Driving behavior evaluation method and device of intelligent driving vehicle and electronic equipment

Abstract

The embodiment of the invention discloses a driving behavior evaluation method and device of an intelligent driving vehicle and electronic equipment. The method comprises the following steps: performing anthropomorphic evaluation index value calculation on a plurality of groups of obtained historical test data to obtain a corresponding safety index value, an efficiency index value and a comfort index value, and then integrating all the anthropomorphic evaluation index values through a weight decision algorithm to obtain a safety index value, an efficiency index value and a comfort index value; and obtaining an association strength index value corresponding to each group of historical test data. Further, clustering processing is carried out on all the association strength index values, and a driving behavior evaluation rule corresponding to the target driving scene is obtained. And finally, based on a driving behavior evaluation rule, obtaining an evaluation result of the target driving behavior from the target test data obtained in real time. Through the evaluation steps, safety, efficiency and comfort index values are calculated, the multi-dimensional anthropomorphic evaluation requirement is met, parameter debugging of a subsequent intelligent driving vehicle is facilitated, and the subsequent vehicle using experience of the intelligent driving vehicle is improved.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to the field of intelligent vehicle technology, and in particular, to a driving behavior evaluation method, device, and electronic device for an intelligent driving vehicle. Background Art

[0002] With the rapid development of intelligent connected vehicle technology, during the testing of intelligent driving vehicles, it is necessary to continuously evaluate the driving behavior of each test, so as to complete the parameter revision of the intelligent driving vehicle, so as to reduce the instability of traffic flow and the occurrence of traffic accidents. Therefore, a driving behavior evaluation method is needed to objectively evaluate the driving results of test vehicles in different scenarios. However, the existing driving behavior evaluation methods often only consider a single physical indicator in the driving process, such as the speed parameter of the driving vehicle to evaluate its driving behavior, which leads to the evaluation results can only be considered from a single dimension, and cannot meet the requirements of multi-dimensional anthropomorphic evaluation, which affects the subsequent intelligent driving vehicle parameter debugging and reduces the driving experience of the intelligent driving vehicle. Summary of the invention

[0003] The embodiments of this specification provide a driving behavior evaluation method, device and electronic device for an intelligent driving vehicle, and the technical solutions thereof are as follows:

[0004] In a first aspect, an embodiment of the present specification provides a driving behavior evaluation method for an intelligent driving vehicle, the method comprising:

[0005] Obtain target test data and at least one group of historical test data of a target driving scenario, and determine anthropomorphic evaluation index values ​​corresponding to each group of the historical test data, wherein the anthropomorphic evaluation index values ​​include a safety index value, an efficiency index value, and a comfort index value, wherein the safety index value is calculated based on the minimum collision time of the vehicle, the potential risk of the vehicle, and the eye movement frequency of the driver, the efficiency index value is calculated based on the average driving speed, the driving trajectory accuracy, and the number of times the brakes are used, and the comfort index value is calculated based on the lateral and longitudinal accelerations of the driving, the steering wheel angle, and the pedal depth;

[0006] Integrate and calculate the safety index value, efficiency index value, and comfort index value of each group of the historical test data to obtain the correlation strength index value corresponding to each group of the historical test data;

[0007] Clustering all the association strength index values, and setting a driving behavior evaluation rule corresponding to the target driving scenario according to the clustering result, wherein the driving behavior evaluation rule is used to classify driving behaviors, and each driving behavior category corresponds to a different index threshold;

[0008] The target test data is evaluated based on the driving behavior evaluation rule to obtain a driving behavior evaluation result.

[0009] In a second aspect, a driving behavior evaluation device for an intelligent driving vehicle is provided, the device comprising:

[0010] an acquisition module, used to acquire target test data and at least one group of historical test data of a target driving scenario, and determine an anthropomorphic evaluation index value corresponding to each group of the historical test data, wherein the anthropomorphic evaluation index value includes a safety index value, an efficiency index value, and a comfort index value, wherein the safety index value is calculated based on the minimum collision time of the vehicle, the potential risk of the vehicle, and the eye movement frequency of the driver, the efficiency index value is calculated based on the average driving speed, the driving trajectory accuracy, and the number of brake usages, and the comfort index value is calculated based on the driving lateral and longitudinal accelerations, the steering wheel angle, and the pedal depth;

[0011] A calculation module, used for integrating and calculating the safety index value, efficiency index value and comfort index value of each group of the historical test data to obtain the correlation strength index value corresponding to each group of the historical test data;

[0012] A clustering module, used for clustering all the association strength index values, and setting a driving behavior evaluation rule corresponding to the target driving scene according to the clustering result, wherein the driving behavior evaluation rule is used for driving behavior classification, and each driving behavior category corresponds to a different index threshold;

[0013] The evaluation module is used to evaluate the target test data based on the driving behavior evaluation rule to obtain a driving behavior evaluation result.

[0014] In a third aspect, an electronic device is provided, including a device processor and a memory;

[0015] The device processor is connected to the memory;

[0016] The memory is used to store executable program code;

[0017] The device processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method provided in the first aspect or any possible implementation manner of the first aspect.

[0018] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a device processor, cause the computer or the device processor to execute the method provided in the first aspect or any possible implementation of the first aspect.

[0019] The beneficial effects brought by the technical solutions provided by some embodiments of this specification include at least:

[0020] In one or more embodiments of the present specification, anthropomorphic evaluation index values ​​are first calculated for multiple groups of historical test data to obtain corresponding safety index values, efficiency index values, and comfort index values, and then the anthropomorphic evaluation index values ​​are integrated through a weight decision algorithm to obtain the correlation strength index values ​​corresponding to each group of historical test data. Furthermore, all correlation strength index values ​​are clustered to obtain driving behavior evaluation rules corresponding to the target driving scenario. Finally, the target test data obtained in real time is based on the driving behavior evaluation rules to obtain the evaluation results of the target driving behavior. Through the above evaluation steps, the safety, efficiency, and comfort index values ​​are calculated to meet the multi-dimensional anthropomorphic evaluation requirements, so as to facilitate the subsequent parameter debugging of the intelligent driving vehicle and improve the subsequent vehicle experience of the intelligent driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A schematic diagram of the system architecture of a driving behavior evaluation method for an intelligent driving vehicle provided in an embodiment of this specification;

[0023] Figure 2 A flowchart of a driving behavior evaluation method for an intelligent driving vehicle provided in an embodiment of this specification;

[0024] Figure 3 A schematic diagram of the structure of a driving behavior evaluation device for an intelligent driving vehicle provided in an embodiment of this specification;

[0025] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0027] The terms "first", "second", "third", etc. in the description and claims of this specification and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0028] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present specification. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described with respect to some examples may be combined in other examples.

[0029] See also Figure 1 , Figure 1 A schematic diagram of the system architecture of a driving behavior evaluation method for an intelligent driving vehicle provided in an embodiment of this specification is shown.

[0030] like Figure 1 As shown, the system architecture of the driving behavior evaluation method of the intelligent driving vehicle may include at least a terminal 10, a server 20 and a network 30.

[0031] The terminal 10 includes but is not limited to electronic devices such as smart phones, desktop computers, tablet computers, laptops, smart speakers, digital assistants, smart wearable devices, etc., and may also be software running on the above electronic devices, such as applications, etc. Optionally, the operating system running on the electronic device may include but is not limited to Android system, IOS system, Linux, Windows, etc. Optionally, the terminal 10 provides a driving behavior assessment service to the user, and the terminal 10 may obtain a driving behavior assessment instruction of an application program interface and send a driving behavior assessment request to the server 20.

[0032] The server 20 can provide background services for the terminal 10. According to the driving behavior evaluation request sent by the terminal 10, the server 20 will obtain a series of driving behavior evaluation instructions, and the server 20 transmits the driving behavior evaluation instructions to other terminals 10 through the network 30. Specifically, the server 20 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0033] The network 30 is used to provide a medium for a communication link between the terminal 10 and the server 20. The network 30 may include various connection types, such as wired or wireless communication links or optical fiber cables.

[0034] In addition, it should be noted that Figure 1 What is shown is only one system provided by the present disclosure. In practical applications, other systems may also be included, for example, more terminals may be included.

[0035] In the embodiments of the present specification, the terminal 10 and the server 20 may be directly or indirectly connected via wired or wireless communication, which is not limited in the present disclosure.

[0036] See next Figure 2 , Figure 2 The overall flow chart of a driving behavior evaluation method for an intelligent driving vehicle provided in an embodiment of the present specification is shown. The driving behavior evaluation method for an intelligent driving vehicle can be used in the server 20.

[0037] like Figure 2 As shown, the driving behavior evaluation method of the intelligent driving vehicle may at least include the following steps:

[0038] Step 201: Obtain target test data and at least one set of historical test data for a target driving scenario, and determine an anthropomorphic evaluation index value corresponding to each set of the historical test data.

[0039] Among them, the anthropomorphic evaluation index value includes a safety index value, an efficiency index value and a comfort index value. The safety index value is calculated based on the vehicle's minimum collision time, the vehicle's potential risk and the driver's eye movement frequency. The efficiency index value is calculated based on the average driving speed, driving trajectory accuracy and the number of brake uses. The comfort index value is calculated based on the driving lateral and longitudinal accelerations, the steering wheel angle and the pedal depth.

[0040] In the embodiment of this specification, in order to evaluate the driving behavior of the intelligent driving vehicle, it is necessary to first obtain the target test data and multiple groups of historical test data in the same target driving scene, first obtain the driving behavior evaluation rules under the target driving scene through multiple groups of historical test data, and then analyze the obtained target test data to obtain the corresponding driving behavior evaluation results. Among them, the test data can be first obtained through the sensor set inside the vehicle, and each test will correspond to a set of test data. Among them, each set of test data may include the speed, acceleration, position coordinates of the vehicle, the speed, acceleration, position coordinates of the surrounding traffic, the driver's eye movement frequency during driving, the number of brake applications, the steering wheel angle, the pedal depth and other data. Then, the minimum collision time of the vehicle, the potential risk of the vehicle, the driver's eye movement frequency, the average driving speed, the driving trajectory accuracy, the number of brake applications, the lateral and longitudinal accelerations of driving, the steering wheel angle and the pedal depth are determined through each set of historical test data. Furthermore, the safety index value is obtained by calculating the minimum collision time of the vehicle, the potential risk of the vehicle and the eye movement frequency of the driver. The efficiency index value is calculated by calculating the average driving speed, driving trajectory accuracy and the number of brake usage. The comfort index value is calculated by calculating the lateral and longitudinal acceleration, steering wheel angle and pedal depth. Finally, the safety index value, efficiency index value and comfort index value corresponding to each group of historical test data are counted to determine the anthropomorphic evaluation index value corresponding to each group of historical test data.

[0041] In one possible implementation manner, after acquiring the target test data of the target driving scenario and at least one set of historical test data, the method further includes:

[0042] Performing standardization processing on each group of historical test data to obtain historical standard data corresponding to each group of historical test data;

[0043] Determining the anthropomorphic evaluation index value corresponding to each group of the historical test data includes:

[0044] Determine the anthropomorphic evaluation index value corresponding to each group of the historical standard data.

[0045] In the embodiments of this specification, since the units of different indicators may be different, the numerical ranges may also vary greatly, and these differences will lead to deviations when directly comparing different indicator values, in order to eliminate the influence of the dimension so that different indicators can be directly compared, the Z-score standardization method can be used to standardize each group of historical test data, and the historical standard data corresponding to each group of historical test data can be obtained. When subsequently determining the anthropomorphic evaluation index value corresponding to each group of historical test data, the anthropomorphic evaluation index value corresponding to each group of historical standard data can be directly determined.

[0046] Among them, the Z-score standardized processing data formula is: Among them, x ij * is the standardized value of the data j to be processed for vehicle i, x ij is the original value of the data j to be processed of vehicle i; is the mean value of the data j to be processed for vehicle i; σ ij is the standard deviation of the data j to be processed for vehicle i, σ ij The calculation formula is

[0047] In one possible implementation, determining the anthropomorphic evaluation index value corresponding to each group of the historical test data includes:

[0048] Determining a scene type of the target driving scene, and determining an evaluation mode corresponding to the scene type based on a scene type database;

[0049] The anthropomorphic evaluation index value corresponding to each group of the historical test data is determined based on the evaluation mode.

[0050] In the embodiment of the present specification, since the evaluation parameters to be considered when conducting driving tests in different types of scenes are different, when determining the corresponding anthropomorphic evaluation index value through each set of historical test data, the scene type of the target driving scene can be determined first. Then, in the preset scene type database, each scene type has a determined evaluation mode corresponding to it one by one, so the determined scene type can be input into the preset scene type database, and the evaluation mode corresponding to the scene type can be obtained after query. As an example: the evaluation mode corresponding to the following scene is the longitudinal risk evaluation mode, and the evaluation mode corresponding to the lane change scene is the lateral risk evaluation mode. Further, after determining the corresponding evaluation mode, the corresponding anthropomorphic evaluation index calculation formula under the evaluation mode is determined. Among them, the anthropomorphic evaluation index value may include a safety index value, an efficiency index value and a comfort index value. As an example, in the longitudinal risk evaluation mode and the lateral risk evaluation mode, the minimum collision time coefficient of the surrounding vehicles in the corresponding safety index formula is different. Therefore, the anthropomorphic evaluation index value corresponding to each set of historical test data can be determined according to the determined anthropomorphic evaluation index calculation formula.

[0051] In one possible implementation, determining the anthropomorphic evaluation index value corresponding to each group of the historical test data based on the evaluation mode includes:

[0052] Determine the minimum collision time of the vehicle, the potential risk of the vehicle, the driver's eye movement frequency, the average driving speed, the driving trajectory accuracy, the number of brake applications, the lateral and longitudinal accelerations of the vehicle, the steering wheel angle and the pedal depth in each group of the historical test data;

[0053] Determining a first index model parameter, a second index model parameter and a third index model parameter based on the evaluation mode, wherein the first index model parameter is used to calculate a safety index, the second index model parameter is used to calculate an efficiency index, and the third index model parameter is used to calculate a comfort index;

[0054] Calculating the minimum collision time of each of the vehicles, the potential risk of the vehicle, and the eye movement frequency of the driver based on the first index model parameters to obtain a safety index value;

[0055] Calculating the average driving speed, driving trajectory accuracy and brake usage times based on the second index model parameter to obtain an efficiency index value;

[0056] Calculating the lateral and longitudinal accelerations, the steering wheel angle and the pedal depth based on the third index model parameter to obtain a comfort index value;

[0057] The safety index value, efficiency index value and comfort index value are statistically calculated to obtain the anthropomorphic evaluation index value corresponding to each group of the historical test data.

[0058] In the embodiment of this specification, since the anthropomorphic evaluation index value may include a safety index value, an efficiency index value, and a comfort index value, the minimum collision time of the vehicle, the potential risk of the vehicle, the driver's eye movement frequency, the average driving speed, the driving trajectory accuracy, the number of brake usage, the lateral and longitudinal accelerations, the steering wheel angle, and the pedal depth in each group of historical test data can be determined first. Then, when calculating the safety index SI of the self-vehicle i and the surrounding vehicles j ij When the minimum collision time TTC(t), vehicle potential risk PCRI(t) and driver eye movement frequency RME of each vehicle at time t are determined by the following formula, the safety index SI is then determined: ij (t).

[0059]

[0060] r=αv i (t)

[0061] SI ij =a1TTCX ij (t)+a2TTCY ij (t)+a3PCRI ij (t)+a4RME

[0062] Among them, α, β, a1, a2, a3 and a4 are all parameters of the SI model and are all defined as the first indicator model parameters. The values ​​of the parameters vary according to different scenarios; x i 、x j ,y i ,y j represents the longitudinal and lateral position coordinates of the vehicle i and surrounding vehicles j; l i represents the longitudinal length of the vehicle, w i represents the width of the vehicle in the horizontal direction; r represents the safe distance between vehicles during driving, which is related to the speed v of the vehicle at time t during driving. i (t) Related. TTCX ij (t) represents the minimum longitudinal collision time between vehicle i and surrounding vehicle j at time t; TTCY ij (t) represents the minimum lateral collision time between vehicle i and surrounding vehicle j at time t, PCRI ij (t) represents the potential risk value of vehicle i and surrounding vehicles j at time t.

[0063] In calculating the efficiency index value EI of vehicle i and surrounding vehicles j ij When the average driving speed is Driving trajectory accuracy X max and brake usage times t brake After that, determine the efficiency index value EI.

[0064]

[0065] X max =|y lane -y i |

[0066] EI ij =b1v i (t)+b2X max +b3t brake

[0067] Among them, v i (t) represents the vehicle's speed at time t, b1, b2, and b3 are all parameters of the EI model and are all defined as the second indicator model parameters.

[0068] In calculating the comfort index CI of vehicle i and surrounding vehicles j ij When the value is, the lateral and longitudinal acceleration a can be determined first. x 、a y , steering wheel angle δ and pedal depth d Pedal , and then determine the comfort index CI ij .

[0069]

[0070] in, is the lateral acceleration a x The derivative value of is the longitudinal acceleration a y The derivative values ​​of c1, c2, c3, c4, c5, and c6 are all CI ij The parameters of the model are all defined as third indicator model parameters.

[0071] Furthermore, after obtaining the safety index value, efficiency index value and comfort index value through the above indicator model parameters and the corresponding model calculation formulas, all the calculated index values ​​are counted to obtain the anthropomorphic evaluation index value corresponding to each group of historical test data. The anthropomorphic evaluation index value corresponding to each group of historical test data obtained by statistics includes the safety index value, efficiency index value and comfort index value.

[0072] Step 202: Integrate and calculate the safety index value, efficiency index value, and comfort index value of each group of the historical test data to obtain the correlation strength index value corresponding to each group of the historical test data.

[0073] In the embodiment of the present specification, after obtaining the safety index value, efficiency index value and comfort index value of each group of historical test data, in order to facilitate the subsequent classification of driving behaviors of each group of historical test data, the correlation strength index value corresponding to each group of historical test data can be calculated first, and the correlation between each group of historical test data can be determined by analyzing each correlation strength index value. Wherein, when calculating the correlation strength index value, the obtained safety index value, efficiency index value and comfort index value can be directly integrated and calculated. Wherein, when performing the integrated calculation, since the integrated calculation weights corresponding to different driving modes are different, the correlation strength index value corresponding to the historical test data can be calculated by determining the calculation weight corresponding to the driving instruction. As an example, when the driving mode is a high-speed driving mode, the corresponding safety index weight is higher, and when the driving instruction is a peak driving mode in the urban area, the corresponding efficiency index weight is higher. Different integration algorithms can also be determined by environmental factors such as driving weather, and the correlation strength index value corresponding to each group of historical test data can be obtained by different integration algorithms corresponding to each type of weather.

[0074] In one possible implementation, the safety index value, efficiency index value and comfort index value of each group of the historical test data are integrated and calculated to obtain the correlation strength index value corresponding to each group of the historical test data, including:

[0075] Determine the safety weight, efficiency weight and comfort weight corresponding to the safety index value, efficiency index value and comfort index value respectively based on the weight decision algorithm;

[0076] Based on the safety weight, efficiency weight and comfort weight, a weighted correlation calculation is performed on each group of the safety index value, efficiency index value and comfort index value to obtain the correlation strength index value corresponding to each group of the historical test data.

[0077] In the embodiment of this specification, the safety weight d1, efficiency weight d2 and comfort weight d3 corresponding to the safety index value, efficiency index value and comfort index value in the current driving mode can be determined by the weight decision algorithm. Then, the following weight calculation formula is used to calculate the safety index value SI ij , Efficiency Index Value EI ij and comfort index value CI ij Calculate the correlation strength index value F between each set of historical test data corresponding to the vehicle i and the surrounding vehicles j ij .

[0078]

[0079] Step 203: cluster all the association strength index values, and set a driving behavior evaluation rule corresponding to the target driving scenario according to the clustering result.

[0080] The driving behavior evaluation rules are used to classify driving behaviors, and each driving behavior category corresponds to a different indicator threshold.

[0081] In the embodiment of the present specification, after obtaining the association strength index value corresponding to all test data groups, the appropriate corresponding clustering algorithm can be selected first, and then the clustering parameters can be set further by the data characteristics of the association strength index value and the clustering purpose. As an example, when the K-means clustering algorithm is selected, the K value thereof needs to be set, and when the DBSCAN clustering algorithm is selected, the MinPts (the number of minimum points) and ε (neighborhood radius) values ​​thereof need to be set. Then, clustering processing is performed by determining a good clustering algorithm to obtain a clustering result. As an example, the clustering result may include three different categories and category intervals, corresponding to category 1 (immature driving), category 2 (general driving) and category 3 (excellent driving). Further, the driving behavior evaluation rules corresponding to the target driving scene can be set according to the clustering results, that is, the calculated anthropomorphic evaluation index value can be used to determine which category interval it belongs to, and then determine which driving behavior it belongs to.

[0082] Among them, when selecting a clustering algorithm, you can also choose clustering algorithms such as modularity clustering, hierarchical clustering, Mean-shiftClustering and Spectral Clustering.

[0083] In one possible implementation, clustering all the association strength index values ​​and setting the driving behavior evaluation rule corresponding to the target driving scenario according to the clustering result includes:

[0084] Calculating clustering results corresponding to all the association strength index values ​​based on the modularity clustering method, wherein the clustering results include the number of modules and each modularity data;

[0085] The driving behavior evaluation rule corresponding to the clustering result is determined based on the Louvain algorithm.

[0086] In the embodiment of the present specification, when the modularity clustering method is used to calculate the clustering results corresponding to all the association strength index values, the modularity Q corresponding to the association strength index value can be first calculated by the following formula.

[0087]

[0088] Among them, M represents the total strength of association, F′ ij represents the index association strength of nodes i and j with adjacent connection relationship, k i represents the degree of node i, k j represents the degree of node j, δ(c i ,c j ) is used to determine whether nodes i and j belong to the same community. If they are in the same community, it is 1; if they are not in the same community, it is 0.

[0089] Next, the indicators related to vehicle anthropomorphism evaluation are regarded as nodes, and each node is considered as a separate community;

[0090] Calculate the gain of the module. If the gain is greater than 0, return the node to the community of the adjacent node with the largest gain. Repeat this step until the community to which the node belongs does not change. The gain of the module can be calculated using the following formula:

[0091]

[0092] Among them, ∑ in is the sum of the internal connection weights in the community; ∑ tot is the sum of all connection weights of the community pointing to the node, k i,in It is the sum of the connection weights between node i and other nodes in the community.

[0093] As an example, the obtained driving behavior evaluation rules are expressed in the following table (three decimal places are retained):

[0094]

[0095] Step 204: Evaluate the target test data based on the driving behavior evaluation rule to obtain a driving behavior evaluation result.

[0096] In the embodiment of this specification, after obtaining the driving behavior evaluation rules corresponding to the target driving scene through multiple groups of test data, in order to evaluate the driving behavior corresponding to the target test data, the target anthropomorphic evaluation index value corresponding to the target test data can be calculated through the same steps as above for processing historical test data, and then the target safety index value, target efficiency index value and target comfort index value in the target anthropomorphic evaluation index value are judged by the set driving behavior evaluation rules to obtain the target driving behavior evaluation result. Optionally, the target anthropomorphic evaluation index values ​​corresponding to the target test data can also be calculated by other deep learning algorithms or neural network algorithms, and then judged by the set driving behavior evaluation rules to obtain the target driving behavior evaluation result.

[0097] In one possible implementation, the evaluating the target test data based on the driving behavior evaluation rule to obtain a driving behavior evaluation result includes:

[0098] Determining a target safety index value, a target efficiency index value, and a target comfort index value corresponding to the target test data;

[0099] The target driving behavior categories corresponding to the target safety index value, the target efficiency index value and the target comfort index value are judged based on the index thresholds, and the driving behavior evaluation results corresponding to the target driving behavior categories are determined.

[0100] In the embodiment of the present specification, after obtaining the driving behavior evaluation rules of the target driving scene, the obtained target test data can be standardized first, and then the target safety index value, target efficiency index value and target comfort index value corresponding to the target standard test data can be calculated in the same way. Then, according to the driving behavior evaluation rules, it is determined in which target driving behavior category value interval the calculated target safety index value, target efficiency index value and target comfort index value fall, and finally the corresponding driving behavior evaluation result is determined according to the target driving behavior category.

[0101] As an example, when the target safety index value calculated according to the target test data is 0.9, the target efficiency index value is 0.5, and the target comfort index value is 0.8, the corresponding driving behavior evaluation result is determined according to the previously obtained driving behavior evaluation rule table: this driving behavior is judged as excellent driving from the perspective of safety, general driving from the perspective of efficiency, and excellent driving from the perspective of comfort.

[0102] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0103] See next Figure 3 , Figure 3 The schematic diagram of the structure of a driving behavior evaluation device for an intelligent driving vehicle provided in an embodiment of this specification is shown. It should be noted that: Figure 3 The driving behavior evaluation device of the intelligent driving vehicle shown is used to execute the present application Figure 2 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 2 The embodiment shown.

[0104] like Figure 3 As shown, the driving behavior evaluation device of the intelligent driving vehicle may at least include:

[0105] An acquisition module 301 is used to acquire target test data and at least one group of historical test data of a target driving scenario, and determine an anthropomorphic evaluation index value corresponding to each group of the historical test data, wherein the anthropomorphic evaluation index value includes a safety index value, an efficiency index value, and a comfort index value. The safety index value is calculated based on the minimum collision time of the vehicle, the potential risk of the vehicle, and the eye movement frequency of the driver. The efficiency index value is calculated based on the average driving speed, the driving trajectory accuracy, and the number of brake usages. The comfort index value is calculated based on the driving lateral and longitudinal accelerations, the steering wheel angle, and the pedal depth.

[0106] A calculation module 302 is used to integrate and calculate the safety index value, efficiency index value and comfort index value of each group of the historical test data to obtain the correlation strength index value corresponding to each group of the historical test data;

[0107] A clustering module 303 is used to perform clustering processing on all the association strength index values, and set a driving behavior evaluation rule corresponding to the target driving scene according to the clustering result, wherein the driving behavior evaluation rule is used to classify driving behaviors, and each driving behavior category corresponds to a different index threshold;

[0108] The evaluation module 304 is used to evaluate the target test data based on the driving behavior evaluation rule to obtain a driving behavior evaluation result.

[0109] In one possible implementation, the acquisition module 301 is specifically used for:

[0110] Performing standardization processing on each group of historical test data to obtain historical standard data corresponding to each group of historical test data;

[0111] Determining the anthropomorphic evaluation index value corresponding to each group of the historical test data includes:

[0112] Determine the anthropomorphic evaluation index value corresponding to each group of the historical standard data.

[0113] In one possible implementation, the acquisition module 301 is further specifically used for:

[0114] Determining a scene type of the target driving scene, and determining an evaluation mode corresponding to the scene type based on a scene type database;

[0115] The anthropomorphic evaluation index value corresponding to each group of the historical test data is determined based on the evaluation mode.

[0116] In one possible implementation, the acquisition module 301 is further specifically used for:

[0117] Determine the minimum collision time of the vehicle, the potential risk of the vehicle, the driver's eye movement frequency, the average driving speed, the driving trajectory accuracy, the number of brake applications, the lateral and longitudinal accelerations of the vehicle, the steering wheel angle and the pedal depth in each group of the historical test data;

[0118] Determining a first index model parameter, a second index model parameter and a third index model parameter based on the evaluation mode, wherein the first index model parameter is used to calculate a safety index, the second index model parameter is used to calculate an efficiency index, and the third index model parameter is used to calculate a comfort index;

[0119] Calculating the minimum collision time of each of the vehicles, the potential risk of the vehicle, and the eye movement frequency of the driver based on the first index model parameters to obtain a safety index value;

[0120] Calculating the average driving speed, driving trajectory accuracy and brake usage times based on the second index model parameter to obtain an efficiency index value;

[0121] Calculating the lateral and longitudinal accelerations, the steering wheel angle and the pedal depth based on the third index model parameter to obtain a comfort index value;

[0122] The safety index value, efficiency index value and comfort index value are statistically calculated to obtain the anthropomorphic evaluation index value corresponding to each group of the historical test data.

[0123] In one possible implementation, the calculation module 302 is specifically used for:

[0124] Determine the safety weight, efficiency weight and comfort weight corresponding to the safety index value, efficiency index value and comfort index value respectively based on the weight decision algorithm;

[0125] Based on the safety weight, efficiency weight and comfort weight, a weighted correlation calculation is performed on each group of the safety index value, efficiency index value and comfort index value to obtain the correlation strength index value corresponding to each group of the historical test data.

[0126] In one possible implementation, the clustering module 303 is specifically used for:

[0127] Calculating clustering results corresponding to all the association strength index values ​​based on the modularity clustering method, wherein the clustering results include the number of modules and each modularity data;

[0128] The driving behavior evaluation rule corresponding to the clustering result is determined based on the Louvain algorithm.

[0129] In one embodiment, the evaluation module 304 is specifically configured to:

[0130] Determining a target safety index value, a target efficiency index value, and a target comfort index value corresponding to the target test data;

[0131] The target driving behavior categories corresponding to the target safety index value, the target efficiency index value and the target comfort index value are judged based on the index thresholds, and the driving behavior evaluation results corresponding to the target driving behavior categories are determined.

[0132] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (Field-Programmable Gate Array, FPGA), an integrated circuit (Integrated Circuit, IC), etc.

[0133] Each processing unit and / or module of the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0134] See next Figure 4 , Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification is shown.

[0135] like Figure 4 As shown, the electronic device 400 may include: at least one device processor 401 , at least one network interface 404 , a user interface 403 , a memory 405 , and at least one communication bus 402 .

[0136] The communication bus 402 may be used to realize the connection and communication among the above-mentioned components.

[0137] The user interface 403 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0138] The network interface 404 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0139] Among them, the device processor 401 may include one or more processing cores. The device processor 401 uses various interfaces and lines to connect various parts within the entire electronic device 400, and executes various functions and processes data of the electronic device 400 by running or executing instructions, programs, code sets or instruction sets stored in the memory 405, and calling data stored in the memory 405. Optionally, the device processor 401 can be implemented in at least one hardware form of DSP, FPGA, and PLA. The device processor 401 can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to handle wireless communications. It can be understood that the above-mentioned modem may not be integrated into the device processor 401, and it can be implemented separately through a chip.

[0140] The memory 405 may include RAM or ROM. Optionally, the memory 405 includes a non-transitory computer-readable medium. The memory 405 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 405 may optionally be at least one storage device located away from the aforementioned device processor 401. As Figure 4 As shown, the memory 405 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0141] Specifically, the device processor 401 may be used to call the driving behavior evaluation application for the intelligent driving vehicle stored in the memory 405, and specifically perform the following operations:

[0142] Obtain target test data and at least one group of historical test data of a target driving scenario, and determine anthropomorphic evaluation index values ​​corresponding to each group of the historical test data, wherein the anthropomorphic evaluation index values ​​include a safety index value, an efficiency index value, and a comfort index value, wherein the safety index value is calculated based on the minimum collision time of the vehicle, the potential risk of the vehicle, and the eye movement frequency of the driver, the efficiency index value is calculated based on the average driving speed, the driving trajectory accuracy, and the number of times the brakes are used, and the comfort index value is calculated based on the lateral and longitudinal accelerations of the driving, the steering wheel angle, and the pedal depth;

[0143] Integrate and calculate the safety index value, efficiency index value, and comfort index value of each group of the historical test data to obtain the correlation strength index value corresponding to each group of the historical test data;

[0144] Clustering all the association strength index values, and setting a driving behavior evaluation rule corresponding to the target driving scenario according to the clustering result, wherein the driving behavior evaluation rule is used to classify driving behaviors, and each driving behavior category corresponds to a different index threshold;

[0145] The target test data is evaluated based on the driving behavior evaluation rule to obtain a driving behavior evaluation result.

[0146] As an option of the embodiment of this specification, after acquiring the target test data of the target driving scene and at least one set of historical test data, the method further includes:

[0147] Performing standardization processing on each group of historical test data to obtain historical standard data corresponding to each group of historical test data;

[0148] Determining the anthropomorphic evaluation index value corresponding to each group of the historical test data includes:

[0149] Determine the anthropomorphic evaluation index value corresponding to each group of the historical standard data.

[0150] As an option in the embodiment of this specification, the determining of the anthropomorphic evaluation index value corresponding to each group of the historical test data includes:

[0151] Determining a scene type of the target driving scene, and determining an evaluation mode corresponding to the scene type based on a scene type database;

[0152] The anthropomorphic evaluation index value corresponding to each group of the historical test data is determined based on the evaluation mode.

[0153] As an option of the embodiment of this specification, the determining the anthropomorphic evaluation index value corresponding to each group of the historical test data based on the evaluation mode includes:

[0154] Determine the minimum collision time of the vehicle, the potential risk of the vehicle, the driver's eye movement frequency, the average driving speed, the driving trajectory accuracy, the number of brake applications, the lateral and longitudinal accelerations of the vehicle, the steering wheel angle and the pedal depth in each group of the historical test data;

[0155] Determining a first index model parameter, a second index model parameter and a third index model parameter based on the evaluation mode, wherein the first index model parameter is used to calculate a safety index, the second index model parameter is used to calculate an efficiency index, and the third index model parameter is used to calculate a comfort index;

[0156] Calculating the minimum collision time of each of the vehicles, the potential risk of the vehicle, and the eye movement frequency of the driver based on the first index model parameters to obtain a safety index value;

[0157] Calculating the average driving speed, driving trajectory accuracy and brake usage times based on the second index model parameter to obtain an efficiency index value;

[0158] Calculating the lateral and longitudinal accelerations, the steering wheel angle and the pedal depth based on the third index model parameter to obtain a comfort index value;

[0159] The safety index value, efficiency index value and comfort index value are statistically calculated to obtain the anthropomorphic evaluation index value corresponding to each group of the historical test data.

[0160] As an optional embodiment of this specification, the safety index value, efficiency index value and comfort index value of each group of the historical test data are integrated and calculated to obtain the correlation strength index value corresponding to each group of the historical test data, including:

[0161] Determine the safety weight, efficiency weight and comfort weight corresponding to the safety index value, efficiency index value and comfort index value respectively based on the weight decision algorithm;

[0162] Based on the safety weight, efficiency weight and comfort weight, a weighted correlation calculation is performed on each group of the safety index value, efficiency index value and comfort index value to obtain the correlation strength index value corresponding to each group of the historical test data.

[0163] As an option of an embodiment of this specification, clustering all the association strength index values ​​and setting the driving behavior evaluation rule corresponding to the target driving scenario according to the clustering result includes:

[0164] Calculating clustering results corresponding to all the association strength index values ​​based on the modularity clustering method, wherein the clustering results include the number of modules and each modularity data;

[0165] The driving behavior evaluation rule corresponding to the clustering result is determined based on the Louvain algorithm.

[0166] As an option of the embodiment of this specification, the target test data is evaluated based on the driving behavior evaluation rule to obtain a driving behavior evaluation result, including:

[0167] Determining a target safety index value, a target efficiency index value, and a target comfort index value corresponding to the target test data;

[0168] The target driving behavior categories corresponding to the target safety index value, the target efficiency index value and the target comfort index value are judged based on the index thresholds, and the driving behavior evaluation results corresponding to the target driving behavior categories are determined.

[0169] The embodiments of this specification also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0170] 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 preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0171] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0172] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods 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 through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0173] 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.

[0174] In addition, each functional unit in each embodiment of the present application 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0175] If the integrated unit 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 memory. Based on this understanding, the technical solution of the present application is essentially 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, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program code.

[0176] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0177] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A driving behavior evaluation method for an intelligent driving vehicle, characterized in that: The method comprises: Obtain target test data and at least one group of historical test data of a target driving scenario, and determine anthropomorphic evaluation index values ​​corresponding to each group of the historical test data, wherein the anthropomorphic evaluation index values ​​include a safety index value, an efficiency index value, and a comfort index value, wherein the safety index value is calculated based on the minimum collision time of the vehicle, the potential risk of the vehicle, and the eye movement frequency of the driver, the efficiency index value is calculated based on the average driving speed, the driving trajectory accuracy, and the number of times the brakes are used, and the comfort index value is calculated based on the lateral and longitudinal accelerations of the driving, the steering wheel angle, and the pedal depth; Integrate and calculate the safety index value, efficiency index value, and comfort index value of each group of the historical test data to obtain the correlation strength index value corresponding to each group of the historical test data; Clustering all the association strength index values, and setting a driving behavior evaluation rule corresponding to the target driving scenario according to the clustering result, wherein the driving behavior evaluation rule is used to classify driving behaviors, and each driving behavior category corresponds to a different index threshold; The target test data is evaluated based on the driving behavior evaluation rule to obtain a driving behavior evaluation result.

2. The method according to claim 1, characterized in that After acquiring the target test data of the target driving scenario and at least one set of historical test data, the method further includes: Performing standardization processing on each group of historical test data to obtain historical standard data corresponding to each group of historical test data; Determining the anthropomorphic evaluation index value corresponding to each group of the historical test data includes: Determine the anthropomorphic evaluation index value corresponding to each group of the historical standard data.

3. The method according to claim 1, characterized in that Determining the anthropomorphic evaluation index value corresponding to each group of the historical test data includes: Determining a scene type of the target driving scene, and determining an evaluation mode corresponding to the scene type based on a scene type database; The anthropomorphic evaluation index value corresponding to each group of the historical test data is determined based on the evaluation mode.

4. The method according to claim 3, characterized in that The determining, based on the evaluation mode, the anthropomorphic evaluation index value corresponding to each group of the historical test data includes: Determine the minimum collision time of the vehicle, the potential risk of the vehicle, the driver's eye movement frequency, the average driving speed, the driving trajectory accuracy, the number of brake applications, the lateral and longitudinal accelerations of the vehicle, the steering wheel angle and the pedal depth in each group of the historical test data; Determining a first index model parameter, a second index model parameter and a third index model parameter based on the evaluation mode, wherein the first index model parameter is used to calculate a safety index, the second index model parameter is used to calculate an efficiency index, and the third index model parameter is used to calculate a comfort index; Calculating the minimum collision time of each of the vehicles, the potential risk of the vehicle, and the eye movement frequency of the driver based on the first index model parameters to obtain a safety index value; Calculating the average driving speed, driving trajectory accuracy and brake usage times based on the second index model parameter to obtain an efficiency index value; Calculating the lateral and longitudinal accelerations, the steering wheel angle and the pedal depth based on the third index model parameter to obtain a comfort index value; The safety index value, efficiency index value and comfort index value are statistically calculated to obtain the anthropomorphic evaluation index value corresponding to each group of the historical test data.

5. The method according to claim 1, characterized in that: The safety index value, efficiency index value and comfort index value of each group of the historical test data are integrated and calculated to obtain the correlation strength index value corresponding to each group of the historical test data, including: Determine the safety weight, efficiency weight and comfort weight corresponding to the safety index value, efficiency index value and comfort index value respectively based on the weight decision algorithm; Based on the safety weight, efficiency weight and comfort weight, a weighted correlation calculation is performed on each group of the safety index value, efficiency index value and comfort index value to obtain the correlation strength index value corresponding to each group of the historical test data.

6. The method according to claim 1, characterized in that The clustering process is performed on all the association strength index values, and the driving behavior evaluation rule corresponding to the target driving scenario is set according to the clustering result, including: Calculating clustering results corresponding to all the association strength index values ​​based on the modularity clustering method, wherein the clustering results include the number of modules and each modularity data; The driving behavior evaluation rule corresponding to the clustering result is determined based on the Louvain algorithm.

7. The method according to claim 1, characterized in that The step of evaluating the target test data based on the driving behavior evaluation rule to obtain a driving behavior evaluation result includes: Determining a target safety index value, a target efficiency index value, and a target comfort index value corresponding to the target test data; The target driving behavior categories corresponding to the target safety index value, the target efficiency index value and the target comfort index value are judged based on the index thresholds, and the driving behavior evaluation results corresponding to the target driving behavior categories are determined.

8. A driving behavior evaluation device for an intelligent driving vehicle, characterized in that: The device comprises: an acquisition module, used to acquire target test data and at least one group of historical test data of a target driving scenario, and determine an anthropomorphic evaluation index value corresponding to each group of the historical test data, wherein the anthropomorphic evaluation index value includes a safety index value, an efficiency index value, and a comfort index value, wherein the safety index value is calculated based on the minimum collision time of the vehicle, the potential risk of the vehicle, and the eye movement frequency of the driver, the efficiency index value is calculated based on the average driving speed, the driving trajectory accuracy, and the number of brake usages, and the comfort index value is calculated based on the driving lateral and longitudinal accelerations, the steering wheel angle, and the pedal depth; A calculation module, used for integrating and calculating the safety index value, efficiency index value and comfort index value of each group of the historical test data to obtain the correlation strength index value corresponding to each group of the historical test data; A clustering module, used for clustering all the association strength index values, and setting a driving behavior evaluation rule corresponding to the target driving scene according to the clustering result, wherein the driving behavior evaluation rule is used for driving behavior classification, and each driving behavior category corresponds to a different index threshold; The evaluation module is used to evaluate the target test data based on the driving behavior evaluation rule to obtain a driving behavior evaluation result.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium has instructions stored therein, and when the instructions are executed on a computer or a processor, the computer or the processor executes the steps of the method according to any one of claims 1 to 7.

Images