Driving behavior scoring method and device, electronic equipment and storage medium

By monitoring and predicting driving status by vehicle sensors, driving behavior scores are combined with targets and expected characteristics, which solves the problem of inaccurate evaluation of driving behavior in the prior art, improves the accuracy of the score and reduces safety risks.

CN119058716APending Publication Date: 2024-12-03CHONGQING SELIS PHOENIX INTELLIGENT INNOVATION TECH CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410986731.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The prior art cannot accurately evaluate driving behavior, resulting in safety hazards.

Method used

The driving state is monitored and predicted through sensors on the vehicle, and the target state value is determined based on the status monitoring value and predicted value, and the driving behavior score is performed based on the target driving behavior characteristics and the expected driving behavior characteristics.

Benefits of technology

It improves the accuracy of driving behavior scores, reduces the impact of data noise, avoids safety hazards, and achieves accurate acquisition of driving behavior scores.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119058716A_ABST
    Figure CN119058716A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of vehicle control, and provides a driving behavior scoring method and device, electronic equipment and a storage medium. According to the method, the target state value is jointly determined through the state monitoring value obtained by the sensor and the state prediction value obtained through prediction, so that the target state value is the same as or tends to be the same as the actual value corresponding to the vehicle driving state, the influence of the target state value of data noise is effectively reduced, and the accuracy of the target state value is improved; the target driving behavior characteristics of the vehicle are determined according to the target state value subsequently, the effect of accurately obtaining the target driving behavior characteristics is achieved, the driving behavior score corresponding to the vehicle is determined according to the target driving behavior characteristics and the expected driving behavior characteristics subsequently, the driving behavior score is accurately obtained, and the driving behavior score is accurately obtained. The problem that potential safety hazards exist due to the fact that the driving behaviors cannot be accurately evaluated in the prior art is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] With the growth of material culture, driving has become the first choice for people to go out, and users' driving behavior will affect vehicle driving safety.

[0003] In the existing technology, it is impossible to accurately evaluate the user's driving behavior, resulting in the user being unable to accurately determine whether his or her driving behavior is standard when driving the vehicle, which poses a safety hazard. How to accurately evaluate driving behavior has become an issue that needs to be urgently addressed. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a driving behavior scoring method, device, electronic device and storage medium to solve the problem in the prior art that driving behavior cannot be accurately assessed, resulting in safety hazards.

[0005] In a first aspect of an embodiment of the present application, a driving behavior scoring method is provided, the method comprising: monitoring the driving state of a vehicle through sensors on the vehicle to obtain a state monitoring value corresponding to the vehicle; predicting the driving state of the vehicle to obtain a state prediction value corresponding to the vehicle; determining a target state value corresponding to the vehicle based on the state monitoring value and the state prediction value; determining a target driving behavior characteristic of the vehicle according to the target state value, and determining a driving behavior score corresponding to the vehicle based on the target driving behavior characteristic and the expected driving behavior characteristic.

[0006] According to a second aspect of an embodiment of the present application, a driving behavior scoring device is provided, which includes: a monitoring module, which is used to monitor the driving state of a vehicle through sensors on the vehicle to obtain a state monitoring value corresponding to the vehicle; a prediction module, which is used to predict the driving state of the vehicle to obtain a state prediction value corresponding to the vehicle; a determination module, which is used to determine a target state value corresponding to the vehicle based on the state monitoring value and the state prediction value; and a scoring module, which is used to determine a target driving behavior feature of the vehicle according to the target state value, and determine a driving behavior score corresponding to the vehicle based on the target driving behavior feature and the expected driving behavior feature.

[0007] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0008] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0009] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the method in the embodiments of the present application monitors the driving state of the vehicle through the sensor on the vehicle to obtain the state monitoring value corresponding to the vehicle; predicts the driving state of the vehicle to obtain the state prediction value corresponding to the vehicle; determines the target state value corresponding to the vehicle based on the state monitoring value and the state prediction value; determines the target driving behavior characteristics of the vehicle according to the target state value, and determines the driving behavior score corresponding to the vehicle based on the target driving behavior characteristics and the expected driving behavior characteristics, wherein the state monitoring value obtained by the sensor and the predicted state prediction value jointly determine the target state value, so that the target state value is the same or tends to be the same as the actual value corresponding to the driving state of the vehicle, effectively reducing the influence of the target state value of the data noise, and improving the accuracy of the target state value; subsequently, based on determining the target driving behavior characteristics of the vehicle according to the target state value, the effect of accurately obtaining the target driving behavior characteristics is achieved, and subsequently the driving behavior score corresponding to the vehicle is determined by the target driving behavior characteristics and the expected driving behavior characteristics, so as to achieve accurate acquisition of the driving behavior score, thereby avoiding the problem of inability to accurately evaluate driving behavior in related technologies, resulting in safety hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art 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 any creative work.

[0011] Figure 1 It is a flowchart of a driving behavior scoring method provided in an embodiment of the present application;

[0012] Figure 2 is a flow chart of another driving behavior scoring method provided in an embodiment of the present application;

[0013] Figure 3 is a flow chart of another driving behavior scoring method provided in an embodiment of the present application;

[0014] Figure 4 It is a flowchart of another driving behavior scoring method provided in an embodiment of the present application;

[0015] Figure 5 is a flowchart of another driving behavior scoring method provided in an embodiment of the present application;

[0016] Figure 6 It is a flowchart of an optional driving behavior scoring method provided in an embodiment of the present application;

[0017] Figure 7 is a flow chart of another optional driving behavior scoring method provided in an embodiment of the present application;

[0018] Figure 8 is a flowchart of another optional driving behavior scoring method provided in an embodiment of the present application;

[0019] Fig. 9 It is a flowchart of another optional driving behavior scoring method provided in an embodiment of the present application;

[0020] Fig.10 is a flowchart of another optional driving behavior scoring method provided in an embodiment of the present application;

[0021] Fig.11 is a structural schematic diagram of a driving behavior scoring device provided in an embodiment of the present application;

[0022] Fig.12 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0024] A driving behavior scoring method and device according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 A driving behavior scoring method provided in an embodiment of the present application is as follows: Figure 1 As shown, the method includes:

[0026] S101, monitoring the driving state of the vehicle through sensors on the vehicle to obtain a state monitoring value corresponding to the vehicle;

[0027] S102, predicting the driving state of the vehicle to obtain a corresponding state prediction value of the vehicle;

[0028] S103, determining a target state value corresponding to the vehicle based on the state monitoring value and the state prediction value;

[0029] S104: Determine a target driving behavior characteristic of the vehicle according to the target state value, and determine a driving behavior score corresponding to the vehicle based on the target driving behavior characteristic and the expected driving behavior characteristic.

[0030] It can be understood that the driving behavior scoring method provided in this example is applied to vehicles, including vehicles with automatic driving or intelligent driving (including vehicles with passenger functions (such as cars, buses, large buses, minibuses, etc.), cargo vehicles (such as ordinary trucks, vans, trailers, closed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, special structure trucks), special vehicles (such as logistics distribution vehicles, automatic guided transport vehicles AGV, patrol cars, cranes, cranes, excavators, bulldozers, forklifts, rollers, loaders, off-road engineering vehicles, armored engineering vehicles, sewage treatment vehicles, sanitation vehicles, vacuum trucks, floor washing vehicles, sprinkler trucks, sweeping robots, food delivery robots, shopping guide robots, lawn mowers, golf carts, etc.), vehicles with entertainment functions (such as entertainment vehicles, amusement park automatic driving devices, balance cars, etc.), rescue vehicles (such as fire trucks, ambulances, power repair vehicles, engineering rescue vehicles, etc.)), etc.

[0031] It can be understood that the above driving state includes but is not limited to position, speed, steering angle, acceleration, and brake pressure. The vehicle is provided with sensors for sensing the above driving state, and the above sensors include but are not limited to cameras, laser radars, millimeter wave radars, GPS, and inertial navigation modules. The sensors on the vehicle monitor their own states to obtain the state monitoring values ​​corresponding to the vehicle; it can be understood that due to certain errors in the sensor during the test process, there is a certain gap between the above state monitoring values ​​and the actual values ​​(true values) corresponding to the driving state, so the state monitoring values ​​cannot be directly used to determine the driving behavior characteristics of the vehicle. Among them, the sensor transmits the collected state monitoring values ​​to the data processing unit for data processing, and the data processing includes an integrity check on the received data to ensure the availability of the data. Through data cleaning, outliers, missing values, and noise data are removed to improve data quality. The cleaned data is standardized so that data with different characteristics are at the same scale for subsequent analysis.

[0032] In some examples, the driving state of the vehicle is predicted to obtain a corresponding state prediction value of the vehicle. Specifically, in this example, the driving state of the vehicle is predicted through an algorithm to obtain a corresponding state prediction value of the vehicle. It can be understood that in step S102, no sensor is required, and therefore, the state prediction value obtained in step S102 is different from the state monitoring value obtained in the above step S101.

[0033] Continuing from the above example, how to predict the driving state of the vehicle through the algorithm and obtain the corresponding state prediction value of the vehicle will be described in detail later, and will not be repeated here. It can be understood that in step S102, when the state prediction value is obtained through the algorithm, due to the influence of noise, there is a certain gap between the above state prediction value and the actual value (true value) corresponding to the driving state, and the state prediction value cannot be directly used to determine the driving behavior characteristics of the vehicle.

[0034] After obtaining the state monitoring value and the state prediction value respectively, this example determines the target state value corresponding to the vehicle based on the state monitoring value and the state prediction value. Specifically, the error between the above state monitoring value and the actual value (true value) corresponding to the driving state is used as the monitoring error, and the error between the above state prediction value and the actual value corresponding to the driving state is used as the process error. This example obtains the final target state value by weighted averaging the above process error and observation error to offset each other, so that the target state value is the same or tends to be the same as the actual value corresponding to the driving state.

[0035] It can be understood that the above-mentioned step S101 and step S102 are steps executed simultaneously, and the state monitoring value and the state prediction value at the same time are obtained; illustratively, taking the current time as t0 as an example, the state monitoring value at time t0 is obtained through step S101 at time t0, and the state prediction value at time t0 is obtained through step S102 at time t0, and finally, the target state value at time t0 is obtained based on the state monitoring value and the state prediction value at time t0.

[0036] In order to better understand the present method, the present embodiment provides a more specific example for illustration, wherein the driving state of the vehicle includes position, speed, steering angle, and brake pressure, and the above driving state is monitored by the vehicle sensor to obtain a state monitoring value, wherein the monitored state monitoring value is recorded as x0={p0, v0, b0, s0}, wherein (p0, v0, b0, s0) respectively represent the position, speed, braking force, and steering force of the vehicle obtained by the sensor. The driving state of the vehicle is predicted by the algorithm to obtain the state prediction value corresponding to the vehicle, and the predicted state prediction value is recorded as x1 (the state value contained in x1 is the same as the above x0, which will not be repeated here), and then the target state value corresponding to the vehicle is obtained through x1 and x2, and the target state value can reflect the position, speed, steering angle, and brake pressure of the vehicle during actual driving, so the target state value is used as the actual value corresponding to the driving state.

[0037] In some examples, the target driving behavior characteristics of the vehicle are determined based on the target state values, wherein the target state values ​​include basic information such as position and speed corresponding to the vehicle's driving state, and the target state values ​​also include more detailed information such as braking force and steering force. By analyzing the target state values, characteristic parameters reflecting the target driving behavior characteristics can be extracted, such as acceleration, steering force, braking force, etc.

[0038] This example also obtains expected driving behavior characteristics, where the expected driving behavior characteristics are driving behavior characteristics that the vehicle should have under the premise of safe driving, for example, the acceleration, steering rate, and braking force that the vehicle should have under the premise of safe driving.

[0039] Continuing from the previous example, after obtaining the expected driving behavior characteristics and the target driving behavior characteristics, this example determines the driving behavior score corresponding to the vehicle based on the target driving behavior characteristics and the expected driving behavior characteristics. Exemplarily, the target driving behavior characteristics are compared with the expected driving behavior characteristics to determine whether the vehicle has behaviors such as excessive speed or too low braking force. Finally, the vehicle is given a driving behavior score based on the comparison result between the target driving behavior characteristics and the expected driving behavior characteristics.

[0040] It can be understood that the above-mentioned expected driving behavior characteristics are determined by relevant personnel based on historical data, and relevant personnel can flexibly set the above-mentioned expected driving behavior characteristics according to the actual usage scenarios and / or usage requirements of the vehicle.

[0041] According to the technical solution provided in the embodiment of the present application, the driving state of the vehicle is monitored by a sensor on the vehicle to obtain a state monitoring value corresponding to the vehicle; the driving state of the vehicle is predicted to obtain a state prediction value corresponding to the vehicle; the target state value corresponding to the vehicle is determined based on the state monitoring value and the state prediction value; the target driving behavior characteristics of the vehicle are determined according to the target state value, and the driving behavior score corresponding to the vehicle is determined based on the target driving behavior characteristics and the expected driving behavior characteristics, wherein the state monitoring value obtained by the sensor and the predicted state prediction value jointly determine the target state value, so that the target state value is the same or tends to be the same as the actual value corresponding to the driving state of the vehicle, effectively reducing the influence of the target state value of the data noise, and improving the accuracy of the target state value; subsequently, based on determining the target driving behavior characteristics of the vehicle according to the target state value, the effect of accurately obtaining the target driving behavior characteristics is achieved, and subsequently the driving behavior score corresponding to the vehicle is determined by the target driving behavior characteristics and the expected driving behavior characteristics, so that the driving behavior score is accurately obtained, avoiding the problem of inability to accurately evaluate driving behavior in related technologies, resulting in safety hazards.

[0042] In some embodiments, Figure 2As shown, the driving state of the vehicle is predicted to obtain the corresponding state prediction value of the vehicle, including:

[0043] S201, obtaining a preset state transfer matrix, and obtaining a target state value corresponding to the vehicle at a previous moment, and determining a first state prediction value according to the state transfer matrix and the target state value at the previous moment;

[0044] S202, obtaining a preset control input matrix and a control instruction received by the vehicle, mapping the control instruction according to the control input matrix, and obtaining a second state prediction value;

[0045] S203: Sum the first state prediction value and the second state prediction value to obtain a state prediction value.

[0046] Specifically, this example first obtains a preset state transfer matrix, which is a matrix that describes the evolution law of the system state. The state transfer matrix is ​​used to transfer the state of the previous moment to the state of the current moment to complete the prediction and estimation of the state. In some examples, the state transfer matrix is ​​recorded as F, and the state transfer matrix is ​​as follows:

[0047]

[0048] According to the above records, the state transfer matrix is ​​used to transfer the state of the previous moment to the state of the current moment. Therefore, this example also needs to obtain the target state value corresponding to the vehicle at the previous moment, and then actually predict the state prediction value of the current moment based on the target state value corresponding to the previous moment; specifically, obtain the target state value corresponding to the vehicle at the previous moment, and determine the first state prediction value according to the state transfer matrix and the target state value at the previous moment, where the target state value corresponding to the vehicle at the previous moment is The first state prediction value is

[0049] In some examples, when the vehicle is driving, the current state prediction value is also related to the control command received by the vehicle, which is used to control the vehicle to brake, accelerate, turn, etc. In order to map the above control command to the driving state of the vehicle, this example also obtains the control input matrix. For example, in the state variables of this example, the control input (control command) only affects the speed (i.e., the second element of the driving state) and has no effect on other states. Therefore, when the control command is multiplied by this control input matrix, the result is a vector containing only speed changes. Therefore, let the control input matrix be B, and the control input matrix is ​​as follows:

[0050]

[0051] Assume that the control instruction is u, then the second state prediction value is Bu.

[0052] After obtaining the first state prediction value and the second state prediction value, this example combines the first state prediction value and the second state prediction value to obtain the state prediction value of the vehicle at the current moment; specifically, the first state prediction value and the second state prediction value are summed to obtain the state prediction value. Assuming the current moment is moment t, the state prediction value at moment t is but in, is the state prediction value at time t, F is the state transfer matrix, is the target state value at time t-1, B is the control input matrix, and u is the control instruction.

[0053] It can be understood that the above control input matrix can be flexibly set by relevant technical personnel according to historical data or actual needs, and this embodiment is not intended to limit the control input matrix to only the above example.

[0054] It can be understood that in this example, the target state value corresponding to the last moment of the vehicle is obtained in steps S201 to S203. If the target state value corresponding to the last moment cannot be obtained at the initial moment of vehicle startup, therefore, the target state value at the initial moment is also set in this example. For example, the target state value at the initial moment is as follows: Among them, p est,0 、v est,0 、b est,0 、s est,0 They represent the position, speed, braking force and steering force at the initial moment respectively. The target state value at the initial moment is based on historical data or determined by relevant personnel according to actual conditions.

[0055] According to the technical solution provided in the embodiment of the present application, a preset state transfer matrix is ​​obtained, and the target state value corresponding to the vehicle at the previous moment is obtained, and a first state prediction value is determined according to the state transfer matrix and the target state value at the previous moment; a preset control input matrix and a control instruction received by the vehicle are obtained, and the control instruction is mapped according to the control input matrix to obtain a second state prediction value; the first state prediction value and the second state prediction value are summed to obtain a state prediction value, wherein the above method takes into account the influence of the target state value at the previous moment and the control instruction at the current moment on the state prediction value, thereby achieving accurate acquisition of the state prediction value, avoiding the problem of inaccurate state prediction value obtained by only considering the target state value at the previous moment and ignoring the influence of the control instruction, and at the same time avoiding the problem of inaccurate state prediction value obtained by only considering the control instruction and ignoring the target state value at the previous moment.

[0056] In some embodiments, Figure 3 As shown, the target state value corresponding to the vehicle is determined based on the state monitoring value and the state prediction value, including:

[0057] S301, obtaining a preset monitoring matrix, and mapping the state prediction value through the monitoring matrix to obtain a mapping prediction value;

[0058] S302, obtaining the difference between the state monitoring value and the mapping prediction value, and determining the state gain value corresponding to the target state value;

[0059] S303, performing gain processing on the difference between the state monitoring value and the mapping prediction value according to the state gain value to obtain a corrected state monitoring value;

[0060] S304: sum the state prediction value and the corrected state monitoring value to obtain a target state value.

[0061] Specifically, the monitoring matrix is ​​used to map the state prediction value to the same space as the state monitoring value. For example, in this example, the position of the vehicle is taken as the only state directly measured by the sensor. Assuming the monitoring matrix is ​​H, the monitoring matrix H is as follows:

[0062] H=[1 0 0 0].

[0063] After obtaining the above monitoring matrix, this example maps the state prediction value through the monitoring matrix to obtain the mapped prediction value. Specifically, the state prediction value is The monitoring matrix is ​​H, then the mapping prediction value is

[0064] After mapping the state prediction value to the same space as the state monitoring value through the monitoring matrix, this example will further determine the difference between the state monitoring value and the mapped prediction value, and then determine the error between the state monitoring value and the state prediction value. Specifically, assuming that the state monitoring value is z t , then the difference between the state monitoring value and the mapping prediction value is

[0065] This example will further determine the state gain value corresponding to the target state value. It can be understood that the target state value at each moment corresponds to a state gain value. How to determine the state gain value corresponding to the target state value at the current moment will be described in detail later and will not be repeated here.

[0066] It can be understood that the state gain value is used to characterize the weight of the error between the state monitoring value and the state prediction value at the current moment. Therefore, this example will perform gain processing on the difference between the state monitoring value and the mapping prediction value according to the state gain value to obtain a corrected state monitoring value, wherein, assuming that the current moment is t, and the state gain value at moment t is Kt , then the corrected state monitoring value is

[0067] Finally, this example will sum the state prediction value and the modified state monitoring value to obtain the target state value. Specifically, let the current time be t, and the state prediction value at time t be The target state value at time t but

[0068] According to the technical solution provided in the embodiment of the present application, a preset monitoring matrix is ​​obtained, and the state prediction value is mapped through the monitoring matrix to obtain a mapping prediction value; the difference between the state monitoring value and the mapping prediction value is obtained, and the state gain value corresponding to the target state value is determined; the difference between the state monitoring value and the mapping prediction value is gain processed according to the state gain value to obtain a corrected state monitoring value; the state prediction value and the corrected state monitoring value are summed to obtain the target state value, wherein the state prediction value is mapped to the same space as the state monitoring value through the above method, thereby achieving accurate acquisition of the error between the state prediction value and the state monitoring value, and subsequently obtaining an accurate target state value based on the corrected state monitoring value and state prediction value obtained by correcting the above error.

[0069] In some embodiments, Figure 4 As shown, determining the state gain value corresponding to the target state value includes:

[0070] S401, obtaining a priori error covariance matrix corresponding to the target state value, and mapping the transpose of the monitoring matrix based on the priori error covariance matrix to obtain a first gain value;

[0071] S402, determining a target covariance matrix based on the monitoring matrix, the prior error covariance matrix, and the transpose of the monitoring matrix, and determining a second gain value according to the target covariance matrix and a preset monitoring noise covariance matrix;

[0072] S403: Use the ratio between the first gain value and the second gain value as the state gain value.

[0073] Specifically, the a priori error covariance matrix corresponding to the target state value at the current moment is determined based on the a posteriori error covariance matrix at the previous moment, where, assuming that the current moment is t, the a priori error covariance matrix at moment t is but Among them, P t-1 is the posterior error covariance matrix of the previous moment, F is the state transfer matrix, F T is the transpose of the state transfer matrix, Q t is the process noise covariance matrix at time t.

[0074] It can be understood that the above process noise covariance matrix describes the uncertainty and external interference of the system model. The process noise covariance matrix is ​​used to quantify the influence of uncertainty and external interference on the state of the vehicle during driving. Exemplarily, the process noise covariance matrix can be expressed as:

[0075]

[0076] Among them, q p ,q v ,q b ,q s They respectively represent the process noise when the vehicle position, speed, braking force and steering force are predicted by the algorithm. The process noise covariance matrix is ​​based on historical data or is set by relevant technical personnel according to actual conditions.

[0077] In some examples, after obtaining the prior error covariance matrix corresponding to the target state value, the transpose of the monitoring matrix is ​​mapped based on the prior error covariance matrix to obtain a first gain value. Specifically, assuming that the monitoring matrix is ​​H, the first gain value is

[0078] In some examples, a target covariance matrix is ​​determined based on a monitoring matrix, a priori error covariance matrix, and the transpose of the monitoring matrix, and a second gain value is determined based on the target covariance matrix and a preset monitoring noise covariance matrix; it can be understood that due to factors such as vehicle sensor errors and in-vehicle communication delays, the monitoring data from the sensor is often imperfect and noisy, and the above monitoring noise covariance matrix describes the uncertainty of the sensor monitoring data, wherein, assuming that the monitoring noise covariance matrix is ​​R, then Among them, r p The variance of the noise of the state monitoring value detected by each sensor (r p Usually determined by historical data or relevant technical personnel based on actual needs); R is used to weigh the credibility between the state monitoring value and the state prediction value. The larger the R value, the greater the observation noise and the lower the credibility; otherwise, the higher the R value.

[0079] Continuing from the above example, let the monitoring matrix be H and the prior error covariance matrix be The second gain value is

[0080] After obtaining the first gain value and the second gain value, this example uses the ratio between the first gain value and the second gain value as the state gain value. Specifically, the first gain value is The second gain value is The state gain value

[0081] It can be understood that after determining the current moment's prior error covariance matrix is After that, the a posteriori error covariance matrix corresponding to the current moment can also be determined based on the prior error covariance matrix. Specifically, the a priori error covariance matrix at the current moment is brought into the a posteriori error covariance matrix formula to obtain the a posteriori error covariance matrix. The a posteriori error covariance matrix formula is as follows:

[0082]

[0083] Among them, P t is the posterior error covariance matrix at time t, is the prior error covariance matrix at time t, K t is the state gain value at time t, H is the monitoring matrix, and subsequently at time t+1, this example can obtain the prior error covariance matrix at time t+1 based on the posterior error covariance matrix at time t.

[0084] It can be understood that this example also defines a priori error covariance matrix corresponding to the target state value at the initial moment. For example, the target state value at the initial moment is as follows: Take as an example, the corresponding prior error covariance matrix is Among them, p var,0 、v var,0 、b var,0 、s var,0 Represents p est,0 、v est,0 、b est,0 、s est,0 The variance is mainly used to measure the uncertainty of the target state value of the vehicle at the initial moment. The larger the variance, the lower the information about the estimated value.

[0085] According to the technical solution provided in the embodiment of the present application, a priori error covariance matrix corresponding to the target state value is obtained, and the transpose of the monitoring matrix is ​​mapped based on the prior error covariance matrix to obtain a first gain value; the target covariance matrix is ​​determined based on the monitoring matrix, the priori error covariance matrix and the transpose of the monitoring matrix, and the second gain value is determined according to the target covariance matrix and a preset monitoring noise covariance matrix; the ratio between the first gain value and the second gain value is used as the state gain value, wherein the process noise covariance matrix is ​​used to quantify the influence of uncertainty and external interference on the state of the vehicle during driving, and the transpose of the monitoring matrix is ​​mapped based on the prior error covariance matrix to accurately obtain the first gain value, and similarly, the second gain value is accurately obtained based on the monitoring noise covariance matrix, and finally, the state gain value is accurately obtained based on the first gain value and the second gain value.

[0086] In some embodiments, Figure 5 As shown, the driving behavior score corresponding to the vehicle is determined based on the target driving behavior characteristics and the expected driving behavior characteristics, including:

[0087] S501, determining an expected driving behavior feature corresponding to the target driving behavior feature;

[0088] S502: Determine a driving behavior according to the target driving behavior characteristics and the corresponding expected driving behavior characteristics, and determine a driving behavior score based on the driving behavior.

[0089] It can be understood that different target driving behavior characteristics correspond to different expected driving behavior characteristics; for example, taking the target driving behavior characteristic as the target steering force, the corresponding expected driving behavior characteristic is the expected steering force; for another example, taking the target driving behavior characteristic as the target braking force, the corresponding expected driving behavior characteristic is the expected braking force.

[0090] Continuing from the above example, after obtaining the target driving behavior feature and the corresponding expected driving behavior feature, this example determines the driving behavior based on the target driving behavior feature and the corresponding expected driving behavior feature. Specifically, this example determines the driving behavior based on the ratio of the target driving behavior feature to the corresponding expected driving behavior feature. Exemplarily, taking the driving behavior including steering force stability and braking force stability as an example, wherein the target driving behavior feature includes a target steering force and a target braking force, the expected driving behavior feature corresponding to the target steering force is the expected steering force, and the expected driving behavior feature corresponding to the target braking force is the expected braking force.

[0091] In some examples, the present example can also directly obtain the corresponding driving behavior based on the associated target driving behavior characteristics. For example, the target driving behavior characteristics include the target acceleration and the target acceleration time interval. The target acceleration is recorded as Δa, and the target acceleration time interval is recorded as Δt. Based on the above target acceleration and target acceleration time interval, the corresponding acceleration change rate can be obtained, as follows:

[0092] like Figure 6 As shown, Figure 6As shown, step S601, obtain steering force stability, braking force stability, and acceleration change rate; step S602, determine the driving behavior score based on the steering force stability, braking force stability, and acceleration change rate. After obtaining the above-mentioned driving behaviors such as steering force stability, braking force stability, and acceleration change rate, since the above-mentioned driving behaviors such as steering force stability, braking force stability, and acceleration change rate can accurately reflect whether the user is driving the vehicle in a standard manner at the current moment, therefore, the driving behavior score can be accurately determined based on the above-mentioned steering force stability, braking force stability, and acceleration change rate.

[0093] According to the technical solution provided in the embodiment of the present application, the expected driving behavior characteristics corresponding to the target driving behavior characteristics are determined; the driving behavior is determined according to the target driving behavior characteristics and the corresponding expected driving behavior characteristics, and the driving behavior score is determined based on the driving behavior, wherein the above method realizes accurate determination of the driving behavior, and then realizes obtaining an accurate driving behavior score based on the accurate driving behavior.

[0094] In some examples, the number of driving behaviors is multiple, such as Figure 7 As shown, a driving behavior score is determined based on the driving behavior, including:

[0095] S701, obtaining an initial driving behavior score corresponding to each driving behavior and a weight value corresponding to each driving behavior;

[0096] S702: Perform weighted summation on each initial driving behavior score according to the obtained weight value to obtain a driving behavior score.

[0097] Specifically, a scoring rule is preset in this example, and the initial driving behavior score corresponding to the above-mentioned driving behavior can be calculated through the scoring rule. It can be understood that different driving behaviors correspond to different initial driving behavior scores. Exemplarily, taking the driving behavior as steering force stability as an example, the scoring rule corresponding to the driving behavior is that when the steering force stability is 1, a score a is obtained, when the steering force stability is lower than 1, b score is obtained, and when the steering force is higher than 1, c score is obtained, wherein a>b, and a>c, and the values ​​of a, b, and c are all>0. It can be understood that a, b, and c can be specifically set by relevant personnel. Subsequently, when the steering force stability is 1, the initial driving behavior score corresponding to the steering force stability is a, when the steering force stability is higher than 1, the initial driving behavior score corresponding to the steering force stability is c, and when the steering force stability is lower than 1, the initial driving behavior score corresponding to the steering force stability is b.

[0098] This example will further obtain the weight value corresponding to each driving behavior, wherein the weight value corresponding to each driving behavior can be determined by historical data or relevant personnel according to actual conditions.

[0099] After obtaining the weight value corresponding to each driving behavior and the initial driving behavior score corresponding to each driving behavior, this example performs weighted summation on each initial driving behavior score according to the obtained weight value to obtain the driving behavior score, as follows:

[0100]

[0101] where x i Score the i-th initial driving behavior, w i is the weight value corresponding to the i-th initial driving behavior score, and n is the number of initial driving behavior scores.

[0102] like Figure 8 As shown, it includes steps S801 to S803. This example normalizes or classifies the initial driving behavior score by introducing thresholds or nonlinear mapping, adds a time window for comprehensive evaluation, and further refines the scoring rules. The driving behavior score finally obtained can be used to evaluate the user's driving level, remind the user to adjust bad driving behavior, or serve as input data for other related applications.

[0103] According to the technical solution provided in the embodiment of the present application, an initial driving behavior score corresponding to each driving behavior and a weight value corresponding to each driving behavior are obtained; a weighted sum is performed on each initial driving behavior score according to the obtained weight value to obtain a driving behavior score, thereby achieving accurate acquisition of the driving behavior score.

[0104] In some examples, such as Fig. 9 As shown, after determining the driving behavior score corresponding to the vehicle based on the target driving behavior characteristics and the expected driving behavior characteristics, the method further includes:

[0105] S901. When the driving behavior score indicates that the vehicle has abnormal driving behavior, display the driving behavior score through an interactive screen of the vehicle;

[0106] S902: Generate a warning prompt based on the driving behavior score, so that the user adjusts the driving operation based on the warning prompt.

[0107] The method provided in this example displays the driving behavior score through the interactive screen of the vehicle when the driving behavior score indicates that the vehicle has abnormal driving behavior. Specifically, a driving behavior score threshold is set in this example. When the above driving score is lower than the score threshold, it is determined that the vehicle has abnormal driving behavior. The method provided in this example will display the driving behavior score based on the interactive screen of the vehicle, so that the user can intuitively understand the abnormal driving behavior of the current vehicle.

[0108] In addition, this example also generates a warning prompt based on the driving behavior score, which is used to indicate how to adjust the abnormal driving behavior of the above-mentioned vehicle, thereby enabling the user to adjust the driving operation based on the warning prompt.

[0109] In some examples, when the driving behavior score does not indicate abnormal driving behavior of the vehicle, the driving behavior score can also be displayed through the interactive screen of the vehicle.

[0110] In some examples, such as Fig.10 As shown, it includes steps S1001 to S1003. After the driving behavior score is displayed on the vehicle's interactive screen, a real-time feedback mechanism can be provided in the cockpit to remind the driver to adjust bad driving behavior through sound, vibration, etc., and the driving behavior score is stored.

[0111] According to the technical solution provided in the embodiment of the present application, when the driving behavior score indicates that the vehicle has abnormal driving behavior, the driving behavior score is displayed through the interactive screen of the vehicle; an alarm prompt is generated based on the driving behavior score, so that the user adjusts the driving operation based on the alarm prompt, and the driving behavior score is displayed based on the interactive screen of the vehicle, so that the user can intuitively understand the abnormal driving behavior of the current vehicle; an alarm prompt is generated based on the driving behavior score, and the alarm prompt is used to indicate how to adjust the abnormal driving behavior of the above-mentioned vehicle, so that the user can adjust the driving operation based on the alarm prompt.

[0112] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0113] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0114] This embodiment also provides a driving behavior scoring device, such as Fig.11 As shown, the device comprises:

[0115] The monitoring module 1101 is used to monitor the driving state of the vehicle through sensors on the vehicle to obtain a state monitoring value corresponding to the vehicle;

[0116] The prediction module 1102 is used to predict the driving state of the vehicle and obtain a corresponding state prediction value of the vehicle;

[0117] A determination module 1103 is used to determine a target state value corresponding to the vehicle based on the state monitoring value and the state prediction value;

[0118] The scoring module 1104 is used to determine the target driving behavior characteristics of the vehicle according to the target state value, and determine the driving behavior score corresponding to the vehicle based on the target driving behavior characteristics and the expected driving behavior characteristics.

[0119] In some examples, the prediction module 1102 is also used to obtain a preset state transfer matrix and a target state value corresponding to the vehicle at the previous moment, and determine a first state prediction value based on the state transfer matrix and the target state value at the previous moment; obtain a preset control input matrix and a control instruction received by the vehicle, map the control instruction according to the control input matrix, and obtain a second state prediction value; and sum the first state prediction value and the second state prediction value to obtain a state prediction value.

[0120] In some examples, the determination module 1103 is also used to obtain a preset monitoring matrix, map the state prediction value through the monitoring matrix to obtain a mapping prediction value; obtain the difference between the state monitoring value and the mapping prediction value, and determine the state gain value corresponding to the target state value; perform gain processing on the difference between the state monitoring value and the mapping prediction value according to the state gain value to obtain a corrected state monitoring value; sum the state prediction value and the corrected state monitoring value to obtain the target state value.

[0121] In some examples, the determination module 1103 is also used to obtain a priori error covariance matrix corresponding to the target state value, and map the transpose of the monitoring matrix based on the prior error covariance matrix to obtain a first gain value; determine the target covariance matrix based on the monitoring matrix, the prior error covariance matrix and the transpose of the monitoring matrix, and determine the second gain value according to the target covariance matrix and a preset monitoring noise covariance matrix; and use the ratio between the first gain value and the second gain value as the state gain value.

[0122] In some examples, the scoring module 1104 is further used to determine an expected driving behavior feature corresponding to the target driving behavior feature; determine the driving behavior according to the target driving behavior feature and the corresponding expected driving behavior feature, and determine a driving behavior score based on the driving behavior.

[0123] In some examples, the scoring module 1104 is also used to obtain an initial driving behavior score corresponding to each driving behavior and a weight value corresponding to each driving behavior; and weighted sum each initial driving behavior score according to the obtained weight value to obtain a driving behavior score.

[0124] In some examples, the scoring module 1104 is also used to display the driving behavior score through the vehicle's interactive screen when the driving behavior score indicates abnormal driving behavior of the vehicle; generate an alarm prompt based on the driving behavior score, so that the user adjusts the driving operation based on the alarm prompt.

[0125] According to the technical solution provided by the embodiment of the present application, the driving behavior scoring device provided by the embodiment monitors the driving state of the vehicle through the sensor on the vehicle to obtain the state monitoring value corresponding to the vehicle; predicts the driving state of the vehicle to obtain the state prediction value corresponding to the vehicle; determines the target state value corresponding to the vehicle based on the state monitoring value and the state prediction value; determines the target driving behavior characteristics of the vehicle according to the target state value, and determines the driving behavior score corresponding to the vehicle based on the target driving behavior characteristics and the expected driving behavior characteristics, wherein the state monitoring value obtained by the sensor and the predicted state prediction value jointly determine the target state value, so that the target state value is the same or tends to be the same as the actual value corresponding to the driving state of the vehicle, effectively reducing the influence of the target state value of the data noise, and improving the accuracy of the target state value; subsequently, based on determining the target driving behavior characteristics of the vehicle according to the target state value, the effect of accurately obtaining the target driving behavior characteristics is achieved, and subsequently the driving behavior score corresponding to the vehicle is determined by the target driving behavior characteristics and the expected driving behavior characteristics, so as to achieve accurate acquisition of the driving behavior score, thereby avoiding the problem that the driving behavior cannot be accurately evaluated in the related technology, resulting in safety hazards.

[0126] Fig.12 Schematic diagram of an electronic device 12 provided in an embodiment of the present application. Fig.12 As shown, the electronic device 12 of this embodiment includes: a processor 1201, a memory 1202, and a computer program 1203 stored in the memory 1202 and executable on the processor 1201. When the processor 1201 executes the computer program 1203, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 1201 executes the computer program 1203, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0127] The electronic device 12 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 12 may include, but is not limited to, a processor 1201 and a memory 1202. Those skilled in the art will appreciate that Fig.12 The electronic device 12 is merely an example and does not limit the electronic device 12 , and may include more or fewer components than those shown in the figure, or different components.

[0128] Processor 1201 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0129] The memory 1202 may be an internal storage unit of the electronic device 12, for example, a hard disk or memory of the electronic device 12. The memory 1202 may also be an external storage device of the electronic device 12, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), etc. equipped on the electronic device 12. The memory 1202 may also include both an internal storage unit of the electronic device 12 and an external storage device. The memory 1202 is used to store computer programs and other programs and data required by the electronic device.

[0130] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0131] If the integrated module / 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 storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of regional requirements and patent practice. For example, in some areas, according to regional requirements and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0132] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A driving behavior scoring method, characterized in that: The method comprises: Monitoring the driving state of the vehicle through sensors on the vehicle to obtain a state monitoring value corresponding to the vehicle; Predicting the driving state of the vehicle to obtain a state prediction value corresponding to the vehicle; Determine a target state value corresponding to the vehicle based on the state monitoring value and the state prediction value; A target driving behavior feature of the vehicle is determined according to the target state value, and a driving behavior score corresponding to the vehicle is determined based on the target driving behavior feature and the expected driving behavior feature.

2. The method according to claim 1, characterized in that: Predicting the driving state of the vehicle to obtain a state prediction value corresponding to the vehicle includes: Obtaining a preset state transfer matrix, and obtaining a target state value corresponding to the vehicle at a previous moment, and determining a first state prediction value according to the state transfer matrix and the target state value at the previous moment; Acquire a preset control input matrix and a control instruction received by the vehicle, and map the control instruction according to the control input matrix to obtain a second state prediction value; The first state prediction value and the second state prediction value are summed to obtain the state prediction value.

3. The method according to claim 2, characterized in that Determining a target state value corresponding to the vehicle based on the state monitoring value and the state prediction value includes: Obtaining a preset monitoring matrix, and mapping the state prediction value through the monitoring matrix to obtain a mapped prediction value; Obtaining a difference between the state monitoring value and the mapping prediction value, and determining a state gain value corresponding to the target state value; Performing gain processing on the difference between the state monitoring value and the mapping prediction value according to the state gain value to obtain a corrected state monitoring value; The state prediction value and the corrected state monitoring value are summed to obtain the target state value.

4. The method according to claim 3, characterized in that Determining a state gain value corresponding to the target state value includes: Obtaining a priori error covariance matrix corresponding to the target state value, and mapping the transpose of the monitoring matrix based on the prior error covariance matrix to obtain a first gain value; Determine a target covariance matrix based on the monitoring matrix, the prior error covariance matrix, and the transpose of the monitoring matrix, and determine a second gain value according to the target covariance matrix and a preset monitoring noise covariance matrix; The ratio between the first gain value and the second gain value is used as the state gain value.

5. The method according to claim 1, characterized in that: Determining a driving behavior score corresponding to the vehicle based on the target driving behavior feature and the expected driving behavior feature includes: Determining an expected driving behavior characteristic corresponding to the target driving behavior characteristic; A driving behavior is determined according to the target driving behavior feature and the corresponding expected driving behavior feature, and the driving behavior score is determined based on the driving behavior.

6. The method according to claim 1, characterized in that There are multiple driving behaviors, and determining the driving behavior score based on the driving behaviors includes: Obtaining an initial driving behavior score corresponding to each driving behavior and a weight value corresponding to each driving behavior; A weighted sum is performed on each of the initial driving behavior scores according to the obtained weight value to obtain the driving behavior score.

7. The method according to claim 1, characterized in that After determining the driving behavior score corresponding to the vehicle based on the target driving behavior feature and the expected driving behavior feature, the method further includes: When the driving behavior score indicates that the vehicle has abnormal driving behavior, displaying the driving behavior score through an interactive screen of the vehicle; A warning prompt is generated based on the driving behavior score, so that the user adjusts the driving operation based on the warning prompt.

8. A driving behavior scoring device, characterized in that: The device comprises: A monitoring module, used to monitor the driving state of the vehicle through sensors on the vehicle to obtain a state monitoring value corresponding to the vehicle; A prediction module, used to predict the driving state of the vehicle and obtain a state prediction value corresponding to the vehicle; A determination module, configured to determine a target state value corresponding to the vehicle based on the state monitoring value and the state prediction value; The scoring module is used to determine the target driving behavior characteristics of the vehicle according to the target state value, and determine the driving behavior score corresponding to the vehicle based on the target driving behavior characteristics and the expected driving behavior characteristics.

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 storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Vehicle driving safety management method and system and storage medium

    CN119636755A

  • Vehicle owner driving behavior habit big data analysis method and system based on cloud platform

    CN120996171A