Dynamic updating method and device for safe distance model, equipment, medium and vehicle

Abstract

The embodiment of the invention provides a dynamic updating method and device for a safety distance model, equipment, a medium and a vehicle, and relates to the technical field of safety monitoring. The method comprises the steps that it is determined that a longitudinal safe distance calculation model meets a preset updating condition, a target estimation strategy corresponding to the type of a current traffic scene where a vehicle is located is obtained, and a dynamic estimation result corresponding to a front vehicle deceleration parameter is obtained according to the target estimation strategy; and updating a front vehicle deceleration parameter in the longitudinal safe distance calculation model based on the dynamic estimation result to obtain a dynamically optimized longitudinal safe distance calculation model. According to the embodiment of the invention, different estimation strategies are adopted to update the front vehicle deceleration parameters of the longitudinal safety distance calculation model according to different traffic scenes, so that the capability of the parameters to adapt to different traffic scenes can be improved, and the calculation accuracy of the longitudinal safety distance is improved.

Description

Technical Field

[0001] The present application relates to the field of security monitoring technology, and in particular to a method, device, equipment, medium and vehicle for dynamically updating a safety distance model. Background Art

[0002] Longitudinal safety distance is an important indicator to measure the distance between the front and rear of a vehicle. Accurately obtaining the longitudinal safety distance during driving is a prerequisite for guiding the driver to drive safely and achieving safe autonomous driving.

[0003] The calculation of the longitudinal safety distance mainly depends on three core parameters: driver reaction time, maximum deceleration of the vehicle, and deceleration of the vehicle ahead. Among them, for the deceleration of the vehicle ahead, the current traditional solution usually relies on preset fixed parameters, or estimates the deceleration of the vehicle ahead based on a single estimation strategy, resulting in low accuracy of the calculated longitudinal safety distance. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method, device, equipment, medium and vehicle for dynamically updating a safety distance model, so as to improve the accuracy of calculating the longitudinal safety distance.

[0005] In a first aspect, an embodiment of the present application provides a method for dynamically updating a safety distance model, comprising:

[0006] Determining that the longitudinal safety distance calculation model meets a preset update condition, obtaining a target estimation strategy corresponding to the current traffic scene type in which the vehicle is located, and obtaining a dynamic estimation result corresponding to the deceleration parameter of the leading vehicle according to the target estimation strategy;

[0007] Based on the dynamic estimation result, the preceding vehicle deceleration parameter in the longitudinal safety distance calculation model is updated to obtain a dynamically optimized longitudinal safety distance calculation model.

[0008] In an embodiment of the present application, by updating the preceding vehicle deceleration parameter of the longitudinal safety distance calculation model using different estimation strategies according to different traffic scenarios, the ability of the parameter to adapt to different traffic scenarios can be improved, thereby improving the calculation accuracy of the longitudinal safety distance.

[0009] In some possible embodiments, the step of obtaining a target estimation strategy corresponding to the current traffic scene type in which the vehicle is located includes at least one of the following:

[0010] When it is determined that the current traffic scene type in which the vehicle is located is an urban scene, obtaining an estimation strategy based on big data statistics as the target estimation strategy;

[0011] When it is determined that the current traffic scene type in which the vehicle is located is a suburban scene, obtaining a Markov-based estimation strategy as the target estimation strategy;

[0012] When it is determined that the current traffic scene type in which the vehicle is located is a high-speed scene, obtaining an estimation strategy based on fuzzy theory as the target estimation strategy;

[0013] The current traffic scene type of the vehicle is obtained by matching the current positioning information of the vehicle with a preset traffic scene annotation chart.

[0014] In the embodiments of the present application, by adopting parameter estimation strategies based on big data statistics, Markov theory and fuzzy theory for the three traffic scenarios of urban, suburban and highway respectively, the accuracy of parameter estimation can be improved according to the characteristics of each traffic scenario, thereby improving the calculation accuracy of the longitudinal safety distance.

[0015] In some possible embodiments, obtaining a dynamic estimation result corresponding to a deceleration parameter of a preceding vehicle according to the target estimation strategy includes:

[0016] Acquire current feature information corresponding to a preset key feature type, and obtain target deceleration statistical information corresponding to the current feature information based on a correspondence between the preset feature information and the deceleration statistical information; wherein the preset key feature type includes at least one of a time period feature and a weather feature, and the deceleration statistical information is obtained by statistics based on pre-collected vehicle driving history data;

[0017] A dynamic estimation result corresponding to a deceleration parameter of the preceding vehicle is obtained based on the target deceleration statistical information.

[0018] In an embodiment of the present application, by classifying and counting vehicle driving data according to characteristics such as time period and weather, and obtaining corresponding statistical information based on the current characteristic information of the vehicle to dynamically estimate the deceleration parameters of the preceding vehicle, the calculation accuracy of the longitudinal safety distance in urban scenarios can be improved.

[0019] In some possible embodiments, obtaining a dynamic estimation result corresponding to a deceleration parameter of a preceding vehicle according to the target estimation strategy includes:

[0020] Acquire acceleration monitoring data of the preceding vehicle, and based on the acceleration monitoring data, use a pre-statisticed Markov probability transfer matrix to make a prediction to obtain a dynamic estimation result corresponding to a deceleration parameter of the preceding vehicle;

[0021] The method for obtaining the Markov probability transfer matrix includes:

[0022] Collecting a vehicle driving sample data set, and classifying the vehicle driving sample data set according to different preset vehicle speed intervals to obtain a sample data subset corresponding to each vehicle speed interval;

[0023] For each sample data subset, each sample data therein is divided into a unit operating condition instance corresponding to a preset acceleration state interval;

[0024] The state transition probabilities of each acceleration state interval are statistically analyzed based on the divided unit operating condition instances, and a Markov probability transfer matrix corresponding to each vehicle speed interval is constructed.

[0025] In the embodiment of the present application, by dividing the vehicle speed intervals and counting the acceleration state transitions of each interval respectively, and using the statistically obtained Markov probability transfer matrix to estimate the deceleration of the preceding vehicle, the calculation accuracy of the longitudinal safety distance in the suburban scenario can be improved.

[0026] In some possible embodiments, obtaining a dynamic estimation result corresponding to a deceleration parameter of a preceding vehicle according to the target estimation strategy includes:

[0027] Acquire a current feature value set corresponding to at least one preset deceleration influencing factor of the preceding vehicle; wherein the at least one deceleration influencing factor of the preceding vehicle includes at least one of vehicle speed, vehicle flow, and vehicle flow density;

[0028] Based on the eigenvalue set, respectively obtaining fuzzy subsets corresponding to the deceleration influencing factors of each preceding vehicle;

[0029] Determine the corresponding fuzzy value of the preceding vehicle deceleration based on the fuzzy subsets of the influencing factors of the preceding vehicle deceleration and the preset preceding vehicle deceleration fuzzy rule control table;

[0030] The fuzzy value of the preceding vehicle deceleration is defuzzified based on a preset preceding vehicle deceleration membership function to obtain a dynamic estimation result corresponding to the preceding vehicle deceleration parameter.

[0031] In an embodiment of the present application, by collecting characteristic information corresponding to key factors of the vehicle and using fuzzy theory to calculate the dynamic estimation result of the deceleration of the preceding vehicle, the accuracy of calculating the longitudinal safety distance in high-speed scenarios can be improved.

[0032] In some possible embodiments, determining that the longitudinal safety distance calculation model meets a preset update condition includes:

[0033] Real-time acquisition of the cumulative time from the historical moment when the longitudinal safety distance calculation model was last updated to the current moment, and when it is determined that the cumulative time exceeds a preset model update cycle, determination that the longitudinal safety distance calculation model meets a preset update condition;

[0034] Alternatively, the current traffic scene type of the vehicle is monitored in real time, and when the current traffic scene type of the vehicle is changed, it is determined that the longitudinal safety distance calculation model meets the preset update conditions.

[0035] In an embodiment of the present application, by using a set period or changes in the scene in which the vehicle is located as a condition for determining the model update, the timeliness of the model update can be improved, and the accuracy of calculating the longitudinal safety distance in different traffic scenarios can be further improved.

[0036] In a second aspect, an embodiment of the present application provides a device for dynamically updating a safety distance model, including:

[0037] A parameter dynamic estimation module, used to determine whether the longitudinal safety distance calculation model meets the preset update conditions, obtain a target estimation strategy corresponding to the current traffic scene type in which the vehicle is located, and obtain a dynamic estimation result corresponding to the deceleration parameter of the leading vehicle according to the target estimation strategy;

[0038] The calculation model updating module is used to update the preceding vehicle deceleration parameter in the longitudinal safety distance calculation model based on the dynamic estimation result to obtain a dynamically optimized longitudinal safety distance calculation model.

[0039] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the method described in any embodiment of the first aspect when executing the program.

[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any embodiment of the first aspect can be implemented.

[0041] In a fifth aspect, an embodiment of the present application provides a vehicle, comprising the electronic device described in the third aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A schematic diagram of a flow chart of a method for dynamically updating a safety distance model provided in an embodiment of the present application;

[0044] Figure 2 A schematic diagram showing an example of the probability distribution of the vehicle deceleration value provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram of a processing process based on fuzzy theory provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of the structure of a dynamic updating device for a safety distance model provided in an embodiment of the present application;

[0047] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0049] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0050] It should be noted that in the field of driving, especially in the field of autonomous driving, safety monitoring is an important function to ensure vehicle driving safety. Among them, the longitudinal safety distance is one of the most important indicators in the safety monitoring function. By reasonably calculating the longitudinal safety distance, the driver is guided or the vehicle is automatically controlled to maintain an appropriate safety distance from the vehicle in front. In the process of calculating the longitudinal safety distance, if the calculation result of this indicator is too large, the risk based on the safety distance estimate will be too conservative, affecting the normal operation of the vehicle; if the calculation result of this indicator is too small, the risk based on the safety distance will be underestimated, increasing the risk of rear-end collisions and other collisions.

[0051] Generally, the longitudinal safety distance can be calculated using the following formula (longitudinal safety distance calculation model):

[0052]

[0053] Among them, v1 represents the speed of the main vehicle (ego vehicle), v2 represents the speed of the front vehicle, ρ represents the driver's reaction time, and a 1accel represents the real-time acceleration of the vehicle, a 1max,decel represents the maximum deceleration of the vehicle, a 2max,decel Indicates the braking deceleration of the vehicle ahead.

[0054] From the above longitudinal safety distance calculation model, we can know that the values ​​of variables such as the front vehicle speed, the vehicle speed, and the real-time acceleration of the vehicle can be monitored and collected in real time. The driver's reaction time, the maximum braking deceleration of the vehicle, and the braking deceleration of the front vehicle are the three core parameters of the longitudinal safety distance calculation model, which need to be estimated according to the actual situation. Among them, the driver's reaction time is mainly affected by factors such as the driver's age and experience, while the maximum braking deceleration of the vehicle is greatly affected by factors such as the road friction coefficient. These two parameters can be estimated by a predetermined method.

[0055] However, the estimation of the braking deceleration of the preceding vehicle is often affected by traffic environment factors. Existing methods ignore the impact of different traffic scenarios on the braking deceleration of the preceding vehicle. Usually, preset fixed parameters are used or the preceding vehicle deceleration is estimated based on a single fixed method, resulting in low accuracy of the longitudinal safety distance calculated using this model.

[0056] In response to the problems existing in the above-mentioned prior art, an embodiment of the present application provides a method for dynamically updating a safety distance model, which calculates the parameter of the preceding vehicle deceleration by adaptively switching different estimation strategies according to different traffic scenarios and dynamically updates the longitudinal safety distance calculation model, so that the calculation model can better adapt to different traffic scenarios, thereby effectively improving the accuracy of calculating the longitudinal safety distance.

[0057] like Figure 1 As shown, the embodiment of the present application provides a method for dynamically updating a safety distance model, which may include the steps of:

[0058] S1. Determine whether the longitudinal safety distance calculation model meets the preset update conditions, obtain a target estimation strategy corresponding to the current traffic scene type in which the vehicle is located, and obtain a dynamic estimation result corresponding to the deceleration parameter of the preceding vehicle according to the target estimation strategy.

[0059] It should be noted that a separate thread can be used to monitor in real time whether the longitudinal safety distance calculation model needs to be updated, and the parameter of the front vehicle deceleration in the longitudinal safety distance calculation model can be updated when the preset update conditions are met. Two different threads can be used to update the calculation model and to calculate the longitudinal safety distance using the model. In this way, on the one hand, the calculation model can be updated in time according to demand, and on the other hand, the most recently updated model can be used to calculate the longitudinal safety distance.

[0060] Specifically, when it is determined that the longitudinal safety distance calculation model needs to be updated (determining that the longitudinal safety distance calculation model meets the preset update conditions), first determine the type of traffic scene the vehicle is currently in, and then obtain the target estimation strategy corresponding to the traffic scene type based on the preset correspondence relationship, and calculate the dynamic estimation result of the parameter of the preceding vehicle deceleration according to the target estimation strategy.

[0061] S2. Based on the dynamic estimation result, the preceding vehicle deceleration parameter in the longitudinal safety distance calculation model is updated to obtain a dynamically optimized longitudinal safety distance calculation model.

[0062] Specifically, the preceding vehicle deceleration parameter in the longitudinal safety distance calculation model is replaced with the currently calculated dynamic estimation result of the preceding vehicle deceleration to obtain an updated longitudinal safety distance calculation model.

[0063] Based on this, since the longitudinal safety distance calculation model obtained by the current dynamic optimization is updated using the dynamically estimated deceleration parameters of the preceding vehicle, and the estimation of the preceding vehicle deceleration is calculated using an estimation strategy adapted to the current traffic scenario, the updated longitudinal safety distance calculation model can better adapt to the actual conditions of the current traffic scenario, thereby making the longitudinal safety distance calculated using this model have higher accuracy.

[0064] In some possible embodiments, in step S1, obtaining a target estimation strategy corresponding to the current traffic scene type in which the vehicle is located may include at least one of the following:

[0065] 1. When it is determined that the current traffic scene type of the vehicle is an urban scene, an estimation strategy based on big data statistics is obtained as a target estimation strategy;

[0066] 2. When it is determined that the current traffic scene type of the vehicle is a suburban scene, a Markov-based estimation strategy is obtained as a target estimation strategy;

[0067] 3. When it is determined that the current traffic scene type in which the vehicle is located is a high-speed scene, an estimation strategy based on fuzzy theory is obtained as a target estimation strategy;

[0068] Among them, the current traffic scene type of the vehicle is obtained by matching the current positioning information of the vehicle with a preset traffic scene annotation chart.

[0069] It should be noted that the correspondence between the traffic scene type and the estimation strategy can be set according to actual needs. For example, the traffic scene type can be set to three common traffic scenes: urban, suburban and highway. By pre-marking the road sections or area ranges of different traffic scenes on the map, a traffic scene annotation chart is obtained, and then the vehicle positioning information is obtained, and the positioning information is matched with the preset traffic scene annotation chart to determine the traffic scene type of the vehicle's current location.

[0070] It is understandable that the differences between the three traffic scenes of urban, suburban and highway are mainly reflected in the three parts of vehicle speed, traffic flow and traffic density. Among them, considering that the vehicle speed fluctuates greatly, the traffic flow is large, and the traffic density is high in the urban scene, the traffic scene is relatively complex, which will increase the calculation burden of the rule-based method. Therefore, it is advisable to choose a method based on big data statistics as the estimation strategy for the deceleration of the preceding vehicle; considering that the traffic flow is small and the traffic density is small in the suburban scene, but the vehicle speed fluctuates greatly, which will increase the burden of fuzzy theory calculation, but because the categories of each influencing factor are clear, it is advisable to use a Markov-based method as the estimation strategy for the deceleration of the preceding vehicle; considering that the changes in vehicle speed, traffic flow and traffic density in the highway scene are small and fixed, and the traffic scene is relatively simple, the rule-based method is generally more accurate and more convincing than the big data-based method, so the fuzzy theory-based method is selected as the estimation strategy for the deceleration of the preceding vehicle.

[0071] It should be noted that the deceleration of the preceding vehicle obtained by the adaptive estimation strategy in the embodiment of the present application is not the maximum deceleration of the preceding vehicle in the physical sense, but an estimated value of the deceleration with a high probability that is statistically consistent with the characteristics of the current traffic scene.

[0072] Based on this, by adopting appropriate estimation strategies to obtain the deceleration of the leading vehicle according to the characteristics of different traffic scenarios, it is possible to obtain the deceleration estimation result of the leading vehicle that best suits the traffic scenario from a macroscopic probability level, thereby improving the overall accuracy of the estimation of the deceleration of the leading vehicle, and then improving the accuracy of the longitudinal safety distance calculation.

[0073] In some possible embodiments, in step S1, obtaining a dynamic estimation result corresponding to the deceleration parameter of the preceding vehicle according to the target estimation strategy may include:

[0074] S101, obtaining current feature information corresponding to a preset key feature type, and obtaining target deceleration statistical information corresponding to the current feature information based on a correspondence between the preset feature information and the deceleration statistical information; wherein the preset key feature type includes at least one of a time period feature and a weather feature, and the deceleration statistical information is obtained by statistics based on pre-collected vehicle driving history data;

[0075] S102: Obtain a dynamic estimation result corresponding to a deceleration parameter of the preceding vehicle based on the target deceleration statistical information.

[0076] It should be noted that when the current traffic scene type in which the vehicle is located is an urban scene, an estimation strategy based on big data statistics can be used to obtain the deceleration of the preceding vehicle. Specifically, firstly, the corresponding statistical information of the preceding vehicle deceleration under different characteristic situations is obtained. Exemplarily, the process may include the following steps:

[0077] 1. Collect vehicle driving data (vehicle driving history data) corresponding to urban scenes from multiple sources, including but not limited to video records of traffic monitoring systems, data recorded by vehicle-mounted equipment, published or purchased data sets, etc. Among them, vehicle driving history data includes the real-time deceleration value of the vehicle, timestamp, and corresponding weather conditions, etc.

[0078] 2. Perform pre-processing operations such as cleaning, denoising, and formatting on the collected vehicle driving history data to ensure the consistency and accuracy of the data.

[0079] 3. Classify the vehicle driving history data according to preset key features, for example, classify the data according to one or more dimensions such as time period, weather conditions, etc. The type and number of key features can be set according to requirements.

[0080] 4. For each type of vehicle driving history data after classification, the deceleration value of each small segment of data (for example, a value is captured every 5 seconds) can be used as a unit to calculate the probability distribution of the deceleration values ​​of these vehicles (deceleration statistical information).

[0081] For example, the statistical information corresponding to different feature dimensions may be shown in the following table:

[0082] Time period sunny rain Snowy Days 6:00-9:00 map1 map8 map15 9:00-11:00 map2 map9 map16 11:00-13:00 map3 map10 map17 13:00-18:00 map4 map11 map18 18:00-20:00 map5 map12 map19 20:00-24:00 map6 map13 map20 24:00-6:00 map7 map14 map21

[0083] Among them, map1 to map21 respectively correspond to a deceleration statistical information chart (for example, a deceleration value probability distribution chart).

[0084] Based on the statistically obtained deceleration statistics corresponding to different feature dimensions such as time period and weather, the deceleration statistics of the corresponding category are matched and obtained according to the current feature information of the currently collected key feature type, and then the dynamic estimation result of the deceleration parameter of the preceding vehicle can be calculated based on the deceleration statistics. For example, if the current feature information of the preset key feature type is "sunny" and "time is 10:30", the matched deceleration statistics information is map2 in the above table; then, according to the vehicle deceleration value probability distribution diagram shown in map2 (such as Figure 2As shown), a preset statistical index is used as the final leading vehicle deceleration parameter estimation value (for example, the maximum deceleration value within a 95% confidence interval is calculated as the leading vehicle deceleration parameter estimation value).

[0085] In some possible embodiments, in step S1, obtaining a dynamic estimation result corresponding to the deceleration parameter of the preceding vehicle according to the target estimation strategy may include:

[0086] S111, acquiring acceleration monitoring data of the preceding vehicle, and based on the acceleration monitoring data, performing prediction using a pre-statisticed Markov probability transfer matrix to obtain a dynamic estimation result corresponding to a deceleration parameter of the preceding vehicle;

[0087] Among them, the method for obtaining the Markov probability transfer matrix includes:

[0088] Collecting a vehicle driving sample data set, and classifying the vehicle driving sample data set according to different preset vehicle speed intervals to obtain a sample data subset corresponding to each vehicle speed interval;

[0089] For each sample data subset, each sample data therein is divided into a unit operating condition instance corresponding to a preset acceleration state interval;

[0090] The state transition probabilities of each acceleration state interval are statistically analyzed based on the divided unit operating condition instances, and a Markov probability transfer matrix corresponding to each vehicle speed interval is constructed.

[0091] It should be noted that when the current traffic scene type of the vehicle is a suburban scene, a Markov-based estimation strategy can be used to obtain the deceleration of the preceding vehicle. Specifically, firstly, the Markov probability transfer matrix corresponding to different vehicle speed intervals is obtained. For example, the process may include the following steps:

[0092] 1. Similar to the method based on big data statistics, first collect the vehicle driving sample data set, which includes the vehicle speed, real-time acceleration and other information.

[0093] 2. The collected sample data are classified according to the divided speed intervals. For example, they can be divided into three speed intervals: [0, 40] km / h, (40, 80] km / h, and (80, 120] km / h, which are set as slow speed interval, medium speed interval, and high speed interval respectively. Each speed interval corresponds to a sample data subset.

[0094] 3. For each sample data subset, each sample data (the data of a single vehicle traveling in the corresponding speed range is taken as a sample data) is divided into corresponding unit operating condition instances according to the pre-divided acceleration state range. For example, assuming that the overall acceleration range is [-10m / s 2, 10m / s 2 ], where ±6m / s 2 The acceleration between them is 0.5m / s 2 As the unit interval, the final division results in a total of 26 corresponding acceleration state intervals: [-10m / s 2 , -6m / s 2 ),[-6m / s 2 , -5.5m / s 2 ),…,[5.5m / s 2 , 6m / s 2 ), [6m / s 2 , 10m / s 2 ].

[0095] 4. Count the state transition probability corresponding to each acceleration state interval. Exemplarily, the state transition probability is a first-order state transition probability, that is, for any state E i After a change, it moves to another state E j Probability:

[0096]

[0097] Among them, statistics can be performed based on the divided unit working condition instances to obtain the number of acceleration state interval transfers for each working condition instance, and then the state transfer probability corresponding to each acceleration state interval can be obtained by statistics, and finally the Markov probability transfer matrix under the current vehicle speed interval can be obtained. The calculation formula is as follows:

[0098]

[0099] In the process of estimating the deceleration of the preceding vehicle, the Markov probability transfer matrix corresponding to the corresponding speed range is first obtained based on the current speed of the vehicle. Then, based on the acceleration monitoring data of the vehicle, the acceleration value corresponding to the acceleration monitoring data and the Markov probability transfer matrix can be used to obtain the acceleration value at the next moment as the estimation result of the deceleration of the preceding vehicle.

[0100] In some possible embodiments, in step S1, obtaining a dynamic estimation result corresponding to the deceleration parameter of the preceding vehicle according to the target estimation strategy may include:

[0101] S121, obtaining a current set of characteristic values ​​corresponding to at least one preset deceleration influencing factor of the preceding vehicle; wherein the at least one deceleration influencing factor of the preceding vehicle includes at least one of vehicle speed, vehicle flow, and vehicle flow density;

[0102] S122, based on the eigenvalue set, respectively obtaining fuzzy subsets corresponding to the deceleration influencing factors of each preceding vehicle;

[0103] S123, determining the corresponding fuzzy value of the preceding vehicle deceleration based on the fuzzy subsets of the preceding vehicle deceleration influencing factors and a preset preceding vehicle deceleration fuzzy rule control table;

[0104] S124. Defuzzify the fuzzy value of the preceding vehicle deceleration based on a preset preceding vehicle deceleration membership function to obtain a dynamic estimation result corresponding to the preceding vehicle deceleration parameter.

[0105] Specifically, in a high-speed scenario, the influencing factors related to the deceleration of the preceding vehicle mainly include vehicle speed, traffic volume, and traffic density, etc. Therefore, the influencing factors of the preceding vehicle deceleration can be determined as vehicle speed, traffic volume, and traffic density.

[0106] It should be noted that the working process of the estimation strategy based on fuzzy theory can be as follows: Figure 3 Specifically, we first need to define the fuzzy membership function corresponding to each influencing factor:

[0107] 1. Taking vehicle speed as the domain, it can be divided into three fuzzy subsets: slow speed V1, medium speed V2 and high speed V3. For example, the domain value range is [0,120]. Based on the trapezoidal membership function, the membership functions of the fuzzy subsets V1, V2 and V3 are set to v1, v2 and v3 respectively:

[0108]

[0109] Among them, 0≤x≤120, the value range of v1, v2 and v3 is [0,1].

[0110] 2. Take the hourly traffic volume as the domain. The traffic volume generally starts from 0, and its value range is defined as [0, +∞). Divide the traffic volume into three fuzzy subsets: low traffic volume Q1, medium traffic volume Q2, and high traffic volume Q3. Based on the trapezoidal membership function, the membership functions of the fuzzy subsets Q1, Q2, and Q3 are set to q1, q2, and q3 respectively. In order to simplify the calculation, the traffic volume is in the unit of "thousands". The membership functions corresponding to the above three fuzzy subsets are as follows:

[0111]

[0112] Among them, 0≤x<+∞, and the value range of q1, q2 and q3 is [0,1].

[0113] 3. Take the traffic density (vehicles / km) per lane as the domain, with a value range of [0, +∞). Divide the traffic density into three fuzzy subsets: low density K1, medium density K2, and high density K3. Based on the trapezoidal membership function, the membership functions of the fuzzy subsets K1, K2, and K3 are set to k1, k2, and k3 respectively. In order to simplify the calculation, the traffic density is in the unit of "thousands". The membership functions corresponding to the above three fuzzy subsets are as follows:

[0114]

[0115] Among them, 0≤x<+∞, and the value range of k1, k2 and k3 is [0,1].

[0116] It should be noted that the number of fuzzy subsets corresponding to the above-mentioned influencing factors can be set according to demand. It is not difficult to understand that the more the number of fuzzy subset divisions is, the more accurate the preceding vehicle deceleration calculated based on the fuzzy rules is.

[0117] In the process of estimating the deceleration of the preceding vehicle, the eigenvalue set corresponding to the factors affecting the deceleration of the preceding vehicle is first obtained, where one factor affecting the deceleration of the preceding vehicle corresponds to one eigenvalue; then the eigenvalue is substituted into the corresponding membership function mentioned above, and the fuzzy subsets corresponding to each factor affecting the deceleration of the preceding vehicle are calculated respectively (the result with the largest probability value is taken as the fuzzy subset).

[0118] Then, the corresponding fuzzy value of the preceding vehicle's deceleration can be determined according to the fuzzy subset and the preset fuzzy rule control table. Among them, the fuzzy rule control table can be formulated according to the influence of vehicle speed, flow rate and traffic density on the preceding vehicle's deceleration. It can be understood that the corresponding relationship between each influencing factor and the preceding vehicle's deceleration follows the following principles: the greater the vehicle speed, the greater the braking deceleration; the higher the flow rate, the faster the average vehicle speed per unit time, and the greater the preceding vehicle's deceleration; the greater the traffic density, the more vehicles per unit mileage, the lower the speed, and the smaller the preceding vehicle's deceleration. Based on this, the fuzzy rule control table can be set as shown in the following table by way of example:

[0119]

[0120]

[0121] The preceding vehicle deceleration A can be exemplarily divided into three fuzzy subsets: fast A1, medium A2 and slow A3. The specific number of fuzzy subsets and the corresponding relationship of fuzzy rules can be set according to actual conditions.

[0122] It should be noted that after determining the corresponding fuzzy subset result based on the current eigenvalue and determining the fuzzy value of the preceding vehicle deceleration according to the fuzzy rule, it is necessary to further perform defuzzification and obtain the accurate preceding vehicle deceleration value.

[0123] Specifically, for the deceleration of the preceding vehicle, according to the results of literature research, the deceleration of the preceding vehicle is generally 0 m / s 2 to 9.8m / s 2 , so the value range of its domain is [0,9.8]. The fuzzy quantity corresponding to the deceleration of the preceding vehicle is divided into three fuzzy subsets, namely fast A1, medium A2 and slow A3. The membership functions of the fuzzy subsets A1, A2 and A3 are set to a1, a2 and a3 respectively. Exemplarily, the membership functions corresponding to the above three fuzzy subsets are as follows:

[0124]

[0125]

[0126] The value range of x is [0,9.8], and the value range of a1, a2 and a3 are all (0,1].

[0127] According to the currently determined fuzzy amount of the preceding vehicle deceleration, the target membership function of the preceding vehicle deceleration matching the current eigenvalue set can be determined. Then, the centroid method can be used to perform defuzzification to obtain the final precise value of the preceding vehicle deceleration. The formula is as follows:

[0128]

[0129] Wherein, a(x) is the membership function corresponding to the currently determined fuzzy value of the preceding vehicle deceleration, and A is the precise value of the preceding vehicle deceleration after defuzzification.

[0130] In some possible embodiments, in step S1, determining whether the longitudinal safety distance calculation model meets a preset update condition may include:

[0131] 1. Obtain in real time the cumulative time from the last time the longitudinal safety distance calculation model was updated to the current time. If it is determined that the cumulative time exceeds the preset model update cycle, determine that the longitudinal safety distance calculation model meets the preset update conditions;

[0132] 2. Monitor the current traffic scene type of the vehicle in real time, and when the current traffic scene type of the vehicle changes, determine whether the longitudinal safety distance calculation model meets the preset update conditions.

[0133] In the embodiment of the present application, any one of the above items can be used as a basis for determining whether the longitudinal safety distance calculation model meets the update conditions. Specifically, for the first method mentioned above, the model update cycle can be set in advance, and then the cumulative time for which the model has not been updated can be monitored in real time, and when it is determined that the cumulative time exceeds the model update cycle, it is determined that the preset update conditions are met. For the second method mentioned above, the current traffic scene type of the vehicle can be monitored in real time. Whenever it is detected that the current traffic scene type of the vehicle is inconsistent with the traffic scene type at the previous moment, it means that the traffic scene of the vehicle has changed, and it is therefore determined that the preset update conditions are met.

[0134] Based on this, by using the set period or the changes in the scene in which the vehicle is located as the condition for judging the model update, the timeliness of the model update can be improved, and the accuracy of calculating the longitudinal safety distance in different traffic scenarios can be further improved.

[0135] Please refer to Figure 4 , Figure 4 FIG. 1 shows a block diagram of a dynamic updating device for a safety distance model provided in some embodiments of the present application. It should be understood that the dynamic updating device for the safety distance model is similar to the above-mentioned Figure 1 Corresponding to the method embodiment, each step involved in the above method embodiment can be executed. The specific functions of the dynamic updating device of the safety distance model can be found in the above description. To avoid repetition, the detailed description is appropriately omitted here.

[0136] Figure 4 The dynamic updating device of the safety distance model includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the dynamic updating device of the safety distance model, and the dynamic updating device of the safety distance model includes:

[0137] The parameter dynamic estimation module 410 is used to determine whether the longitudinal safety distance calculation model meets the preset update condition, obtain a target estimation strategy corresponding to the current traffic scene type in which the vehicle is located, and obtain a dynamic estimation result corresponding to the deceleration parameter of the leading vehicle according to the target estimation strategy;

[0138] The calculation model updating module 420 is used to update the preceding vehicle deceleration parameter in the longitudinal safety distance calculation model based on the dynamic estimation result to obtain a dynamically optimized longitudinal safety distance calculation model.

[0139] It can be understood that the above-mentioned device item embodiment corresponds to the method item embodiment of the present invention. The dynamic update device of a safety distance model provided by the embodiment of the present invention can implement the dynamic update method of the safety distance model provided by any method item embodiment of the present invention.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method, and will not be described in detail here.

[0141] like Figure 5 As shown, some embodiments of the present application provide an electronic device 500, which includes: a memory 510, a processor 520, and a computer program stored in the memory 510 and executable on the processor 520, wherein the processor 520 reads the program from the memory 510 through a bus 530 and executes the program to implement a method of any embodiment of the dynamic update method of the safety distance model as described above.

[0142] Processor 520 can process digital signals and can include various computing structures, such as complex instruction set computer structure, reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, processor 520 can be a microprocessor.

[0143] The memory 510 may be used to store instructions executed by the processor 520 or data related to the execution of instructions. These instructions and / or data may include codes for implementing some or all functions of one or more modules described in the embodiments of the present application. The processor 520 of the disclosed embodiment may be used to execute instructions in the memory 510 to implement the method shown above. The memory 510 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memory known to those skilled in the art.

[0144] Some embodiments of the present application further provide a computer-readable storage medium having a computer program stored thereon. The computer program is executed by a processor to execute the method described in the method embodiment.

[0145] Some embodiments of the present application further provide a computer program product, which, when executed on a computer, enables the computer to execute the method described in the method embodiment.

[0146] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0147] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0148] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0149] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0150] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0151] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0152] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for dynamically updating a safety distance model, characterized in that: include: Determining that the longitudinal safety distance calculation model meets a preset update condition, obtaining a target estimation strategy corresponding to the current traffic scene type in which the vehicle is located, and obtaining a dynamic estimation result corresponding to the deceleration parameter of the leading vehicle according to the target estimation strategy; Based on the dynamic estimation result, the preceding vehicle deceleration parameter in the longitudinal safety distance calculation model is updated to obtain a dynamically optimized longitudinal safety distance calculation model.

2. The method for dynamically updating the safety distance model according to claim 1, characterized in that: The obtaining of a target estimation strategy corresponding to the current traffic scene type in which the vehicle is located includes at least one of the following: When it is determined that the current traffic scene type in which the vehicle is located is an urban scene, obtaining an estimation strategy based on big data statistics as the target estimation strategy; When it is determined that the current traffic scene type in which the vehicle is located is a suburban scene, obtaining a Markov-based estimation strategy as the target estimation strategy; When it is determined that the current traffic scene type in which the vehicle is located is a high-speed scene, obtaining an estimation strategy based on fuzzy theory as the target estimation strategy; The current traffic scene type of the vehicle is obtained by matching the current positioning information of the vehicle with a preset traffic scene annotation chart.

3. The method for dynamically updating the safety distance model according to claim 1, characterized in that: The step of obtaining a dynamic estimation result corresponding to a deceleration parameter of a preceding vehicle according to the target estimation strategy includes: Acquire current feature information corresponding to a preset key feature type, and obtain target deceleration statistical information corresponding to the current feature information based on a correspondence between the preset feature information and the deceleration statistical information; wherein the preset key feature type includes at least one of a time period feature and a weather feature, and the deceleration statistical information is obtained by statistics based on pre-collected vehicle driving history data; A dynamic estimation result corresponding to a deceleration parameter of the preceding vehicle is obtained based on the target deceleration statistical information.

4. The method for dynamically updating the safety distance model according to claim 1, characterized in that: The step of obtaining a dynamic estimation result corresponding to a deceleration parameter of a preceding vehicle according to the target estimation strategy includes: Acquire acceleration monitoring data of the preceding vehicle, and based on the acceleration monitoring data, use a pre-statisticed Markov probability transfer matrix to make a prediction to obtain a dynamic estimation result corresponding to a deceleration parameter of the preceding vehicle; The method for obtaining the Markov probability transfer matrix includes: Collecting a vehicle driving sample data set, and classifying the vehicle driving sample data set according to different preset vehicle speed intervals to obtain a sample data subset corresponding to each vehicle speed interval; For each sample data subset, each sample data therein is divided into a unit operating condition instance corresponding to a preset acceleration state interval; The state transition probabilities of each acceleration state interval are statistically analyzed based on the divided unit operating condition instances, and a Markov probability transfer matrix corresponding to each vehicle speed interval is constructed.

5. The method for dynamically updating the safety distance model according to claim 1, characterized in that: The step of obtaining a dynamic estimation result corresponding to a deceleration parameter of a preceding vehicle according to the target estimation strategy includes: Acquire a current feature value set corresponding to at least one preset deceleration influencing factor of the preceding vehicle; wherein the at least one deceleration influencing factor of the preceding vehicle includes at least one of vehicle speed, vehicle flow, and vehicle flow density; Based on the eigenvalue set, respectively obtaining fuzzy subsets corresponding to the deceleration influencing factors of each preceding vehicle; Determine the corresponding fuzzy value of the preceding vehicle deceleration based on the fuzzy subsets of the influencing factors of the preceding vehicle deceleration and the preset preceding vehicle deceleration fuzzy rule control table; The fuzzy value of the preceding vehicle deceleration is defuzzified based on a preset preceding vehicle deceleration membership function to obtain a dynamic estimation result corresponding to the preceding vehicle deceleration parameter.

6. The method for dynamically updating the safety distance model according to claim 1, characterized in that: The step of determining whether the longitudinal safety distance calculation model satisfies a preset update condition includes: Real-time acquisition of the cumulative time from the historical moment when the longitudinal safety distance calculation model was last updated to the current moment, and when it is determined that the cumulative time exceeds a preset model update cycle, determination that the longitudinal safety distance calculation model meets a preset update condition; Alternatively, the current traffic scene type of the vehicle is monitored in real time, and when the current traffic scene type of the vehicle is changed, it is determined that the longitudinal safety distance calculation model meets the preset update conditions.

7. A dynamic updating device for a safety distance model, characterized in that: include: A parameter dynamic estimation module, used to determine whether the longitudinal safety distance calculation model meets the preset update conditions, obtain a target estimation strategy corresponding to the current traffic scene type in which the vehicle is located, and obtain a dynamic estimation result corresponding to the deceleration parameter of the leading vehicle according to the target estimation strategy; The calculation model updating module is used to update the preceding vehicle deceleration parameter in the longitudinal safety distance calculation model based on the dynamic estimation result to obtain a dynamically optimized longitudinal safety distance calculation model.

8. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for dynamically updating the safety distance model described in any one of claims 1 to 6 can be implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for dynamically updating the safety distance model according to any one of claims 1 to 6 is executed.

10. A vehicle, characterized in that: Comprising the electronic device as claimed in claim 8.

Images