An Automatic Obstacle Avoidance Method and System for Intelligent Connected Vehicles

Abstract

This application relates to the technical field of automotive automatic obstacle avoidance, and specifically relates to an automatic obstacle avoidance method and system for intelligent connected vehicles. The method includes: collecting the lateral speed and tire pressure at each moment when the intelligent connected vehicle is driving, as well as the standard lateral speed at each moment when driving at the standard tire pressure; forming the lateral speed sequence and tire pressure sequence at each moment by respectively combining the lateral speed and tire pressure at each moment and all previous moments, and extracting each detected lateral subsequence in the lateral speed sequence at each moment; determining the lane change confidence of each detected lateral subsequence; classifying the means of the tire pressure sequences at each moment and its historical moments to obtain the tire pressure cluster where the mean of the tire pressure sequence at each moment is located; determining the tire pressure interference degree of the tire pressure cluster; obtaining the lateral adjustment coefficient of the tire pressure cluster at each moment; and obtaining the lateral speed at each moment during the lane change obstacle avoidance process of the intelligent connected vehicle. Thereby, the safety of automotive automatic obstacle avoidance is improved.

Description

Technical Field

[0001] This application relates to the technical field of automatic obstacle avoidance for vehicles, and particularly to an automatic obstacle avoidance method and system for intelligent connected vehicles. Background Art

[0002] With the development of vehicle intelligent and connected technologies, the traditional driving mode is gradually transforming towards automation and intelligent decision-making. Various advanced sensors are applied to intelligent connected vehicles. By combining with technologies such as big data and cloud computing, vehicles are equipped with powerful perception, decision-making, and execution capabilities, enabling them to monitor the surrounding environment in real time and make corresponding responses. Among them, automatic obstacle avoidance, as a core function of intelligent connected vehicles, can quickly and accurately identify and judge obstacles on the road through the vehicle's own intelligent system, and promptly take effective avoidance measures, thereby significantly reducing the risk of traffic accidents caused by human errors or environmental complexity, and improving driving safety and road traffic efficiency.

[0003] In intelligent connected vehicles, when an automatic obstacle avoidance detects that the vehicle in front suddenly stops or has an abnormal speed, it will perform an emergency obstacle avoidance to the left and right sides to ensure the safety of vehicle driving. When the existing technology performs obstacle avoidance, it usually plans an obstacle avoidance route based on the distance between its own vehicle and the obstacle in front, and then sets the lateral speed according to the planned obstacle avoidance route to achieve obstacle avoidance for the obstacle in front. However, the existing technology does not deeply consider that under different tire pressures, there will be a deviation between the lateral speed set by the connected vehicle according to the obstacle avoidance route and the actual lateral speed of the vehicle during driving, which may lead to problems such as vehicle out of control due to too fast lateral speed or inability to safely avoid obstacles due to too slow lateral speed. Summary of the Invention

[0004] To solve the above technical problems, the purpose of this application is to provide an automatic obstacle avoidance method and system for intelligent connected vehicles, and the specific technical solutions adopted are as follows:

[0005] In the first aspect, an embodiment of this application provides an automatic obstacle avoidance method for intelligent connected vehicles, and this method includes the following steps:

[0006] Collect the lateral speed and tire pressure at each moment during the driving of the intelligent connected vehicle, and obtain the standard lateral speed at each moment when the intelligent connected vehicle is driving at the standard tire pressure during the pre-factory test;

[0007] Form the lateral speed sequence and tire pressure sequence at each moment by the lateral speed and tire pressure at each moment and all the moments before it. Based on the distribution of the lateral speed during the vehicle lane change process, extract each detected lateral subsequence in the lateral speed sequence at each moment; determine the lane change confidence of each detected lateral subsequence through the numerical difference and change trend difference of the elements on both sides of the peak in each detected lateral subsequence;

[0008] Classify the means of the tire pressure sequences at each moment and its historical moments to obtain the tire pressure clusters where the means of the tire pressure sequences at each moment are located; extract each lateral subsequence from the detected lateral subsequences corresponding to the moments of all the means in the tire pressure clusters based on the distribution of the lane change confidence;

[0009] Analyze the distribution differences between the lateral speeds and the standard lateral speeds in each lateral subsequence, as well as the differences between the means and the standard tire pressures in the tire pressure clusters, to determine the tire pressure interference degree of the tire pressure clusters; take the number of elements between the first element and the maximum value element in the lateral subsequence as the turning time of the lateral subsequence;

[0010] Based on the differences between the turning times of all the lateral subsequences extracted at each moment and the turning time corresponding to the standard lateral speed, combined with the tire pressure interference degree, determine the lateral adjustment coefficients of the tire pressure clusters at each moment; use the initial lateral speed when the intelligent connected vehicle performs lane change to avoid obstacles and the lateral adjustment coefficients of the tire pressure clusters to which the mean of the tire pressure sequence belongs to determine the lateral speeds at each moment during the lane change obstacle avoidance process of the intelligent connected vehicle.

[0011] In one embodiment, the extraction of each detected lateral subsequence in the lateral speed sequence at each moment includes:

[0012] Divide the lateral speed sequence at each moment into each subsequence by using the sequence segmentation algorithm, calculate the element mean of each subsequence, obtain the segmentation threshold of all the element means by using the threshold segmentation algorithm, and take the subsequence with the element mean greater than the segmentation threshold as each detected lateral subsequence.

[0013] In one embodiment, the determination of the lane change confidence includes:

[0014] For each detected lateral subsequence, use the maximum peak value in the detected lateral subsequence to divide the detected lateral subsequence into a first subsequence and a second subsequence, and record the difference between the element means of the first subsequence and the second subsequence as the first difference;

[0015] Respectively obtain the first-order difference sequences of the first subsequence and the second subsequence, calculate the ratios of the number of positive numerical values, the number of negative numerical values and the number of all numerical values in each first-order difference sequence, calculate the difference between the ratios of the number of positive numerical values and the number of negative numerical values in each first-order difference sequence, and record it as the second difference; take the mean of the second differences of the first subsequence and the second subsequence as the two-sided monotonic coefficient of the corresponding detected lateral subsequence.

[0016] The lane change confidence is positively correlated with the two-sided monotonic coefficient and negatively correlated with the number of peak values and the first difference in the detected lateral subsequence.

[0017] In one embodiment, the extraction of each lateral subsequence includes:

[0018] Using a threshold segmentation algorithm to obtain the segmentation threshold of the lane-changing confidence of all detected lateral subsequences at all corresponding moments in the tire pressure cluster, and taking the detected lateral subsequences with lane-changing confidence greater than the segmentation threshold as each lateral subsequence.

[0019] In one embodiment, the determination of the tire pressure interference degree includes:

[0020] Form a standard lateral speed sequence with the standard lateral speeds at all moments. Based on the standard lateral speed sequence, use the same method as for obtaining each lateral subsequence from the lateral speed sequence to obtain each standard lateral subsequence;

[0021] For the tire pressure cluster, calculate the metric distance between any lateral subsequence and any standard lateral subsequence, and take the mean of all the metric distances as the lateral deviation degree of the tire pressure cluster; record the difference between the mean value of the in-cluster data in the tire pressure cluster and the standard tire pressure as the third difference, and record the difference between the mean value of the elements of all lateral subsequences in the tire pressure cluster and the mean value of the elements of all standard lateral subsequences as the fourth difference;

[0022] The tire pressure interference degree is positively correlated with both the lateral deviation degree and the fourth difference, and negatively correlated with the third difference.

[0023] In one embodiment, the determination of the lateral adjustment coefficient includes:

[0024] Use the same method as for obtaining the steering time of each lateral subsequence to determine the steering time of each standard lateral subsequence. For any tire pressure cluster, calculate the difference between the mean value of the steering times of all its corresponding lateral subsequences and the mean value of the steering times of all standard lateral subsequences as the lane-changing response degree of the any tire pressure cluster;

[0025] Based on the lane-changing response degree and tire pressure interference degree of the any tire pressure cluster, and the lateral speed difference of the connected vehicle at adjacent moments, determine the lateral adjustment coefficient.

[0026] In one embodiment, the expression of the lateral adjustment coefficient is: ; where is the lateral adjustment coefficient of the vth tire pressure cluster at the xth moment, is the tire pressure interference degree of the vth tire pressure cluster, is the lane-changing response degree of the vth tire pressure cluster, sign() is the sign function, is the lateral speed of the connected vehicle at the xth moment, is the lateral speed of the connected vehicle at the (x - 1)th moment.

[0027] In one embodiment, determining the lateral speed at each moment during the lane-changing obstacle avoidance process of the intelligent connected vehicle includes:

[0028] Using the tire pressure sequence at the moment when the intelligent connected vehicle needs to perform lane-changing obstacle avoidance, obtaining the tire pressure cluster to which the mean value of the tire pressure sequence at the moment of lane-changing obstacle avoidance belongs, calculating the normalized value of the lateral adjustment coefficient at each moment during the lane-changing obstacle avoidance process of the intelligent connected vehicle for the obtained tire pressure cluster, and combining the normalized value with the initial lateral speed to determine the lateral speed at each moment during the lane-changing obstacle avoidance process of the intelligent connected vehicle.

[0029] In one embodiment, calculating the sum value of the normalized value and the numerical value 1, and the lateral speed at each moment during the lane-changing obstacle avoidance process of the intelligent connected vehicle is the product of the initial lateral speed and the sum value.

[0030] In a second aspect, an embodiment of the present application further provides an intelligent connected vehicle automatic obstacle avoidance system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the method described in any one of the above are implemented.

[0031] The present application has at least the following beneficial effects:

[0032] This application collects the lateral speed and tire pressure at each moment during the driving of an intelligent connected vehicle, and obtains the standard lateral speed at each moment when the intelligent connected vehicle is driving at the standard tire pressure during the pre-factory test process; through the collaborative monitoring of the lateral speed and tire pressure, the comprehensive perception ability of the vehicle's dynamic state is improved, and the reliability of obstacle avoidance decision-making is enhanced; the lateral speed and tire pressure at each moment and all previous moments are respectively composed into the lateral speed sequence and tire pressure sequence at each moment, and based on the element distribution in the lateral speed sequence, each detected lateral subsequence in the lateral speed sequence at each moment is extracted; through the numerical difference and change trend difference of the elements on both sides of the peak in each detected lateral subsequence, the lane change confidence of each detected lateral subsequence is determined; the dynamic evaluation of the lane change confidence enhances the accuracy of vehicle intention recognition and helps to distinguish normal driving and emergency obstacle avoidance needs in complex road conditions; the means of the tire pressure sequences at each moment and their historical moments are classified to obtain the tire pressure clusters where the means of the tire pressure sequences at each moment are located; based on the distribution of the lane change confidence, each lateral subsequence is extracted from the detected lateral subsequences corresponding to the moments of all the means in the tire pressure cluster; by analyzing the distribution difference between the lateral speed in each lateral subsequence and the standard lateral speed, and the difference between the means in the tire pressure cluster and the standard tire pressure, the tire pressure interference degree of the tire pressure cluster is determined; the tire pressure interference degree realizes the quantification of the influence of tire pressure change on the lateral speed, so that the adjustment range of the lateral speed can be dynamically evaluated according to different tire pressure conditions, and the accuracy and reliability of the lateral speed adjustment are improved; the number of elements between the first element and the maximum value element in the lateral subsequence is used as the steering time of the lateral subsequence; based on the difference between the steering time of all the lateral subsequences extracted at each moment and the steering time corresponding to the standard lateral speed, combined with the tire pressure interference degree, the lateral adjustment coefficient of the tire pressure cluster at each moment is determined; the lateral adjustment coefficient can clarify the adjustment direction and adjustment range of the lateral speed under different tire pressure conditions, so as to avoid the problems of vehicle out-of-control risk or obstacle avoidance failure caused by abnormal tire pressure. Using the initial lateral speed during lane change obstacle avoidance of the intelligent connected vehicle and the lateral adjustment coefficient of the tire pressure cluster to which the mean of the tire pressure sequence belongs, the lateral speed at each moment during the lane change obstacle avoidance process of the intelligent connected vehicle is determined, so that the lateral speed of the vehicle can be effectively adjusted dynamically according to the tire pressure during vehicle obstacle avoidance, realizing the collaborative compensation of environmental interference and vehicle state, overcoming the problems of understeering or oversteering caused by tire pressure fluctuations, improving the obstacle avoidance effect of the vehicle, and avoiding additional traffic risks. Description of the Drawings

[0033] To more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0034] Figure 1 It is a flowchart of the steps of an automatic obstacle avoidance method for an intelligent connected vehicle provided by an embodiment of the present application;

[0035] Figure 2 It is a flowchart for adjusting the lateral speed of the vehicle during lane change and obstacle avoidance. Detailed implementation manners

[0036] In order to further elaborate on the technical means and effects adopted by the present application to achieve the intended invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of an automatic obstacle avoidance method and system for an intelligent connected vehicle proposed according to the present application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs.

[0038] The following specifically describes the specific solutions of an automatic obstacle avoidance method and system for an intelligent connected vehicle provided by the present application in conjunction with the drawings.

[0039] Please refer to Figure 1 , which shows a flowchart of the steps of an automatic obstacle avoidance method for an intelligent connected vehicle provided by an embodiment of the present application. The method includes the following steps:

[0040] S1, collect the lateral speed and tire pressure of the intelligent connected vehicle at each moment during driving, and obtain the standard lateral speed of the intelligent connected vehicle at each moment during the pre-factory test process when driving at the standard tire pressure.

[0041] In this embodiment, any normally running intelligent connected vehicle is taken as an example for analysis. The lateral speed of the intelligent connected vehicle is collected in real time through the in-vehicle IMU sensor. Specifically: the accelerations and angular velocities of the intelligent connected vehicle in the three-dimensional coordinate system are obtained in real time, and then, based on the acceleration and angular velocity data, the lateral speed value of the intelligent connected vehicle is obtained through the vehicle dynamics model. The lateral speeds in this embodiment are all specific values of the lateral speed, without considering the direction; the tire pressure of the intelligent connected vehicle is collected in real time through the central control system of the intelligent connected vehicle. Specifically: since the front wheels are the steering wheels of the vehicle and their tire pressures directly affect the steering response speed of the vehicle, in this embodiment, the central control system of the intelligent connected vehicle is used to obtain the tire pressures of the two front tires of the intelligent connected vehicle in real time, and the average value of the tire pressures of the two front tires is calculated as the tire pressure of the intelligent connected vehicle analyzed in this embodiment. At the same time, the vehicle standard tire pressure when the intelligent connected vehicle leaves the factory, and the standard lateral speed at each moment when the intelligent connected vehicle is driving at the standard tire pressure during the factory test process are obtained through the central control system. The acquisition processes of the vehicle standard tire pressure and the standard lateral speed are the same as the acquisition processes of the real-time lateral speed and tire pressure of the intelligent connected vehicle.

[0042] Among them, obtaining the lateral speed of the vehicle through the IMU sensor and the vehicle dynamics model is a well-known prior art, and the specific process will not be elaborated here; the lateral speed and tire pressure of the intelligent connected vehicle are collected synchronously, and the collection frequencies of the lateral speed, tire pressure, and standard lateral speed of the intelligent connected vehicle are all 10 Hz. Implementers can set them according to the actual situation, and this embodiment does not limit it here. It should be noted that the tire pressure of the intelligent connected vehicle analyzed in the subsequent analysis of this embodiment is the average value of the tire pressures of the two front tires.

[0043] In order to eliminate the influence of the dimension between data, the collected lateral speed, tire pressure, and standard lateral speed are respectively normalized. This embodiment adopts the maximum-minimum normalization processing method. Implementers can choose other existing feasible normalization methods by themselves, and this embodiment does not limit it here.

[0044] It should be noted that in the case of slow vehicle speed, the connected vehicle can usually avoid obstacles by emergency braking without changing lanes. When emergency lane change is required to avoid obstacles, the influence of the vehicle speed change amplitude on the lateral speed within a very short time is not particularly significant, and the influence is usually indirectly reflected through the steering input and path curvature. Therefore, this embodiment does not consider the vehicle speed when the vehicle avoids obstacles.

[0045] S2. For each moment and all moments before it, form a lateral velocity sequence and a tire pressure sequence for each moment respectively with the lateral velocities and tire pressures. Based on the element distribution in the lateral velocity sequence, extract each detected lateral subsequence in the lateral velocity sequence of each moment; determine the lane-changing confidence of each detected lateral subsequence through the numerical difference and change trend difference of the elements on both sides of the peak in each detected lateral subsequence.

[0046] Since the driving direction of a connected vehicle will inevitably change and lane-changing and steering operations will occur when it performs lane-changing to avoid obstacles. Therefore, in order to accurately analyze the influence of tire pressure on the lateral velocity of a connected vehicle, it is first necessary to screen out the tire pressure data when the connected vehicle changes lanes and steers from the historical driving data of the connected vehicle.

[0047] When a connected vehicle is driving straight without direction deviation, its lateral velocity will be 0; while when the connected vehicle is performing normal lane-changing and steering, it will generate a lateral acceleration, thereby causing the lateral velocity to increase from zero. When the lateral velocity reaches the maximum value, it means that the vehicle is performing lane-changing and steering operations with the maximum lateral displacement; when the vehicle completes lane-changing and steering and continues to drive straight, its lateral velocity begins to gradually decrease and return to zero. Therefore, when the vehicle is performing lane-changing and steering, the lateral velocity of the vehicle will show the characteristic of gradually increasing from zero to the peak and then gradually decreasing to zero. However, considering that external interferences such as crosswinds and road surface slopes during vehicle driving will also cause changes in the lateral velocity, the lateral velocity data is divided in this embodiment.

[0048] In this embodiment, the lateral velocities of each moment and all moments before it are arranged in chronological order to form a lateral velocity sequence for each moment, the tire pressures of each moment and all moments before it are arranged in chronological order to form a tire pressure sequence for each moment, and the standard lateral velocities of all moments during the factory test of the intelligent connected vehicle are arranged in chronological order to form a standard lateral velocity sequence.

[0049] For the lateral velocity sequence of each moment, in this embodiment, the lateral velocity sequence is segmented into multiple subsequences through a sequence segmentation algorithm. Since the lateral velocity of a connected vehicle is zero when it is driving straight and not affected by external interferences, the subsequences with changed lateral velocities can be selected through the mean difference of each subsequence. The sequence segmentation algorithm adopted in this embodiment is the BG (Bernaola Galvan) sequence segmentation algorithm. The BG sequence segmentation algorithm is a well-known existing technology, and implementers can choose other existing feasible sequence segmentation algorithms by themselves. This embodiment does not make any restrictions here.

[0050] For each subsequence obtained by segmenting the lateral velocity sequence at each moment, calculate the mean value of all elements in each subsequence, denoted as the first mean value, and use the first mean values of all subsequences of the lateral velocity sequence as the input of the Otsu threshold method to obtain the segmentation threshold. Subsequences with the first mean value greater than the segmentation threshold are used as each detected lateral subsequence. The Otsu threshold method can extract subsequences with large fluctuations in the lateral velocity sequence. On the one hand, it can reduce the amount of data to be processed and improve efficiency. On the other hand, it also avoids the misdetection phenomenon that subsequences full of 0s may be misdetected as subsequences during vehicle lane changes.

[0051] In this embodiment, the u-th detected lateral subsequence obtained by segmenting the lateral velocity sequence at any moment is taken as an example for analysis. First, obtain the peaks in the u-th detected lateral subsequence through the peak detection algorithm, and segment the u-th detected lateral subsequence into a first subsequence and a second subsequence according to the maximum value among all peaks. That is, all elements to the left of the maximum peak in the u-th detected lateral subsequence form the first subsequence, and all elements to the right of the maximum peak form the second subsequence. For example, if the u-th detected lateral subsequence is [1, 2, 3, 5, 4, 2, 3], then the maximum peak is 5, and all elements to the left of the maximum peak are 1, 2, 3, so the first subsequence is [1, 2, 3]. Similarly, all elements to the right of the maximum peak are 4, 2, 3, so the second subsequence is [4, 2, 3]. It should be understood that if there is an element U in the detected lateral subsequence that is greater than the elements on its left and right, then element U is a peak. Calculate the mean value of all elements in the first subsequence, denoted as the second mean value, calculate the mean value of all elements in the second subsequence, denoted as the third mean value, and denote the difference between the second mean value and the third mean value as the first difference. The smaller the first difference, the more similar the data distributions on both sides of the peak in the u-th detected lateral subsequence, and the more in line with the lateral velocity characteristics during normal lane changes or turns. Among them, in this embodiment, the AMPD peak detection algorithm is used. The AMPD peak detection algorithm is a well-known existing technology, and implementers can choose other feasible existing peak detection algorithms by themselves. This embodiment does not limit it here.

[0052] It should be noted that the difference represents the degree of difference between two variables. Specifically, it can be calculated in ways such as the absolute value of the difference, the square of the difference, and the ratio. In this embodiment, the absolute value of the difference between the second mean value and the third mean value is denoted as the first difference.

[0053] Obtain the first-order difference sequence P1 of the first subsequence and the first-order difference sequence P2 of the second subsequence, and calculate the ratio z1 of the number of positive values in the first-order difference sequence P1 to the number of all values in the first-order difference sequence P1, and the ratio z2 of the number of negative values in the first-order difference sequence P1 to the number of all values in the first-order difference sequence P1. Denote the absolute value of the difference between z1 and z2 as the second difference. Correspondingly, for the first-order difference sequence P2, use the same method as calculating the second difference for the first-order difference sequence P1 to obtain the second difference corresponding to the first-order difference sequence P2. Take the mean of the second differences of the first-order difference sequence P1 and the first-order difference sequence P2 as the two-sided monotonicity coefficient of the u-th detected lateral subsequence. The second difference of each first-order difference sequence can reflect whether all the element signs in each first-order difference sequence are all positive or all negative; the two-sided monotonicity coefficient can reflect whether the data on both sides of the maximum value of the u-th detected lateral subsequence conforms to the change characteristics of the lateral speed data during vehicle lane change and turning.

[0054] Based on the above analysis, in this embodiment, the lane change confidence of the u-th detected lateral subsequence is calculated, and the specific calculation method is as follows:

[0055] ; In the formula, is the lane change confidence of the u-th detected lateral subsequence, is the two-sided monotonicity coefficient of the u-th detected lateral subsequence, is the number of peaks in the u-th detected lateral subsequence, is the first difference of the u-th detected lateral subsequence, is a preset value greater than 0. To avoid the denominator being 0, in this embodiment , and the implementer can set it according to the actual situation.

[0056] It should be understood that the larger the two-sided monotonicity coefficient , the more it reflects that the data of the u-th detected lateral subsequence conforms to the characteristics of the lateral speed gradually increasing and then gradually decreasing during normal vehicle lane change and turning. If it is 1, it means that the u-th detected lateral subsequence has only one peak and conforms to the characteristics during vehicle lane change and turning. If is larger or 0, it reflects that the lateral speed in the u-th detected lateral subsequence is more likely to be affected by external interference. The first difference can reflect whether the change of the lateral speed is stable and symmetric. Therefore, through the lane change confidence It can comprehensively reflect whether the lateral velocity data change in the $u$-th detected lateral subsequence conforms to the data characteristics of normal lane change or steering. The greater the lane change confidence, the more the lateral velocity distribution in the $u$-th detected lateral subsequence conforms to the numerical distribution characteristics of normal vehicle lane change, so that subsequences conforming to the characteristics of lane change and steering can be effectively screened out from complex driving data.

[0057] S3. Classify the means of the tire pressure sequences at each moment and its historical moments to obtain the tire pressure clusters where the means of the tire pressure sequences at each moment are located; extract each lateral subsequence from the detected lateral subsequences at all corresponding moments in the tire pressure clusters based on the distribution of the lane change confidence of the detected lateral subsequences.

[0058] In order to more accurately analyze the influence of tire pressure on lateral velocity, in this embodiment, clustering analysis is performed on the tire pressure data to ensure the referability of the analysis results under the same tire pressure conditions. In this embodiment, the tire pressure sequences at each moment and the nearest $N$ moments before it are obtained. In this embodiment, $N = 30$, and the implementer can set it according to the actual situation and is not limited here in this embodiment. Calculate the mean of the tire pressures of all tires in each tire pressure sequence, denoted as the fourth mean. For any moment, use the fourth mean of the tire pressure sequences at the any moment and the nearest $N$ moments before it as the input of the DPC (Density Peak Clustering) density peak clustering algorithm, and the output is each clustering cluster, denoted as the tire pressure cluster. Each tire pressure cluster represents a tire pressure situation. In this embodiment, the cross-validation method is used to obtain the cut-off distance of the DPC clustering algorithm. The DPC density peak clustering algorithm and the cross-validation method are well-known existing technologies, and the implementer can choose other existing feasible clustering algorithms by himself, and is not limited here in this embodiment.

[0059] In this embodiment, the $v$-th tire pressure cluster at the any moment is taken as an example for analysis. Since the tire pressure sequences in this embodiment are the tire pressure sequences at each moment, therefore, each tire pressure sequence corresponds to a moment. So, obtain the lateral velocity sequences at the corresponding moments of the tire pressure sequences corresponding to each of the fourth means in the $v$-th tire pressure cluster, and use the lane change confidences of all the detected lateral subsequences corresponding to the lateral velocity sequences at all corresponding moments in the $v$-th tire pressure cluster as the input of the Otsu threshold method, and the output is the segmentation threshold, denoted as the first segmentation threshold. Take the detected lateral subsequences with lane change confidence greater than the first segmentation threshold as each lateral subsequence.

[0060] Similarly, for the standard lateral velocity sequence, use the same calculation method as that for calculating the lane change confidence of each detected lateral subsequence after segmentation of the lateral velocity sequence at any moment, further obtain each lateral subsequence, segment the standard lateral velocity sequence, calculate the lane change confidence of each segmented sequence, and use the lane change confidence for threshold segmentation, so as to obtain each standard lateral subsequence.

[0061] The extraction of the lateral subsequences and the standard lateral subsequences is carried out by the Otsu threshold method, which can extract the lateral speed data when the connected vehicle changes lanes or turns, so as to further analyze the differential change of the lateral speed caused by the tire pressure difference.

[0062] S4. Analyze the distribution differences between the lateral speeds in each lateral subsequence and the standard lateral speed, as well as the differences between the fourth mean value in the tire pressure cluster and the standard tire pressure, and determine the tire pressure interference degree of the tire pressure cluster; the number of elements between the first element and the maximum value element in the lateral subsequence is used as the steering time of the lateral subsequence.

[0063] For all the lateral subsequences corresponding to the v-th tire pressure cluster, calculate the metric distance between any one of the lateral subsequences and any one of the standard lateral subsequences, and calculate the mean value of the metric distances of all the lateral subsequences of the v-th tire pressure cluster as the lateral deviation degree of the v-th tire pressure cluster. The larger the lateral deviation degree is, the greater the deviation degree between the change characteristics of the lateral speed caused by the tire pressure change and the change characteristics of the standard lateral speed is, thus reflecting that the influence of the tire pressure change on the vehicle lane change is greater, and a greater degree of adjustment of the lateral speed is required. Among them, in this implementation, the metric distance is calculated by using the DTW (Dynamic Time Warping) distance, and the implementer can select other existing feasible calculation methods of the metric distance by himself.

[0064] The absolute value of the difference between the mean value of all the fourth mean values in the v-th tire pressure cluster and the standard tire pressure is denoted as the third difference. Calculate the absolute value of the difference between the mean value of the elements of all the lateral subsequences corresponding to the v-th tire pressure cluster and the mean value of the elements of all the standard lateral subsequences, and denote it as the fourth difference. Calculate the tire pressure interference degree of the v-th tire pressure cluster, and the specific calculation method is as follows:

[0065] ; where is the tire pressure interference degree of the v-th tire pressure cluster; is the lateral deviation degree of the v-th tire pressure cluster; is the fourth difference of the v-th tire pressure cluster; is the third difference of the v-th tire pressure cluster; is a preset value greater than 0. To avoid the denominator being 0, in this embodiment The implementer can set it according to the actual situation, and this embodiment does not limit it here.

[0066] It should be understood that the lateral deviation degree can measure the deviation degree between the lateral speeds when the vehicle changes lanes and turns under different tire pressures, thus reflecting the significant degree of the influence of the tire pressure on the lateral speed. It is then possible to quantify the degree of influence of the change in tire pressure unit on the lateral speed. The greater the degree of influence, the greater the tire pressure interference. Therefore, through the tire pressure interference it is possible to reflect whether the influence of the v-th tire pressure condition on the lateral speed is significant. The greater the tire pressure interference, the more significant the influence of the v-th tire pressure condition on the lateral speed.

[0067] During the process of vehicle lane change and steering, the grip force and steering direction generated by the tire pressure will change with the steering stage. At the initial stage of steering, the steering angle is relatively large; after the steering angle reaches the maximum value, the steering wheel needs to be turned in the opposite direction to straighten the driving angle of the vehicle and maintain normal driving. Therefore, the entire steering process includes two directions: the steering direction and the straightening direction.

[0068] Since tire pressure can cause changes in lateral speed, it is necessary to adjust the lateral speed according to the difference between the tire pressure and the standard tire pressure at different steering stages, so as to more accurately adapt to the lane change requirements and improve the handling and stability of the vehicle.

[0069] Furthermore, in each lateral subsequence and each standard lateral subsequence, the number of elements from the first element to the maximum value element in the lateral subsequence is recorded as the steering time of each lateral subsequence. Correspondingly, the steering time of each standard lateral subsequence is obtained.

[0070] S5. Based on the difference between the steering times of all lateral subsequences extracted at each moment and the steering times corresponding to the standard lateral speed, combined with the tire pressure interference, determine the lateral adjustment coefficient of the tire pressure cluster at each moment; use the initial lateral speed when the intelligent connected vehicle performs lane change and obstacle avoidance, and the lateral adjustment coefficient of the tire pressure cluster to which the tire pressure sequence mean belongs to determine the lateral speed of the intelligent connected vehicle at each moment during the lane change and obstacle avoidance process.

[0071] Taking the v-th tire pressure cluster as an example, calculate the difference between the mean value a1 of the steering times of all lateral subsequences corresponding to it and the mean value a2 of the steering times of all standard lateral subsequences as the lane change response degree of the v-th tire pressure cluster. The lane change response degree can reflect the influence of tire pressure difference on the lateral speed of the vehicle during steering. If the lane change response degree is greater than 0, it reflects that in the v-th tire pressure condition, the actual time taken for vehicle lane change has been extended, and at this time, it is necessary to increase the lateral speed to ensure timely obstacle avoidance; if the lane change response degree is less than 0, it reflects that the time taken for vehicle lane change has decreased, and at this time, it is necessary to decrease the lateral speed to avoid the phenomenon of excessive vehicle offset; if the lane change response degree is 0, it means that there is no need to adjust the lateral speed.

[0072] Based on the above analysis, in this embodiment, the lateral adjustment coefficient of each tire pressure cluster at each moment is calculated, and the specific calculation method is as follows:

[0073] ; In the formula, is the lateral adjustment coefficient of the v-th tire pressure cluster at the x-th moment, is the tire pressure interference degree of the v-th tire pressure cluster, is the lane change response degree of the v-th tire pressure cluster, sign() is the sign function, which outputs -1 when the parameter inside the sign function is less than 0, outputs 1 when the parameter inside the sign function is greater than 0, and outputs 0 when the parameter inside the sign function is equal to 0, is the lateral speed of the connected vehicle at the x-th moment, is the lateral speed of the connected vehicle at the (x - 1)-th moment. Since the lateral speed of the vehicle gradually increases during steering, if , it reflects that the vehicle is steering at the current moment. If it means that the lane change offset has been completed and the vehicle is returning to the straight direction.

[0074] It should be understood that if the current vehicle is steering, since the tire pressure will interfere with the steering efficiency of the vehicle, it is necessary to adjust the lateral speed to ensure the safe obstacle avoidance of the connected vehicle. If the lane change operation has been completed to achieve obstacle avoidance and the vehicle is returning to the straight direction, since the lateral speed of the vehicle is gradually decreasing and tending to be stable, adjusting the lateral speed at this time may cause the vehicle to swing or lose control, increasing additional traffic risks. Therefore, no large adjustment is required to maintain the overall balance and stability of the vehicle. The lateral adjustment coefficient can comprehensively reflect the demand direction and adjustment intensity of tire pressure changes on the lateral speed adjustment in different steering stages, ensuring that the lateral speed adjustment strategy can not only cope with abnormal tire pressure but also adapt to dynamic driving scenarios. The larger the lateral adjustment coefficient, the more it reflects that in the v-th tire pressure condition, a greater degree of adjustment of the lateral speed is required.

[0075] The autonomous obstacle avoidance system of the connected vehicle can real-time monitor the surrounding environment through devices such as sensors, radars, and cameras, identify potential obstacles, and provide environmental information for obstacle avoidance. When the vehicle detects the need to change lanes to avoid obstacles, it will plan an obstacle avoidance path according to the information of the surrounding obstacles, and then achieve automatic obstacle avoidance of the obstacles by controlling the lateral speed, vehicle steering angle, etc. during the driving of the connected vehicle. Among them, the process of the connected vehicle planning the obstacle avoidance path is a well-known prior art, and the specific process will not be elaborated.

[0076] When the vehicle needs to change lanes to avoid obstacles, first obtain the tire pressure sequence at the starting moment of the vehicle's lane-changing obstacle avoidance. Cluster the mean values of the tire pressure sequences at the starting moment and the N nearest moments before it using the DPC density peak clustering algorithm to obtain each tire pressure cluster. Obtain the tire pressure cluster where the mean value of the tire pressure sequence at the starting moment is located. For example, if the tire pressure cluster where the mean value of the tire pressure sequence at the starting moment is located is the v-th tire pressure cluster, in order to improve the obstacle avoidance effect of the connected vehicle and avoid the phenomenon of vehicle out of control or incomplete obstacle avoidance, in this embodiment, the lateral speed at each moment during the vehicle's lane-changing obstacle avoidance is optimized according to the lateral adjustment coefficient, and the lateral speed at each moment during the intelligent connected vehicle's lane-changing obstacle avoidance is determined. Taking the x-th moment as an example, the specific expression is:

[0077] ; In the formula, is the adjusted lateral speed at the x-th moment in the v-th tire pressure condition, that is, the lateral speed at the x-th moment during the intelligent connected vehicle's lane-changing obstacle avoidance, is the initial lateral speed at the starting moment of the vehicle's lane-changing obstacle avoidance, is the lateral adjustment coefficient of the v-th tire pressure cluster at the x-th moment, is a normalization function that normalizes the lateral adjustment coefficient to the range (-1, 1). It should be noted that (-1, 1) is an open interval. The flow chart of the lateral speed adjustment for the vehicle's lane-changing obstacle avoidance is as shown in Figure 2 Figure...

[0078] From the above expression, it can be seen that is the normalized value of the lateral adjustment coefficient of the v-th tire pressure cluster at the x-th moment, is the sum of the normalized value and the value 1. The adjusted lateral speed at the x-th moment in the v-th tire pressure condition is the product of the initial lateral speed at the starting moment of the vehicle's lane-changing obstacle avoidance and the sum value. Using the same calculation method as the lateral speed at the x-th moment during the intelligent connected vehicle's lane-changing obstacle avoidance, the lateral speed at each moment during the intelligent connected vehicle's lane-changing obstacle avoidance can be obtained, that is, the adjusted lateral speed at each moment during the intelligent connected vehicle's lane-changing obstacle avoidance.

[0079] Finally, using the adjusted lateral speed at each moment during the vehicle's lane-changing obstacle avoidance, change lanes and avoid obstacles according to the planned obstacle avoidance path to ensure that it can drive along the planned obstacle avoidance path, improve the obstacle avoidance effect of the vehicle, avoid additional traffic risks, and ensure the stability and safety of the obstacle avoidance process.

[0080] Based on the same inventive concept as the above method, an embodiment of the present application further provides an intelligent connected vehicle automatic obstacle avoidance system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned intelligent connected vehicle automatic obstacle avoidance methods are implemented.

[0081] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification has been made. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

[0083] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present application shall be included in the protection scope of the present application.

Claims

1. An automatic obstacle avoidance method for intelligent connected vehicles, characterized in that, The method includes the following steps: Collect the lateral speed and tire pressure at each moment when the intelligent connected vehicle is driving. Form the lateral speed sequence and tire pressure sequence at each moment from the lateral speed and tire pressure at each moment and all previous moments respectively. Based on the distribution of the lateral speed during the vehicle lane-changing process, extract each detected lateral subsequence in the lateral speed sequence at each moment; determine the lane-changing confidence of each detected lateral subsequence through the numerical difference and change trend difference of the elements on both sides of the peak in each detected lateral subsequence. Classify the means of the tire pressure sequences at each moment and its historical moments to obtain the tire pressure clusters where the means of the tire pressure sequences at each moment are located; extract each lateral subsequence from the detected lateral subsequences corresponding to the moments of all the means in the tire pressure clusters based on the distribution of the lane-changing confidence. Obtain the standard lateral speed at each moment when the intelligent connected vehicle is driving at the standard tire pressure during the pre-factory test; analyze the distribution difference between the lateral speed in each lateral subsequence and the standard lateral speed, and the difference between the mean value in the tire pressure cluster and the standard tire pressure, to determine the tire pressure interference degree of the tire pressure cluster; take the number of elements between the first element and the maximum value element in the lateral subsequence as the steering time of the lateral subsequence. Based on the difference between the steering time of all the lateral subsequences extracted at each moment and the steering time corresponding to the standard lateral speed, combined with the tire pressure interference degree, determine the lateral adjustment coefficient of the tire pressure cluster at each moment; use the initial lateral speed when the intelligent connected vehicle performs lane-changing to avoid obstacles and the lateral adjustment coefficient of the tire pressure cluster to which the mean value of the tire pressure sequence belongs to determine the lateral speed at each moment during the lane-changing obstacle avoidance process of the intelligent connected vehicle.

2. The automatic obstacle avoidance method for an intelligent connected vehicle according to claim 1, characterized in that, The extraction of each detected lateral subsequence in the lateral speed sequence at each moment includes: Divide the lateral speed sequence at each moment into each subsequence by using the sequence segmentation algorithm, calculate the element mean of each subsequence, obtain the segmentation threshold of all the element means by using the threshold segmentation algorithm, and take the subsequence with the element mean greater than the segmentation threshold as each detected lateral subsequence.

3. An automatic obstacle avoidance method for an intelligent connected vehicle according to claim 1, characterized in that, The determination of the lane-changing confidence includes: For each detected lateral subsequence, use the maximum peak in the detected lateral subsequence to divide the detected lateral subsequence into a first subsequence and a second subsequence, and record the difference between the element means of the first subsequence and the second subsequence as the first difference. Obtain the first-order difference sequences of the first subsequence and the second subsequence respectively, calculate the ratios of the number of positive numerical values, the number of negative numerical values to the total number of numerical values in each first-order difference sequence, calculate the difference between the ratios of the number of positive numerical values and the number of negative numerical values in each first-order difference sequence, and record it as the second difference; take the mean value of the second differences of the first subsequence and the second subsequence as the monotonic coefficient on both sides of the corresponding detected lateral subsequence. The lane-changing confidence is positively correlated with the monotonic coefficient on both sides, and negatively correlated with the number of peaks and the first difference in the detected lateral subsequence.

4. The automatic obstacle avoidance method for an intelligent connected vehicle according to claim 1, characterized in that, The extraction of each lateral subsequence includes: The segmentation threshold for obtaining the lane-changing confidence of all detected lateral subsequences corresponding to all moments in the tire pressure cluster is obtained by using a threshold segmentation algorithm, and the detected lateral subsequences with lane-changing confidence greater than the segmentation threshold are used as each lateral subsequence.

5. The automatic obstacle avoidance method for an intelligent connected vehicle according to claim 1, characterized in that, The determination of the tire pressure interference degree includes: The standard lateral velocity at all moments forms a standard lateral velocity sequence. Based on the standard lateral velocity sequence, the same method as that for obtaining each lateral subsequence from the lateral velocity sequence is used to obtain each standard lateral subsequence; For the tire pressure cluster, calculate the metric distance between any lateral subsequence and any standard lateral subsequence, and take the mean of all the metric distances as the lateral deviation degree of the tire pressure cluster; record the difference between the in-cluster data mean within the tire pressure cluster and the standard tire pressure as the third difference, and record the difference between the element mean of all lateral subsequences in the tire pressure cluster and the element mean of all standard lateral subsequences as the fourth difference; The tire pressure interference degree is positively correlated with both the lateral deviation degree and the fourth difference, and negatively correlated with the third difference.

6. The automatic obstacle avoidance method for an intelligent connected vehicle according to claim 5, wherein, The determination of the lateral adjustment coefficient includes: The same method as that for obtaining the steering time of each lateral subsequence is used to determine the steering time of each standard lateral subsequence. For any tire pressure cluster, calculate the difference between the mean steering time of all its corresponding lateral subsequences and the mean steering time of all standard lateral subsequences as the lane-changing response degree of the any tire pressure cluster; Based on the lane-changing response degree and tire pressure interference degree of the any tire pressure cluster, and the lateral velocity difference of the connected vehicle at adjacent moments, determine the lateral adjustment coefficient.

7. The automatic obstacle avoidance method for an intelligent connected vehicle according to claim 6, wherein The expression of the lateral adjustment coefficient is as follows: ; where is the lateral adjustment coefficient of the v-th tire pressure cluster at the x-th moment, is the tire pressure interference degree of the v-th tire pressure cluster, is the lane-changing response degree of the v-th tire pressure cluster, sign() is the sign function, is the lateral speed of the connected vehicle at the x-th moment, is the lateral speed of the connected vehicle at the (x - 1)-th moment.

8. The automatic obstacle avoidance method for an intelligent connected vehicle according to claim 1, characterized in that, The determination of the lateral velocity at each moment during the lane-changing obstacle avoidance process of the connected vehicle includes: Using the tire pressure sequence at the moment when the connected vehicle needs to perform lane-changing obstacle avoidance, obtain the tire pressure cluster to which the mean value of the tire pressure sequence at the lane-changing obstacle avoidance moment belongs, calculate the normalized value of the lateral adjustment coefficient at each moment during the lane-changing obstacle avoidance process of the belonging tire pressure cluster, and combine the normalized value with the initial lateral velocity to determine the lateral velocity at each moment during the lane-changing obstacle avoidance process of the connected vehicle.

9. The automatic obstacle avoidance method for an intelligent connected vehicle according to claim 8, characterized in that, Calculate the sum value of the normalized value and the numerical value 1, and the lateral velocity at each moment during the lane-changing obstacle avoidance process of the connected vehicle is the product of the initial lateral velocity and the sum value.

10. An automatic obstacle avoidance system for an intelligent connected vehicle, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-9.

Images