Vehicle driving control method, device, equipment and storage medium

Abstract

The present invention discloses a vehicle driving control method, device, equipment and storage medium, the method comprising: collecting multiple frames of target image data along the vehicle's driving direction; detecting the positional relationship between the vehicle and the control range of a stop and yield sign based on the target image data; if the positional relationship is that the vehicle is within the control range of the stop and yield sign, controlling the vehicle to decelerate until the vehicle stops in front of the stop and yield sign; and controlling the vehicle to accelerate from a stop to pass the stop and yield sign. This embodiment develops an auxiliary control process for stop and yield signs, which, combined with computer vision processing, can control the vehicle to decelerate in front of a stop and yield sign to stop and observe, and then smoothly accelerate to pass through. This can effectively reduce the violation rate of vehicles passing stop and yield signs, and at the same time, does not affect other performances of the end-to-end autonomous driving model. It is a plug-and-play module with strong scalability.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and in particular to a vehicle driving control method, device, equipment and storage medium. Background Art

[0002] With the rapid improvement of autonomous driving technology, autonomous driving technology has begun to be deployed in vehicles in scenarios such as highways and urban roads to assist users in driving vehicles.

[0003] As the collected data continues to increase, it provides a good foundation for the optimization of end-to-end autonomous driving models. Therefore, in autonomous driving technology, end-to-end autonomous driving models are usually used, which can directly realize the mapping of input images and vehicle control signals.

[0004] Due to the obvious long-tail distribution in the collected data, especially the specific specifications of some traffic signs, end-to-end autonomous driving models often perform poorly in some rare scenarios.

[0005] Among them, the stop and yield sign is one of the traffic signs with a long tail distribution. When the end-to-end autonomous driving model faces a stop and yield sign, it will have the abnormality of continuous parking. Summary of the Invention

[0006] The present invention provides a vehicle driving control method, device, equipment and storage medium to solve the problem of how to drive in accordance with regulations when facing a stop and yield sign during automatic driving.

[0007] According to one aspect of the present invention, there is provided a vehicle driving control method, comprising:

[0008] Collect multiple frames of target image data along the vehicle's traveling direction;

[0009] detecting a positional relationship between the vehicle and a control range of a stop and yield sign based on the target image data;

[0010] If the position relationship indicates that the vehicle is within the control range of the stop and yield sign, controlling the vehicle to decelerate until the vehicle stops before the stop and yield sign;

[0011] The vehicle is controlled to accelerate from the stop to pass the stop sign.

[0012] According to another aspect of the present invention, there is provided a vehicle travel control device, comprising:

[0013] A target image data acquisition module is used to acquire multiple frames of target image data along the vehicle's travel direction;

[0014] a positional relationship detection module, configured to detect a positional relationship between the vehicle and a control range of a stop and yield sign based on the target image data;

[0015] a deceleration and stopping control module, configured to control the vehicle to decelerate until the vehicle stops before the stop and yield sign if the positional relationship indicates that the vehicle is within the control range of the stop and yield sign;

[0016] An acceleration control module is used to control the vehicle to accelerate from the stop state to pass the stop sign.

[0017] According to another aspect of the present invention, an electronic device is provided, comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle driving control method described in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable a processor to implement the vehicle driving control method according to any embodiment of the present invention when executed.

[0022] In this embodiment, multiple frames of target image data are collected along the vehicle's travel direction; the positional relationship between the vehicle and the control range of the stop and yield sign is detected based on the target image data; if the positional relationship indicates that the vehicle is within the control range of the stop and yield sign, the vehicle is controlled to decelerate until it stops before the stop and yield sign; and the vehicle is controlled to accelerate from a stop to pass the stop and yield sign. This embodiment develops an auxiliary control process for stop and yield signs, combined with computer vision processing, to control the vehicle to decelerate before the stop and yield sign, stop and observe, and then smoothly accelerate through the stop and yield sign. This can effectively reduce the violation rate of vehicles passing stop and yield signs, while not affecting other performance aspects of the end-to-end autonomous driving model. It is a plug-and-play module with strong scalability.

[0023] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 This is a flow chart of a vehicle driving control method provided according to the first embodiment of the present invention;

[0026] Figure 2 This is a schematic structural diagram of a vehicle provided according to a first embodiment of the present invention;

[0027] Figure 3 This is an example diagram of a stop and yield sign provided according to the first embodiment of the present invention;

[0028] Figure 4 This is an example diagram of another stop and yield sign provided according to the first embodiment of the present invention;

[0029] Figure 5 This is an example diagram of another stop and yield sign provided according to the first embodiment of the present invention;

[0030] Figure 6 This is an example diagram of positive sample image data provided according to the first embodiment of the present invention;

[0031] Figure 7 This is an example diagram of another type of positive sample image data provided according to the first embodiment of the present invention;

[0032] Figure 8 This is an example diagram of negative sample image data provided according to the first embodiment of the present invention;

[0033] Figure 9 1 is a schematic structural diagram of a vehicle driving control device provided according to a second embodiment of the present invention;

[0034] Figure 10 It is a structural diagram of an electronic device provided according to the third embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] Example 1

[0038] Figure 1 This is a flow chart of a vehicle driving control method provided in the first embodiment of the present invention. This embodiment is applicable to the situation where the control range of the stop and yield sign is classified and the vehicle is driven according to the regulations. The method can be executed by the vehicle driving control device, which can be implemented in the form of hardware and / or software. The vehicle driving control device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0039] Step 101: Collect multiple frames of target image data along the vehicle's travel direction.

[0040] The vehicle in this embodiment is equipped with an automatic driving program, which can support the vehicle to achieve automatic driving. The so-called automatic driving can refer to the vehicle itself having the ability to perceive the environment, plan the path and independently achieve vehicle control, that is, human-like driving controlled by electronic technology.

[0041] Based on the degree of control over vehicle control tasks, autonomous vehicles can be divided into L0 non-automation (NoAutomotion), L1 driver assistance (Driver Assistance), L2 partial automation (Partial Automation), L3 conditional automation (Conditional Automation), L4 high automation (High Automation), and L5 full automation (Full Automation).

[0042] The vehicle deployed with the autonomous driving program in this embodiment may refer to a vehicle that meets any of the requirements of L1-L5, wherein the system performs auxiliary functions in L1-L3, and when it reaches L4, the vehicle driving will be handed over to the system. Therefore, the autonomous driving vehicle may be selected as a vehicle that meets any of the requirements of L4 and L5.

[0043] like Figure 2 As shown, the vehicle 200 may include a driving control device 201 , a body bus 202 , ECUs (Electronic Control Units) 203 , ECU 204 , ECU 205 , sensors 206 , 207 , 208 , and actuators 209 , 210 , 211 .

[0044] The driving control device (also known as the onboard brain) 201 is responsible for the overall intelligent control of the entire vehicle 200. The driving control device 201 can be a standalone controller, such as a programmable logic controller (PLC), a single-chip microcomputer, or an industrial control computer. It can also be a device composed of other electronic components with input / output ports and computational control capabilities, or a computer equipped with vehicle driving control applications. The driving control device analyzes and processes data received from various ECUs and / or sensors on the vehicle body bus 202, makes decisions accordingly, and sends corresponding instructions to the vehicle body bus.

[0045] The body bus 202 may be a bus for connecting the driving control device 201, ECUs 203, 204, 205, sensors 206, 207, 208, and other devices (not shown) in the vehicle 200. The CAN (Controller Area Network) bus is a commonly used body bus in current motor vehicles due to its widely recognized high performance and reliability. Of course, it is understood that the body bus may also be other types of buses.

[0046] The vehicle body bus 202 can send the instructions sent by the driving control device 201 to the ECU 203, ECU 204, and ECU 205. The ECU 203, ECU 204, and ECU 205 then analyze and process the instructions and send them to corresponding execution devices for execution.

[0047] Sensors 206 , 207 , and 208 include but are not limited to lidar, millimeter-wave radar, cameras, and the like.

[0048] For example, cameras are installed on a vehicle in an array, and one of the cameras is an RGB (Red Green Blue) camera with a FOV (Field of View) of 100° facing forward, and the output image data has a width and height of 800×600.

[0049] It should be understood that Figure 2 The number of vehicles, driving control devices, body buses, ECUs, actuators, and sensors in the embodiment is merely illustrative. Any number of vehicles, driving control devices, body buses, ECUs, and sensors may be provided as needed.

[0050] The vehicle in this embodiment may refer to a vehicle simulated in an autonomous driving simulator or a real vehicle. Regardless of whether the vehicle is simulated driving on the road in the autonomous driving simulator or a real vehicle is driving on the road, the camera deployed in the vehicle may be driven to continuously collect multiple frames of image data along the direction of vehicle travel (i.e., toward the front of the vehicle's direction of travel), which are recorded as target image data.

[0051] Step 102: Detect the positional relationship between the vehicle and the control range of the stop and yield sign based on the target image data.

[0052] The stop and give way sign is a traffic prohibition sign, which stipulates that vehicles should stop and look before the stop line and can only pass after confirming safety. The design of the stop and give way sign varies in different regions.

[0053] In one design, Figure 3 As shown, the stop and yield sign is octagonal in shape, with a red background and a white lining, and a white "Stop" in the sign.

[0054] In another design, such as Figure 4 As shown, the stop and yield sign is octagonal in shape, with a red background and a white lining, and the word "STOP" in white in the sign.

[0055] In another design, Figure 5 As shown, the stop and yield sign is a white "STOP" written on the road surface.

[0056] When intersections on certain roads are affected by special reasons and vehicles cannot fully ensure safety by slowing down alone, stop and yield signs will be used to require vehicles to come to a complete stop and then observe traffic conditions.

[0057] Generally speaking, stop and yield signs can be set up in the following situations:

[0058] (1) At intersections not controlled by traffic lights, stop and yield signs are usually set up on lower-level roads.

[0059] (2) At intersections not controlled by traffic lights, when the levels of the two roads are the same, or when the traffic volume of vehicles and pedestrians on both roads is large, stop and yield signs shall be set at the intersections of all roads at the same time.

[0060] (3) Although traffic lights are installed at the intersection, they do not work all day long. The stop and yield sign is effective when the light is off or flashing yellow.

[0061] (4) Unmanned railway crossings.

[0062] The stop and yield sign has a control range, that is, the range within which the stop and yield sign is effective. When a vehicle enters this control range, it shall start to slow down in accordance with the provisions of the stop and yield sign, stop before the stop line and look around, and pass after confirming it is safe.

[0063] The control range of the stop and yield sign varies in different regions. In some areas, the control range of the stop and yield sign is 20 meters in front of it. That is, the vehicle enters the control range and starts to slow down 20 meters in front of the stop and yield sign.

[0064] In this embodiment, image processing can be performed on multiple frames of target image data. When the parameters of the vehicle's camera are known (such as FOV, focal length, etc.), the vision of the vehicle's camera can be analyzed to detect the positional relationship between the vehicle and the control range of the stop and yield sign, that is, whether the vehicle is within the control range of the stop and yield sign, or whether the vehicle is outside the control range of the stop and yield sign.

[0065] Furthermore, the vehicle being outside the control range of the stop and yield sign may mean that there is no stop and yield sign in front of the vehicle, or that there is a stop and yield sign in front of the vehicle but the vehicle has not yet entered the control range of the stop and yield sign.

[0066] In one embodiment of the present invention, step 102 may include the following steps:

[0067] Step 1021: Determine a classifier trained on the control range of the stop and yield sign.

[0068] In this embodiment, a binary classifier may be constructed and trained in advance for the control range of the stop and yield sign, so that the classifier can classify whether a vehicle is within the control range of the stop and yield sign.

[0069] The classifier may be a machine learning model, such as SVM (Support Vector Machine), or a deep learning model, such as VGG (Visual Geometry Group).

[0070] Furthermore, the structure of the classifier is not limited to artificially designed neural networks, but can also be a neural network optimized by a model quantization method, a neural network searched for characteristics of the control range of a stop and yield sign by a NAS (Neural Architecture Search) method, and so on. This embodiment does not impose any restrictions on this.

[0071] In one embodiment of the present invention, step 1021 may include the following steps:

[0072] Step 10211: Start the autonomous driving simulator to load the simulation environment of the simulated vehicle while driving.

[0073] Considering that the stop and yield sign is one of the traffic signs with a long-tail distribution, the actual sample data volume is relatively low. In order to save costs, enrich the sample data volume, and improve the performance of the classifier, that is, to improve the classification accuracy, in addition to using real vehicles to collect video data as samples (including positive samples and negative samples), you can start an autonomous driving simulator (such as Carla) and load the simulation environment of the simulated vehicle when driving in the autonomous driving simulator, so as to capture samples in the simulation environment.

[0074] Step 10212: Collect positive sample image data and negative sample image data in a simulation environment.

[0075] In the autonomous driving simulator, different simulation environments can be located, and part of the image data from the vision of the simulated vehicle (camera) is collected as positive sample image data (i.e., positive samples), and part of the image data is collected as negative sample image data (i.e., negative samples).

[0076] Among them, such as Figure 6 、 Figure 7 As shown, the positive sample image data indicates that the simulated vehicle is within the control range of the stop and yield sign.

[0077] like Figure 8 As shown, the negative sample image data indicates that the simulated vehicle is outside the control range of the stop and yield sign.

[0078] In the specific implementation, the agent with data collection permission in the autonomous driving simulator (such as auto_pilot in Carla) can be queried.

[0079] In the autonomous driving simulator, the simulated vehicle is controlled to drive. On the one hand, the agent is called to perform image acquisition operations when the simulated vehicle is in a control state to obtain positive sample image data. On the other hand, the agent is called to perform image acquisition operations when the simulated vehicle is not in a control state to obtain negative sample image data.

[0080] The control state indicates that the distance between the simulated vehicle and the stop and yield sign is less than a control threshold (eg, 20 meters) representing a control range.

[0081] Furthermore, in the vehicle's vision, the top of the image data is mostly the sky, and the weather in the sky (such as sunny days and rainy days) often changes, causing certain interference to the training classifier.

[0082] Therefore, part of the data (pixel points) at the top can be cropped in the positive sample image data, and part of the data (pixel points) at the top can be cropped in the negative sample image data to eliminate the interference of weather, focus on the road, further improve the performance of the classifier, and improve the accuracy of the classifier classification.

[0083] Furthermore, the top portion of data may refer to N rows (or M% of pixels) from top to bottom in the image data (including positive sample image data and negative sample image data), where N is a positive integer and M is a positive number.

[0084] Step 10213: Build a training set and a validation set.

[0085] Samples (including positive samples and negative samples) belong to the data set and provide supervised training. They can be divided into training set and validation set using methods such as holdout method and cross-validation method. The training set contains some positive sample image data and some negative sample image data, and the validation set contains some positive sample image data and some negative sample image data.

[0086] The training set is used to fit the classifier parameters, and the validation set is used to check the training effect and determine whether the effect of training the classifier is heading in a bad direction. For example, by checking the relationship between the loss values ​​of the training set and the validation set as the epoch (number of training rounds) changes, it can be seen whether the classifier is overfitting. If so, the training can be stopped in time, and then the structure and hyperparameters of the classifier can be adjusted according to the situation to save time.

[0087] In a specific implementation, part of the positive sample image data is divided into a training set, and part of the positive sample image data is divided into a verification set, so that the number of positive sample image data in the training set and the number of positive sample image data in the verification set meet the first ratio (such as 9:1).

[0088] Part of the negative sample image data is divided into a training set, and part of the negative sample image data is divided into a validation set, so that the number of negative sample image data in the training set and the number of negative sample image data in the validation set meet the second ratio (such as 9:1).

[0089] Considering that the long tail phenomenon is more obvious, data augmentation operations can be performed on the negative sample image data in the training set to generate new negative sample image data in the training set.

[0090] Considering that the long tail phenomenon is more obvious, data augmentation operations can be performed on the negative sample image data in the validation set to generate new negative sample image data in the validation set.

[0091] Among them, data enhancement operations include flipping (such as horizontal flipping, vertical flipping, etc.), color jittering (such as adjusting brightness, adjusting hue, adjusting contrast, adjusting sharpness, etc.), adding noise (such as Gaussian noise, salt and pepper noise, etc.), etc.

[0092] Furthermore, all positive sample image data and all negative sample image data are adjusted to a uniform width and height (eg, 120×120) to meet the input requirements of the classifier.

[0093] For example, a total of 120,000 samples were collected, including 8,000 positive samples and 112,000 negative samples, from which training sets and validation sets were divided. There were 641 positive samples in the validation set, and 1,013 negative samples in the validation set were randomly sampled as the final validation set. 30,000 negative samples in the training set were randomly sampled (data augmentation operation) as the final training set, which can significantly improve the convergence speed of the classifier.

[0094] Step 10214: Use the training set to train the classifier so that the classifier has the function of classifying whether the vehicle is within the control range of the stop and yield sign.

[0095] In this embodiment, the classifier is trained using the training set according to preset training parameters (such as learning rate, batch_size (the size of the training set input during each training), optimizer, loss function, number of training rounds, etc.), and the classifier is trained to have the function of classifying whether it is within the control range of the stop and yield sign.

[0096] For example, the learning rate is 0.00003, the batch_size is 32, the Adam (Adaptive Moment Estimation) optimizer is used, the loss function is the cross entropy loss, and a total of 10 epochs are trained.

[0097] Step 10215: If the training is completed, the validation set is used to verify the classifier's ability to classify whether the classifier is within the control range of the stop and yield sign.

[0098] If the classifier is trained at the beginning of the year, the validation set can be used to verify the classifier's ability to classify whether the vehicle is within the control range of the stop and yield sign according to preset indicators (such as accuracy, etc.).

[0099] For example, when verifying the classifier, the accuracy on the verification set is 99.94%, among which the accuracy of positive sample recognition is 99.69% and the accuracy of negative sample recognition is 100%, thereby determining that the accuracy of the classifier recognition meets practical requirements, has passed verification, and can be deployed and run.

[0100] In actual applications, the classifier is trained and verified offline. Once the verification is passed, it can be distributed to various vehicles for deployment. The vehicle loads the classifier and its parameters into memory for operation.

[0101] Step 1022: Input the target image data into a classifier for classification to obtain a category indicating whether the target image data is within the control range of the stop and yield sign.

[0102] Adjust the target image data of each frame to a uniform width and height. If the adjustment is completed, input the target image data of each frame into the classifier in sequence. The classifier classifies the target image data according to its structure and outputs a category indicating whether it is within the control range of the stop and yield sign, that is, within the control range of the stop and yield sign, or outside the control range of the stop and yield sign.

[0103] Step 1023: Determine the positional relationship between the vehicle and the control range of the stop and yield sign based on the category.

[0104] Generally speaking, the category output by the classifier can be set as the positional relationship between the vehicle and the control range of the stop and yield sign. That is, if the category output by the classifier is within the control range of the stop and yield sign, then the positional relationship between the vehicle and the control range of the stop and yield sign can be determined as the vehicle is within the control range of the stop and yield sign. If the category output by the classifier is outside the control range of the stop and yield sign, then the positional relationship between the vehicle and the control range of the stop and yield sign can be determined as the vehicle is outside the control range of the stop and yield sign.

[0105] However, considering that the accuracy of the classifier cannot reach 100%, in order to improve the driving smoothness of the vehicle without violating traffic rules, a queue of length T (T is a positive integer, such as 20) can be created to cache the categories of nearly T frames of target image data. When the queue is not full of categories, the queue caches the categories. When the queue is full, if a new category comes, the category with the earliest timestamp in the queue is popped out and the new category is pushed into the queue.

[0106] Then, multiple categories recently classified by the classifier may be cached in a preset queue, and the number of categories within the control range of the stop and yield sign may be counted in the queue.

[0107] The number is compared with a proportion threshold, where the proportion threshold is generated by taking a specified proportion of the queue length. For example, when the queue length is 20, the proportion threshold is 15.

[0108] If the number is greater than or equal to the proportion threshold, it means that the result of being within the control range of the stop and yield sign is relatively stable, then the positional relationship between the vehicle and the control range of the stop and yield sign can be determined as the vehicle being within the control range of the stop and yield sign.

[0109] If the number is less than the proportion threshold, it means that the result of being within the control range of the stop and yield sign is unstable, then it can be determined that the positional relationship between the vehicle and the control range of the stop and yield sign is that the vehicle is outside the control range of the stop and yield sign.

[0110] This embodiment uses a queue to cache multiple classification results and selects stable classification results, thereby improving the fault tolerance of the sorting control process.

[0111] Step 103: If the position relationship indicates that the vehicle is within the control range of the stop and yield sign, the vehicle is controlled to decelerate until the vehicle stops before the stop and yield sign.

[0112] If it is detected that the current vehicle is within the control range of the stop and yield sign, the vehicle can be controlled to slow down until the vehicle stops before the stop and yield sign.

[0113] In one embodiment of the present invention, step 103 may include the following steps:

[0114] Step 1031: Determine the deceleration mark position and the stop mark position.

[0115] If a multi-target detection model for stop and yield signs is trained to identify the category information of traffic signs in the environment, and a vehicle control model (such as a convolutional neural network) is trained to map traffic category information to vehicle control signals, the input of the vehicle control model is the image data of the environment and the category information of traffic signs. During the entire process of the vehicle driving to the stop and yield sign, the information input to the vehicle control model does not change, and remains the image data of the environment and the category information of traffic signs. The vehicle control model will fall into a state of slowing down to stop but unable to accelerate through.

[0116] In this embodiment, two variables can be created, one variable is the deceleration flag need_brake, and the other variable is the stop flag stop_complete. The deceleration flag indicates whether to decelerate, and the stop flag indicates whether to stop. The deceleration flag and the stop flag are used as inputs of the automatic driving program. During the entire process of the vehicle traveling to the stop and yield sign, the deceleration flag and the stop flag are changed, thereby changing the input of the automatic driving program, so that the vehicle decelerates and stops before the stop and yield sign, and accelerates to pass the stop and yield sign.

[0117] When the vehicle starts and each time it passes a stop sign, the deceleration flag and the stop flag are initialized. The deceleration flag is initially a first value indicating no deceleration (such as need_brake=0), and the stop flag is initially a second value indicating no stop (such as stop_complete=0).

[0118] Step 1032: If the position relationship is that the vehicle is within the control range of the stop and yield sign, the deceleration sign is modified from the first value to a third value indicating deceleration, and the stop sign is maintained at the second value.

[0119] If the vehicle is within the control range of the stop and yield sign, the deceleration flag can be modified from the first value (such as need_brake=0) to the third value indicating deceleration (such as need_brake=1), while the stop flag remains unchanged at the second value (such as stop_complete=0).

[0120] Step 1033: When the deceleration flag is the third value and the stop flag is the second value, a brake signal is sent to the automatic driving program, and the speed of the vehicle is detected.

[0121] In a specific implementation, when it is detected that the deceleration flag is the third value (such as need_brake=1) and the parking flag is the second value (such as stop_complete=0), on the one hand, the braking signal control.brake can be continuously sent to the automatic driving program, and on the other hand, the vehicle's driving speed can be continuously detected.

[0122] Among them, the brake signal control.brake is used to control the vehicle to reduce its speed according to the control range of the stop and yield sign. That is, when the automatic driving program receives the brake signal control.brake, it determines the deceleration according to the control range of the stop and yield sign (such as control.brake = 0.6). This deceleration can stop the vehicle within the control range of the stop and yield sign. The deceleration is used to trigger the brake signal to brake the vehicle, thereby reducing the speed of the vehicle.

[0123] Step 1034: If the speed is less than the stop threshold, determine that the vehicle has stopped before the stop sign, stop sending the stop signal to the automatic driving program, maintain the deceleration flag at the third value, and change the stop flag from the second value to the fourth value indicating stop.

[0124] If the vehicle's speed is less than the stop threshold (such as 0.1m / s) and the deceleration flag is the third value (such as need_brake=1), it can be determined that the vehicle has stopped before the stop sign. At this time, the brake signal control.brake is stopped from being sent to the automatic driving program, so that the vehicle stops braking, and the deceleration flag is maintained at the third value (such as need_brake=1). The stop flag is changed from the second value (such as stop_complete=0) to the fourth value indicating stop (such as stop_complete=1), and waits for re-acceleration.

[0125] Step 104: Control the vehicle to accelerate from a stop and pass the stop sign.

[0126] If the vehicle moves forward to the stop sign and stops, the vehicle can be controlled to accelerate from the stopped state and pass the stop sign under safe conditions.

[0127] In one embodiment of the present invention, step 104 may include the following steps:

[0128] Step 1041: Call the automatic driving program to query the deceleration flag and the stop flag, so as to perceive the environmental information around the vehicle when it is detected that the deceleration flag is a third value and the stop flag is a fourth value.

[0129] The autonomous driving program will continuously query the deceleration flag and the parking flag. When it detects that the deceleration flag is the third value (such as need_brake=1) and the parking flag is the fourth value (such as stop_complete=1), it can call on sensors such as lidar and cameras to perceive the environmental information around the vehicle. In addition, it will also perceive the vehicle's own status information, such as position information, posture, acceleration, etc.

[0130] Step 1042: If the environmental information is suitable for passing, call the automatic driving program to control the vehicle to accelerate from a stop and pass the stop sign.

[0131] Step 1043: If the environmental information is suitable for giving way, the automatic driving program is called to control the vehicle to remain stationary.

[0132] Environmental and state information is input into the end-to-end autonomous driving model to predict the movement trajectory of perceived obstacles. Based on the perceived information, a route to the destination is planned, as well as the detailed trajectory and vehicle status of the vehicle at each moment in the future.

[0133] If it is determined that the environmental information is safe and the vehicle is suitable for passing in the current environment, that is, the current environmental information is suitable for acceleration, the automatic driving program can be called to control the vehicle to accelerate from a stopped state and pass the stop and yield sign.

[0134] If it is determined that there is a risk in the environmental information and the vehicle is suitable for giving way in the current environment, that is, the current environmental information is suitable for deceleration, stopping, etc., the automatic driving program can be called to control the vehicle to maintain the stopped state and continue to wait to accelerate through the stop and give way sign under safe conditions.

[0135] After the vehicle passes the stop and yield sign, the classifier classifies the vehicle as being outside the control range of the stop and yield sign. At this time, it can be determined that the vehicle is outside the control range of the stop and yield sign.

[0136] If the position relationship is that the vehicle is outside the control range of the stop and yield sign, the deceleration flag can be modified from the third value (such as need_brake=1) to the first value (such as need_brake=0).

[0137] If it is detected that the deceleration flag is the first value (such as need_brake=0), the stop flag can be modified from the fourth value (such as stop_complete=1) to the second value (such as stop_complete=0) to return to the initial state.

[0138] This embodiment uses the deceleration sign and the stop sign to construct a vehicle control model. The implementation method is simple and efficient, has no threshold, and can adapt to most real-world scenarios.

[0139] In this embodiment, multiple frames of target image data are collected along the vehicle's travel direction; the positional relationship between the vehicle and the control range of the stop and yield sign is detected based on the target image data; if the positional relationship indicates that the vehicle is within the control range of the stop and yield sign, the vehicle is controlled to decelerate until it stops before the stop and yield sign; and the vehicle is controlled to accelerate from a stop to pass the stop and yield sign. This embodiment develops an auxiliary control process for stop and yield signs, combined with computer vision processing, to control the vehicle to decelerate before the stop and yield sign, stop and observe, and then smoothly accelerate through the stop and yield sign. This can effectively reduce the violation rate of vehicles passing stop and yield signs, while not affecting other performance aspects of the end-to-end autonomous driving model. It is a plug-and-play module with strong scalability.

[0140] The vehicle control method for stop and yield signs proposed in this embodiment was integrated into an end-to-end autonomous driving model and tested on the test set Longest06 (containing 36 test routes). The results showed that the number of stop and yield sign violations decreased from 21 to 13, and the overall driving score increased from 52.2 to 59.7. These results demonstrate that the proposed method can reduce the violation rate of autonomous vehicles passing stop and yield signs.

[0141] Example 2

[0142] Figure 9 This is a schematic diagram of the structure of a vehicle driving control device provided by the second embodiment of the present invention. Figure 9 As shown, the device includes:

[0143] The target image data acquisition module 901 is used to acquire multiple frames of target image data along the vehicle's travel direction;

[0144] a positional relationship detection module 902 for detecting a positional relationship between the vehicle and a control range of a stop and yield sign based on the target image data;

[0145] a deceleration and stopping control module 903 configured to control the vehicle to decelerate until the vehicle stops before the stop and yield sign if the position relationship indicates that the vehicle is within the control range of the stop and yield sign;

[0146] The acceleration control module 904 is configured to control the vehicle to accelerate from the stop state to pass the stop sign.

[0147] In one embodiment of the present invention, the position relationship detection module 902 includes:

[0148] A classifier determination module, used to determine a classifier to be trained on the control range of the stop and yield sign;

[0149] an image classification module, configured to input the target image data into the classifier for classification to obtain a category indicating whether the target image data is within the control range of a stop and yield sign;

[0150] A position relationship determination module is used to determine the position relationship between the vehicle and the control range of the stop and yield sign based on the category.

[0151] In one embodiment of the present invention, the classifier determination module includes:

[0152] A simulation module is used to start the autonomous driving simulator to load the simulation environment of the simulated vehicle while driving;

[0153] a sample collection module, configured to collect positive sample image data and negative sample image data in the simulation environment, wherein the positive sample image data indicates that the simulated vehicle is within the control range of the stop and yield sign, and the negative sample image data indicates that the simulated vehicle is outside the control range of the stop and yield sign;

[0154] A set construction module is used to construct a training set and a validation set, wherein the training set includes part of the positive sample image data and part of the negative sample image data, and the validation set includes part of the positive sample image data and part of the negative sample image data;

[0155] a classifier training module, configured to train a classifier using the training set so that the classifier has the function of classifying whether a vehicle is within the control range of a stop and yield sign;

[0156] The classifier verification module is used to verify the function of the classifier in classifying whether the vehicle is within the control range of the stop and yield sign using the verification set after the training is completed.

[0157] In one embodiment of the present invention, the sample collection module includes:

[0158] An agent query module, used to query the agent with data collection authority in the autonomous driving simulator;

[0159] a positive sample image data acquisition module, configured to call the agent to perform an image acquisition operation when the simulated vehicle is in a control state, thereby obtaining positive sample image data;

[0160] a negative sample image data acquisition module, configured to call the agent to perform an image acquisition operation when the simulated vehicle is not in a control state, thereby obtaining negative sample image data;

[0161] The control state indicates that the distance between the simulated vehicle and the stop and yield sign is less than a control threshold indicating a control range.

[0162] In one embodiment of the present invention, the sample collection module further includes:

[0163] A first top cropping module, configured to crop a portion of data located at the top of the positive sample image data;

[0164] The second top cropping module is configured to crop a portion of data located at the top of the negative sample image data.

[0165] In one embodiment of the present invention, the set building module includes:

[0166] a positive sample image data partitioning module, configured to partition part of the positive sample image data into a training set and part of the positive sample image data into a validation set, so that the number of the positive sample image data in the training set and the number of the positive sample image data in the validation set conform to a first ratio;

[0167] a negative sample image data division module, configured to divide part of the negative sample image data into a training set and part of the negative sample image data into a validation set, so that the number of the negative sample image data in the training set and the number of the negative sample image data in the validation set conform to a second ratio;

[0168] a first data augmentation operation module, configured to perform a data augmentation operation on the negative sample image data in the training set to generate new negative sample image data in the training set;

[0169] The second data augmentation operation module is configured to perform a data augmentation operation on the negative sample image data in the validation set to generate new negative sample image data in the validation set.

[0170] In one embodiment of the present invention, the position relationship determination module includes:

[0171] A category cache module, configured to cache a plurality of categories recently classified by the classifier in a preset queue;

[0172] a number counting module, configured to count the number of the categories within the control range of the stop and yield sign in the queue;

[0173] a range determination module configured to determine, if the number is greater than or equal to a percentage threshold, that the positional relationship between the vehicle and the control range of the stop and yield sign is that the vehicle is within the control range of the stop and yield sign;

[0174] The out-of-range determination module is configured to determine that the positional relationship between the vehicle and the control range of the stop and yield sign is that the vehicle is outside the control range of the stop and yield sign if the number is less than a proportion threshold.

[0175] In one embodiment of the present invention, the deceleration and parking control module 903 includes:

[0176] The flag determination module is used to determine the deceleration flag and the parking flag, wherein the deceleration flag is initially a first value indicating no deceleration, and the parking flag is initially a first value indicating no

[0177] The second value of the stop;

[0178] a deceleration updating module, configured to modify the deceleration flag from the first value to a third value indicating deceleration, and maintain the stop flag at the second value, if the positional relationship indicates that the vehicle is within the control range of the stop and yield sign;

[0179] a deceleration control module, configured to send a brake signal to the automatic driving program when the deceleration flag is the third value and the stop flag is the second value, and to detect the speed of the vehicle, the brake signal being used to control the vehicle to reduce its speed within the control range of the stop sign;

[0180] and a stop update module configured to determine, if the speed is less than a stop threshold, that the vehicle has stopped before the stop sign, stop sending a stop signal to the autonomous driving program, and maintain the deceleration flag at the third value and modify the stop flag from the second value to a fourth value indicating a stop.

[0181] In one embodiment of the present invention, the acceleration control module 904 includes:

[0182] an environmental information perception module, configured to call the automatic driving program to query the deceleration flag and the stop flag, so as to perceive environmental information surrounding the vehicle when detecting that the deceleration flag is the third value and the stop flag is the fourth value;

[0183] an acceleration control module, configured to, if the environmental information is suitable for passage, invoke the automatic driving program to control the vehicle to accelerate from the stop to pass the stop sign;

[0184] The stop maintenance module is used to call the automatic driving program to control the vehicle to maintain the stop if the environmental information is suitable for giving way.

[0185] In one embodiment of the present invention, it further comprises:

[0186] an out-of-range updating module, configured to modify the deceleration flag from the third value to the first value if the position relationship indicates that the vehicle is outside the control range of the stop and yield sign;

[0187] An initial updating module is configured to modify the stop flag from the fourth value to the second value if it is detected that the deceleration flag is the first value.

[0188] The vehicle driving control device provided in the embodiment of the present invention can execute the vehicle driving control method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the vehicle driving control method.

[0189] Example 3

[0190] Figure 10 A schematic diagram of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0191] like Figure 10 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0192] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0193] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the vehicle driving control method.

[0194] In some embodiments, the vehicle driving control method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the vehicle driving control method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the vehicle driving control method in any other appropriate manner (for example, by means of firmware).

[0195] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0196] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0197] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0198] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0199] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0200] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0201] Example 4

[0202] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the vehicle driving control method provided by any embodiment of the present invention.

[0203] The computer program product may be implemented by writing computer program code for performing the operations of the present invention in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0204] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0205] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A vehicle driving control method, characterized in that: include: Collect multiple frames of target image data along the vehicle's travel direction; Start the autonomous driving simulator to load the simulation environment of the simulated vehicle while driving; Collecting positive sample image data and negative sample image data in the simulation environment, the positive sample image data indicating that the simulated vehicle is within the control range of the stop and yield sign, and the negative sample image data indicating that the simulated vehicle is outside the control range of the stop and yield sign; Constructing a training set and a validation set, wherein the training set includes part of the positive sample image data and part of the negative sample image data, and the validation set includes part of the positive sample image data and part of the negative sample image data; Using the training set to train a classifier, so that the classifier has the function of classifying whether the vehicle is within the control range of the stop and yield sign; If the training is completed, the validation set is used to verify the classifier's ability to classify whether the vehicle is within the control range of the stop and yield sign; Inputting the target image data into the classifier for classification to obtain a category indicating whether the target image data is within the control range of the stop and yield sign; Determining a positional relationship between the vehicle and a control range of a stop and yield sign based on the category; If the position relationship indicates that the vehicle is within the control range of the stop and yield sign, controlling the vehicle to decelerate until the vehicle stops before the stop and yield sign; The vehicle is controlled to accelerate from the stop to pass the stop sign.

2. The method according to claim 1, characterized in that The collecting of positive sample image data and negative sample image data in the simulation environment includes: Querying an agent with data collection authority in the autonomous driving simulator; calling the agent to perform an image acquisition operation when the simulated vehicle is in a control state to obtain positive sample image data; calling the agent to perform an image acquisition operation when the simulated vehicle is not in a control state to obtain negative sample image data; The control state indicates that the distance between the simulated vehicle and the stop and yield sign is less than a control threshold indicating a control range.

3. The method according to claim 2, characterized in that The collecting of positive sample image data and negative sample image data in the simulation environment further includes: Cutting out a portion of data at the top of the positive sample image data; A portion of data located at the top of the negative sample image data is cropped.

4. The method according to claim 1, wherein The construction of the training set and the validation set includes: dividing part of the positive sample image data into a training set and part of the positive sample image data into a validation set, so that the number of the positive sample image data in the training set and the number of the positive sample image data in the validation set meet a first ratio; dividing part of the negative sample image data into a training set and part of the negative sample image data into a validation set, so that the number of the negative sample image data in the training set and the number of the negative sample image data in the validation set conform to a second ratio; performing a data augmentation operation on the negative sample image data in the training set to generate new negative sample image data in the training set; A data augmentation operation is performed on the negative sample image data in the validation set to generate new negative sample image data in the validation set.

5. The method according to claim 1, wherein Determining the positional relationship between the vehicle and the control range of the stop and yield sign based on the category includes: caching the multiple categories most recently classified by the classifier in a preset queue; Counting the number of the categories in the queue that are within the control range of the stop and yield sign; If the number is greater than or equal to the proportion threshold, determining that the positional relationship between the vehicle and the control range of the stop and yield sign is that the vehicle is located within the control range of the stop and yield sign; If the number is less than the proportion threshold, it is determined that the positional relationship between the vehicle and the control range of the stop and yield sign is that the vehicle is outside the control range of the stop and yield sign.

6. The method according to any one of claims 1 to 5, characterized in that If the positional relationship indicates that the vehicle is within the control range of the stop and yield sign, controlling the vehicle to decelerate until the vehicle stops before the stop and yield sign includes: Determining a deceleration flag position and a stop flag position, wherein the deceleration flag position is initially a first value indicating no deceleration, and the stop flag position is initially a second value indicating no stop; If the positional relationship indicates that the vehicle is within the control range of the stop and yield sign, modifying the deceleration sign from the first value to a third value indicating deceleration, and maintaining the stop sign at the second value; When the deceleration flag is the third value and the stop flag is the second value, sending a brake signal to the automatic driving program, and detecting the speed of the vehicle, the brake signal is used to control the vehicle to reduce its speed according to the control range of the stop sign; If the speed is less than the stop threshold, the vehicle is determined to have stopped before the stop sign, and the stop signal is stopped from being sent to the automatic driving program. In addition, the deceleration flag is maintained at the third value, and the stop flag is modified from the second value to a fourth value indicating stop.

7. The method according to claim 6, characterized in that The controlling the vehicle to accelerate from the stop to pass the stop sign includes: calling the automatic driving program to query the deceleration flag and the stop flag, so as to perceive environmental information around the vehicle when detecting that the deceleration flag is the third value and the stop flag is the fourth value; If the environmental information is suitable for passing, calling the automatic driving program to control the vehicle to accelerate from the stop to pass the stop sign; If the environmental information is suitable for giving way, the automatic driving program is called to control the vehicle to maintain the stop.

8. The method according to claim 6, characterized in that After controlling the vehicle to accelerate from the stop to pass the stop sign, the method further includes: If the position relationship is that the vehicle is outside the control range of the stop and yield sign, modifying the deceleration flag from the third value to the first value; If it is detected that the deceleration flag is the first value, the parking flag is modified from the fourth value to the second value.

9. A vehicle driving control device, characterized in that: include: A target image data acquisition module is used to acquire multiple frames of target image data along the vehicle's travel direction; A simulation module is used to start the autonomous driving simulator to load the simulation environment of the simulated vehicle while driving; a sample collection module, configured to collect positive sample image data and negative sample image data in the simulation environment, wherein the positive sample image data indicates that the simulated vehicle is within the control range of the stop and yield sign, and the negative sample image data indicates that the simulated vehicle is outside the control range of the stop and yield sign; A set construction module is used to construct a training set and a validation set, wherein the training set includes part of the positive sample image data and part of the negative sample image data, and the validation set includes part of the positive sample image data and part of the negative sample image data; a classifier training module, configured to train a classifier using the training set so that the classifier has the function of classifying whether a vehicle is within the control range of a stop and yield sign; a classifier verification module, configured to verify, if training is complete, the ability of the classifier to classify whether the vehicle is within the control range of a stop and yield sign using the verification set; an image classification module, configured to input the target image data into the classifier for classification to obtain a category indicating whether the target image data is within the control range of a stop and yield sign; a position relationship determination module, configured to determine a position relationship between the vehicle and a control range of a stop and yield sign based on the category; a deceleration and stopping control module, configured to control the vehicle to decelerate until the vehicle stops before the stop and yield sign if the positional relationship indicates that the vehicle is within the control range of the stop and yield sign; An acceleration control module is used to control the vehicle to accelerate from the stop state to pass the stop sign.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the vehicle driving control method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is used to enable a processor to implement the vehicle driving control method according to any one of claims 1 to 8 when executed.

Images