Vehicle control method and device, vehicle, storage medium and product
By obtaining and analyzing the driving status and environmental information of the vehicle, using neural network models to identify the sliding status of the vehicle in front and avoiding it, the problem of accurate identification and avoidance in the prior art is solved, and driving safety is improved.
Patent Information
- Application Number
- CN202411299483.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-18
- Publication Date
- 2024-11-08
AI Technical Summary
The prior art is difficult to accurately identify the slipping status of the vehicle ahead and avoid it in time, resulting in low detection accuracy and ineffective avoidance, which affects the safety of the vehicle.
By obtaining the driving status and environmental information of the target vehicle, the neural network model is used to identify image information to judge the slipping status of the vehicle ahead, and perform avoidance operations when the avoidance conditions are met, including the first neural network model to judge displacement changes and the second nerve Network model analyzes movable path information.
It improves the accurate judgment and avoidance operation of the vehicle ahead, reduces misjudgment and misoperation, and improves driving safety.
Smart Images

Figure CN118907146A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicles, and more specifically, to a vehicle control method, a vehicle control device, a vehicle, a computer-readable storage medium, and a computer program product. Background Art
[0002] As the proportion of autonomous vehicles in the automotive market increases, the requirements for the safety and reliability of autonomous vehicles are also getting higher and higher. During the driving process of the vehicle, if the vehicle in front is in a slipping state, it will affect the driving safety of the vehicle. Therefore, how to identify the slipping state of the vehicle in front and avoid it is very important.
[0003] In the related art, radar, laser and other sensor equipment are usually used to monitor and analyze the vehicle's surrounding environment in real time to determine whether the vehicle ahead is in a slipping state. However, this method may be affected by environmental factors such as weather and light, which may affect the accuracy of the detection results. Therefore, the accuracy rate is low, and the related art cannot avoid it in time when it is determined that the vehicle ahead is in a slipping state. Summary of the invention
[0004] In view of this, the present invention provides a vehicle control method, a vehicle control device, a vehicle, a computer-readable storage medium and a computer program product, which aim to more accurately judge the state of a target front vehicle and perform avoidance operations when the target front vehicle is in a slipping state, thereby reducing the risk of vehicle damage.
[0005] In order to achieve the above object, the present invention adopts the following technical scheme:
[0006] In a first aspect, the present invention provides a vehicle control method, the method comprising:
[0007] Obtain the current driving status information of the target vehicle and determine whether the target vehicle is stationary;
[0008] In response to determining that the target vehicle is stationary, obtaining environmental information of the target vehicle, wherein the environmental information of the target vehicle at least includes image information of a target preceding vehicle, where the target preceding vehicle is a preceding vehicle in the same lane as the target vehicle;
[0009] If it is determined based on the image information of the target vehicle in front that the target vehicle in front is in a slipping state, the target vehicle is controlled to avoid the target vehicle in front;
[0010] If it is determined based on the image information of the target front vehicle that the target front vehicle is in a normal state, the target vehicle is controlled to travel normally.
[0011] In a possible implementation, the controller determines that the target front vehicle is in a sliding state based on the image information of the target front vehicle, including:
[0012] The image information of the target front vehicle is recognized by the first neural network model to obtain the displacement change information between the target front vehicle and the target vehicle;
[0013] In response to the displacement change information being higher than a preset threshold, it is determined that the target front vehicle is in a slipping state.
[0014] In a possible implementation, the environmental information of the target vehicle also includes movable path information of the target vehicle, and controlling the target vehicle to avoid the target vehicle in front includes:
[0015] Analyzing the movable path information of the target vehicle through the second neural network model to obtain an analysis result; wherein the analysis result at least includes movable range information and obstacle information, and the movable range information includes a movable range;
[0016] Determine whether the target vehicle meets the avoidance conditions based on the analysis results;
[0017] In response to determining that the target vehicle satisfies the avoidance condition, the target vehicle is controlled to avoid the target preceding vehicle.
[0018] In a possible implementation, in response to determining that the target vehicle satisfies the avoidance condition, controlling the target vehicle to avoid the target preceding vehicle includes:
[0019] In response to determining that the obstacle information is no obstacle and the movable range is greater than a preset movable range threshold, determining that the target vehicle meets the avoidance condition;
[0020] Control the target vehicle to avoid the target vehicle in front along the movable range.
[0021] In a possible implementation, the method further includes:
[0022] In response to determining that the target front vehicle is in a slipping state, a first warning message is generated; wherein the first warning message is used to indicate to the user that the target vehicle needs to be avoided.
[0023] In a possible implementation, the method further includes:
[0024] In response to determining that the target vehicle does not meet the avoidance condition, a second warning message is generated; wherein the second warning message is used to prompt a user that the target vehicle does not meet the avoidance condition.
[0025] In a second aspect, the present invention provides a vehicle control device, including an acquisition module, a determination module, and a control module, wherein:
[0026] An acquisition module, electrically connected to the determination module, for acquiring the driving state information of the current target vehicle and determining whether the target vehicle is in a stationary state;
[0027] The determination module is electrically connected to the acquisition module and the control module respectively, and is used to acquire environmental information of the target vehicle in response to determining that the target vehicle is in a stationary state, wherein the environmental information of the target vehicle at least includes image information of a target preceding vehicle, and the target preceding vehicle is a preceding vehicle in the same lane as the target vehicle;
[0028] The determination module is also used to send the environmental information of the target vehicle to the control module;
[0029] A control module is electrically connected to the determination module, and is used to determine that the target vehicle in front is in a slipping state based on the image information of the target vehicle in front, and control the target vehicle to avoid the target vehicle in front;
[0030] The control module is also used to determine that the target front vehicle is in a normal state based on the image information of the target front vehicle, and control the target vehicle to drive normally.
[0031] The vehicle control device provided by the present invention can obtain image information of a target front vehicle when the vehicle is in a stationary state, and then identify the image information of the target front vehicle to accurately judge the state of the target front vehicle, ensuring that avoidance operation is performed only when the target front vehicle is in a slipping state, and maintaining normal driving when the target front vehicle is in a normal state, thereby reducing the possibility of misjudgment and misoperation and improving driving safety.
[0032] In a third aspect, the present invention provides a vehicle, comprising:
[0033] A control unit, the control unit includes a processor and a memory, the memory is used to store computer program code, the computer program code includes computer instructions, when the processor executes the computer instructions, the vehicle control device executes the vehicle control method such as the first aspect and any possible implementation thereof.
[0034] The vehicle provided by the present invention can obtain image information of a target front vehicle when the vehicle is in a stationary state, and then identify the image information of the target front vehicle to accurately judge the state of the target front vehicle, ensuring that avoidance operation is performed only when the target front vehicle is in a slipping state, and maintaining normal driving when the target front vehicle is in a normal state, thereby reducing the possibility of misjudgment and misoperation and improving driving safety.
[0035] In a fourth aspect, the present invention provides a computer-readable storage medium, comprising: computer instructions, which, when executed on a control device of a vehicle, cause the control device of the vehicle to execute a vehicle control method as in the first aspect and any possible implementation thereof.
[0036] The computer-readable storage medium provided by the present invention can obtain image information of a target front vehicle when the vehicle is in a stationary state, and then identify the image information of the target front vehicle to accurately judge the state of the target front vehicle, ensuring that avoidance operation is performed only when the target front vehicle is in a slipping state, and maintaining normal driving when the target front vehicle is in a normal state, thereby reducing the possibility of misjudgment and misoperation and improving driving safety.
[0037] In a fifth aspect, the present invention provides a computer program product, comprising: computer instructions, which, when executed on a control device of a vehicle, cause the control device of the vehicle to execute a vehicle control method as in the first aspect and any possible implementation thereof.
[0038] The computer program product provided by the present invention can obtain image information of a target front vehicle when the vehicle is in a stationary state, and then identify the image information of the target front vehicle to accurately judge the state of the target front vehicle, ensuring that avoidance operation is performed only when the target front vehicle is in a slipping state, and maintaining normal driving when the target front vehicle is in a normal state, thereby reducing the possibility of misjudgment and misoperation and improving driving safety.
[0039] Compared with the prior art, the vehicle control method provided by the present invention achieves at least the following beneficial effects: obtaining the driving state information of the current target vehicle and judging whether the target vehicle is in a stationary state. Further, in response to determining that the target vehicle is in a stationary state, obtaining the environmental information of the target vehicle, wherein the environmental information of the target vehicle at least includes the image information of the target front vehicle, and the target front vehicle is the front vehicle in the same lane as the target vehicle. If it is determined based on the image information of the target front vehicle that the target front vehicle is in a slipping state, the target vehicle is controlled to avoid the target front vehicle; if it is determined based on the image information of the target front vehicle that the target front vehicle is in a normal state, the target vehicle is controlled to drive normally. The present invention can obtain the image information of the target front vehicle when the vehicle is in a stationary state, and then identify the image information of the target front vehicle to accurately judge the state of the target front vehicle, ensure that the avoidance operation is performed only when the target front vehicle is in a slipping state, and maintain normal driving when the target front vehicle is in a normal state, reduce the possibility of misjudgment and misoperation, and improve driving safety.
[0040] Of course, any product implementing the present invention does not necessarily need to achieve all of the above technical effects at the same time.
[0041] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.
[0043] Figure 1 is a flow chart of a vehicle control method provided by an embodiment of the present invention;
[0044] Figure 2 is a flow chart of another vehicle control method provided by an embodiment of the present invention;
[0045] Figure 3 It is a structural schematic diagram of a vehicle control device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0046] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.
[0047] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
[0048] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.
[0049] In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.
[0050] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.
[0051] Example 1
[0052] Reference Figure 1 , Figure 1 1 is a flow chart of a vehicle control method provided by an embodiment of the present invention. The vehicle control method includes the following steps.
[0053] In step S11, the driving state information of the current target vehicle is obtained, and it is determined whether the target vehicle is in a stationary state.
[0054] The driving status information is used to characterize the running status of the target vehicle, including, for example, speed information, acceleration information, direction information, and position information.
[0055] For example, the driving state information of the target vehicle may be acquired through sensors (for example, including but not limited to speed sensors, accelerometers) or positioning systems installed on the vehicle body, so that it is possible to determine whether the target vehicle is stationary based on the driving state information.
[0056] In step S12, in response to determining that the target vehicle is in a stationary state, environmental information of the target vehicle is acquired.
[0057] For example, when the speed of the target vehicle represented by the driving state information is 0, it can be determined that the target vehicle is stationary. Therefore, after determining that the target vehicle is stationary, the controller can obtain the environmental information of the target vehicle through a vehicle-mounted camera or other equipment. The environmental information of the target vehicle may include but is not limited to objects around the target vehicle, road signs, and traffic lights, etc., which are not limited in the present invention.
[0058] For example, the vehicle-mounted camera includes a CMOS (Complementary Metal Oxide Semiconductor) camera with a resolution of 1280*720 and a frame rate of 30fps, thereby obtaining the environmental information of the target vehicle in real time. Furthermore, a high-speed storage device (such as a solid-state hard disk with a read and write speed of 500MB / s) can be used to quickly save the environmental information captured by the vehicle-mounted camera for timely application.
[0059] Optionally, the environmental information of the target vehicle includes at least image information of a target preceding vehicle, where the target preceding vehicle is a vehicle in the same lane as the target vehicle. Thus, the controller can provide support for subsequent vehicle control decisions based on the image information of the target preceding vehicle.
[0060] In step S13, if it is determined based on the image information of the target front vehicle that the target front vehicle is in a slipping state, the target vehicle is controlled to avoid the target front vehicle.
[0061] In step S14, if it is determined based on the image information of the target front vehicle that the target front vehicle is in a normal state, the target vehicle is controlled to travel normally.
[0062] For example, the image information of the target vehicle in front can be identified by image recognition technology to determine whether the target vehicle in front is in a slipping state, wherein the slipping state includes, but is not limited to, the target vehicle in front automatically sliding backward or backing up, deviating from the lane, showing signs of failure (such as smoking), and other unstable behaviors.
[0063] For example, in the process of identifying the image information of the target vehicle in front through image recognition technology, the image information can be processed and analyzed through an open source computer vision library (such as OpenCV), such as performing pre-processing operations such as cropping, scaling, and grayscale conversion on the image information, and then input into a neural network model for recognition.
[0064] For example, when it is determined that the target front vehicle is in a slipping state, the controller can control the target vehicle to perform an avoidance operation, for example, including but not limited to changing lanes or driving in a direction away from the target front vehicle, so as to avoid a possible collision or accident.
[0065] For example, when it is determined that the target preceding vehicle is in a normal state, the controller can control the target vehicle to maintain the current driving state.
[0066] The above method can determine the driving state of the target vehicle in front by identifying the image information of the target vehicle in front, and control the target vehicle to perform a response action according to the driving state of the target vehicle in front, thereby ensuring driving safety.
[0067] The vehicle control method provided by the present invention achieves at least the following beneficial effects: the controller obtains the driving state information of the current target vehicle and determines whether the target vehicle is in a stationary state. Further, in response to determining that the target vehicle is in a stationary state, the environmental information of the target vehicle is obtained, wherein the environmental information of the target vehicle at least includes the image information of the target front vehicle, and the target front vehicle is the front vehicle in the same lane as the target vehicle. If it is determined based on the image information of the target front vehicle that the target front vehicle is in a slipping state, the target vehicle is controlled to avoid the target front vehicle; if it is determined based on the image information of the target front vehicle that the target front vehicle is in a normal state, the target vehicle is controlled to drive normally. The present invention can obtain the image information of the target front vehicle when the vehicle is in a stationary state, and then identify the image information of the target front vehicle to accurately judge the state of the target front vehicle, ensure that the avoidance operation is performed only when the target front vehicle is in a slipping state, and maintain normal driving when the target front vehicle is in a normal state, reduce the possibility of misjudgment and misoperation, and improve driving safety.
[0068] Optionally, determining that the target front vehicle is in a slipping state based on the image information of the target front vehicle includes: identifying the image information of the target front vehicle through a first neural network model to obtain displacement change information between the target front vehicle and the target vehicle; and the controller determines that the target front vehicle is in a slipping state in response to the displacement change information being higher than a preset threshold.
[0069] For example, the controller can input the image information of the target vehicle in front into the first neural network model, so that the first neural network model can identify the displacement change information of the target vehicle in front and the target vehicle by analyzing the image information of the target vehicle in front. For example, the first neural network model can calculate the displacement change information of the target vehicle in front and the target vehicle by analyzing the feature points in the image information (such as the front and tail lights of the target vehicle in front), combined with the focal length, viewing angle and other parameters of the camera that captured the image information.
[0070] It should be noted that the first neural network model is a mathematical model that imitates the neural network structure of the human brain, which can be used to process and analyze complex data, and automatically learn rules from the data to perform prediction or classification tasks. The present invention does not limit the type of the above-mentioned first neural network model. For example, the first neural network model can include a feedforward neural network model, a convolutional neural network model, and a recurrent neural network model.
[0071] For example, the image information of the target vehicle in front can be identified through a convolutional neural network model, and the displacement change information of the target vehicle in front and the target vehicle can be obtained. Among them, the convolutional neural network model is a deep learning model specially used to process grid structure data (such as images), and is widely used in tasks such as image classification, target detection, and semantic segmentation. The convolutional neural network model has a high efficiency in processing image information, and has a certain robustness to transformations such as translation and rotation of image information. Therefore, based on the convolutional neural network model, the image information of the target vehicle in front can be identified, and a more accurate identification result can be obtained, so that the displacement change information of the target vehicle in front and the target vehicle can be determined more accurately.
[0072] For example, after obtaining the displacement change information between the target front vehicle and the target vehicle, the displacement change information may be compared with a preset threshold value to determine whether the target front vehicle is in a sliding state or a normal state.
[0073] Among them, the preset threshold is used to characterize the maximum displacement change threshold at which there is no collision risk between the target front vehicle and the target vehicle. The present invention does not limit the preset threshold. For example, the preset threshold is 0.5m / s, 0.8m / s, 1m / s, etc.
[0074] It should be understood that when the displacement change information between the target front vehicle and the target vehicle is higher than a preset threshold, it can be determined that the target front vehicle is in a slipping state, that is, there is a potential collision risk between the target front vehicle and the target vehicle, and therefore the target vehicle can be controlled to perform avoidance measures.
[0075] For example, when the displacement change information between the target preceding vehicle and the target vehicle is less than or equal to a preset threshold, it can be determined that the target preceding vehicle is in a normal state, that is, there is no potential collision risk between the target preceding vehicle and the target vehicle, and the target vehicle can be controlled to drive normally.
[0076] The above embodiments can analyze the image information of the target front vehicle through the first neural network model, thereby obtaining the displacement change information of the target front vehicle and the target vehicle, and then determine the driving state of the target front vehicle based on the displacement change information, providing a basis for subsequent driving decisions of the target vehicle.
[0077] Optionally, the environmental information of the target vehicle also includes movable path information of the target vehicle, and controlling the target vehicle to avoid the target preceding vehicle includes: analyzing the movable path information of the target vehicle through a second neural network model to obtain an analysis result; a controller determines whether the target vehicle meets an avoidance condition based on the analysis result; and in response to determining that the target vehicle meets the avoidance condition, the controller controls the target vehicle to avoid the target preceding vehicle.
[0078] The movable path information includes the route or track that the target vehicle can move; the analysis result includes at least movable range information and obstacle information. The movable range information includes the range of the movable path of the target vehicle; the obstacle information includes obstacles on the movable path that hinder the target vehicle from traveling, such as other vehicles, pedestrians, etc.
[0079] For example, the controller can analyze the movable path information of the target vehicle through the neural network model to obtain an analysis result. Then, based on the analysis result of the neural network model, it is determined whether the target vehicle needs to avoid. Among them, the judgment conditions include but are not limited to: whether the movable range can make the target vehicle not deviate from the lane, and whether there are obstacles on the movable path, etc. The present invention is described by taking this as an example.
[0080] It should be understood that when the movable range enables the target vehicle to travel without deviating from the lane and there are no obstacles on the movable path, it means that the target vehicle has the conditions to avoid the target vehicle in front. At this time, it can be determined that the target vehicle meets the avoidance conditions and the target vehicle can be controlled to avoid.
[0081] It should be noted that the present application does not limit the second neural network model for analyzing movable path information. For example, the second neural network model includes a deep neural network model, which is an artificial neural network model with a multi-layer structure, constructed by multiple levels of neurons (or nodes) to simulate the learning process of the human brain to achieve complex data processing and pattern recognition tasks. The multi-layer structure of the deep neural network model enables it to automatically learn and extract features from complex data, so it has a high accuracy rate and is suitable for analysis of various types of data (such as images, text, audio, time series, etc.).
[0082] For example, after determining that the target vehicle in front is in a slipping state based on the image information of the target vehicle in front, a prompt message can also be sent to the user to prompt the user to perform intelligent environmental recognition, so that in response to the user confirming the execution of intelligent environmental recognition, the environmental information is obtained through deep learning model recognition, and the target vehicle is controlled by ADAS to perform automatic avoidance within a preset distance range. The preset distance range can be 1m, 2m, etc. Further, the deep learning model can be trained by the deep learning framework TensorFlow, which is not limited in this application.
[0083] It should be noted that ADAS (Advanced Driver Assistance Systems) is a type of intelligent system that aims to improve driving safety and convenience by enhancing the driver's perception, decision-making and operating capabilities. ADAS can use on-board sensors (such as cameras, radars, ultrasonic sensors, lidar, etc.) to monitor the environment around the vehicle in real time and provide warnings to the driver or directly intervene to prevent collisions or reduce driving dangers.
[0084] TensorFlow is an open source deep learning framework that is widely used in the fields of machine learning and deep learning, especially in building and training neural network models. TensorFlow provides a complete set of tools to help developers with the entire process from model design to training and deployment.
[0085] The above method can analyze the movable path information of the target vehicle based on the second neural network model to determine whether the target vehicle meets the avoidance conditions, and control the target vehicle to avoid when it is determined that the target vehicle meets the avoidance conditions. This enables the target vehicle to make an intelligent decision on whether to avoid under complex road conditions, thereby improving driving safety.
[0086] Optionally, in response to determining that the target vehicle meets the avoidance condition, controlling the target vehicle to avoid the target front vehicle, including: in response to determining that the obstacle information is no obstacle and the movable range is greater than a preset movable range threshold, determining that the target vehicle meets the avoidance condition; controlling the target vehicle to avoid the target front vehicle along the movable range.
[0087] The preset moving range threshold is used to characterize the minimum moving range that the target vehicle can travel. That is, when the movable range is greater than the preset moving range threshold, it means that the target vehicle can travel within the movable range, that is, it can perform avoidance operations within the movable range; when the movable range is not greater than the preset moving range threshold, it means that the target vehicle cannot travel within the movable range, that is, it cannot perform avoidance operations within the movable range.
[0088] For example, when the obstacle information is determined to be no obstacle and the movable range is greater than the preset movable range threshold, it means that the target vehicle can successfully avoid the obstacle within the movable range. Therefore, it can be determined that the target vehicle meets the avoidance conditions and the target vehicle is controlled to avoid the obstacle.
[0089] The above method can determine that there are no obstacles in the movable path of the target vehicle and the movable range is greater than the preset movable range threshold, confirm that the target vehicle meets the avoidance conditions, and control the target vehicle to perform avoidance operations, thereby ensuring the safety and reliability of the target vehicle's avoidance.
[0090] Optionally, the vehicle control method provided by the present invention also includes: the controller generates a first warning message in response to determining that the target front vehicle is in a slipping state; optionally, the vehicle control method provided by the present invention also includes: in response to determining that the target vehicle does not meet the avoidance conditions, generating a second warning message; wherein the second warning message is used to prompt the user that the target vehicle does not meet the avoidance conditions.
[0091] Example 2
[0092] Please refer to Figure 2 , Figure 2 FIG. 1 is a flow chart of another vehicle control method provided by an embodiment of the present invention. Figure 2 As shown, the controller can obtain the driving state information of the current target vehicle and determine whether the target vehicle is in a stationary state; when the controller determines that the target vehicle is in a stationary state, the environmental information of the target vehicle can be obtained. Among them, the environmental information of the target vehicle at least includes the image information of the target front vehicle. Further, it can be determined whether the target front vehicle is in a slipping state based on the image information of the target vehicle. If the controller determines that the target front vehicle is in a slipping state based on the image information of the target front vehicle, the target vehicle is controlled to avoid the target front vehicle and a first warning message is generated; if the controller determines that the target front vehicle is in a normal state based on the image information of the target front vehicle, the target vehicle is controlled to drive normally and a second warning message is generated.
[0093] The first warning information is used to indicate to the user that the target vehicle needs to be avoided; the second warning information is used to remind the user that the target vehicle does not meet the avoidance condition. The first warning information or the second warning information can be conveyed to the user through a display screen in the vehicle, a sound warning, or a steering wheel vibration, etc., which is not limited by the present invention.
[0094] For example, when the controller determines that the target vehicle in front is in a slipping state, it can generate a first warning message to indicate to the user that the target vehicle needs to be avoided. In addition, when the controller determines that the target vehicle does not meet the avoidance conditions, it can generate a second warning message to prompt the user that the target vehicle does not meet the avoidance conditions, so that the user can obtain relevant information in time and make corresponding decisions. As a result, the user can be prompted with the current state of the target vehicle through a multi-level warning mechanism, so that the user can make corresponding decisions based on the relevant information, thereby improving the safety of vehicle driving and avoiding potential accidents.
[0095] For example, after the target vehicle performs the avoidance operation, it is also possible to detect in real time whether the target vehicle in front is still in a sliding state, and whether the driver has intervened in the driving operation. In response to the driver having intervened in the driving operation and the target vehicle in front is not in a sliding state, it can be determined that the target vehicle does not have a collision risk at this time.
[0096] The above embodiments can accurately determine the state of the target front vehicle and perform an evasive operation when the target front vehicle is in a sliding state, thereby reducing the risk of vehicle damage.
[0097] It should be easily appreciated by those skilled in the art that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0098] Example 3
[0099] Figure 3 is a schematic diagram of the structure of a vehicle control device provided by an embodiment of the present invention, such as Figure 3 As shown, the vehicle control device 200 includes an acquisition module 21 , a determination module 22 , and a control module 23 .
[0100] The acquisition module 21 is electrically connected to the determination module 22 and is used to obtain the driving state information of the current target vehicle and determine whether the target vehicle is in a stationary state;
[0101] The determination module 22 is electrically connected to the acquisition module 21 and the control module 23, respectively, and is used to obtain environmental information of the target vehicle in response to determining that the target vehicle is in a stationary state, wherein the environmental information of the target vehicle at least includes image information of a target preceding vehicle, and the target preceding vehicle is a preceding vehicle in the same lane as the target vehicle;
[0102] The determination module 22 is also used to send the environmental information of the target vehicle to the control module 23;
[0103] The control module 23 is electrically connected to the determination module 22, and is used to determine that the target front vehicle is in a slipping state based on the image information of the target front vehicle, and control the target vehicle to avoid the target front vehicle;
[0104] The control module 23 is also used to determine that the target front vehicle is in a normal state based on the image information of the target front vehicle, and control the target vehicle to travel normally.
[0105] Optionally, the determination module 22 is also used to identify the image information of the target front vehicle through a neural network model to obtain displacement change information between the target front vehicle and the target vehicle; in response to the displacement change information being less than a preset threshold, it is determined that the target front vehicle is in a slipping state.
[0106] Optionally, the control module 23 is also used to analyze the movable path information of the target vehicle through the first neural network model to obtain an analysis result; wherein the analysis result at least includes movable range information and obstacle information; based on the analysis result, it is determined whether the target vehicle meets the avoidance condition; in response to determining that the target vehicle meets the avoidance condition, the target vehicle is controlled to avoid the target front vehicle.
[0107] Optionally, the control module 23 is further used to determine that the target vehicle meets the avoidance condition in response to determining that the obstacle information is no obstacle and the movable range is greater than a preset movable range threshold; and control the target vehicle to avoid the target front vehicle along the movable range.
[0108] Optionally, the determination module 22 is further configured to generate a first warning message in response to determining that the target front vehicle is in a slipping state; wherein the first warning message is configured to indicate to the user that the target vehicle needs to be avoided.
[0109] Optionally, the determination module 22 is further configured to generate a second warning message in response to determining that the target vehicle does not satisfy the avoidance condition; wherein the second warning message is configured to prompt the user that the target vehicle does not satisfy the avoidance condition.
[0110] Of course, the vehicle control device provided by the embodiment of the present invention includes but is not limited to the above modules.
[0111] The vehicle control device provided by the present invention is intended to accurately judge the state of a target front vehicle and perform an evasive operation when the target front vehicle is in a slipping state, thereby reducing the risk of vehicle damage.
[0112] Example 4
[0113] In an embodiment of the present invention, a vehicle is further provided, the vehicle comprising: a control unit, the control unit comprising a processor and a memory. The memory is used to store computer program code, the computer program code comprising computer instructions. When the processor executes the computer instructions, the control device of the vehicle executes each step executed by the control device of the vehicle in the method flow shown in the above method embodiment.
[0114] Example 5
[0115] An embodiment of the present invention also provides a computer-readable storage medium on which computer instructions are stored. When the computer instructions are executed on a control device of a vehicle, the control device of the vehicle executes each step executed by the control device of the vehicle in the method flow shown in the above method embodiment.
[0116] Example 6
[0117] An embodiment of the present invention also provides a computer program product, which includes computer instructions. When the computer instructions are executed on a control device of a vehicle, the control device of the vehicle executes each step executed by the control device of the vehicle in the method flow shown in the above method embodiment.
[0118] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will be appreciated by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.
Claims
1. A vehicle control method, characterized in that: The method comprises: Obtaining the driving status information of the current target vehicle and determining whether the target vehicle is in a stationary state; In response to determining that the target vehicle is stationary, acquiring environmental information of the target vehicle, wherein the environmental information of the target vehicle at least includes image information of a target preceding vehicle, and the target preceding vehicle is a preceding vehicle in the same lane as the target vehicle; If it is determined based on the image information of the target front vehicle that the target front vehicle is in a slipping state, controlling the target vehicle to avoid the target front vehicle; If it is determined based on the image information of the target front vehicle that the target front vehicle is in a normal state, the target vehicle is controlled to travel normally.
2. The method according to claim 1, characterized in that The determining that the target front vehicle is in a sliding state based on the image information of the target front vehicle includes: Recognizing the image information of the target front vehicle through a first neural network model to obtain displacement change information between the target front vehicle and the target vehicle; In response to the displacement change information being higher than a preset threshold, it is determined that the target front vehicle is in the sliding state.
3. The method according to claim 1, characterized in that The environmental information of the target vehicle also includes movable path information of the target vehicle, and the controlling the target vehicle to avoid the target preceding vehicle includes: Analyzing the movable path information of the target vehicle through a second neural network model to obtain an analysis result; wherein the analysis result at least includes movable range information and obstacle information, and the movable range information includes a movable range; Determining whether the target vehicle meets the avoidance condition based on the analysis result; In response to determining that the target vehicle satisfies the avoidance condition, the target vehicle is controlled to avoid the target preceding vehicle.
4. The method according to claim 3, characterized in that In response to determining that the target vehicle satisfies the avoidance condition, controlling the target vehicle to avoid the target preceding vehicle includes: In response to determining that the obstacle information indicates that there is no obstacle and the movable range is greater than a preset movable range threshold, determining that the target vehicle satisfies the avoidance condition; The target vehicle is controlled to avoid the target front vehicle along the movable range.
5. The method according to claim 1, characterized in that The method further comprises: In response to determining that the target front vehicle is in a slipping state, a first warning message is generated; wherein the first warning message is used to indicate to the user that the target vehicle needs to be avoided.
6. The method according to claim 3, characterized in that The method further comprises: The controller generates a second warning message in response to determining that the target vehicle does not satisfy the avoidance condition; wherein the second warning message is used to prompt a user that the target vehicle does not satisfy the avoidance condition.
7. A vehicle control device, characterized in that: It includes an acquisition module, a determination module, and a control module, wherein: The acquisition module is electrically connected to the determination module and is used to acquire the driving state information of the current target vehicle and determine whether the target vehicle is in a stationary state; The determination module is electrically connected to the acquisition module and the control module respectively, and is used to acquire the environmental information of the target vehicle in response to determining that the target vehicle is in a stationary state, wherein the environmental information of the target vehicle at least includes image information of a target preceding vehicle, and the target preceding vehicle is a preceding vehicle in the same lane as the target vehicle; The determination module is also used to send the environmental information of the target vehicle to the control module; The control module is electrically connected to the determination module, and is used to determine that the target front vehicle is in a slipping state based on the image information of the target front vehicle, and control the target vehicle to avoid the target front vehicle; The control module is also used to determine that the target front vehicle is in a normal state based on the image information of the target front vehicle, and control the target vehicle to travel normally.
8. A vehicle, characterized in that: include: A control unit, the control unit includes a processor and a memory, the memory is used to store computer program code, the computer program code includes computer instructions, when the processor executes the computer instructions, the vehicle control device executes the vehicle control method as described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that: include: Computer instructions, when the computer instructions are executed on a control device of a vehicle, cause the control device of the vehicle to execute a vehicle control method as described in any one of claims 1 to 6.
10. A computer program product, the computer program product comprising: Computer instructions, when the computer instructions are executed on a control device of a vehicle, cause the control device of the vehicle to execute a vehicle control method as described in any one of claims 1 to 6.
