Vehicle control method and device, vehicle and storage medium

Abstract

The invention discloses a vehicle control method and device, a vehicle and a storage medium, and relates to the technical field of vehicle control, and the disclosed vehicle control method comprises the steps that obstacle position errors sensed in the vehicle running process are obtained; performing chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area; if the obstacle is located in the safe area, the width of a lane where the obstacle is located currently is obtained; if it is determined that the vehicle meets the overtaking condition according to the safety area and the width of the lane, the vehicle is controlled to execute the overtaking action, and the vehicle collision risk can be reduced.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle control method, device, vehicle and storage medium. Background Art

[0002] At present, in complex road environments, vehicles need to face various obstacles, such as vehicles, pedestrians, road facilities, etc. These obstacles pose a severe challenge to the safe driving of vehicles. In order to ensure driving safety, vehicles need to actively avoid multiple obstacles on the road, which usually relies on the accurate recognition of the obstacle position by its vehicle perception system.

[0003] Most existing driving obstacle avoidance technologies are based on an idealized assumption: the perception system is perfect and can accurately identify the location of obstacles. Under this assumption, the vehicle can establish a safe driving corridor based on the location of the obstacle and make overtaking decisions accordingly.

[0004] However, in actual situations, due to the limitations of environmental perception sensor hardware, factors such as sensor accuracy, resolution, coverage, and environmental interference will lead to perception errors, making the vehicle perception system often unable to accurately identify the precise obstacle location. When the vehicle makes an overtaking decision based on the wrong obstacle location, there is a risk of vehicle collision. Summary of the invention

[0005] The main purpose of the present application is to provide a vehicle control method, device, vehicle and storage medium, aiming to solve the problem of low obstacle position error recognition accuracy during vehicle driving, which leads to the risk of vehicle collision.

[0006] To achieve the above objectives, the present application proposes a vehicle control method, the method comprising: Obtain the obstacle position error perceived by the vehicle during driving; Performing a chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area; If the obstacle is located in the safety area, obtaining the width of the lane where the obstacle is currently located; If it is determined that the vehicle meets the overtaking condition according to the safety area and the width of the lane, the vehicle is controlled to perform an overtaking action.

[0007] In one embodiment, the obstacle position error includes a lateral position error and a longitudinal position error between the vehicle and the obstacle, and the step of performing a chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area includes: Based on the horizontal position error and vertical position error of the historical period, the chi-square statistic is determined; Determine degrees of freedom and risk parameters; determining a chi-square quantile based on the degrees of freedom and the risk parameter, wherein the risk parameter represents a probability that an obstacle is located in a confidence region, and the confidence region is located in the safety region; Whether the obstacle is located in a safe area is determined according to the chi-square statistic and the chi-square quantile.

[0008] In one embodiment, the step of determining the chi-square statistic based on the lateral position error and the longitudinal position error of the historical period includes: Determine a lateral position average error and a lateral position error variance based on each of the lateral position errors in the historical period, and determine a longitudinal position average error and a longitudinal position error variance based on each of the longitudinal position errors in the historical period; Determine a lateral position error standard deviation based on the lateral position error variance, and determine a longitudinal position error standard deviation based on the longitudinal position error variance; Performing standardization based on the lateral position error, the lateral position average error and the lateral position error standard deviation to obtain a first standard random variable, and performing standardization based on the longitudinal position error, the longitudinal position average error and the longitudinal position error standard deviation to obtain a second standard random variable; The chi-square statistic is obtained based on the sum of the square of the first standard random variable and the square of the second standard random variable.

[0009] In one embodiment, the step of determining whether the obstacle is located in a safe area according to the chi-square statistic and the chi-square quantile comprises: If the chi-square statistic is less than or equal to the chi-square quantile, it is determined that the obstacle is located in the safety area; If the chi-square statistic is greater than the chi-square quantile, it is determined that the obstacle is outside the safety area.

[0010] In one embodiment, if it is determined that the vehicle meets the overtaking condition according to the safety area and the width of the lane, the step of controlling the vehicle to perform the overtaking action includes: If it is determined that the vehicle meets the overtaking condition according to the safety area and the width of the lane, determining the virtual position of the vehicle according to the position of the obstacle; Constructing a safe driving corridor for the vehicle according to the virtual position of the vehicle and the current position of the vehicle; The vehicle is controlled to travel along the safe driving corridor.

[0011] In one embodiment, the step of constructing a safe driving corridor for the vehicle according to the virtual position of the vehicle and the current position of the vehicle includes: A path planning is performed using a fifth-order polynomial curve according to the virtual position of the vehicle and the current position of the vehicle to obtain a safe driving corridor for the vehicle.

[0012] In one embodiment, after the step of constructing a safe driving corridor for the vehicle according to the virtual position of the vehicle and the current position of the vehicle, the step further includes: Performing feasibility verification on the safe driving corridor to obtain a feasibility verification result, and performing safety verification on the safe driving corridor to obtain a safety verification result; If the feasibility verification result is that the safe driving corridor is feasible and the safety verification result is that the safe driving corridor is safe, the step of controlling the vehicle to travel along the safe driving corridor is performed.

[0013] In one embodiment, when the obstacle is a private vehicle, after the step of obtaining the width of the lane where the obstacle is currently located when the obstacle is located in the safety area, the method further includes: If it is determined that the vehicle does not meet the overtaking condition based on the safety area and the width of the lane, the vehicle is controlled to follow the social vehicle.

[0014] In one embodiment, if the obstacle is located in the safety area, after the step of obtaining the width of the lane where the obstacle is currently located, the method further includes: Determining a passable width of the vehicle in the lane according to the safety area and the width of the lane; Obtaining a lateral safe driving threshold of the vehicle; If the difference between the passable width and the lateral safe driving threshold is greater than the vehicle width, determining that the vehicle meets the overtaking condition; If the difference between the passable width and the lateral safe driving threshold is less than or equal to the vehicle width, it is determined that the vehicle does not meet the overtaking condition.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle control device, the vehicle control device comprising: A first acquisition module is used to acquire the obstacle position error sensed during the vehicle driving process; A chi-square test module, used to perform a chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area; A second acquisition module, used for acquiring the width of the lane where the obstacle is currently located if the obstacle is located in the safety area; The overtaking module is used to control the vehicle to perform an overtaking action if it is determined that the vehicle meets the overtaking condition based on the safety area and the width of the lane.

[0016] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle control method as described above.

[0017] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle control method described above are implemented.

[0018] The present application obtains the obstacle position error perceived during vehicle driving and performs a chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area. Since the chi-square test is mainly used to determine whether there is a significant difference between the perceived obstacle position error and the theoretical obstacle position error, when the obstacle is located in the safe area, it means that there is no significant difference between the obstacle position error and the theoretical obstacle position error, that is, the currently perceived obstacle position is accurate. At this time, when it is determined that the vehicle meets the overtaking conditions based on the safe area corresponding to the accurate obstacle position, the lane width and the vehicle width, the vehicle is controlled to perform overtaking action, which can reduce the risk of vehicle collision. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0021] Figure 1 A schematic diagram of a flow chart provided for a first embodiment of a vehicle control method of the present application; Figure 2 A schematic flow chart of a second embodiment of a vehicle control method of the present application; Figure 3 A schematic diagram of the safety area for this application; Figure 4 A schematic flow chart of a third embodiment of a vehicle control method of the present application; Figure 5A schematic diagram of the present application for implementing path planning for a social vehicle to achieve overtaking; Figure 6 Another schematic diagram of the present application for implementing path planning for multiple social vehicles to achieve overtaking; Figure 7 A schematic diagram of the module structure of the control device of the vehicle of the present application; Figure 8 This is a schematic diagram of the structure of the vehicle of this application.

[0022] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0023] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0024] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0025] At present, most of the existing driving obstacle avoidance technologies are based on an idealized assumption: the perception system is perfect and can accurately identify the location of obstacles. Under this assumption, the vehicle can establish a safe driving corridor based on the location of the obstacle and make overtaking decisions accordingly. However, in actual situations, due to the limitations of the environmental perception sensor hardware, factors such as the accuracy, resolution, coverage of the sensor, and environmental interference will lead to perception errors, making the vehicle perception system often unable to accurately identify the precise obstacle location. When the vehicle makes an overtaking decision based on the wrong obstacle location, there is a risk of vehicle collision.

[0026] In response to the above problems, the present application proposes a vehicle control method, the main technical solutions of which include: obtaining the obstacle position error perceived during the vehicle's driving process; performing a chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area; if the obstacle is located in the safe area, obtaining the width of the lane where the obstacle is currently located; if it is determined that the vehicle meets the overtaking conditions based on the safety area and the width of the lane, controlling the vehicle to perform an overtaking action.

[0027] By obtaining the obstacle position error perceived during vehicle driving, a chi-square test is performed based on the obstacle position error to determine whether the obstacle is located in a safe area. Since the chi-square test is mainly used to determine whether there is a significant difference between the perceived obstacle position error and the theoretical obstacle position error, when the obstacle is located in a safe area, it means that there is no significant difference between the obstacle position error and the theoretical obstacle position error, that is, the currently perceived obstacle position is accurate. At this time, based on the safe area corresponding to the accurate obstacle position, the lane width and the vehicle width, when it is determined that the vehicle meets the overtaking conditions, the vehicle is controlled to perform overtaking actions, which can reduce the risk of vehicle collision.

[0028] It should be noted that the execution subject of the embodiment of the present application can be a vehicle, for example, it can be a vehicle-mounted terminal of the vehicle, and the vehicle control method is executed on the vehicle-mounted terminal of the vehicle. The execution subject of the embodiment of the present application can also be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc. These computing service devices are connected to the vehicle-mounted terminal of the present application, and the vehicle-mounted terminal can receive the obstacle position error perceived by the environment perception sensor, and send the perceived obstacle position error to the computing service device, and execute the vehicle control method on the computing service device. After the computing service device performs corresponding processing on the obstacle position error, it sends an overtaking action instruction to the vehicle-mounted terminal, and the vehicle-mounted terminal performs the corresponding overtaking action. It can also be that the computing service device sends the processing result of whether the vehicle overtaking condition is met to the vehicle-mounted terminal, and the vehicle-mounted terminal determines whether to perform the overtaking action based on the processing result. In this way, through the coordinated use of the vehicle-mounted terminal and the computing service device, the data processing pressure of the vehicle-mounted terminal can be reduced, so that the vehicle-mounted terminal can have more computing power to perform other operations. The present embodiment and the following embodiments are described below by taking a vehicle as an execution subject and executing a vehicle control method on the vehicle as an example.

[0029] It should be noted that the safe driving corridor mentioned in the embodiment of the present application is a virtual spatial range, which ensures that the vehicle maintains a sufficient safe distance from obstacles during driving, thereby avoiding the occurrence of safety problems such as collisions. It can be regarded as a drivable path for the vehicle to overtake, and the safe driving corridor is composed of multiple trajectory points.

[0030] It should be noted that the chi-square test technology used in the embodiment of the present application is a hypothesis testing method in statistics. The difference between the actual perceived obstacle position error and the theoretical obstacle position error is measured by the chi-square statistic to determine whether there is a significant relationship between the two variables. If there is a significant difference, then there is reason to reject the null hypothesis and believe that the actual perceived obstacle position error is inconsistent with the theoretical obstacle position error. Otherwise, the null hypothesis is accepted and it is believed that the actual perceived obstacle position error is consistent with the theoretical obstacle position error.

[0031] The null hypothesis here can be that the obstacle is located in the safe area, that is, when the actual perceived obstacle position error does not match the theoretical obstacle position error, it means that the perceived obstacle position is inaccurate. At this time, the null hypothesis is rejected, and it is determined that the obstacle position is outside the safe area. If overtaking is performed, there is a risk of collision. When the actual perceived obstacle position error matches the theoretical obstacle position error, it means that the perceived obstacle position is accurate. At this time, the null hypothesis is accepted, and it is determined that the obstacle is located in the safe area, and overtaking can be performed.

[0032] Based on this, the present application embodiment provides a vehicle control method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle control method of the present application.

[0033] In this embodiment, the vehicle control method includes: Step S10, obtaining the obstacle position error sensed during the vehicle driving process; It should be noted that the obstacle can be a dynamic obstacle such as a pedestrian or a private vehicle, or a static obstacle such as a road facility. This application takes the obstacle as a private vehicle as an example, and ultimately achieves the purpose of overtaking or bypassing the private vehicle in front or following the private vehicle in front.

[0034] The number of the above obstacles can be one or more.

[0035] The above-mentioned obstacle and the vehicle may be located in the same lane or in different lanes. The obstacle may be located in front of the vehicle, for example, the obstacle is located in front of the lane where the vehicle is currently traveling, or it may be located behind or to the side of the vehicle.

[0036] It should be noted that the obstacle position error refers to the difference between the actual obstacle position perceived by the vehicle during driving and the theoretical obstacle position. Due to the limitations of the environment perception sensor hardware, factors such as the sensor's accuracy, resolution, coverage, and environmental interference will lead to errors in the obstacle position perceived during vehicle driving, and the obstacle position error increases as the longitudinal distance between the vehicle and the obstacle increases, making it impossible to accurately identify the obstacle position.

[0037] Obtaining the obstacle position error perceived by the vehicle during driving includes any of the following methods: In a feasible implementation, the obstacle position error is measured based on the distance measurement principle of a monocular camera. Specifically, the road image is first captured by a monocular camera, and obstacles such as cars and pedestrians are identified using an image matching algorithm. The distance of the obstacle is estimated using a pre-established distance measurement model based on the size, shape and other features of the obstacle in the image. The real distance of the obstacle is measured in an actual environment using high-precision distance measurement equipment such as a laser rangefinder and radar. The estimated distance is compared with the actual measured distance to calculate the obstacle position error perceived during vehicle driving.

[0038] In another feasible implementation, the obstacle position error can be measured based on the ranging principle of a binocular camera. Specifically, a binocular camera is used to capture road images simultaneously. The images of the left and right cameras are corrected to ensure that they are on the same plane, and the corresponding obstacle feature points in the left and right images are found. According to the coordinate difference of the obstacle feature points in the left and right images, the distance of the obstacle is calculated using a three-dimensional reconstruction algorithm. Similarly, a high-precision ranging device is used to measure the actual distance of the obstacle, and the calculated distance is compared with the actual distance to obtain the obstacle position error perceived during vehicle driving.

[0039] In another feasible implementation, the obstacle position error perceived during vehicle driving can also be obtained based on perception model training. Specifically, it includes: using high-precision sensors such as laser radar, millimeter wave radar, camera, etc. to collect obstacle position data perceived during vehicle driving in a variety of driving environments. At the same time, record the actual obstacle position data, which can be obtained through high-precision maps, GPS positioning or other reliable means. Clean the collected data to remove noise and outliers. Label the data to clarify the obstacle type, location and other information corresponding to each data point. Perform preprocessing operations such as scaling, cropping, and color space conversion on the data as needed for subsequent model training. Select a suitable perception model architecture according to task requirements, such as convolutional neural network, recurrent neural network or a combination thereof. For obstacle position perception tasks, you can consider using target detection models such as YOLO, Faster R-CNN, etc. or semantic segmentation models such as U-Net, DeepLab, etc. Use the preprocessed data set to train the perception model. During the training process, continuously adjust the model's hyperparameters such as learning rate, batch size, optimizer, etc. to optimize model performance. Regularization techniques such as Dropout, weight decay, and early stopping strategies are used to avoid model overfitting. After the model training is completed, an independent validation dataset is used to evaluate the performance of the model. The obstacle position error is calculated by comparing the difference between the obstacle position predicted by the model and the actual obstacle position. The error can be measured by a variety of indicators, such as mean square error, mean absolute error, accuracy, precision, recall, and F1 score. Finally, the trained perception model is deployed in the autonomous driving system for real-time perception of obstacle position errors.

[0040] In another feasible implementation, high-precision positioning technology can also be used to obtain the position of obstacles perceived by the vehicle during driving. For example, the position of obstacles is determined by an autonomous fusion positioning method based on feature point calibration, or more accurate positioning and perception is achieved through communication and data exchange between the vehicle and the road infrastructure based on a vehicle-road collaborative positioning method. For example, the position of obstacles is assisted in perception and positioning by using equipment such as cameras and radars on the side of the lane, and the position of obstacles perceived by these equipment is obtained, and the position of obstacles perceived by these equipment is analyzed to obtain the error of the position of obstacles perceived by the vehicle during driving.

[0041] In summary, obtaining the obstacle position error perceived by the vehicle during driving requires the comprehensive use of multiple sensor technologies, multi-sensor fusion technology, and high-precision positioning technology. The comprehensive application of these technologies can achieve accurate perception and identification of obstacle position errors, providing a strong guarantee for the safe driving of the vehicle.

[0042] Step S20, performing a chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area; A safety zone can be defined based on the vehicle's position and direction of travel. This is usually an area with a specific radius or boundary centered on the vehicle. It should be noted that the safety zone is the spatial location area where obstacles are expected to appear in the future. Obstacles need to be within the safety zone. If they exceed the safety zone, there is a risk of collision with the vehicle.

[0043] In a feasible implementation, a chi-square test is performed based on the obstacle position error to determine whether the obstacle is located in a safe area, including: dividing the obstacle position error into several discrete areas, such as a safe area, a dangerous area, etc., which should be defined based on actual application scenarios and safety standards. Define a categorical variable to indicate whether the obstacle is located in a safe area, for example, 1 indicates that it is in a safe area, and 0 indicates that it is not in a safe area. According to the defined categorical variable, the obstacle position error perceived during vehicle driving is marked as being in a safe area or not in a safe area. Create a contingency table to show the relationship between the obstacle position error and the safe area. The contingency table should contain two dimensions: one dimension is the location of the obstacle divided by area, and the other dimension is whether the obstacle is located in a safe area. Use the statistical method of the chi-square test to analyze the data in the contingency table to determine whether there is a significant correlation between the obstacle position error and the safe area. According to the results of the chi-square test, it is determined whether there is a significant correlation between the obstacle position error and the safe area. If the result is significant, it can be considered that there is a certain correlation between the obstacle position error and the safe area. If the result is not significant, it can be considered that there is no correlation between the obstacle position error and the safe area. In this way, the purpose of performing a chi-square test based on the obstacle position error to determine whether the obstacle is located in the safe area is achieved.

[0044] Step S30, if the obstacle is located in the safety area, obtaining the width of the lane where the obstacle is currently located; In a feasible implementation, obtaining the width of the lane where the obstacle is currently located includes: using image processing algorithms such as edge detection and Hough transform to identify lane lines from camera images, and calculating the width of the lane based on the detected lane line positions.

[0045] In a feasible implementation, obtaining the vehicle width includes: establishing a database containing various vehicle models and their sizes. Using a camera and a machine learning algorithm to identify the vehicle model. According to the identified vehicle model, querying the corresponding vehicle width from the database. Alternatively, if the vehicle itself is an autonomous driving vehicle and is equipped with corresponding sensors, the vehicle width can be directly measured using sensors on the vehicle, such as ultrasonic sensors, cameras, etc.

[0046] Step S40: If it is determined that the vehicle meets the overtaking condition based on the safety area and the width of the lane, the vehicle is controlled to perform an overtaking action.

[0047] When overtaking, you need to ensure that there is enough safety area behind the obstacle so that the vehicle can respond to possible emergencies. This includes ensuring that there is enough space in front for acceleration and returning to the original lane after overtaking. Check the rearview mirror to ensure that the vehicle behind is far enough away from you to avoid being rear-ended during the overtaking process. When overtaking, especially on a two-way single lane, ensure that there is enough lateral safety distance from the oncoming vehicle to prevent collision with the oncoming vehicle during the overtaking process.

[0048] In this embodiment, the obstacle position error perceived during vehicle driving is obtained, and a chi-square test is performed based on the obstacle position error to determine whether the obstacle is located in a safe area. Since the chi-square test is mainly used to determine whether there is a significant difference between the perceived obstacle position error and the theoretical obstacle position error, when the obstacle is located in the safe area, it means that there is no significant difference between the obstacle position error and the theoretical obstacle position error, that is, the currently perceived obstacle position is accurate. At this time, when it is determined that the vehicle meets the overtaking conditions based on the safe area corresponding to the accurate obstacle position, the lane width and the vehicle width, the vehicle is controlled to perform overtaking action, which can reduce the risk of vehicle collision.

[0049] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be repeated hereafter. On this basis, the obstacle position error includes the lateral position error and the longitudinal position error between the vehicle and the obstacle. When performing the chi-square test, the lateral position error and the longitudinal position error need to be comprehensively considered to improve the accuracy of the obstacle position error. Specifically, refer to Figure 2 , step S20 comprises: Step S21, determining a chi-square statistic based on the horizontal position error and the vertical position error of the historical period; It should be noted that the historical period can be set according to the actual situation, and the lateral position error and longitudinal position error can be obtained once every preset time interval in the historical period. Assuming that the historical period is 5 minutes and the preset time is 10 seconds, the lateral position error and longitudinal position error obtained can be the data corresponding to every 10 seconds in the past 5 minutes. At this time, there are multiple lateral position errors and longitudinal position errors obtained.

[0050] It should be noted that the lateral position error refers to the difference between the lateral position of the social vehicle detected by the vehicle perception system, that is, perpendicular to the direction of vehicle travel, and the actual position. The lateral position error is usually manifested as the vehicle perception system believes that the social vehicle is at a certain lateral position of the lane line, but in fact the social vehicle is on the other side of the lane line or deviates from the lane line. The longitudinal position error refers to the difference between the longitudinal position of the social vehicle detected by the vehicle perception system, that is, the direction of vehicle travel, and the actual position. The longitudinal position error is usually manifested as the vehicle perception system believes that the social vehicle is at a certain longitudinal position, but in fact the social vehicle is at another longitudinal position.

[0051] It should be noted that the chi-square statistic is mainly used to measure the difference between the actual perceived obstacle position error and the theoretical obstacle position error. The calculation formula of the chi-square statistic is: χ² = ∑((Oi - Ei)² / Ei).

[0052] Among them, Oi represents the actual perceived obstacle position error, Ei represents the theoretical obstacle position error, ∑ represents the sum of all categories, and the theoretical obstacle position error here can be the average obstacle position error. Since the lateral position error and the longitudinal position error are independent, the obstacle position error includes the average lateral position error and the average longitudinal position error.

[0053] In a feasible implementation manner, determining the chi-square statistic based on the lateral position error and the longitudinal position error obtained in the historical period includes: determining the lateral position average error and the lateral position error variance based on each lateral position error in the historical period, and determining the longitudinal position average error and the longitudinal position error variance based on each longitudinal position error in the historical period; determining the lateral position error standard deviation based on the lateral position error variance, and determining the longitudinal position error standard deviation based on the longitudinal position error variance; performing standardization based on the lateral position error, the lateral position average error and the lateral position error standard deviation to obtain a first standard random variable, and performing standardization based on the longitudinal position error, the longitudinal position average error and the longitudinal position error standard deviation to obtain a second standard random variable; and obtaining the chi-square statistic based on the sum of the square of the first standard random variable and the square of the second standard random variable.

[0054] For example, assume that the lateral position error is expressed as , the longitudinal position error is expressed as , then the average lateral position error is expressed as , the lateral position error variance is expressed as , the average longitudinal position error is expressed as , the longitudinal position error variance is expressed as The standard deviation of the lateral position error can be obtained by calculating the variance of the lateral position error Take the square root and record it as The standard deviation of the longitudinal position error can be obtained by calculating the longitudinal position error variance Take the square root and record it as .

[0055] Assuming lateral position error and longitudinal position error It forms a bivariate normal distribution, and the longitudinal position error and the lateral position error are independent of each other. Therefore, two independent standard random variables that obey the standard normal distribution can be obtained respectively: .

[0056] Among them, the first standard random variable is , the second standard random variable is . Average lateral position error and the average longitudinal position error Determines the center position of the corresponding standard normal distribution and the standard deviation of the horizontal position error and the standard deviation of the longitudinal position error Determines the width or dispersion of the corresponding standard normal distribution. The average error of the horizontal position can be set and the average longitudinal position error are all 0, so that the center position of their corresponding standard normal distribution is at point 0, and the lateral position error and the longitudinal position error are symmetrically distributed around their corresponding point 0.

[0057] It can be understood that by adopting the above method, even if the mean values ​​and standard deviations of the lateral position error and the longitudinal position error are different, the differences between the corresponding data points therein can be compared by calculating the corresponding first standard random variables and second standard random variables, thereby making the comparison and interpretation between different data easier.

[0058] Step S22, determining degrees of freedom and risk parameters; It should be noted that, considering the existence of two independent standard random variables, the degree of freedom here can be set to 2.

[0059] It should be noted that the risk parameter represents the probability of an obstacle appearing in the confidence area. The confidence area is located within the safety area, and the confidence area becomes larger as the risk parameter increases. The risk parameter here can be preset according to actual conditions.

[0060] Step S23, determining a chi-square quantile based on the degrees of freedom and the risk parameter, wherein the risk parameter represents a probability that an obstacle is located in a confidence region, and the confidence region is located in the safety region; It should be noted that the chi-square quantile mentioned above is used to describe the confidence zone around the obstacle. The chi-square quantile refers to the critical value of the chi-square distribution under a given degree of freedom and significance level. The chi-square critical value is usually used in the chi-square test to determine whether there is a significant difference between the perceived obstacle position error and the theoretical obstacle position error. This critical value is used in statistical hypothesis testing to determine whether to reject the null hypothesis. The chi-square quantile can be obtained by looking up the chi-square distribution table, or it can be obtained by theoretical calculation using a specific mathematical formula, such as by calculating the probability density function and cumulative distribution function of the chi-square distribution.

[0061] It should be noted that the above confidence region is derived based on the properties of the chi-square distribution. This confidence region indicates that the overall parameter has a certain probability of falling within this region, that is, the lateral position error and the longitudinal position error have a certain probability of falling within this region. It is usually necessary to set a confidence level, where the confidence level is the above risk parameter, and then determine the chi-square quantile based on the confidence level and degrees of freedom, and then determine a confidence region through the chi-square quantile.

[0062] Reference Figure 3 As shown in , the confidence region can be formed by an elliptical contour envelope. The lateral position error variance can be determined based on the lateral position error, and the longitudinal position error variance can be determined based on the longitudinal position error; the safe region can be determined based on the chi-square quantile, the lateral position error variance, and the longitudinal position error variance. The safe region is Figure 3 The ellipse shown.

[0063] Exemplarily, the lengths of the semi-major axis and the semi-minor axis of the ellipse boundary corresponding to the confidence region can be obtained according to the following formula: ; ; Among them, a represents Figure 3 The semi-major axis of the median ellipse, b represents Figure 3 The semi-minor axis of the median ellipse, is the chi-square quantile.

[0064] Step S24: determining whether the obstacle is located in a safe area according to the chi-square statistic and the chi-square quantile.

[0065] In the chi-square test, if the calculated chi-square statistic is greater than the chi-square quantile, the null hypothesis is rejected, and it is considered that there is a significant difference between the perceived obstacle position error and the theoretical obstacle position error, and the obstacle is determined to be outside the safe area. Conversely, if the chi-square statistic is less than or equal to the chi-square quantile, the null hypothesis is not rejected, and it is considered that there is no significant difference between the perceived obstacle position error and the theoretical obstacle position error, and the obstacle is determined to be within the safe area.

[0066] In this embodiment, the chi-square test is performed by comprehensively considering the lateral position error and the longitudinal position error to improve the accuracy of obstacle position error identification.

[0067] Based on the above embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be described in detail later. Figure 4 , step S30 comprises: Step S31, if it is determined that the vehicle meets the overtaking condition according to the safety area and the width of the lane, then determining the virtual position of the vehicle according to the position of the obstacle; It should be noted that the virtual position of a vehicle refers to the position where the vehicle is expected to reach at a certain point in the future, which is usually predicted based on factors such as the vehicle's current speed, acceleration, driving direction, and road conditions. The virtual position of a vehicle can also be the position of the vehicle's virtual center point, which is the position of the vehicle predicted to be parallel to the obstacle when the vehicle overtakes at its current position. Figure 5 The virtual position of the vehicle can be the position when the vehicle is parallel to the obstacle. For example, the center point position of the obstacle can be obtained. The virtual center point position of the vehicle and the center point position of the obstacle are located on the same horizontal line, and a certain safety distance is maintained between the virtual center point position of the vehicle and the obstacle.

[0068] In this embodiment, if the lane width is sufficient and the safety area is sufficient, the overtaking condition is met and the vehicle can smoothly perform the overtaking operation. At this time, the turn signal should be turned on in advance, the speed should be reduced, a safe distance should be maintained from the vehicle being overtaken, and the situation in the opposite lane should be observed. If the lane width is insufficient or the safety area is insufficient, the overtaking condition is not met and the overtaking operation is not recommended.

[0069] Step S32, constructing a safe driving corridor for the vehicle according to the virtual position of the vehicle and the current position of the vehicle; It should be noted that the current position of the vehicle refers to the actual position of the vehicle on the road.

[0070] It should be noted that a safe driving corridor is a driving path planned for vehicles without collision risk within a certain time and space range. It ensures that the vehicle maintains a sufficient safe distance from obstacles during driving, thereby avoiding the occurrence of safety problems such as collisions.

[0071] In a feasible implementation, a road model can be constructed using high-precision map data, including information such as lane lines, road width, curvature, etc. Based on the current position, virtual position and road model of the vehicle, a path planning algorithm is used to determine the safe driving corridor of the vehicle. Specifically, a preliminary driving path is generated using a path planning algorithm such as an A* algorithm, a Dijkstra algorithm, etc. The preliminary path should avoid known obstacles and consider the vehicle's driving constraints such as the maximum steering angle, the maximum driving speed, etc. On the basis of the preliminary path, a safe driving corridor is generated according to the obstacle position and the virtualized obstacle avoidance safety distance. The safe driving corridor should have a certain width to accommodate the vehicle's driving error and possible lateral movement. Polygons such as rectangles or more complex shapes can be used to represent the safe driving corridor, and the specific shape should be determined according to the actual situation and algorithm performance. In addition, the generated safe driving corridor can be optimized to reduce unnecessary changes in curvature and width, and improve driving efficiency and safety. Alternatively, the safe driving corridor is adjusted and replanned online according to sensor data and vehicle status to adapt to dynamically changing environments.

[0072] In another possible implementation, referring to Figure 5 , and path planning can also be performed using a fifth-order polynomial curve according to the virtual position of the vehicle and the current position of the vehicle to obtain a safe driving corridor for the vehicle. Specifically, the following steps are included: (1) The current position of the vehicle is taken as the starting point of the path, and the virtual position of the vehicle is taken as the end point of the path. The quintic polynomial curve is defined as: y(x)=ax 5 +bx 4 +cx 3 +dx 2 +ex+f, where x and y represent the horizontal and vertical coordinates on the path respectively.

[0073] (2) At the starting point and the end point of the path, the continuity conditions of position, velocity, and acceleration must be met. These conditions can be converted into boundary conditions and derivative conditions of a quintic polynomial curve.

[0074] (3) Establish a system of equations based on the constraints and use numerical methods such as Gaussian elimination and matrix inversion to solve the system of equations and obtain the coefficients a, b, c, d, e, f of the quintic polynomial.

[0075] (4) Based on the fifth-order polynomial curve, the path offset is calculated by considering the vehicle's driving error and possible lateral movement. The offset can be determined based on factors such as the vehicle's width, driving speed, road conditions, and obstacle avoidance safety distance.

[0076] (5) Using the fifth-order polynomial curve as the center line, generate safety boundary lines on the left and right sides according to the offset. The safety boundary line should have a certain width to accommodate the vehicle's driving error and possible lateral movement. Polygons such as rectangles or more complex shapes can be used to represent the safe driving corridor.

[0077] (6) In the process of generating a safe driving corridor, it is necessary to detect and avoid surrounding obstacles in real time. If an obstacle is located within the safe driving corridor, the path needs to be replanned to ensure that the vehicle can drive safely.

[0078] By using the quintic polynomial curve for path planning, a safe driving corridor for the vehicle can be obtained, which can achieve accurate planning and real-time adjustment of the vehicle's driving path, thereby improving the safety and reliability of vehicle driving.

[0079] In another possible implementation, referring to Figure 6 If there are multiple social vehicles, it is necessary to check whether there is a conflict in obstacle avoidance. The following conditions need to be met: establish a safe driving corridor for each obstacle respectively, and check whether the passage width of the vehicle's virtual position meets the passable width. Plan the quintic polynomial curves from point A to point B and from point B to point C respectively. If the obstacle avoidance from B to C is not satisfied, it indicates that there is a conflict, then it is necessary to follow the obstacle Obs2 and avoid the obstacle 1.

[0080] Step S33, controlling the vehicle to travel along the safe driving corridor.

[0081] The generated safe driving corridor can be converted into actual control instructions for the vehicle, such as steering angle, acceleration / braking instructions, etc. The vehicle control system is used to execute these instructions to achieve overtaking. During the overtaking process, the deviation between the actual driving trajectory of the vehicle and the safe driving corridor can be monitored in real time. According to the deviation, the vehicle control instructions are adjusted in time to ensure that the vehicle always drives within the safe driving corridor to avoid collision with obstacles.

[0082] In this embodiment, if it is determined that the vehicle meets the overtaking condition based on the safety area and the width of the lane, a safe driving corridor for the vehicle is constructed, which can achieve accurate planning of the vehicle's driving path, thereby improving the safety and reliability of vehicle driving.

[0083] Furthermore, in order to ensure that the vehicle can drive safely, after the safe driving corridor is constructed, the feasibility and safety of the safe driving corridor may be verified. Specifically, after step S32, the following steps are included: Step S34, performing feasibility verification on the safe driving corridor to obtain a feasibility verification result, and performing safety verification on the safe driving corridor to obtain a safety verification result; It should be noted that the feasibility verification results include whether the safe driving corridor is feasible or not. The feasibility is determined by checking whether the maximum curvature of the path satisfies the vehicle's non-integrity constraints. The safety verification results include whether the safe driving corridor is safe or not. The safety is determined by checking whether each point on the path collides with the confidence area of ​​the current obstacle.

[0084] If the feasibility verification result is that the safe driving corridor is feasible and the safety verification result is that the safe driving corridor is safe, step S33 is executed to control the vehicle to travel along the safe driving corridor.

[0085] In a feasible implementation manner, performing feasibility verification on the safe driving corridor to obtain a feasibility verification result includes: obtaining the curvature of each trajectory point of the safe driving corridor, wherein the safe driving corridor is composed of multiple trajectory points; if the inverse of the curvature of each trajectory point satisfies the minimum turning radius of the vehicle, determining that the feasibility verification result is that the safe driving corridor is feasible; if there is a trajectory point whose inverse of the curvature does not satisfy the minimum turning radius of the vehicle, determining that the feasibility verification result is that the safe driving corridor is not feasible.

[0086] In a feasible implementation manner, the safety verification of the safe driving corridor obtains a safety verification result including: if each trajectory point area and obstacle area of ​​the safe driving corridor do not overlap, determining that the safety verification result is that the safe driving corridor is safe; deducing the moment when the ego vehicle avoids obstacles based on the predicted trajectory of the rear vehicle, and the position error of the rear vehicle at this time, if the deduced lateral distance between the ego vehicle and the rear vehicle is within a certain threshold, and the longitudinal distance is less than a certain safety distance, it is considered that there is a safety risk, then determining that the safe driving corridor is unsafe, and continuing to follow the vehicle without avoiding obstacles.

[0087] In this embodiment, the feasibility and safety of the safe driving corridor are verified to ensure that the vehicle can drive safely.

[0088] Based on the above embodiments of the present application, in the fourth embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be repeated in the following. On this basis, when the obstacle is a private vehicle, after step S30, it includes: Step S50: If it is determined that the vehicle does not meet the overtaking condition based on the safety area and the width of the lane, the vehicle is controlled to follow the social vehicle.

[0089] In this embodiment, when it is determined that the vehicle does not meet the overtaking condition based on the safety area and the width of the lane, the vehicle is controlled to follow other vehicles to avoid collision between the vehicle and other vehicles, thereby improving the driving safety of the vehicle.

[0090] Based on the above embodiments of the present application, in the fifth embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be repeated hereafter. On this basis, step S30 includes: judging whether the vehicle meets the overtaking condition, including: determining the passable width of the vehicle in the lane according to the width of the safety area and the lane; obtaining the lateral safe driving threshold of the vehicle; if the difference between the passable width and the lateral safe driving threshold is greater than the vehicle width, determining that the vehicle meets the overtaking condition; if the difference between the passable width and the lateral safe driving threshold is less than or equal to the vehicle width, determining that the vehicle does not meet the overtaking condition. Among them, the passable width of the vehicle in the lane can be obtained by taking the difference between the width of the lane and the width of the lane occupied by the safety area, for example Figure 5 The lateral safe driving threshold can be a fixed value or can be adjusted in real time according to different vehicle types and / or lane widths, for example Figure 5 The safe_buff in it is represented.

[0091] In other embodiments, judging whether the vehicle meets the overtaking condition may also be as follows: based on the width of the safety area and the lane, the passable width of the vehicle in the lane may be determined; when the passable width is greater than the vehicle width, it is determined that the vehicle meets the overtaking condition; if the passable width is less than or equal to the vehicle width, it is determined that the vehicle does not meet the overtaking condition.

[0092] In this embodiment, if the difference between the passable width and the lateral safe driving threshold is greater than the vehicle width, it is determined that the vehicle meets the overtaking condition; if the difference between the passable width and the lateral safe driving threshold is less than or equal to the vehicle width, it is determined that the vehicle does not meet the overtaking condition. By setting the corresponding overtaking condition, accurate overtaking judgment can be achieved.

[0093] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the control method of the vehicle of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0094] Based on the same invention purpose, the present application also provides a vehicle control device, please refer to Figure 7 , the control device of the vehicle comprises: A first acquisition module 10 is used to acquire the obstacle position error sensed during the vehicle driving process; A chi-square test module 20, configured to perform a chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area; A second acquisition module 30 is used to acquire the width of the lane where the obstacle is currently located if the obstacle is located in the safety area; The overtaking module 40 is used to control the vehicle to perform an overtaking action if it is determined that the vehicle meets the overtaking condition according to the safety area and the width of the lane.

[0095] Optionally, the chi-square test module 20 is also used to: determine the chi-square statistic based on the lateral position error and the longitudinal position error of the historical period; determine the degrees of freedom and the risk parameter; determine the chi-square quantile based on the degrees of freedom and the risk parameter, wherein the risk parameter represents the probability that the obstacle is located in the confidence area, and the confidence area is located in the safety area; determine whether the obstacle is located in the safety area based on the chi-square statistic and the chi-square quantile.

[0096] Optionally, the chi-square test module 20 is also used to: determine the lateral position average error and the lateral position error variance based on each of the lateral position errors in the historical period, and determine the longitudinal position average error and the longitudinal position error variance based on each of the longitudinal position errors in the historical period; determine the lateral position error standard deviation according to the lateral position error variance, and determine the longitudinal position error standard deviation according to the longitudinal position error variance; perform standardization based on the lateral position error, the lateral position average error and the lateral position error standard deviation to obtain a first standard random variable, and perform standardization based on the longitudinal position error, the longitudinal position average error and the longitudinal position error standard deviation to obtain a second standard random variable; obtain the chi-square statistic based on the sum of the square of the first standard random variable and the square of the second standard random variable.

[0097] Optionally, the chi-square test module 20 is further used to: if the chi-square statistic is less than or equal to the chi-square quantile, determine that the obstacle is located in the safety area; if the chi-square statistic is greater than the chi-square quantile, determine that the obstacle is located outside the safety area.

[0098] Optionally, the overtaking module 40 is also used for: if it is determined that the vehicle meets the overtaking condition based on the safety area and the width of the lane, determining the virtual position of the vehicle based on the position of the obstacle; constructing a safe driving corridor for the vehicle based on the virtual position of the vehicle and the current position of the vehicle; and controlling the vehicle to travel along the safe driving corridor.

[0099] Optionally, the overtaking module 40 is further used to: perform path planning using a quintic polynomial curve according to the virtual position of the vehicle and the current position of the vehicle to obtain a safe driving corridor for the vehicle.

[0100] Optionally, the overtaking module 40 is also used to: perform feasibility verification on the safe driving corridor to obtain a feasibility verification result, and perform safety verification on the safe driving corridor to obtain a safety verification result; if the feasibility verification result is that the safe driving corridor is feasible and the safety verification result is that the safe driving corridor is safe, then execute the step of controlling the vehicle to travel along the safe driving corridor.

[0101] Optionally, the control device of the vehicle further includes a following module, and the following module is used to control the vehicle to follow the social vehicle if it is determined that the vehicle does not meet the overtaking condition based on the safety area and the width of the lane.

[0102] Optionally, the control device of the vehicle also includes an overtaking judgment module, which is used to determine the passable width of the vehicle in the lane based on the width of the safety area and the lane; obtain a lateral safe driving threshold of the vehicle; if the difference between the passable width and the lateral safe driving threshold is greater than the vehicle width, it is determined that the vehicle meets the overtaking condition; if the difference between the passable width and the lateral safe driving threshold is less than or equal to the vehicle width, it is determined that the vehicle does not meet the overtaking condition.

[0103] The vehicle control device provided by the present application adopts the vehicle control method in the above embodiment, which can solve the technical problem that the obstacle position error recognition accuracy is low during vehicle driving, resulting in the risk of vehicle collision. Compared with the prior art, the beneficial effects of the vehicle control device provided by the present application are the same as the beneficial effects of the vehicle control method provided by the above embodiment, and the other technical features in the vehicle control device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0104] Based on the same invention purpose, the present application also provides a vehicle, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle control method in the above-mentioned embodiment one.

[0105] Reference below Figure 8 , which shows a schematic diagram of the structure of a vehicle suitable for implementing the embodiment of the present application. The vehicle in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The vehicle shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0106] like Figure 8 As shown, the vehicle may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for vehicle operation are also stored in RAM1004. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the vehicle to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a vehicle with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0107] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0108] The vehicle provided by the present application adopts the vehicle control method in the above embodiment, which can solve the technical problem that the obstacle position error recognition accuracy is low during vehicle driving, resulting in the risk of vehicle collision. Compared with the prior art, the beneficial effects of the vehicle provided by the present application are the same as the beneficial effects of the vehicle control method provided by the above embodiment, and the other technical features in the vehicle are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0109] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0110] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0111] Based on the same invention purpose, the present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, and the computer-readable program instructions are used to execute the vehicle control method in the above-mentioned embodiment.

[0112] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0113] The computer-readable storage medium may be included in the vehicle, or may exist independently without being installed in the vehicle.

[0114] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the vehicle, the vehicle obtains an obstacle position error perceived during vehicle driving; performs a chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area; if the obstacle is located in the safe area, obtains the width of the lane where the obstacle is currently located; if it is determined that the vehicle meets the overtaking condition based on the safety area and the width of the lane, controls the vehicle to perform an overtaking action.

[0115] Computer program code for performing the operations of the present application may be written 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 separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through 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).

[0116] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0117] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0118] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle control method, and can solve the technical problem that the obstacle position error recognition accuracy is low during vehicle driving, resulting in the risk of vehicle collision. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the vehicle control method provided by the above-mentioned embodiment, and will not be repeated here.

[0119] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A vehicle control method, characterized in that: The method comprises: Obtain the obstacle position error perceived by the vehicle during driving; Performing a chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area; If the obstacle is located in the safety area, obtaining the width of the lane where the obstacle is currently located; If it is determined that the vehicle meets the overtaking condition according to the safety area and the width of the lane, the vehicle is controlled to perform an overtaking action.

2. The method according to claim 1, characterized in that The obstacle position error includes a lateral position error and a longitudinal position error between the vehicle and the obstacle. The step of performing a chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area includes: Based on the horizontal position error and vertical position error of the historical period, the chi-square statistic is determined; Determine degrees of freedom and risk parameters; determining a chi-square quantile based on the degrees of freedom and the risk parameter, wherein the risk parameter represents a probability that an obstacle is located in a confidence region, and the confidence region is located in the safety region; Whether the obstacle is located in a safe area is determined according to the chi-square statistic and the chi-square quantile.

3. The method according to claim 2, characterized in that The step of determining the chi-square statistic based on the horizontal position error and the vertical position error of the historical period includes: Determine a lateral position average error and a lateral position error variance based on each of the lateral position errors in the historical period, and determine a longitudinal position average error and a longitudinal position error variance based on each of the longitudinal position errors in the historical period; Determine a lateral position error standard deviation based on the lateral position error variance, and determine a longitudinal position error standard deviation based on the longitudinal position error variance; Performing standardization based on the lateral position error, the lateral position average error and the lateral position error standard deviation to obtain a first standard random variable, and performing standardization based on the longitudinal position error, the longitudinal position average error and the longitudinal position error standard deviation to obtain a second standard random variable; The chi-square statistic is obtained based on the sum of the square of the first standard random variable and the square of the second standard random variable.

4. The method according to claim 2, characterized in that The step of determining whether the obstacle is located in a safe area according to the chi-square statistic and the chi-square quantile comprises: If the chi-square statistic is less than or equal to the chi-square quantile, it is determined that the obstacle is located in the safety area; If the chi-square statistic is greater than the chi-square quantile, it is determined that the obstacle is outside the safety area.

5. The method according to any one of claims 1 to 4, characterized in that: If it is determined according to the safety area and the width of the lane that the vehicle meets the overtaking condition, the step of controlling the vehicle to perform the overtaking action includes: If it is determined that the vehicle meets the overtaking condition according to the safety area and the width of the lane, determining the virtual position of the vehicle according to the position of the obstacle; Constructing a safe driving corridor for the vehicle according to the virtual position of the vehicle and the current position of the vehicle; The vehicle is controlled to travel along the safe driving corridor.

6. The method according to claim 5, characterized in that The step of constructing a safe driving corridor for the vehicle according to the virtual position of the vehicle and the current position of the vehicle comprises: A path planning is performed using a fifth-order polynomial curve according to the virtual position of the vehicle and the current position of the vehicle to obtain a safe driving corridor for the vehicle.

7. The method according to claim 5 or 6, characterized in that After the step of constructing a safe driving corridor for the vehicle according to the virtual position of the vehicle and the current position of the vehicle, the method further includes: Performing feasibility verification on the safe driving corridor to obtain a feasibility verification result, and performing safety verification on the safe driving corridor to obtain a safety verification result; If the feasibility verification result is that the safe driving corridor is feasible and the safety verification result is that the safe driving corridor is safe, the step of controlling the vehicle to travel along the safe driving corridor is performed.

8. The method according to claim 1, characterized in that When the obstacle is a private vehicle, after the step of obtaining the width of the lane where the obstacle is currently located when the obstacle is located in the safety area, the method further includes: If it is determined that the vehicle does not meet the overtaking condition based on the safety area and the width of the lane, the vehicle is controlled to follow the social vehicle.

9. The method according to claim 1 or 8, characterized in that If the obstacle is located in the safety area, after the step of obtaining the width of the lane where the obstacle is currently located, the method further includes: Determining a passable width of the vehicle in the lane according to the safety area and the width of the lane; Obtaining a lateral safe driving threshold of the vehicle; If the difference between the passable width and the lateral safe driving threshold is greater than the vehicle width, determining that the vehicle meets the overtaking condition; If the difference between the passable width and the lateral safe driving threshold is less than or equal to the vehicle width, it is determined that the vehicle does not meet the overtaking condition.

10. A vehicle control device, characterized in that: The control device of the vehicle comprises: A first acquisition module is used to acquire the obstacle position error perceived during the vehicle driving process; A chi-square test module, used to perform a chi-square test based on the obstacle position error to determine whether the obstacle is located in a safe area; A second acquisition module, used for acquiring the width of the lane where the obstacle is currently located if the obstacle is located in the safety area; The overtaking module is used to control the vehicle to perform an overtaking action if it is determined that the vehicle meets the overtaking condition based on the safety area and the width of the lane.

11. A vehicle, characterized in that: The vehicle comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle control method according to any one of claims 1 to 9.

12. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle control method according to any one of claims 1 to 9 are implemented.

Images