operations. Furthermore, the vehicle can drive stably on the wading section, and the safety of the vehicle and the users in the vehicle is guaranteed to a certain extent.

[0108] In some embodiments of the present application, the control method includes:

[0109] When it is confirmed according to the first driving environment information that the vehicle driving section type is a wading section, according to the position of the target obstacle in the first water body image, control the vehicle to drive around the target obstacle, where the position of the target obstacle is determined according to the first water body image and a pre-determined image recognition model.

[0110] The processing unit according to the embodiment of the present application is further configured to, when it is confirmed according to the first driving environment information that the vehicle driving section type is a wading section, control the vehicle to drive around the target obstacle according to the position of the target obstacle in the first water body image, where the position of the target obstacle is determined according to the first water body image and a pre-determined image recognition model.

[0111] The processor according to the embodiment of the present application is further configured to, when it is confirmed according to the first driving environment information that the vehicle driving section type is a wading section, control the vehicle to drive around the target obstacle according to the position of the target obstacle in the first water body image, where the position of the target obstacle is determined according to the first water body image and a pre-determined image recognition model.

[0112] That is, the vehicle according to the embodiment of the present application can also, after obtaining the first underwater image of the vehicle acoustic wave detection unit, identify the target obstacle in the first underwater image based on the image recognition model carried by itself, so as to determine the position of the target obstacle, and further avoid the target obstacle during the automatic driving process.

[0113] Alternatively, the vehicle can send the first underwater image to an electronic device such as a cloud service equipped with an image recognition model, so that after the electronic device identifies the target obstacle in the first underwater image and determines the position of the target obstacle, it feeds back the position of the target obstacle to the vehicle, so that the vehicle can avoid the obstacle according to the received position of the target obstacle and drive.

[0114] It can be understood that due to the complexity of the underwater environment, identifying the categories of all objects in the first underwater image requires relatively high computing power, and the real-time requirement for vehicle obstacle avoidance is relatively high. Therefore, the embodiment of the present application can only determine the position of specific objects in the first underwater image to avoid obstacles, that is, it can determine the target obstacle in the first underwater image, such as an object with a sharp shape, to avoid obstacles.

[0115] It can also be understood that in the second underwater image determined by the generative adversarial network based on the first underwater image, there may be objects that do not exist in the first underwater image, or rather, compared with the first underwater image, the second underwater image may have a "super-real" situation. Therefore, the embodiment of the present application determines the target obstacle according to the first underwater image to ensure that "the position of the target obstacle determined according to the first water body image and the image recognition model" is "the position of the real target obstacle in the real world", that is, the position of the real target obstacle in the first underwater image.

[0116] In this way, the embodiment of the present application enables the vehicle to avoid obstacles according to the position of the target obstacle in the first underwater image, so that the vehicle can drive stably. The position of the target obstacle obtained by the embodiment of the present application is determined according to the pre-trained image recognition model, so the credibility of the obtained position of the target obstacle is guaranteed to a certain extent.

[0117] In addition, it can also be understood that the specific structure of the image recognition network in the embodiment of the present application can be set according to the actual situation.

[0118] In addition, in some embodiments of the present application, the vehicle will also, while displaying the second underwater image, mark or highlight the target obstacle in the displayed second underwater image based on the determined position of the target obstacle, so that the user can know the underwater target obstacle through the second underwater image. Further, the vehicle can also display the distance between the vehicle radar and the road surface deposits together, so that the user can know the current water depth.

[0119] In some embodiments of the present application, step 01 includes:

[0120] When it is confirmed according to the second driving environment information that the type of the vehicle driving section is a wading section, obtain the first driving environment information, wherein the second driving environment information is obtained by the vehicle radar.

[0121] The transceiver unit of the embodiment of the present application is further configured to obtain the first driving environment information when it is confirmed according to the second driving environment information that the type of the vehicle driving section is a wading section, wherein the second driving environment information is obtained by the vehicle radar.

[0122] The processor of the embodiment of the present application is further configured to obtain the first driving environment information when it is confirmed according to the second driving environment information that the type of the vehicle driving section is a wading section, wherein the second driving environment information is obtained by the vehicle radar.

[0123] That is, in order to avoid the situation that the vehicle acoustic wave detection unit needs to maintain the working state for a long time to collect the first driving environment information in real time, resulting in excessive power consumption of the vehicle by the vehicle acoustic wave detection unit, a radar, that is, a vehicle radar, is also installed in the vehicle. It can be understood that, compared with acoustic wave detection units such as sonar, the operating power consumption of radar detection units such as ultrasonic radars is relatively low. Therefore, the vehicle radar in the present application can be powered on when the vehicle is powered on, or when the user starts the vehicle, to start working.

[0124] It should be noted that the radar can emit ultrasonic waves (or electromagnetic waves) in a specific direction in the working state. When the ultrasonic waves are reflected back to the radar after contacting an object during propagation, the radar can determine the position of the object contacted by the ultrasonic waves according to the propagation speed of the ultrasonic waves in the propagation medium and in combination with the ultrasonic wave return time, so as to complete positioning.

[0125] It should also be noted that, compared with the acoustic impedance of other media, the acoustic impedance of air is relatively extremely small. When electromagnetic waves or ultrasonic waves contact or reach a non-air interface in the air medium, electromagnetic waves or ultrasonic waves may generate echoes in the form of total reflection. For example, when the vehicle is driving on a road with bushes, the electromagnetic waves emitted by the radar will also exhibit total reflection when contacting objects such as bushes. For a clearer description of the vehicle radar of the embodiment of the present application, please refer to Figure 5 and Figure 6 , Figure 5 and Figure 6 are simulation schematic diagrams of the total reflection phenomenon of ultrasonic waves. It should be clear that, Figure 5 and Figure 6It refers to the propagation of ultrasonic waves at the air-water interface layer under different frequency bands. That is, at different frequency bands, the reflectivity of ultrasonic waves satisfies the total reflection condition, so ultrasonic waves cannot enter the water area from the air layer.

[0126] Furthermore, in the embodiment of the present application, when the vehicle radar sends out electromagnetic waves or ultrasonic waves to obtain the second driving environment information based on the echoes of the electromagnetic waves or ultrasonic waves, since total reflection occurs when the electromagnetic waves or ultrasonic waves encounter non-air objects or non-air interfaces in the air, it is difficult for the second driving environment information obtained from the electromagnetic waves or ultrasonic waves to reflect the types of objects encountered or contacted by the electromagnetic waves or ultrasonic waves. Furthermore, the vehicle can detect the distance between the external object and the vehicle radar through the radar, but it is difficult to determine whether the external object is water through the radar. That is, the credibility of the type of driving section of the vehicle confirmed through the second driving environment information is not high. Or rather, there is a situation where the type of driving section of the vehicle is confirmed as a wading section through the second driving environment information, but the vehicle is actually not driving on a wading section.

[0127] Therefore, in the embodiment of the present application, after detecting or detecting the outside of the vehicle through the vehicle radar to obtain the second driving environment information and confirming that the type of driving section of the vehicle is a wading section based on the second driving environment information, the vehicle acoustic detection unit can be used to detect or detect the external object again to obtain the first driving environment information and confirm the type of driving section based on the driving environment information, so as to ensure the reliable control of the vehicle.

[0128] In addition, it should be clear that the vehicle radar in the embodiment of the present application can be any one of radars such as ultrasonic radars, millimeter wave radars, and lidar. Further, in some embodiments where the installation position of the vehicle radar is located on the outside rearview mirror and is used to detect the distance of the object directly below the outside rearview mirror relative to the vehicle radar, since the distance between the outside rearview mirror and the ground is about 1 meter, the vehicle radar is a radar with an accuracy that can support effective ranging within a range of 1 meter, including but not limited to ultrasonic radars.

[0129] It should also be clear that the second driving environment information in the embodiment of the present application can be understood as determining the distance of the external object relative to the vehicle radar through the electromagnetic waves or ultrasonic waves sent and received by the vehicle radar.

[0130] Moreover, the specific method for determining the type of the vehicle driving section according to the second driving environment information is content that can be set according to the actual situation. For example, in some embodiments where the installation position of the vehicle radar is on the outside rearview mirror and is used to detect the distance of the object directly below the outside rearview mirror relative to the vehicle radar, when the second driving environment information reflects that the first distance of the object directly below the outside rearview mirror relative to the vehicle radar is not higher than the second distance of the contact surface between the wheel and the ground relative to the vehicle radar, and the difference between the first distance and the second distance is not within the preset allowable range, it can be confirmed that the type of the vehicle driving section is a wading section. Conversely, if the difference between the first distance and the second distance is within the preset allowable range, it can be confirmed that the type of the vehicle driving section is a non-wading section.

[0131] Furthermore, when it is determined that the type of the vehicle driving section is a wading section according to the second driving environment information, the embodiment of the present application can control the vehicle acoustic wave detection unit to start, or make the vehicle acoustic wave detection unit enter the normal working state to collect or generate the first driving environment information.

[0132] In this way, the embodiment of the present application enables the vehicle to obtain the second driving environment information through the vehicle radar, and when it is confirmed that the type of the vehicle driving section is a wading section by the second driving environment information, or in other words, when it is determined through the vehicle radar that the vehicle is suspected of driving in a wading section, then obtain the first driving environment information through the vehicle acoustic wave detection unit to reconfirm the type of the vehicle driving section, so as to avoid the situation that the vehicle acoustic wave detection unit needs to continuously collect or generate the first driving environment information after the vehicle is powered on, and reduce the vehicle power consumption brought by the vehicle acoustic wave detection unit to a certain extent.

[0133] In addition, it should be noted that the step of determining the type of the vehicle driving section according to the second driving environment information can be executed by the vehicle itself, or by other devices or components outside the vehicle. That is, in some embodiments, after the vehicle obtains the second driving environment information, it can determine the type of the vehicle driving section by using the second driving environment information according to the pre-set program and / or hardware unit. In other embodiments, after the vehicle obtains the second driving environment information, it can send the second driving environment information to an electronic device that does not belong to the vehicle, such as a cloud server, so that the electronic device receives the second driving environment information, determines the type of the vehicle driving section by using the second driving environment information according to the pre-set program and / or hardware unit, and then feeds back the determined type of the vehicle driving section to the vehicle.

[0134] In some embodiments of the present application, the vehicle radar is installed outside the vehicle cockpit, and the second driving environment information includes the distance information of the vehicle radar relative to the accumulation on the road surface; when the distance information indicates that the distance of the vehicle radar relative to the accumulation on the road surface is less than a preset distance, the vehicle driving section type is confirmed as a wading section, and / or when the distance information indicates that the distance of the vehicle radar relative to the accumulation on the road surface is higher than the preset distance, the vehicle driving section type is confirmed as a non-wading section.

[0135] That is, the second driving environment information obtained by the vehicle radar installed outside the cockpit in the embodiments of the present application includes the distance information of the vehicle radar relative to the accumulation on the road surface. Or rather, the vehicle radar in the embodiments of the present application can be used to emit electromagnetic waves or ultrasonic waves to the ground, so as to determine the distance between the accumulated object (such as water) on the ground and the vehicle radar according to the corresponding echo information of the electromagnetic waves or ultrasonic waves. For example, in some embodiments, the vehicle radar is installed at the outside rearview mirror of the vehicle, and is used to detect the distance of the object directly below the outside rearview mirror relative to the vehicle radar. For a clearer illustration of the embodiments of the present application, please refer to Figure 2 and Figure 3 , Figure 2 and Figure 3 which are schematic diagrams of the vehicle in some embodiments of the present application. That is, the vehicle radar 220 is installed at the position of the vehicle rearview mirror ( Figure 2 and Figure 3 both not shown), and is used to detect the distance of the object on the ground 300 directly below the vehicle radar 220 relative to the vehicle radar 220 through waves such as electromagnetic waves or ultrasonic waves (corresponding to the cone directly below the vehicle radar 220 in Figure 2 or Figure 3 ). Figure 2 For example, in

[0136] when the vehicle is traveling in the forward direction (corresponding to the arrow in Figure 2 and Figure 2 and Figure 3 ), since there is no water accumulation on the ground 300, or rather, since the current vehicle driving section type is a non-wading section, the distance information detected by the vehicle radar 220 through electromagnetic waves or ultrasonic waves can represent the distance of the vehicle radar 220 relative to the ground 300. While in Figure 3 , since there is water accumulation on the ground 300, the distance information detected by the vehicle radar 220 through electromagnetic waves or ultrasonic waves can represent the distance of the vehicle radar 220 relative to the water surface 400.

[0137] Further, it may be due to the presence of accumulated water on the ground, resulting in the distance between the accumulated objects on the ground and the vehicle radar being less than the preset distance, and then it is confirmed that the type of the vehicle driving section is a wading section. On the contrary, when there is no accumulated water wading or other objects on the ground, making the distance between the accumulated objects on the ground and the vehicle radar not less than the preset distance, the type of the vehicle driving section can be confirmed as a non-wading section, or in other words, it is not confirmed as a wading section.

[0138] Furthermore, it should also be noted that the vehicle radar installed outside the vehicle cockpit can be understood as a radar transducer or a radar signal transceiver for transmitting and receiving waves outward. Or, the "vehicle radar installed outside the vehicle cockpit" can be understood as a "transducer for transmitting electromagnetic waves or ultrasonic waves, etc." in a radar device, while the "processor for generating or processing electromagnetic waves or ultrasonic waves, etc." may not be installed outside the vehicle cockpit.

[0139] It can be understood that the specific numerical value of the preset distance can be set according to the actual situation. For example, in some embodiments, the distance between the vehicle radar and the "contact surface of the tire and the ground" is 1 meter, then the aforementioned preset distance can be 1 meter. Considering errors, the aforementioned preset distance can be a value slightly less than 1 meter, such as 0.9 meter.

[0140] In this way, the embodiments of the present application enable the vehicle to determine the type of the vehicle driving section according to the distance information between the vehicle radar and the accumulated objects on the road surface in the second driving environment information collected or generated by the vehicle radar. For example, when the distance information indicates that the distance between the vehicle radar and the accumulated objects on the road surface is less than the preset distance, it is confirmed that the type of the vehicle driving section is a wading section, and / or when the distance information indicates that the distance between the vehicle radar and the accumulated objects on the road surface is higher than the preset distance, it is confirmed that the type of the vehicle driving section is a non-wading section. Furthermore, the credibility of the type of the vehicle driving section confirmed by the first driving environment information is improved to a certain extent.

[0141] In addition, it should also be noted that in some embodiments as shown in Figure 2 and Figure 3 where the vehicle radar is located outside the vehicle cockpit, the radar transmitting head of the vehicle radar emits waves directly downward at an angle of "90° to the horizontal plane". Also, when installing the vehicle radar, the contact between the radar beam and the vehicle body can be considered, that is, when installing the vehicle radar, it is necessary to avoid the vehicle body being within the radar beam to avoid the situation where the vehicle wrongly confirms the type of the vehicle driving section as a wading section due to the vehicle radar detecting the vehicle body.

[0142] In some embodiments of the present application, the vehicle acoustic detection unit is installed outside the vehicle cockpit. The first driving environment information includes the reception time of the echo corresponding to the acoustic wave emitted by the vehicle acoustic detection unit. When the reception time is less than the preset time, the type of the vehicle driving section is confirmed as a wading section, and / or when the reception time is higher than the preset time, the type of the vehicle driving section is confirmed as a non-wading section.

[0143] That is, the vehicle acoustic detection unit of the embodiment of the present application is installed outside the vehicle cockpit. Furthermore, when the vehicle acoustic detection unit can accurately or reliably detect an external object through the acoustic wave, it indicates that the vehicle acoustic detection unit is submerged in water, and thus the type of the vehicle driving section is confirmed as a wading section.

[0144] Optionally, to ensure the reliability of the type of the vehicle driving section confirmed by the first driving environment information, in some embodiments, the vehicle acoustic detection unit is installed on the bottom of the vehicle. To more clearly illustrate the embodiments of the present application, please refer to again. To more clearly illustrate the embodiments of the present application, please refer to again Figure 2 and Figure 3 . That is, the vehicle acoustic detection unit 210 is installed on the vehicle chassis and can detect water through waves such as electromagnetic waves or ultrasonic waves (corresponding to the cone directly below the vehicle acoustic detection unit 210 in Figure 4 or Figure 5 ) when submerged in water to obtain the first driving environment information.

[0145] Furthermore, in Figure 2 , when the vehicle is traveling in the forward direction (corresponding to the arrow in Figure 2 and Figure 3 ), since there is no accumulated water on the ground 300, or rather, since the type of the current vehicle driving section is a non-wading section, after the vehicle acoustic detection unit 210 emits an acoustic wave, due to the propagation loss and attenuation of the acoustic wave in the air medium, the emitted acoustic wave is difficult to form an echo that can be fed back to the vehicle acoustic detection unit 210, or rather, the echo is difficult to return to the vehicle acoustic detection unit 210 within the preset time. Therefore, the reception time of the echo in the first driving environment information exceeds the preset time, and the type of the vehicle driving section is confirmed as a non-wading section.

[0146] While in Figure 3 , since the water surface 400 submerges the vehicle acoustic detection unit 210 and the propagation loss and attenuation of the acoustic wave in the water medium are weak, after the vehicle acoustic detection unit 210 emits an acoustic wave (corresponding to Figure 3After the cone directly below the vehicle acoustic wave detection unit 210, the echo of the acoustic wave will return to the vehicle acoustic wave detection unit 210 in a relatively short time. That is, the reception time of the echo corresponding to the emitted acoustic wave is within the preset time. Furthermore, the type of the vehicle driving section is confirmed as a wading section.

[0147] In this way, the embodiment of the present application enables the vehicle to determine, according to the vehicle acoustic wave detection unit installed outside the vehicle cockpit, the reception time of the echo corresponding to the acoustic wave emitted outward by the vehicle acoustic wave detection unit in the first driving environment information obtained by acoustic wave detection. Furthermore, the type of the vehicle driving section is determined according to the reception time of the echo. That is, when the reception time is less than the time, the type of the vehicle driving section is confirmed as a wading section, and / or when the reception time is higher than the preset time, the type of the vehicle driving section is confirmed as a non-wading section. Thus, the credibility of the type of the vehicle driving section determined by the first driving environment information is improved or guaranteed to a certain extent.

[0148] In addition, it can be understood that the preset time in the embodiment of the present application is a content that can be set according to the actual situation and can be determined according to factors such as vehicle type, the accuracy of the vehicle acoustic wave detection unit 210, and the installation height of the vehicle acoustic wave detection unit 210. Specifically, in some embodiments, the preset time t satisfies the following formula, that is:

[0149] d = 0.5 * c water * t * cosθ

[0150] In the formula, d is the set value of the acoustic wave detection depth, c water is the propagation speed of the acoustic wave in the water medium, and θ is the inclination angle between the horizontal plane and the acoustic wave transmitter during vehicle driving. Among them, θ can be measured by a sensor installed on the vehicle body, such as an inertial measurement unit.

[0151] Therefore, when setting the preset time of the embodiment of the present application, the specific numerical value of the preset time can be determined with reference to the above formula.

[0152] Moreover, it can also be understood that the vehicle acoustic wave detection unit installed outside the vehicle cockpit can be understood as an acoustic wave detection unit transducer or an acoustic wave transceiver for sending and receiving waves outward. Or rather, the "vehicle acoustic wave detection unit installed outside the vehicle cockpit" can be understood as the "transducer for sending and receiving acoustic waves" in an acoustic wave detection unit device, and the "processor for generating or processing acoustic waves" may not be installed outside the vehicle cockpit.

[0153] In some embodiments of the present application, the control method includes:

[0154] When it is confirmed according to the first driving environment information that the type of the vehicle driving section is a wading section, the vehicle is controlled to enter a preset working mode, wherein when the vehicle changes from a state of not being in the preset working mode to a state of being in the preset working mode, the maximum driving force that the vehicle can generate decreases.

[0155] The processing unit according to the embodiment of the present application is further configured to control the vehicle to enter a preset working mode when it is confirmed according to the first driving environment information that the type of the vehicle driving section is a wading section, wherein when the vehicle changes from a state of not being in the preset working mode to a state of being in the preset working mode, the maximum driving force that the vehicle can generate decreases.

[0156] The processor according to the embodiment of the present application is further configured to control the vehicle to enter a preset working mode when it is confirmed according to the first driving environment information that the type of the vehicle driving section is a wading section, wherein when the vehicle changes from a state of not being in the preset working mode to a state of being in the preset working mode, the maximum driving force that the vehicle can generate decreases.

[0157] That is to say, the vehicle according to the embodiment of the present application can also, when it is confirmed according to the first driving environment information that the vehicle driving section is a wading section, or rather, control the maximum driving force of the vehicle to decrease, so as to reduce to a certain extent the probability of the vehicle getting out of control caused by accelerating.

[0158] For example, when the user drives the vehicle on a non-wading section and steps on the accelerator pedal, the vehicle can generate a maximum driving force of 200 N to accelerate. When the user drives the vehicle on a wading section and the vehicle enters the preset working mode, after the user steps on the accelerator pedal, the vehicle can generate a maximum driving force of 100 N to accelerate. Thus, the probability of the vehicle getting out of control caused by accelerating decreases.

[0159] Further, the vehicle according to the embodiment of the present application can also limit the maximum driving speed of the vehicle when it is confirmed according to the first driving environment information that the vehicle driving section is a wading section. For example, when the user drives the vehicle on a non-wading section, the user can make the vehicle move forward at a maximum speed of 150 yards. When the user drives the vehicle on a wading section and the vehicle enters the preset working mode, the user can make the vehicle move forward at a maximum speed of 60 yards. Thus, the probability of the vehicle getting out of control caused by accelerating further decreases.

[0160] In this way, the embodiment of the present application enables the vehicle to reduce the maximum driving force that the vehicle can generate based on the entry of the preset working mode. Furthermore, it can reduce to a certain extent the probability of the vehicle getting out of control due to accelerating on a wading section, and the safety of the vehicle and the user in the vehicle is guaranteed to a certain extent.

[0161] Optionally, in some embodiments of the present application, reference may be specifically made to Figure 7 , Figure 7 which is a schematic diagram of a vehicle in some embodiments of the present application. That is, the vehicle in the embodiments of the present application is based on the front domain controller 230, the rear domain controller 240, the left domain controller 250, and the right domain controller 260 to manage and control each electronic and electrical component in the vehicle. At the same time, in the embodiments of the present application, to avoid the situation where the vehicle cannot obtain the first driving environment information by controlling the vehicle acoustic detection unit 210 through the vehicle radar when a single vehicle radar fails, a first vehicle radar 221 and a second vehicle radar 222 are provided in the vehicle to achieve radar redundancy. In addition, when the vehicle acoustic detection unit 210 can confirm that the vehicle driving section type is a wading section according to the two second driving environment information respectively obtained by the first vehicle radar 221 and the second vehicle radar 222, the first driving environment information is obtained or collected.

[0162] In addition, it should be noted that Figure 7 the vehicle acoustic detection unit 210 and the first vehicle radar 221 in

[0163] being managed and controlled by the left domain controller and the second vehicle radar 222 being managed and controlled by the right domain controller are only one of the feasible embodiments of the present application. Which domain controller specifically manages and controls the vehicle acoustic detection unit 210, the first vehicle radar 221, and the second vehicle radar 222 can be set according to the actual situation. For example, in some embodiments, the vehicle acoustic detection unit 210, the first vehicle radar 221, and the second vehicle radar 222 are all managed and controlled by the front domain controller 230. Figure 8 , Figure 8 which is a schematic diagram of the vehicle operation process in some embodiments of the present application. Specifically, after power-on, the vehicle can control the vehicle radar to start working so that the vehicle radar signal source generates a signal. The signal conditioning circuit processes the signal generated by the radar signal source, such as signal amplification. The processed radar signal then receives the echo of the radar signal from the outside, and when it is determined according to the echo that the distance between the vehicle radar and the road deposit is less than the preset distance, that is, when it is confirmed according to the second driving environment information that the vehicle driving section type is a wading section, the vehicle acoustic detection unit is then controlled to enter the working state.

[0164] After the vehicle acoustic detection unit enters the working state, the acoustic signal source will generate an acoustic signal, and the acoustic generated signal enters the corresponding signal conditioning circuit for corresponding processing, such as signal amplification, etc. The processed acoustic signal is sent to the outside by the transducer. At the same time, the transducer is based on electronic beam scanning. The receiving-side analog conditioning circuit processes the electronic beam scanning result to facilitate the subsequent generation of the corresponding first underwater image.

[0165] When a transducer for receiving the echo of a sound wave receives an echo signal, the signal processing circuit on the sound wave receiving side processes the received echo signal and determines the type of the vehicle driving section according to the processed sound wave signal.

[0166] If it is confirmed according to the first driving environment information that the type of the vehicle driving section is a non-wading section, return to the initial step, that is, the step of generating a signal by the radar signal source. On the contrary, if it is confirmed according to the first driving environment information that the type of the vehicle driving section is a wading section, the vehicle can generate a first underwater image based on the signal obtained by previously processing the electronic beam scanning result. Then, according to the first underwater image and a pre-trained image recognition network, determine the position of the target obstacle, and perform obstacle avoidance driving according to the position of the target obstacle.

[0167] At the same time, input the first underwater image into a pre-trained generative adversarial network to obtain a second underwater image with a resolution higher than that of the first underwater image, and then display the second underwater image on a vehicle display screen such as a head-up display.

[0168] In addition, the vehicle will also enter a preset working mode to temporarily reduce the maximum driving force of the vehicle.

[0169] In addition, the vehicle can also control the vehicle radar to continue to work to detect the distance between the vehicle radar and the road accumulation, that is, the water surface height. When the water surface height is higher than a preset value, such as 1 meter, it is determined that the water surface height adjustment is satisfied, and then the vehicle issues a warning message. For example, the warning message can be a voice and text of "The wading depth of this vehicle is too high. Please drive carefully" to prompt the user to drive carefully.

[0170] An embodiment of the present application also provides an electronic device. The electronic device includes a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the control method of the above vehicle is implemented.

[0171] An embodiment of the present application also provides a vehicle. The vehicle includes the above control device or includes the above electronic device.

[0172] The present application also provides a computer-readable storage medium storing a computer program, which when executed by one or more processors, implements the control method of the above vehicle.

[0173] In the description of this specification, the descriptions referring to terms such as "specifically", "furthermore", "specially", "understandably", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0174] Any process or method description shown in the flowchart or described in other ways herein can be understood to represent a module, segment or part of code including one or more executable instructions for implementing a specific logical function or process, and the scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, not in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0175] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present application.

Claims

1. A control method for a vehicle, characterized in that, Including: Obtaining first driving environment information, where the first driving environment information is obtained by a vehicle acoustic wave detection unit; When it is confirmed according to the first driving environment information that the vehicle driving road section type is a wading section, controlling the vehicle to drive according to a second underwater image, where the second underwater image is obtained based on a first underwater image and a pre-determined generative adversarial network, and the first underwater image is obtained by the vehicle acoustic wave detection unit when the vehicle driving road section type is a wading section.

2. The method according to claim 1, characterized in that, The method further includes: When the vehicle driving road section type is a wading section, determining an image encoding result according to the first underwater image and an encoding sub-network of the generative adversarial network, and determining the second underwater image according to the image encoding result and a decoding sub-network of the generative adversarial network.

3. The method according to claim 2, characterized in that, The encoding sub-network includes a convolutional neural network, and the decoding sub-network includes a transposed convolutional neural network.

4. The method according to claim 1, characterized in that, The vehicle acoustic wave detection unit is installed outside the vehicle cockpit, and the vehicle acoustic wave detection unit is configured to be able to scan the underwater environment by acoustic waves to generate the first underwater image when submerged in water.

5. The method according to claim 1, characterized in that, The controlling the vehicle to drive according to the second underwater image when it is confirmed according to the first driving environment information that the vehicle driving road section type is a wading section includes: When it is confirmed according to the first driving environment information that the vehicle driving road section type is a wading section, displaying the second underwater image.

6. The method according to claim 1, characterized in that, The method further includes: When it is confirmed according to the first driving environment information that the vehicle driving road section type is a wading section, controlling the vehicle to avoid driving past a target obstacle according to the position of the target obstacle in the first water body image, where the position of the target obstacle is determined according to the first water body image and a pre-determined image recognition model.

7. The method according to any one of claims 1-6, characterized in that, The obtaining the first driving environment information includes: When it is confirmed according to second driving environment information that the vehicle driving road section type is a wading section, obtaining the first driving environment information, where the second driving environment information is obtained by a vehicle radar.

8. The method according to claim 7, characterized in that, The vehicle radar is installed outside the vehicle cockpit, and the second driving environment information includes distance information of the vehicle radar relative to accumulated objects on the road surface; when the distance information is that the distance of the vehicle radar relative to the accumulated objects on the road surface is less than a preset distance, the vehicle driving road section type is confirmed as a wading section, and / or when the distance information is that the distance of the vehicle radar relative to the accumulated objects on the road surface is higher than the preset distance, the vehicle driving road section type is confirmed as a non-wading section.

9. The method according to any one of claims 1-8, characterized in that, The vehicle acoustic wave detection unit is installed outside the vehicle cockpit, and the first driving environment information includes the reception time of an echo corresponding to the acoustic wave emitted by the vehicle acoustic wave detection unit; when the reception time is less than a preset time, the vehicle driving road section type is confirmed as a wading section, and / or when the reception time is higher than the preset time, the vehicle driving road section type is confirmed as a non-wading section.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: When it is confirmed according to the first driving environment information that the road section type where the vehicle is traveling is a wading section, the vehicle is controlled to enter a preset working mode. Among them, when the vehicle changes from a state of not being in the preset working mode to a state of being in the preset working mode, the maximum driving force that the vehicle can generate decreases.

11. A control device, characterized in that, It includes: a transceiver unit for obtaining first driving environment information, where the first driving environment information is obtained through a vehicle acoustic detection unit; a processing unit for controlling the vehicle to travel according to a second underwater image when it is confirmed according to the first driving environment information that the road section type where the vehicle is traveling is a wading section, where the second underwater image is obtained based on a first underwater image and a pre-determined generative adversarial network, and the first underwater image is obtained by the vehicle acoustic detection unit when the road section type where the vehicle is traveling is a wading section.

12. An electronic device, characterized in that, It includes a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the method described in any one of claims 1-10 is implemented.

13. A vehicle, characterized in that, It includes the control device described in claim 11, or includes the electronic device described in claim 12.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program. When the computer program is executed by one or more processors, the method described in any one of claims 1-10 is implemented.

Images