Vehicle cut-in scene construction method and device for different road working conditions

Abstract

The embodiment of the invention provides a vehicle cut-in scene construction method and device oriented to different road working conditions. The method comprises the steps that a first vehicle cut-in data set is obtained, the first vehicle cut-in data set comprises multiple sets of first vehicle cut-in data, for each set of first vehicle cut-in data, the ratio of the vehicle longitudinal distance to the vehicle relative speed in the first vehicle cut-in data is calculated to serve as the collision time length, and the collision time length is calculated to serve as the collision time length. Calculating the ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the vehicle speed of the main vehicle as the time headway, screening out a dangerous cut-in data set from the first vehicle cut-in data set according to the collision duration and the time headway, and finally constructing vehicle cut-in scene data according to the first vehicle cut-in data set and the dangerous cut-in data set. The method and device are used for achieving the effect of covering all lane-changing cut-in scenes.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method and device for constructing vehicle entry scenarios for different road conditions. Background Art

[0002] Changing lanes is one of the most common basic operations during vehicle driving, especially the lane-changing cut-in scenario, which is prone to traffic accidents and affects the driving experience. Lane-changing cut-in scenarios are of great significance in intelligent driving simulation testing, especially for evaluating the functionality and safety of intelligent driving systems. These scenarios can simulate complex and potentially dangerous traffic conditions commonly seen in actual driving, helping developers and testers fully understand the performance and limitations of the system.

[0003] The lane change cut-in scenario data is a collection of vehicle data, wherein the vehicle data includes: the main vehicle speed, the cut-in vehicle speed, the longitudinal distance between the main vehicle and the cut-in vehicle, the road curvature data, etc. Since the amount of lane change cut-in scenario data is too large, when simulating the lane change cut-in scenario, the prior art will use a probabilistic algorithm to perform statistical analysis on the lane change cut-in scenario, and then obtain parameter screening rules, and then filter out the lane change cut-in data of each scenario according to the parameter screening rules, and finally simulate the lane change cut-in data of each scenario.

[0004] However, since the probabilistic algorithm performs statistical analysis on the lane change scene data and then obtains the parameter screening rules, the lane change scene data is screened by the parameter screening rules, which will lead to ignoring the lane change scene data with low probability but high risk, thereby resulting in low coverage of the simulation test scenario. Summary of the invention

[0005] The embodiments of the present application provide a method and device for constructing vehicle cut-in scenarios for different road conditions, so as to achieve the effect of covering all lane change cut-in scenarios.

[0006] In a first aspect, the present application provides a method for constructing vehicle entry scenarios for different road conditions, comprising:

[0007] Acquire a first vehicle cut-in data set, the first vehicle cut-in data set comprising a plurality of groups of first vehicle cut-in data, each group of first vehicle cut-in data comprising at least one of the following scene parameters, and each scene parameter shall include: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature;

[0008] For each set of the first vehicle cut-in data, a ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the vehicle relative speed is calculated as the collision duration, and a ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the vehicle speed of the host vehicle is calculated as the headway;

[0009] Filtering a dangerous cut-in data set from the first vehicle cut-in data set according to the collision duration and the headway time;

[0010] Vehicle cut-in scenario data is constructed according to the first vehicle cut-in data set and the dangerous cut-in data set.

[0011] In a possible implementation manner, constructing vehicle cut-in scenario data according to the first vehicle cut-in dataset and the dangerous cut-in dataset includes:

[0012] Performing clustering processing on the first vehicle entry data set to obtain at least one first cluster, and screening out the first clusters whose data volume is greater than or equal to a first data volume threshold as first target clusters;

[0013] Performing clustering processing on the risk entry data set to obtain at least one second cluster;

[0014] Vehicle cut-in scenario data is constructed according to any group of first vehicle cut-in data in each of the first target clusters and any group of dangerous cut-in data in each of the second clusters.

[0015] In a possible implementation manner, constructing vehicle cut-in scenario data according to any group of first vehicle cut-in data in each of the first target clusters and any group of dangerous cut-in data in each of the second clusters includes:

[0016] Randomly selecting a set of first vehicle cut-in data from each of the first target clusters as first target data;

[0017] Randomly selecting a set of dangerous entry scene data from each of the second-type clusters as second target data;

[0018] Generalizing the first target data and the second target data to obtain extended scene data;

[0019] The first target data, the second target data and the extended scenario data are respectively regarded as a group of the vehicle entry scenario data.

[0020] In a possible implementation manner, the filtering out dangerous cut-in data from the first vehicle cut-in data set according to the collision duration and the headway time includes:

[0021] The first vehicle cut-in data whose collision duration is greater than or equal to the first duration threshold, whose collision duration is less than the second duration threshold, and whose headway is less than or equal to the third duration threshold are filtered out from the first vehicle cut-in data set as dangerous cut-in data.

[0022] In a possible implementation manner, obtaining the first vehicle cut-in data set includes:

[0023] Acquire a second vehicle cut-in data set, the second vehicle cut-in data set comprising a plurality of sets of second vehicle cut-in data, each set of second vehicle cut-in data comprising at least one of the following scene parameters: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature;

[0024] For each type of the scene parameter, calculating a statistical value of the scene parameter of the type included in each of the second vehicle cut-in data, the statistical value including a mean value and a variance;

[0025] According to the mean value and the variance of the scene parameters of the type, each type of scene parameter included in each group of the second vehicle cut-in data is standardized to obtain the first vehicle cut-in data. The formula for the standardized processing is as follows:

[0026]

[0027] Among them, y ij is the j-th type of scene parameter included in the i-th group of first vehicle cut-in data, x ij is the j-th type of scene parameter included in the i-th group of second vehicle cut-in data, is the average value of the j-th type of scene parameters included in all groups of second vehicle cut-in data, s j is the standard deviation of the j-th type of scene parameters included in all groups of second vehicle cut-in data.

[0028] In a possible implementation manner, obtaining the second vehicle cut-in data set includes:

[0029] Acquire a natural driving data set, and traverse the natural driving data set to obtain the second vehicle entry data set;

[0030] The traversal process includes the following steps:

[0031] For each set of natural driving data, each set of natural driving data includes at least one of the following scene parameters: acquisition time, main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, vehicle lateral distance, cut-in duration, road curvature, calculate the distance between the main vehicle and the traffic vehicles around the main vehicle, the distance includes: lateral distance and longitudinal distance;

[0032] Acquire natural driving data in which the lateral distance is within a first distance range and the longitudinal distance is within a second distance range as initial cut-in data;

[0033] Acquire natural driving data in which the lateral distance is 0 and the longitudinal distance is within the second distance range as end cut-in data;

[0034] A set of the second vehicle cut-in data is generated according to the start cut-in data and the end cut-in data.

[0035] In a second aspect, the present application provides a vehicle entry scenario construction system for different road conditions, including:

[0036] an acquisition module, configured to acquire a first vehicle cut-in data set, wherein the first vehicle cut-in data set includes a plurality of groups of first vehicle cut-in data, each group of first vehicle cut-in data includes at least one of the following scene parameters, and each scene parameter should include: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature;

[0037] The processing module is further used to calculate, for each set of the first vehicle cut-in data, a ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the vehicle relative speed as a collision duration, and to calculate a ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the vehicle speed of the host vehicle as a headway;

[0038] The processing module is further used to filter out a dangerous cut-in data set from the first vehicle cut-in data set according to the collision duration and the headway time;

[0039] The processing module is further used to construct vehicle cut-in scenario data according to the first vehicle cut-in data set and the dangerous cut-in data set.

[0040] In a vehicle entry scenario construction system for different road conditions provided in this application:

[0041] Performing clustering processing on the first vehicle entry data set to obtain at least one first cluster, and screening out the first clusters whose data volume is greater than or equal to a first data volume threshold as first target clusters;

[0042] Performing clustering processing on the risk entry data set to obtain at least one second cluster;

[0043] Vehicle cut-in scenario data is constructed according to any group of first vehicle cut-in data in each of the first target clusters and any group of dangerous cut-in data in each of the second clusters.

[0044] In a vehicle entry scenario construction system for different road conditions provided in this application:

[0045] Randomly selecting a set of first vehicle cut-in data from each of the first target clusters as first target data;

[0046] Randomly selecting a set of dangerous entry scene data from each of the second-type clusters as second target data;

[0047] Generalizing the first target data and the second target data to obtain extended scene data;

[0048] The first target data, the second target data and the extended scenario data are respectively regarded as a group of the vehicle entry scenario data.

[0049] In a vehicle entry scenario construction system for different road conditions provided in this application:

[0050] The first vehicle cut-in data whose collision duration is greater than or equal to the first duration threshold, whose collision duration is less than the second duration threshold, and whose headway is less than or equal to the third duration threshold are filtered out from the first vehicle cut-in data set as dangerous cut-in data.

[0051] In a vehicle entry scenario construction system for different road conditions provided in this application:

[0052] Acquire a second vehicle cut-in data set, the second vehicle cut-in data set comprising a plurality of sets of second vehicle cut-in data, each set of second vehicle cut-in data comprising at least one of the following scene parameters: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature;

[0053] For each type of the scene parameter, calculating a statistical value of the scene parameter of the type included in each of the second vehicle cut-in data, the statistical value including a mean value and a variance;

[0054] According to the mean value and the variance of the scene parameters of the type, each type of scene parameter included in each group of the second vehicle cut-in data is standardized to obtain the first vehicle cut-in data. The formula for the standardized processing is as follows:

[0055]

[0056] Among them, y ij is the j-th type of scene parameter included in the i-th group of first vehicle cut-in data, x ij is the j-th type of scene parameter included in the i-th group of second vehicle cut-in data, is the average value of the j-th type of scene parameters included in all groups of second vehicle cut-in data, s j is the standard deviation of the j-th type of scene parameters included in all groups of second vehicle cut-in data.

[0057] In a vehicle entry scenario construction system for different road conditions provided in this application:

[0058] Acquire a natural driving data set, and traverse the natural driving data set to obtain the second vehicle entry data set;

[0059] The traversal process includes the following steps:

[0060] For each set of natural driving data, each set of natural driving data includes at least one of the following scene parameters: acquisition time, main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, vehicle lateral distance, cut-in duration, road curvature, calculate the distance between the main vehicle and the traffic vehicles around the main vehicle, the distance includes: lateral distance and longitudinal distance;

[0061] Acquire natural driving data in which the lateral distance is within a first distance range and the longitudinal distance is within a second distance range as initial cut-in data;

[0062] Acquire natural driving data in which the lateral distance is 0 and the longitudinal distance is within the second distance range as end cut-in data;

[0063] A set of the second vehicle cut-in data is generated according to the start cut-in data and the end cut-in data.

[0064] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0065] The memory stores computer-executable instructions;

[0066] The processor executes the computer-executable instructions stored in the memory to implement a method for constructing vehicle entry scenarios for different road conditions as described in any one of the first aspects.

[0067] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement a method for constructing a vehicle entry scenario for different road conditions as described in any one of the first aspects.

[0068] In a fifth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it is used to implement a method for constructing a vehicle entry scenario for different road conditions as described in any one of the first aspects.

[0069] The embodiments of the present application provide a method and device for constructing vehicle cut-in scenarios for different road conditions, by acquiring a first vehicle cut-in data set, the first vehicle cut-in data set includes multiple groups of first vehicle cut-in data, each group of first vehicle cut-in data includes at least one of the following scenario parameters, each scenario parameter should include: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, road curvature, for each group of first vehicle cut-in data, calculate the ratio of the vehicle longitudinal distance and the vehicle relative speed in the first vehicle cut-in data as the collision duration, and calculate the ratio of the vehicle longitudinal distance and the main vehicle speed in the first vehicle cut-in data as the headway, according to the collision duration and the headway, filter out a dangerous cut-in data set from the first vehicle cut-in data set, and finally construct vehicle cut-in scenario data based on the first vehicle cut-in data set and the dangerous cut-in data set. Compared with the prior art, in which the lane change cut-in scene data is statistically analyzed through a probabilistic algorithm to obtain parameter screening rules, and the lane change cut-in scene data is screened through the parameter screening rules, which leads to the ignoring of low-probability but high-risk lane change cut-in scene data. The present application screens out dangerous cut-in data from the first vehicle cut-in data set according to the collision duration and the head-on time distance, and then constructs the vehicle cut-in scene data based on the first vehicle cut-in data set and the dangerous cut-in data set, ensuring that the lane change cut-in scene data with low probability but high risk can also be taken into account, thereby improving the coverage of the simulation test scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] 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.

[0071] Figure 1 A flowchart of a first embodiment of a method for constructing vehicle entry scenarios for different road conditions provided in this embodiment;

[0072] Figure 2 A schematic flow chart of a second embodiment of a method for constructing vehicle entry scenarios for different road conditions provided in this embodiment;

[0073] Figure 3 A schematic diagram of a flow chart of a third embodiment of a method for constructing vehicle entry scenarios for different road conditions provided in this embodiment;

[0074] Figure 4 A schematic flow chart of a fourth embodiment of a method for constructing vehicle entry scenarios for different road conditions provided in this embodiment;

[0075] Figure 5 A vehicle entry scenario construction system for different road conditions provided in this embodiment;

[0076] Figure 6 A schematic diagram of the structure of an electronic device embodiment 1 provided in an embodiment of the present application.

[0077] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0078] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0079] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0080] In the prior art, a statistical analysis of lane change scenarios is performed using a probabilistic algorithm to screen out lane change scenarios with high probability, which may result in ignoring lane change scenarios with low probability but high risk, thereby resulting in low coverage of simulation test scenarios.

[0081] Based on this, the inventive concept of the present application is to provide a new method for constructing vehicle cut-in scenarios for different road conditions, by obtaining a vehicle cut-in data set, and screening out a dangerous cut-in data set based on the collision duration and the headway, and then constructing vehicle cut-in scenario data based on the vehicle cut-in data set and the dangerous cut-in data set, so that lane change cut-in scenario data with low probability but high risk can also be taken into account, thereby covering all simulation test scenarios.

[0082] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0083] Figure 1A flow chart of a first embodiment of a method for constructing vehicle entry scenarios for different road conditions provided in this embodiment is shown in FIG. Figure 1 As shown, the method comprises the following steps:

[0084] S101: Acquire a first vehicle cut-in data set, where the first vehicle cut-in data set includes multiple groups of first vehicle cut-in data, and each group of first vehicle cut-in data includes at least one of the following scene parameters: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature.

[0085] In this embodiment, a first vehicle cut-in data set is first obtained. The first vehicle cut-in data set consists of multiple groups of first vehicle cut-in data, and each group of first vehicle cut-in data includes at least one of the following scene parameters: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature.

[0086] Optionally, different first vehicle entry data sets are obtained according to different road conditions, wherein the road conditions are divided into: expressways, ordinary urban roads, urban express roads, rural roads, etc. That is, each road condition corresponds to a first vehicle entry data set.

[0087] On the basis of the above step S101, obtaining the first vehicle cut-in data set includes:

[0088] A second vehicle cut-in data set is obtained, where the second vehicle cut-in data set includes multiple groups of second vehicle cut-in data, and each group of second vehicle cut-in data includes at least one of the following scene parameters: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature.

[0089] In this embodiment, a second vehicle cut-in data set is obtained, wherein the second vehicle cut-in data set includes multiple groups of second vehicle cut-in data, each group of second vehicle cut-in data includes at least one of the following scene parameters, and each scene parameter should include: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature. The scene parameters in each group of second vehicle cut-in data are accurately corresponded by each timestamp, that is, each timestamp corresponds to a series of scene parameters of the second vehicle cut-in data. And each road condition corresponds to a group of second vehicle cut-in data sets.

[0090] For each type of scene parameter, a statistical value of the type of scene parameter included in each second vehicle cut-in data is calculated, the statistical value including a mean value and a variance.

[0091] In this embodiment, each set of second vehicle cut-in data in the acquired second vehicle cut-in data set is processed. That is, the average value and variance are calculated for each type of scene parameter in each set of second vehicle cut-in data. That is, the average value and variance of the main vehicle speed, the average value and variance of the main vehicle longitudinal acceleration, the average value and variance of the vehicle relative speed, the average value and variance of the vehicle longitudinal distance, the average value and variance of the cut-in duration, and the average value and variance of the road curvature in each set of second vehicle cut-in data are calculated.

[0092] According to the mean value and variance of the scene parameters of the type, each type of scene parameters included in each group of second vehicle cut-in data is standardized to obtain the first vehicle cut-in data. The formula for the standardized processing is as follows:

[0093]

[0094] Among them, y ij is the j-th type of scene parameter included in the i-th group of first vehicle cut-in data, x ij is the j-th type of scene parameter included in the i-th group of second vehicle cut-in data, is the average value of the j-th type of scene parameters included in all groups of second vehicle cut-in data, s j is the standard deviation of the j-th type of scene parameters included in all groups of second vehicle cut-in data.

[0095] In this embodiment, the scene parameters in the second vehicle cut-in data are standardized to eliminate the influence of different units and magnitudes. Using the standardized processed data, the clustering algorithm can more accurately calculate the distance and similarity between samples, thereby improving the clustering effect of the model.

[0096] A specific implementation method of obtaining the second vehicle cut-in data set mentioned above is:

[0097] A natural driving data set is obtained, and the natural driving data set is traversed to obtain a second vehicle entry data set.

[0098] In this embodiment, natural driving data collected by various sensors on the test vehicle are first obtained, and the natural driving data collected by the test vehicle are classified according to road driving conditions, wherein the road conditions are divided into: expressways, ordinary urban roads, urban express roads, and rural roads, etc. That is, the collected natural driving data are classified according to different road driving conditions, so as to obtain vehicle cut-in scene data under different road driving conditions.

[0099] The traversal process includes the following steps:

[0100] For each set of natural driving data, each set of natural driving data includes at least one of the following scene parameters: acquisition time, main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, vehicle lateral distance, cut-in duration, road curvature, calculate the distance between the main vehicle and the traffic vehicles around the main vehicle, the distance includes: lateral distance and longitudinal distance;

[0101] In this embodiment, the acquired natural driving data is preprocessed, wherein the preprocessing operation includes: processing data loss, invalid data, and removing invalid, erroneous or duplicated data, and then resampling the natural driving data to synchronize the timestamps to ensure that the data collected in different time periods are consistent in time, thereby facilitating cross-time data comparison and analysis. The longitudinal distance of the vehicle and the lateral distance of the vehicle in each set of natural driving data are obtained as the lateral distance and longitudinal distance between the main vehicle and the traffic vehicles around the main vehicle.

[0102] Natural driving data in which the lateral distance is within the first distance range and the longitudinal distance is within the second distance range is acquired as the initial cut-in data.

[0103] In this embodiment, by traversing the natural driving data set, natural driving data with a lateral distance within a first distance range and a longitudinal distance within a second distance range is obtained as the starting cut-in data. Considering that the standard road width in China is 3.5 meters to 3.75 meters, the first distance range is set to be greater than or equal to 1.8 meters and less than or equal to 5 meters. The value of the second distance range is different according to different road driving conditions. Optionally, taking the highway as an example, referring to the literature on highway vehicle driving data analysis, the second distance range is set to 1 meter to 120 meters. Therefore, when the lateral distance is greater than or equal to 1.8 meters and less than or equal to 5 meters, and when the longitudinal distance is greater than or equal to 1 meter and less than or equal to 120 meters, the natural driving data at this moment is selected as the starting cut-in data.

[0104] The natural driving data in which the lateral distance is 0 and the longitudinal distance is within the second distance range is obtained as the end cut-in data.

[0105] In this embodiment, the natural driving data set is traversed to obtain natural driving data with a lateral distance of 0 and a longitudinal distance within the second distance range as the end cut-in data. That is, when the lateral distance is 0 and the longitudinal distance is greater than or equal to 1 meter and less than or equal to 120 meters, the natural driving data at this moment is selected as the end cut-in data.

[0106] A set of second vehicle cut-in data is generated according to the start cut-in data and the end cut-in data.

[0107] In this embodiment, according to the timestamp of the start cut-in data and the timestamp of the end cut-in data, the natural driving data corresponding to all timestamps within the timestamp of the start cut-in data and the timestamp of the end cut-in data are selected as a group of second vehicle cut-in data. All groups of natural driving data are traversed to generate all groups of second vehicle cut-in data, thereby obtaining a second vehicle cut-in data set.

[0108] S102: For each set of first vehicle cut-in data, calculate the ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the vehicle relative speed as the collision duration, and calculate the ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the main vehicle speed as the headway.

[0109] In this embodiment, for each set of first vehicle cut-in data, the ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the vehicle relative speed is calculated as the collision time. And the ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the main vehicle speed is calculated as the headway time. In this way, the collision time and headway time of each set of first vehicle cut-in data are obtained.

[0110] S103: Filtering out a dangerous cut-in data set from the first vehicle cut-in data set according to the collision duration and the headway time.

[0111] In this embodiment, based on the collision duration and headway time calculated from each set of first vehicle cut-in data, the first vehicle cut-in data whose collision duration and headway time are within the given threshold are selected according to a given threshold to form a dangerous cut-in data set.

[0112] S104: Constructing vehicle cut-in scenario data according to the first vehicle cut-in data set and the dangerous cut-in data set.

[0113] In this embodiment, the vehicle cut-in scenario data is constructed by obtaining the first vehicle cut-in dataset and the dangerous cut-in dataset. Since different road conditions correspond to the first vehicle cut-in dataset, the vehicle cut-in scenario data of different road conditions can be obtained.

[0114] In this embodiment, a first vehicle cut-in data set is obtained, and the first vehicle cut-in data set includes multiple groups of first vehicle cut-in data, each group of the first vehicle cut-in data includes at least one of the following scene parameters, and each scene parameter should include: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature. For each group of first vehicle cut-in data, the ratio of the vehicle longitudinal distance and the vehicle relative speed in the first vehicle cut-in data is calculated as the collision duration, and the ratio of the vehicle longitudinal distance and the main vehicle speed in the first vehicle cut-in data is calculated as the headway time. According to the collision duration and the headway time, a dangerous cut-in data set is screened out from the first vehicle cut-in data set. Finally, according to the first vehicle cut-in data set and the dangerous cut-in data set, vehicle cut-in scene data is constructed. Compared with the prior art, in which the lane change cut-in scene data is statistically analyzed through a probabilistic algorithm to obtain parameter screening rules, and the lane change cut-in scene data is screened through the parameter screening rules, which leads to the ignoring of low-probability but high-risk lane change cut-in scene data. The present application screens out dangerous cut-in data from the first vehicle cut-in data set according to the collision duration and the head-on time distance, and then constructs the vehicle cut-in scene data based on the first vehicle cut-in data set and the dangerous cut-in data set, ensuring that the lane change cut-in scene data with low probability but high risk can also be taken into account, thereby improving the coverage of the simulation test scenarios.

[0115] Figure 2 The flowchart of the second embodiment of the vehicle cutting scene construction method for different road conditions provided in this embodiment is as follows. Figure 1 Based on the embodiment shown, Figure 2 As shown, a specific implementation of step S104 is:

[0116] S201: Clustering is performed on a first vehicle entry data set to obtain at least one first cluster, and first clusters having a data volume greater than or equal to a first data volume threshold are screened out as first target clusters.

[0117] In this embodiment, the first vehicle cut-in data set is clustered to obtain at least one first cluster. In order to avoid the data in the first cluster from containing a dangerous cut-in data set, the first cluster in which the amount of data is greater than or equal to the first data amount threshold is selected as the first target cluster.

[0118] S202: performing clustering processing on the risk entry data set to obtain at least one second cluster.

[0119] In this embodiment, clustering is performed on the dangerous cut-in data set to obtain at least one second cluster.

[0120] For example, we can select the RECOME algorithm for clustering. The full name of the RECOME algorithm is a new density-based clustering algorithm that uses relative KNN kernel density. The RECOME algorithm requires two parameters for clustering data, namely parameter α and parameter K. For parameter K, we use the traversal method to find Traverse in units of 1, where n is the number of samples. For each selected K value, obtain a series of α values ​​using the RECOME quantization parameter method. Cluster the traversed K and a series of α values ​​corresponding to K, respectively, to obtain the clustering results corresponding to each K and α. Based on the clustering results, calculate the DBI index. When the DBI index value is the smallest, the corresponding K value and α value are the optimal K value and α value.

[0121]

[0122] Where N is the number of clusters obtained after clustering with the current K value and α value, s i is the average distance from the data within the class to the centroid of the cluster, M ij is the distance between cluster i and cluster j.

[0123] S203: Constructing vehicle cut-in scenario data according to any group of first vehicle cut-in data in each first target cluster and any group of dangerous cut-in data in each second cluster.

[0124] In this embodiment, any group of first vehicle cut-in data in each first target cluster is selected, and any group of dangerous cut-in data in each second cluster is selected to construct vehicle cut-in scene data. Optionally, the cluster centroid in each first target cluster and the cluster centroid in each second cluster are selected to construct vehicle cut-in scene data. Clustering processing is performed on the first vehicle cut-in data set for different road conditions, and clustering processing is performed on the dangerous cut-in data set for different road conditions. Finally, according to any group of first vehicle cut-in data in each first target cluster and any group of dangerous cut-in data in each second cluster, the vehicle cut-in scene data is constructed under different road conditions, that is, different road conditions will obtain corresponding vehicle cut-in scene data.

[0125] In this embodiment, clustering is performed on the first vehicle entry data set to obtain at least one first cluster, and the first cluster with a data volume greater than or equal to the first data volume threshold is selected as the first target cluster, and the dangerous entry data set is clustered to obtain at least one second cluster, and then the vehicle entry scene data is constructed according to any group of first vehicle entry data in each first target cluster and any group of dangerous entry data in each second cluster. The first cluster and the second cluster are obtained by clustering the first vehicle entry data set and the dangerous entry data set using a clustering algorithm, so as to avoid the data in the first cluster including the second cluster, select the first cluster with a data volume greater than or equal to the first data volume threshold as the first target cluster, and finally select the data in the first target cluster and the second cluster as the vehicle entry scene data. The clustering algorithm can automatically group the scenes in the first vehicle entry data and the dangerous entry data set according to their characteristics, thereby identifying different types of driving scenes, ensuring that the scenes in each cluster have high internal similarity and low external similarity, thereby improving the representativeness of the test scene.

[0126] Figure 3 The flowchart of the third embodiment of the method for constructing vehicle entry scenarios for different road conditions provided in this embodiment is as follows. Figure 2 Based on the embodiment shown, Figure 3 As shown, a specific implementation of step S203 is:

[0127] S301: Randomly select a group of first vehicle cut-in data from each first target cluster as first target data.

[0128] In this embodiment, for each first target cluster obtained by clustering, a group of first vehicle cut-in data is randomly selected from each first target cluster as the first target data, or the centroid of each first target cluster is selected as the first target data.

[0129] S302: Randomly select a set of dangerous entry scene data from each second cluster as second target data.

[0130] In this embodiment, for each second cluster obtained by clustering, a group of dangerous entry scene data is randomly selected from each second cluster as the second target data, or the centroid of each second cluster is selected as the second target data.

[0131] S303: Generalize the first target data and the second target data to obtain extended scenario data.

[0132] In this embodiment, the first target data and the second target data are generalized to obtain extended scene data, and the generalization step length can be set to generalize specific parameters. Among them, the specific parameters refer to the data included in the first target data and the second target data: the main vehicle speed, the cut-in vehicle speed, the longitudinal distance of the vehicle, the road curvature, etc., wherein the cut-in vehicle speed is calculated based on the main vehicle speed and the relative speed of the vehicle. The generalization step length is selected for the specific parameter to be generalized, and when the generalization threshold is reached, the generalization is stopped. For example, the specific parameter is selected as the main vehicle speed, the main vehicle speed is 60 kilometers per hour, the generalization step length is 10, and when the generalization threshold is 100 kilometers per hour, the main vehicle speed can be generalized to 70 kilometers per hour, 80 kilometers per hour, 90 kilometers per hour, and 100 kilometers per hour. The extended scene data is obtained by generalizing the specific parameters through the generalization step length.

[0133] S304: The first target data, the second target data and the extended scenario data are respectively regarded as a group of vehicle entry scenario data.

[0134] In this embodiment, the obtained first target data, the second target data, and the extended scenario data obtained by generalizing the first target data and the second target data are taken as a set of vehicle entry scenario data.

[0135] In this embodiment, the first target data, the second target data and the extended scenario data are used as vehicle cut-in scenario data, and the vehicle cut-in scenario data are simulated using simulation software Prescan, VTD, and SCANeR to generate a vehicle cut-in test scenario.

[0136] Figure 4 The flowchart of the fourth embodiment of the vehicle cutting scene construction method for different road conditions provided in this embodiment is as follows. Figures 1 to 3 Based on any of the embodiments shown, Figure 4 As shown, a specific implementation of step S103 is:

[0137] S401: Filter out first vehicle cut-in data whose collision duration is greater than or equal to the first duration threshold, whose collision duration is less than or equal to the second duration threshold, and whose headway is less than or equal to the third duration threshold from the first vehicle cut-in data set as dangerous cut-in data.

[0138] In this embodiment, a dangerous cut-in data set is screened out from the first vehicle cut-in data set according to the collision duration and the headway time. When the collision duration is greater than or equal to the first duration threshold, and the collision duration is less than the second duration threshold, wherein the first duration threshold is 1 second, and the second duration threshold is 3 seconds, that is, when the collision duration is greater than or equal to 1 second and less than or equal to 3 seconds. And when the headway time is less than or equal to the third duration threshold, wherein the third duration threshold is 2 seconds, that is, when the headway time is less than or equal to 2 seconds, the data that meets the collision duration threshold and the headway time threshold is screened out from the first vehicle cut-in data as dangerous cut-in data.

[0139] Among them, it takes a certain amount of time for the driver to judge and react after receiving a collision warning or sensing potential danger. This time usually includes perception time, decision time and action time. Studies have shown that the average reaction time of drivers is between 0.5 seconds and 1 second, but may vary due to individual differences, driving environment, fatigue level and other factors. When TTC is less than the driver's reaction time, the driver may not be able to take timely measures before the collision occurs, thereby increasing the risk of collision. Therefore, situations with smaller TTC values ​​are usually regarded as collision situations. Therefore, the collision duration threshold needs to be greater than or equal to 1 second and less than or equal to 3 seconds.

[0140] Figure 5 A vehicle cut-in scenario construction system for different road conditions provided in this embodiment. A vehicle cut-in scenario construction system for different road conditions provided in this application includes: an acquisition module 51 and an acquisition module 52; wherein:

[0141] The acquisition module 51 is used to acquire a first vehicle cut-in data set, the first vehicle cut-in data set includes multiple groups of first vehicle cut-in data, each group of the first vehicle cut-in data includes at least one of the following scene parameters, and each scene parameter should include: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature; the processing module 52 is also used to calculate, for each group of first vehicle cut-in data, the ratio of the vehicle longitudinal distance and the vehicle relative speed in the first vehicle cut-in data as the collision duration, and to calculate the ratio of the vehicle longitudinal distance and the main vehicle speed in the first vehicle cut-in data as the headway time; the processing module 52 is also used to filter out a dangerous cut-in data set from the first vehicle cut-in data set according to the collision duration and the headway time; the processing module 52 is also used to construct vehicle cut-in scene data based on the first vehicle cut-in data set and the dangerous cut-in data set.

[0142] Figure 6 This is a structural diagram of an electronic device embodiment 1 provided in the present application. Figure 6, an electronic device provided in this embodiment includes: at least one processor 61 and a memory 62. The processor 61 and the memory 62 are connected via a bus 63.

[0143] The specific implementation process of the processor 61 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0144] In the above Figure 6 In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0145] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0146] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0147] The present application also provides a computer-readable storage medium having computer execution instructions stored thereon. When a processor executes the computer execution instructions, a method for constructing a vehicle entry scenario for different road conditions as described above is implemented.

[0148] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The computer-readable storage medium may be any available medium that can be accessed by a general or special purpose computer.

[0149] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0150] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0151] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0152] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0153] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0154] The present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it is used to implement the above-mentioned method for constructing a vehicle entry scenario for different road conditions.

[0155] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0156] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0157] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0158] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0159] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. If not specifically stated, the processor may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. If not specifically stated, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc.

[0160] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0161] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0162] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0163] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for constructing vehicle entry scenarios for different road conditions, characterized in that: include: Acquire a first vehicle cut-in data set, the first vehicle cut-in data set comprising a plurality of groups of first vehicle cut-in data, each group of first vehicle cut-in data comprising at least one of the following scene parameters, and each scene parameter shall include: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature; For each set of the first vehicle cut-in data, a ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the vehicle relative speed is calculated as the collision duration, and a ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the vehicle speed of the host vehicle is calculated as the headway; Filtering a dangerous cut-in data set from the first vehicle cut-in data set according to the collision duration and the headway time; Vehicle cut-in scenario data is constructed according to the first vehicle cut-in data set and the dangerous cut-in data set.

2. The method according to claim 1, characterized in that Constructing vehicle cut-in scenario data according to the first vehicle cut-in dataset and the dangerous cut-in dataset, including: Performing clustering processing on the first vehicle entry data set to obtain at least one first cluster, and screening out the first clusters whose data volume is greater than or equal to a first data volume threshold as first target clusters; Performing clustering processing on the risk entry data set to obtain at least one second cluster; Vehicle cut-in scenario data is constructed according to any group of first vehicle cut-in data in each of the first target clusters and any group of dangerous cut-in data in each of the second clusters.

3. The method according to claim 2, characterized in that The constructing the vehicle cut-in scenario data according to any group of first vehicle cut-in data in each of the first target clusters and any group of dangerous cut-in data in each of the second clusters includes: Randomly selecting a set of first vehicle cut-in data from each of the first target clusters as first target data; Randomly selecting a set of dangerous entry scene data from each of the second-type clusters as second target data; Generalizing the first target data and the second target data to obtain extended scene data; The first target data, the second target data and the extended scenario data are respectively regarded as a group of the vehicle entry scenario data.

4. The method according to any one of claims 1 to 3, characterized in that The step of screening out dangerous cut-in data from the first vehicle cut-in data set according to the collision duration and the headway time distance includes: The first vehicle cut-in data whose collision duration is greater than or equal to the first duration threshold, whose collision duration is less than the second duration threshold, and whose headway is less than or equal to the third duration threshold are filtered out from the first vehicle cut-in data set as dangerous cut-in data.

5. The method according to any one of claims 1 to 3, characterized in that The obtaining of the first vehicle cut-in data set includes: Acquire a second vehicle cut-in data set, the second vehicle cut-in data set comprising a plurality of sets of second vehicle cut-in data, each set of second vehicle cut-in data comprising at least one of the following scene parameters: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature; For each type of the scene parameter, calculating a statistical value of the scene parameter of the type included in each of the second vehicle cut-in data, the statistical value including a mean value and a variance; According to the mean value and the variance of the scene parameters of the type, each type of scene parameter included in each group of the second vehicle cut-in data is standardized to obtain the first vehicle cut-in data. The formula for the standardized processing is as follows: Among them, y ij is the j-th type of scene parameter included in the i-th group of first vehicle cut-in data, x ij is the j-th type of scene parameter included in the i-th group of second vehicle cut-in data, is the average value of the j-th type of scene parameters included in all groups of second vehicle cut-in data, s j is the standard deviation of the j-th type of scene parameters included in all groups of second vehicle cut-in data.

6. The method according to claim 5, characterized in that The obtaining of the second vehicle cut-in data set includes: Acquire a natural driving data set, and traverse the natural driving data set to obtain the second vehicle entry data set; The traversal process includes the following steps: For each set of natural driving data, each set of natural driving data includes at least one of the following scene parameters: acquisition time, main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, vehicle lateral distance, cut-in duration, road curvature, calculate the distance between the main vehicle and the traffic vehicles around the main vehicle, the distance includes: lateral distance and longitudinal distance; Acquire natural driving data in which the lateral distance is within a first distance range and the longitudinal distance is within a second distance range as initial cut-in data; Acquire natural driving data in which the lateral distance is 0 and the longitudinal distance is within the second distance range as end cut-in data; A set of the second vehicle cut-in data is generated according to the start cut-in data and the end cut-in data.

7. A vehicle entry scenario construction system for different road conditions, characterized in that: include: an acquisition module, configured to acquire a first vehicle cut-in data set, wherein the first vehicle cut-in data set includes a plurality of groups of first vehicle cut-in data, each group of first vehicle cut-in data includes at least one of the following scene parameters, and each scene parameter should include: main vehicle speed, main vehicle longitudinal acceleration, vehicle relative speed, vehicle longitudinal distance, cut-in duration, and road curvature; The processing module is further used to calculate, for each set of the first vehicle cut-in data, a ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the vehicle relative speed as a collision duration, and to calculate a ratio of the vehicle longitudinal distance in the first vehicle cut-in data to the vehicle speed of the host vehicle as a headway; The processing module is further used to filter out a dangerous cut-in data set from the first vehicle cut-in data set according to the collision duration and the headway time; The processing module is further used to construct vehicle cut-in scenario data according to the first vehicle cut-in data set and the dangerous cut-in data set.

8. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The method comprises a computer program, which is used to implement the method according to any one of claims 1 to 6 when the computer program is executed by a processor.

Images