Geographic feature fused full-scene driving condition development method and device

Abstract

The invention relates to the technical field of vehicles, in particular to a full-scene driving condition development method and device fusing geographic features, and the method comprises the steps: obtaining the current operation data of a vehicle and the current geographic information data of the position where the vehicle is located; based on the current operation data and the current geographic information data, a first alternative working condition set meeting preset characteristic parameter deviation is determined from a preset road scene database, and the preset road scene database is obtained based on a dynamically adjusted multi-dimensional Markov model; the dynamically adjusted multi-dimensional Markov model is obtained by dividing state variables dynamically generated by historical operation data and historical geographic information data; and determining a target driving working condition of the vehicle from the first alternative working condition set based on the current operation data and the current geographic information data. Therefore, the problems of lack of geographic feature fusion, incomplete speed section coverage, low working condition generation accuracy and the like in related technologies are solved, and a scientific basis is provided for vehicle design and road planning.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method and device for developing full-scenario driving conditions integrating geographical features. Background Art

[0002] With the rapid development of the automobile industry and the continuous improvement of the road traffic network, the study of vehicle driving conditions is of great significance in the fields of automobile design, emission control, energy consumption optimization, etc. Driving conditions are time series data that describe the operating status of a vehicle under specific road conditions, usually including parameters such as vehicle speed and acceleration; by constructing a real and comprehensive driving condition, a scientific basis can be provided for vehicle performance optimization, emission testing, and energy conservation and emission reduction strategies.

[0003] In related technologies, the driving condition development method is mainly based on the statistical characteristics of vehicle speed and acceleration. With the popularization of geographic information technology, the ability to collect vehicle operation data has been significantly improved, which makes it possible to develop driving conditions that integrate geographic features.

[0004] However, the methods in related technologies ignore the impact of road geographical features on vehicle operation status, making it difficult to fully reflect the actual operation of vehicles under different terrain conditions; at the same time, the speed segment division is usually limited to certain specific speed ranges, failing to cover the driving characteristics of the full speed segment, resulting in certain limitations in the applicability and accuracy of the generated operating conditions. In addition, how to effectively use the data obtained by geographic information technology, combined with different speed segments and geographical features, to construct a comprehensive and realistic driving condition is still a difficult point in current research and needs to be solved urgently. Summary of the invention

[0005] The present application provides a method and device for developing full-scenario driving conditions integrating geographical features, so as to solve the problems in related technologies such as lack of geographical feature integration, incomplete speed segment coverage and insufficient accuracy of condition generation, and provide a scientific basis for vehicle design, road planning and energy conservation and emission reduction.

[0006] The first aspect of the present application provides a method for developing a full-scenario driving condition integrating geographical features, comprising the following steps:

[0007] Acquiring current operation data of the vehicle and current geographic information data of the location of the vehicle;

[0008] Based on the current operating data and the current geographic information data, determining a first set of candidate operating conditions that meets a preset characteristic parameter deviation from a preset road scene database, wherein the preset road scene database is obtained based on a dynamically adjusted multidimensional Markov model, and the dynamically adjusted multidimensional Markov model is obtained by dividing state variables dynamically generated by historical operating data and historical geographic information data;

[0009] Based on the current operating data and the current geographic information data, determine the target driving condition of the vehicle from the first alternative condition set.

[0010] Optionally, before determining the first alternative condition set that meets the preset characteristic parameter deviation from the preset road scene database based on the current operating data and the current geographic information data, it further includes:

[0011] Obtain the historical operating data of the vehicle and the historical geographic information data corresponding to the historical operating data;

[0012] Obtain multiple scenario combinations based on the historical operating data and the historical geographic information data;

[0013] Based on the short travel segments of the multiple scenario combinations, transform the historical operating data and the historical geographic information data into state variables, dynamically adjust the division of the state variables, and construct a dynamically adjusted multi-dimensional Markov model;

[0014] Generate multiple state sequences based on the Markov model, and screen the multiple state sequences through low-pass filtering to obtain multiple single driving conditions, and based on the multiple scenario combinations, combine the multiple driving conditions to obtain the preset road scene database.

[0015] Optionally, the obtaining multiple scenario combinations based on the historical operating data and the historical geographic information data includes:

[0016] Determine multiple driving speed intervals based on the historical operating data;

[0017] Determine multiple driving altitude intervals and multiple driving slope intervals based on the historical geographic information data;

[0018] Combine the multiple driving speed intervals, the multiple driving altitude intervals, and the multiple driving slope intervals to obtain the multiple scenario combinations.

[0019] Optionally, the calculation formula of the low-pass filtering is:

[0020] y c = α × x c +(1 - α) × y c-1 ;

[0021] where y c is the value of the filtered signal at the c-th moment, α is the filtering coefficient, and x c is the value of the original input vehicle speed or slope sequence at the c-th moment.

[0022] Optionally, the current operating data includes a speed parameter and an acceleration parameter, and the current geographic information data includes a slope parameter and an altitude parameter.

[0023] Optionally, determining a first set of alternative operating conditions that meet preset characteristic parameter deviations from a preset road scenario database based on the current operating data and the current geographic information data includes:

[0024] Based on the speed parameter, the acceleration parameter, the slope parameter, and the altitude parameter, screen out driving conditions from the preset road scenario database whose overall characteristic parameter deviation value from the current operating data and the current geographic information data is less than a first deviation threshold, and the deviation value of each characteristic parameter is less than a second preset threshold;

[0025] Generate the first set of alternative operating conditions according to the driving conditions whose overall characteristic parameter deviation value is less than the first deviation threshold and the deviation value of each characteristic parameter is less than the second preset threshold.

[0026] Optionally, determining the target driving condition of the vehicle from the first set of alternative operating conditions based on the current operating data and the current geographic information data includes:

[0027] Based on the slope parameter in the current geographic information data, determine whether the vehicle is in a preset flat road condition;

[0028] If the vehicle is in the preset flat road condition, then based on the speed parameter and the acceleration parameter in the current operating data, screen out the driving condition with the smallest cumulative deviation of the speed distribution parameter from the first set of alternative operating conditions as the target driving condition;

[0029] And, if the vehicle is not in the preset flat road condition, then screen out a second set of alternative operating conditions whose speed distribution parameter from the first set of alternative operating conditions meets a preset cumulative deviation, and screen out the condition with the smallest cumulative deviation of the slope distribution parameter from the current geographic information data as the target driving condition from the second set of alternative operating conditions.

[0030] An embodiment of the second aspect of the present application provides a full-scenario driving condition development device integrating geographic features, including:

[0031] An acquisition module, configured to acquire the current operating data of the vehicle and the current geographic information data of the location where the vehicle is located;

[0032] An alternative module for determining a first set of alternative operating conditions that meet preset characteristic parameter deviations from a preset road scenario database based on the current operating data and the current geographic information data, wherein the preset road scenario database is obtained based on a dynamically adjusted multi-dimensional Markov model, and the dynamically adjusted multi-dimensional Markov model is obtained by dividing state variables dynamically generated from historical operating data and historical geographic information data;

[0033] A determination module for determining the target driving condition of the vehicle from the first set of alternative operating conditions based on the current operating data and the current geographic information data.

[0034] Optionally, before determining the first set of alternative operating conditions that meet the preset characteristic parameter deviations from the preset road scenario database based on the current operating data and the current geographic information data, the alternative module is further configured to:

[0035] Obtain the historical operating data of the vehicle and the historical geographic information data corresponding to the historical operating data;

[0036] Obtain multiple scenario combinations based on the historical operating data and the historical geographic information data;

[0037] Based on short travel segments of the multiple scenario combinations, transform the historical operating data and the historical geographic information data into state variables, dynamically adjust the division of the state variables, and construct a dynamically adjusted multi-dimensional Markov model;

[0038] Generate multiple state sequences based on the Markov model, and filter the multiple state sequences through low-pass filtering to obtain multiple single driving conditions, and combine the multiple driving conditions based on the multiple scenario combinations to obtain the preset road scenario database.

[0039] Optionally, the alternative module is specifically configured to:

[0040] Determine multiple driving speed intervals based on the historical operating data;

[0041] Determine multiple driving altitude intervals and multiple driving slope intervals based on the historical geographic information data;

[0042] Combine the multiple driving speed intervals, the multiple driving altitude intervals, and the multiple driving slope intervals to obtain the multiple scenario combinations.

[0043] Optionally, the calculation formula of the low-pass filtering is:

[0044] y c = α × x c +(1 - α) × y c-1 ;

[0045] Among them, y c is the value of the filtered signal at the c-th moment, α is the filtering coefficient, and x c is the value of the original input vehicle speed or slope sequence at the c-th moment.

[0046] Optionally, the current operation data includes a speed parameter and an acceleration parameter, and the current geographic information data includes a slope parameter and an altitude parameter.

[0047] Optionally, the alternative module is specifically configured to:

[0048] Based on the speed parameter, the acceleration parameter, the slope parameter, and the altitude parameter, select a driving condition from the preset road scenario database whose deviation value of the overall characteristic parameters from the current operation data and the current geographic information data is less than a first deviation threshold, and the deviation value of each characteristic parameter is less than a second preset threshold;

[0049] Generate the first alternative condition set according to the driving conditions whose deviation value of the overall characteristic parameters is less than the first deviation threshold and the deviation value of each characteristic parameter is less than the second preset threshold.

[0050] Optionally, the determination module is specifically configured to:

[0051] Based on the slope parameter in the current geographic information data, determine whether the vehicle is in a preset flat road condition;

[0052] If the vehicle is in the preset flat road condition, based on the speed parameter and the acceleration parameter in the current operation data, select the driving condition with the smallest cumulative deviation of the speed distribution parameter from the current operation data in the first alternative condition set as the target driving condition;

[0053] And, if the vehicle is not in the preset flat road condition, select a second alternative condition set whose speed distribution parameter from the current operation data meets a preset cumulative deviation from the first alternative condition set, and select the condition with the smallest cumulative deviation of the slope distribution parameter from the current geographic information data in the second alternative condition set as the target driving condition.

[0054] An embodiment of the third aspect of the present application provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are set to execute the full-scenario driving condition development method for fusing geographic features as described in the above embodiments.

[0055] The fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and the program is executed by a processor to implement the full-scenario driving condition development method integrating geographical features as described in the above embodiments.

[0056] Accordingly, the current operation data of the vehicle and the current geographical information data of the location where the vehicle is located are obtained; based on the current operation data and the current geographical information data, a first alternative working condition set that meets the preset characteristic parameter deviation is determined from a preset road scenario database, where the preset road scenario database is obtained based on a dynamically adjusted multi-dimensional Markov model, and the dynamically adjusted multi-dimensional Markov model is obtained through the division of state variables dynamically generated by historical operation data and historical geographical information data; based on the current operation data and the current geographical information data, the target driving condition of the vehicle is determined from the first alternative working condition set. Accordingly, by collecting vehicle operation data and geographical features to divide road scenarios, constructing a dynamically adjusted multi-dimensional Markov model, and generating full-scenario driving conditions through low-pass filtering and multi-level feature screening, the problems of lack of geographical feature integration, incomplete coverage of speed segments, and insufficient accuracy of working condition generation in the related art are solved, providing a scientific basis for vehicle design, road planning, and energy conservation and emission reduction.

[0057] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, where:

[0059] Figure 1 is a technical flowchart of a full-scenario driving condition development method integrating geographical features according to an embodiment of the present application;

[0060] Figure 2 is a flowchart of a full-scenario driving condition development method integrating geographical features according to an embodiment of the present application;

[0061] Figure 3 is a schematic diagram of the duration distribution of a short low-altitude - gentle slope - congestion segment according to an embodiment of the present application for a full-scenario driving condition development method integrating geographical features;

[0062] Figure 4 is a schematic diagram of a speed state sequence according to an embodiment of the present application for a full-scenario driving condition development method integrating geographical features;

[0063] Figure 5Schematic diagram of comparison before and after filtering for a full-scenario driving condition development method integrating geographical features provided according to an embodiment of the present application;

[0064] Figure 6 Block diagram of a full-scenario driving condition development device integrating geographical features provided according to an embodiment of the present application;

[0065] Figure 7 Schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. Detailed implementation manners

[0066] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0067] The full-scenario driving condition development method and device integrating geographical features according to the embodiments of the present application will be described below with reference to the accompanying drawings.

[0068] Before introducing the full-scenario driving condition development method integrating geographical features according to the embodiments of the present application, the development process of the full-scenario driving condition development method integrating geographical features will be briefly introduced.

[0069] Specifically, as Figure 1 shown, Figure 1 is the technical flowchart of a full-scenario driving condition development method integrating geographical features provided according to an embodiment of the present application. The vehicle speed and acceleration are collected in real time through the CAN (Controller Area Network) bus, and the slope and altitude are obtained by integrating RTK-GPS (Real-Time Kinematic Global Positioning System) and the inertial measurement unit; preprocessing is performed through outlier rejection (such as abnormal rapid acceleration with acceleration > 4.5 m / s 2 ), data alignment (timestamp synchronized to the millisecond level), and idling condition marking (vehicle speed < 1 km / h for more than 2 seconds), the road scene is divided into altitude, speed, and slope, and various standardized scene combinations are formed, a multi-dimensional Markov model is constructed, and state variables of speed, acceleration, and slope are defined. A state transition probability matrix is generated through the state variables for low-pass filtering to generate driving conditions, and the target driving conditions are determined after three-level condition screening.

[0070] Therefore, by introducing geographical features such as road gradients and combining vehicle operation data, the present application comprehensively reflects the actual operation characteristics of the vehicle under different terrain conditions (such as low altitude, mountain roads), and the generated driving cycle is closer to the real road scenario. The vehicle operation states are divided into full scenarios such as flat road congestion and mountain road high speed, and multiple typical road scenarios are divided in combination with terrain features to ensure that the cycle development is applicable to a variety of complex roads and traffic conditions. Based on the multi-dimensional Markov model, the state division rules of vehicle speed, acceleration and gradient are dynamically adjusted to accurately describe the transfer law of vehicle operation states, and the generated cycle sequence is more accurate. Through feature parameter screening and low-pass filtering processing, the generated driving cycle is superior in terms of smoothness and feature matching degree, effectively meeting the requirements of vehicle design, emission testing and energy conservation and emission reduction strategies.

[0071] The following details the full-scenario driving cycle development method integrating geographical features according to the embodiments of the present application.

[0072] Specifically, Figure 2 is a schematic flow chart of a full-scenario driving cycle development method integrating geographical features provided by an embodiment of the present application.

[0073] As Figure 2 shown, the full-scenario driving cycle development method integrating geographical features includes the following steps:

[0074] In step S201, the current operation data of the vehicle and the current geographical information data of the location where the vehicle is located are obtained.

[0075] Optionally, in some embodiments, the current operation data includes speed parameters and acceleration parameters, and the current geographical information data includes gradient parameters and altitude parameters.

[0076] Specifically, the vehicle operation data is collected in real time through an on-vehicle data acquisition terminal. The collected vehicle data includes operation time, vehicle speed, vehicle acceleration, etc., and the collected geographical information data includes longitude and latitude, road gradient, etc. The sampling frequency is 1 Hz, including but not limited to the operation time (i.e., recording the specific time of data collection), the current speed of the vehicle (the unit is km / h, reflecting the driving speed of the vehicle), the current acceleration of the vehicle (the unit is m / s 2 , reflecting the speed change rate of the vehicle), the current longitude and latitude of the vehicle (which can record the geographical location of the vehicle through a GPS module), and the current road gradient of the vehicle (the unit is percentage (%), reflecting the inclination degree of the road).

[0077] In step S202, based on the current operation data and the current geographic information data, a first set of alternative operating conditions that meet the preset characteristic parameter deviation is determined from a preset road scenario database, where the preset road scenario database is obtained based on a dynamically adjusted multi-dimensional Markov model, and the dynamically adjusted multi-dimensional Markov model is obtained through the division of state variables dynamically generated by historical operation data and historical geographic information data.

[0078] Wherein, the preset characteristic parameters refer to a set of key indicators that are preset and used to quantitatively evaluate the matching degree between the driving condition and the real road scenario; the first set of alternative operating conditions is a set of alternative operating conditions selected from the preset road scenario database with the highest matching degree with the current vehicle's current operation data and current geographic information data.

[0079] Optionally, in some embodiments, before determining the first set of alternative operating conditions that meet the preset characteristic parameter deviation from the preset road scenario database based on the current operation data and the current geographic information data, it further includes: obtaining the historical operation data of the vehicle and the historical geographic information data corresponding to the historical operation data; obtaining multiple scenario combinations based on the historical operation data and the historical geographic information data; transforming the historical operation data and the historical geographic information data into state variables based on short travel segments of the multiple scenario combinations, dynamically adjusting the division of the state variables, and constructing a dynamically adjusted multi-dimensional Markov model; generating multiple state sequences based on the Markov model, and screening the multiple state sequences through low-pass filtering to obtain multiple single driving conditions, and combining the multiple driving conditions based on the multiple scenario combinations to obtain the preset road scenario database.

[0080] Optionally, in some embodiments, obtaining multiple scenario combinations based on the historical operation data and the historical geographic information data includes: determining multiple driving speed intervals based on the historical operation data; determining multiple driving altitude intervals and multiple driving slope intervals based on the historical geographic information data; combining the multiple driving speed intervals, the multiple driving altitude intervals and the multiple driving slope intervals to obtain multiple scenario combinations.

[0081] Optionally, in some embodiments, the calculation formula of the low-pass filtering is:

[0082] y c =α×x c +(1 - α)×y c-1 ;

[0083] Wherein, y c is the value of the filtered signal at the c-th moment, α is the filtering coefficient, and x c is the value of the original input vehicle speed or slope sequence at the c-th moment.

[0084] It is understandable that obtaining the historical operation data of the vehicle and the corresponding historical geographical information data of the historical operation data, including data such as the driving speed, driving acceleration, and driving gradient of the vehicle; dividing the data into short-trip segments according to the driving speed of the vehicle to ensure that each segment of trip data contains complete information such as speed, acceleration, and gradient. The screening rules include deleting segments with a total duration of the short-trip segment < 15s, and segments with a movement duration < 10s, deleting segments with an idle duration > 180s in the short-trip segment, deleting segments with a maximum vehicle speed > 130 km / h in the short-trip segment, deleting segments with an acceleration > 4.5 m / s 2 or a deceleration < -4.5 m / s 2 ; and for the determination of the initial state of the subsequent Markov chain, the acceleration and gradient of the idle part are both set to 0.

[0085] It should be noted that in some embodiments, the idle state is when the vehicle speed ≤ 1 km / h, the acceleration state is when the vehicle speed > 1 km / h and the acceleration > 0.15 m / s 2 ; the deceleration state is when the vehicle speed > 1 km / h and the acceleration < -0.15 m / s 2 ; the constant speed state is when the vehicle speed > 1 km / h and the acceleration ≤ -0.15 m / s 2 and the acceleration ≥ 0.15 m / s 2 between. At the same time, the uphill state is when the gradient > 0.1%, the downhill state is when the gradient < -0.1%, and the small gradient state is when the gradient ≤ 0.1% and the gradient ≥ -0.1%.

[0086] Specifically, various road scenarios are divided according to the driving speed of the vehicle. When the driving speed of the vehicle is less than or equal to the first speed threshold, it is congested. When the driving speed of the vehicle is within the second speed threshold, it is low speed. When the driving speed of the vehicle is within the third speed threshold, it is medium speed. When the driving speed of the vehicle is greater than the fourth speed threshold, it is high speed; various road scenarios are divided according to the gradient where the current vehicle is located. When the gradient where the current vehicle is located is less than or equal to the first gradient threshold, it is flat road. When the gradient where the current vehicle is located is within the second gradient threshold, it is gentle slope. When the gradient where the current vehicle is located is within the third gradient threshold, it is medium slope. When the gradient where the current vehicle is located is greater than the fourth gradient threshold, it is steep slope; various road scenarios are divided according to the altitude where the current vehicle is located. When the altitude where the current vehicle is located is less than or equal to the first altitude threshold, it is low altitude. When the altitude where the current vehicle is located is within the second altitude threshold, it is medium altitude. When the altitude where the current vehicle is located is greater than the third altitude threshold, it is high altitude.

[0087] For example, in some embodiments, the elevation information in the short trip segment is extracted, the average value of the road elevation is calculated, and the short trip segment is divided into low elevation, medium elevation, and high elevation according to this average value. Elevation ≤ 1500 m is low elevation; elevation > 1500 m and elevation ≤ 3500 m is medium elevation, and elevation > 3500 m is high elevation. The slope information in the short trip segment is extracted, the 95th percentile of the uphill segment and the 5th percentile of the downhill segment are calculated, and the average value of the absolute values of the two is calculated as the maximum slope of the short trip segment. The maximum slopes are arranged in ascending order, and the short trip segment is divided into flat road scenario, small slope scenario, and large slope scenario according to the maximum slope. The maximum slope value ≤ 0.5% is the flat road scenario; the scenario with the maximum slope value > 0.5% and ≤ 3% is the gentle slope scenario, the scenario with the maximum slope value > 3% and ≤ 6% is the medium slope scenario, and the scenario with the maximum slope value > 6% is the steep slope scenario. The speed information in the short trip segment is extracted, the maximum vehicle speed of the short trip segment is calculated, and the maximum vehicle speeds are arranged in ascending order. The short trip segment is divided into congestion scenario, low speed scenario, medium speed scenario, and high speed scenario according to the maximum vehicle speed. The maximum speed ≤ 40 km / h is congestion, the maximum speed > 40 km / h and ≤ 60 km / h is low speed, the maximum speed > 60 km / h and ≤ 80 km / h is medium speed, and the maximum speed > 80 km / h is high speed.

[0088] Further, altitude (low altitude, medium altitude, high altitude), terrain (flat road, gentle slope, medium slope, steep slope), and speed (congested, low speed, medium speed, high speed) are combined based on historical operation data and historical geographical information data to obtain various scenario combinations, as follows: low altitude - flat road - congested, low altitude - flat road - low speed, low altitude - flat road - medium speed, low altitude - flat road - high speed, low altitude - gentle slope - congested, low altitude - gentle slope - low speed, low altitude - gentle slope - medium speed, low altitude - gentle slope - high speed, low altitude - medium slope - congested, low altitude - medium slope - low speed, low altitude - medium slope - medium speed, low altitude - medium slope - high speed, low altitude - steep slope - congested, low altitude - steep slope - low speed, low altitude - steep slope - medium speed, low altitude - steep slope - high speed; medium altitude - flat road - congested, medium altitude - flat road - low speed, medium altitude - flat road - medium speed, medium altitude - flat road - high speed, medium altitude - gentle slope - congested, medium altitude - gentle slope - low speed, medium altitude - gentle slope - medium speed, medium altitude - gentle slope - high speed, medium altitude - medium slope - congested, medium altitude - medium slope - low speed, medium altitude - medium slope - medium speed, medium altitude - medium slope - high speed, medium altitude - steep slope - congested, medium altitude - steep slope - low speed, medium altitude - steep slope - medium speed, medium altitude - steep slope - high speed; high altitude - flat road - congested, high altitude - flat road - low speed, high altitude - flat road - medium speed, high altitude - flat road - high speed, high altitude - gentle slope - congested, high altitude - gentle slope - low speed, high altitude - gentle slope - medium speed, high altitude - gentle slope - high speed, high altitude - medium slope - congested, high altitude - medium slope - low speed, high altitude - medium slope - medium speed, high altitude - medium slope - high speed, high altitude - steep slope - congested, high altitude - steep slope - low speed, high altitude - steep slope - medium speed, high altitude - steep slope - high speed. The short trip segments corresponding to each road scenario are stored in a preset road scenario database as the basic data for subsequent modeling.

[0089] Further, based on the short trip segments of various scenario combinations, the historical operation data and historical geographical information data are transformed into state variables. By reading the short trip segments corresponding to various scenario combinations, taking the vehicle speed of 5 km / h, the acceleration of 0.25 m / s 2 , and the slope of 0.5% as intervals, the vehicle speed, acceleration, and slope data are transformed into vehicle speed, acceleration, and slope state variables. The speed state has an interval of 5 km / h. For example, a vehicle speed of 0 is recorded as state 1, (0, 5] km / h is recorded as speed state 2, (5, 10] km / h is recorded as speed state 3, and so on, with a total of i speed states divided, where I is the maximum speed state; the acceleration state has an interval of 0.25 m / s 2 . Considering that the acceleration contains negative values, for example, the minimum acceleration is -2.91 m / s 2 , then [-3, -2.75] m / s 2 is recorded as acceleration state 1, (-2.75, -2.5] m / s 2For acceleration state 2, (-2.5, -2.25] m / s 2 For acceleration state 3, where the data when the acceleration is 0 is defined as a separate state, and so on, a total of j acceleration states are divided, where J is the maximum acceleration state; the slope state takes 0.5% as an interval. Considering that the slope contains negative values, for example, the minimum slope is -4.3 m / s 2 , then [-4.5, -4]% is recorded as slope state 1, (-4, -3.5]% is recorded as slope state 2, (-3.5, -3]% is recorded as slope state 3, where the data when the slope is 0 is defined as a separate state, and so on, a total of k slope states are divided, where K is the maximum slope state.

[0090] Furthermore, the dynamic adjustment of the state variable division includes, in the congestion scenario, statistically calculating the distribution proportion of each speed state (idle speed is not included in the statistics, that is, state 1 is not counted), arranging them in descending order, and successively accumulating the proportion until the accumulated value first > 50%. Record the number of speed states z included at this time. Further divide these z states into speed states with an interval of 2.5 km / h, and re - divide the speed states. The dynamic adjustment is shown in Table 1. The original states 3, 4, and 5 belong to the top 3 in the state sorting, and the cumulative proportion is 50.82%. Therefore, these three states are subdivided into speed intervals of 2.5 km / h. The dynamic state variable division of low - speed scenarios, medium - speed scenarios, and high - speed scenarios is the same as the above description.

[0091] Table 1

[0092]

[0093]

[0094] In the flat - road scenario, the slope is not divided into states; in the gentle - slope scenario, statistically calculate the distribution proportion of each slope state (the slope state corresponding to the idle speed is not included in the statistics), arrange them in descending order, and successively accumulate the proportion until the accumulated value first > 50%. Record the number of speed states j included at this time. Further divide these j states into slope states with an interval of 0.25%, and re - divide the slope states; the dynamic state variable division of the medium - slope scenario is the same as the above description; establish the corresponding state - transition matrix according to different scenarios. In the flat - road scenario, the slope is not divided into states. Use the two - dimensional Markov of speed and acceleration for working condition development, and convert the two - dimensional state variables of speed and acceleration into one - dimensional states according to the formula. The state s′ is defined as shown in the following formula:

[0095] s′ = i+(j - 1)×I;

[0096] Among them, s′ is the one-dimensional state of the speed and acceleration state variables, i is the number of the i-th speed state, j is the j-th acceleration state, and I is the maximum speed state.

[0097] For the non-flat road state, a two-dimensional Markov of speed, acceleration, and slope is used for driving condition development. The three-dimensional state variables of speed, acceleration, and slope are converted into a one-dimensional state according to the formula, and the state s is defined as shown in the following formula:

[0098] s = i + (j - 1)×I + (k - 1)×I×J;

[0099] Among them, s is the one-dimensional state of the speed, acceleration, and slope state variables, i is the number of the i-th speed state, j is the j-th acceleration state, I is the maximum speed state, k is the number of the k-th slope state, and J is the maximum acceleration state.

[0100] Furthermore, the transfer frequencies between different states of the vehicle are statistically counted, and the state transition probability matrix is calculated; the state transition probabilities of the vehicle in different road scenarios are described, and the state transition probability is defined as shown in the following formula:

[0101]

[0102] Among them, P ab is the transition probability from state s a to s b , f ab is the number of times of transitioning from state s a to s b , S is the maximum number of states, where a, b ∈ S and a, b are positive integers. By statistically counting all P ab , the state probability transition matrix P can be obtained, as shown in the following formula:

[0103]

[0104] It should be noted that multiple state sequences are generated based on the Markov model, and multiple state sequences are filtered through low-pass filtering to obtain multiple single driving conditions. And based on multiple scenario combinations, multiple driving conditions are combined to obtain a preset road scenario database. The duration of short travel segments in each road scenario is statistically counted, and its average duration T (seconds) is calculated, and the duration range is limited to T ± 0.2T, which is used as the time basis for the Markov chain to generate a single short travel segment, as Figure 3 shown. Figure 3Schematic diagram of the duration distribution of short segments of a full-scenario driving condition development method integrating geographical features provided by an embodiment of the present application. The average duration of short segments in the low-altitude - gentle slope - congestion scenario is calculated to be 57.38 seconds, and the generated duration range is 45.90 seconds to 68.86 seconds, which is rounded to 46 seconds to 69 seconds. Determine the total working condition generation duration, calculate the number of segments n required for generating the working condition according to the generation time of a single short segment, and round it; if generating a working condition with a duration of 600 seconds, the number of short segments to be generated is 10.45, which is rounded to 10. m}. That is, starting from the initial state s1, randomly select the next state s2 according to the corresponding probability distribution of P, and repeat the above process until a state sequence with a required length within the time of T±0.2T is generated.

[0105] Further, for the flat road scenario, decode the state sequence into two-dimensional state variables of speed and acceleration. The acceleration state decoding formula is:

[0106]

[0107] where j is the jth acceleration state, represents rounding down, s′ is the one-dimensional state of the speed and acceleration state variables, I is the maximum speed state.

[0108] The speed state decoding formula is:

[0109] i = s′-(j - 1)×I;

[0110] where i is the total number of speed states, s′ is the one-dimensional state of the speed and acceleration state variables, j is the jth acceleration state, and I is the maximum speed state.

[0111] For the non-flat road scenario, decode the state sequence into three-dimensional state variables of speed, acceleration, and slope. The slope state decoding formula is:

[0112]

[0113] where k is the kth slope state, s is the one-dimensional state of the speed, acceleration, and slope state variables, I is the maximum speed state, and J is the maximum acceleration state.

[0114] The acceleration state decoding formula is:

[0115]

[0116] Among them, j is the number of the j-th speed state, s is the one-dimensional state of the speed, acceleration, and slope state variables, k is the k-th slope state, I is the maximum speed state, and J is the maximum acceleration state.

[0117] The speed state decoding formula is:

[0118] i = s - (k - 1)×I×J - (j - 1)×I;

[0119] Among them, i is the number of the i-th speed state, s is the one-dimensional state of the speed or acceleration or slope state variable, k is the k-th slope state, I is the maximum speed state, J is the maximum acceleration state, and j is the number of speed states. As Figure 4 shown, Figure 4 is a schematic diagram of the speed state sequence of a full-scenario driving condition development method integrating geographical features provided by an embodiment of the present application.

[0120] Further, according to the obtained speed, acceleration, and slope state sequences, combined with the corresponding speed, acceleration, and slope intervals, speed, acceleration, and slope are randomly generated through uniform distribution. For the flat road scenario, slope random generation is not performed. For example, if the current speed state is state 2, a vehicle speed value is randomly generated within the range of the corresponding speed interval (0, 5] km / h. The speed sequence and slope sequence are smoothed by means of low-pass filtering to remove high-frequency noise and retain low-frequency components, making the vehicle speed and slope changes smoother. The speed and slope state sequences are transformed into a single driving condition, and the acceleration is calculated through the vehicle speed. Among them, the filtering coefficient ranges from 0 < α < 1, and the value here is 0.1; an example of the comparison result of the speed sequence before and after filtering is as Figure 5 shown, Figure 5 is a schematic diagram of the comparison before and after filtering of a full-scenario driving condition development method integrating geographical features provided by an embodiment of the present application; the generated single driving conditions are randomly selected and combined to obtain a preset road scenario database.

[0121] Optionally, in some embodiments, based on the current operating data and current geographical information data, a first alternative condition set that meets the preset characteristic parameter deviations is determined from the preset road scenario database, including: screening out from the preset road scenario database the driving conditions with the overall characteristic parameter deviation value from the current operating data and current geographical information data less than the first deviation threshold and each characteristic parameter deviation value less than the second preset threshold based on the speed parameter, acceleration parameter, slope parameter, and altitude parameter; generating a first alternative condition set according to the driving conditions with the overall characteristic parameter deviation value less than the first deviation threshold and each characteristic parameter deviation value less than the second preset threshold.

[0122] Among them, the first deviation threshold and the second preset threshold can be thresholds preset by the user, thresholds obtained through a finite number of experiments, or thresholds obtained through a finite number of computer simulations, and no specific limitation is made here.

[0123] It can be understood that based on the current operating data of the current vehicle, the current geographic information data, and the characteristic parameters of the corresponding preset road scene database, including average vehicle speed, average acceleration, average deceleration, acceleration ratio, deceleration ratio, constant speed ratio, idling ratio, average uphill slope, average downhill slope, uphill ratio, downhill ratio, small slope ratio and other parameters, speed parameters, acceleration parameters, slope parameters and altitude parameters are calculated. The speed distribution parameters are divided according to 5 km / h, and the slope distribution parameters are divided according to 0.5%. The working conditions with the overall characteristic parameter deviation value less than 5% and the deviation values of each characteristic parameter less than 10% are selected as the first alternative working condition set.

[0124] In step S203, based on the current operating data and the current geographic information data, the target driving condition of the vehicle is determined from the first alternative working condition set.

[0125] Among them, the target driving condition is the driving condition curve that can best represent the current vehicle operating state and the actual road characteristics after multi-level screening and optimization.

[0126] Optionally, in some embodiments, determining the target driving condition of the vehicle from the first alternative working condition set based on the current operating data and the current geographic information data includes: judging whether the vehicle is in a preset flat road condition based on the slope parameter in the current geographic information data; if the vehicle is in the preset flat road condition, then based on the speed parameter and the acceleration parameter in the current operating data, the driving condition with the smallest cumulative deviation from the speed distribution parameter of the current operating data is selected from the first alternative working condition set as the target driving condition; and, if the vehicle is not in the preset flat road condition, then the second alternative working condition set whose speed distribution parameter meets the preset cumulative deviation is selected from the first alternative working condition set, and the working condition with the smallest cumulative deviation from the slope distribution parameter of the current geographic information data is selected from the second alternative working condition set as the target driving condition.

[0127] The preset flat road condition refers to a road scene where the vehicle is driving with extremely small slope changes.

[0128] It can be understood that, based on the speed parameter, acceleration parameter, slope parameter, and altitude parameter of the current vehicle, if the absolute value of the average slope does not exceed 0.5%, the instantaneous slope fluctuation range is within ±0.3%, and the altitude change rate is less than 0.05 m / s, it is determined that the vehicle is in the preset flat road condition, and a condition with a cumulative deviation of the speed distribution parameter less than 20% is selected from the first alternative condition set, and the condition with the smallest deviation among them is selected as the target driving condition. If the vehicle is not in the preset flat road condition and there is no condition with a deviation less than 20% in the first alternative condition set, then the first 10% of the conditions with a smaller deviation ranking in the first alternative condition set are selected as the second alternative condition set, and the condition with the smallest cumulative deviation of the slope distribution parameter is selected from the second alternative condition set as the target driving condition.

[0129] According to the full-scenario driving condition development method integrating geographical features proposed in the embodiments of the present application, the current operation data of the vehicle and the current geographical information data of the location where the vehicle is located are obtained; based on the current operation data and the current geographical information data, a first alternative condition set that meets the preset feature parameter deviation is determined from a preset road scenario database, where the preset road scenario database is obtained based on a dynamically adjusted multi-dimensional Markov model, and the dynamically adjusted multi-dimensional Markov model is obtained through the division of state variables dynamically generated by historical operation data and historical geographical information data; based on the current operation data and the current geographical information data, the target driving condition of the vehicle is determined from the first alternative condition set. Thus, by collecting vehicle operation data and geographical features to divide road scenarios, constructing a dynamically adjusted multi-dimensional Markov model, and generating full-scenario driving conditions through low-pass filtering and multi-level feature screening, the problems of lack of geographical feature integration, incomplete speed segment coverage, and insufficient accuracy of condition generation in the related art are solved, providing a scientific basis for vehicle design, road planning, and energy conservation and emission reduction.

[0130] Next, a full-scenario driving condition development device integrating geographical features proposed in the embodiments of the present application will be described with reference to the accompanying drawings.

[0131] Figure 6 It is a block diagram of a full-scenario driving condition development device integrating geographical features according to an embodiment of the present application.

[0132] As Figure 6 shown, the full-scenario driving condition development device 10 integrating geographical features includes: an acquisition module 100, an alternative module 200, and a determination module 300.

[0133] Among them, the acquisition module 100 is used to acquire the current operation data of the vehicle and the current geographical information data of the location where the vehicle is located;

[0134] An alternative module 200 is configured to determine a first set of alternative operating conditions that meet preset characteristic parameter deviations from a preset road scenario database based on current operating data and current geographic information data, where the preset road scenario database is obtained based on a dynamically adjusted multi-dimensional Markov model, and the dynamically adjusted multi-dimensional Markov model is obtained through the division of state variables dynamically generated by historical operating data and historical geographic information data;

[0135] A determination module 300 is configured to determine a target driving condition of the vehicle from the first set of alternative operating conditions based on the current operating data and the current geographic information data.

[0136] Optionally, before determining the first set of alternative operating conditions that meet the preset characteristic parameter deviations from the preset road scenario database based on the current operating data and the current geographic information data, the alternative module 200 is further configured to: obtain the historical operating data of the vehicle and the historical geographic information data corresponding to the historical operating data; obtain multiple scenario combinations based on the historical operating data and the historical geographic information data; transform the historical operating data and the historical geographic information data into state variables based on short travel segments of the multiple scenario combinations, dynamically adjust the division of the state variables, and construct a dynamically adjusted multi-dimensional Markov model; generate multiple state sequences based on the Markov model, and screen the multiple state sequences through low-pass filtering to obtain multiple single driving conditions, and combine the multiple driving conditions based on the multiple scenario combinations to obtain the preset road scenario database.

[0137] Optionally, the alternative module 200 is specifically configured to: determine multiple driving speed intervals based on the historical operating data; determine multiple driving altitude intervals and multiple driving slope intervals based on the historical geographic information data; combine the multiple driving speed intervals, the multiple driving altitude intervals, and the multiple driving slope intervals to obtain multiple scenario combinations.

[0138] Optionally, the calculation formula for low-pass filtering is:

[0139] y c =α×x c +(1 - α)×y c-1 ;

[0140] where y c is the value of the filtered signal at the c-th moment, α is the filtering coefficient, and x c is the value of the original input vehicle speed or slope sequence at the c-th moment.

[0141] Optionally, the current operating data includes speed parameters and acceleration parameters, and the current geographic information data includes slope parameters and altitude parameters.

[0142] Optionally, the alternative module 200 is specifically configured to: screen, from a preset road scenario database, a driving condition whose deviation value of the overall characteristic parameters from the current operation data and the current geographic information data is less than a first deviation threshold and whose deviation value of each characteristic parameter is less than a second preset threshold based on the speed parameter, the acceleration parameter, the slope parameter, and the altitude parameter; generate a first alternative condition set according to the driving conditions whose deviation value of the overall characteristic parameters is less than the first deviation threshold and whose deviation value of each characteristic parameter is less than the second preset threshold.

[0143] Optionally, the determination module 300 is specifically configured to: determine whether the vehicle is in a preset flat road condition based on the slope parameter in the current geographic information data; if the vehicle is in the preset flat road condition, screen, from the first alternative condition set, a driving condition with the smallest cumulative deviation of the speed distribution parameters from the current operation data based on the speed parameter and the acceleration parameter in the current operation data as the target driving condition; and if the vehicle is not in the preset flat road condition, screen a second alternative condition set whose speed distribution parameters from the current operation data meet a preset cumulative deviation from the first alternative condition set, and screen, from the second alternative condition set, a condition with the smallest cumulative deviation of the slope distribution parameters from the current geographic information data as the target driving condition.

[0144] It should be noted that the foregoing explanation of the embodiments of the full-scenario driving condition development method for fusing geographic features also applies to the full-scenario driving condition development device for fusing geographic features in this embodiment, and will not be repeated here.

[0145] According to the full-scenario driving condition development device for fusing geographic features provided by the embodiments of the present application, the current operation data of the vehicle and the current geographic information data of the location where the vehicle is located are obtained; based on the current operation data and the current geographic information data, a first alternative condition set that meets the preset characteristic parameter deviation is determined from a preset road scenario database, where the preset road scenario database is obtained based on a dynamically adjusted multi-dimensional Markov model, and the dynamically adjusted multi-dimensional Markov model is obtained through the division of state variables dynamically generated by historical operation data and historical geographic information data; based on the current operation data and the current geographic information data, the target driving condition of the vehicle is determined from the first alternative condition set. Thus, by collecting vehicle operation data and geographic features to divide road scenarios, constructing a dynamically adjusted multi-dimensional Markov model, and generating full-scenario driving conditions through low-pass filtering and multi-level feature screening, the problems in the related art such as lack of geographic feature fusion, incomplete coverage of speed segments, and insufficient accuracy of condition generation are solved, providing a scientific basis for vehicle design, road planning, and energy conservation and emission reduction.

[0146] Figure 7 The structural schematic diagram of the electronic device provided by the embodiments of the present application. The electronic device may include:

[0147] A memory 701, a processor 702, and a computer program stored on the memory 701 and executable on the processor 702.

[0148] When the processor 702 executes the program, it implements the full-scenario driving condition development method for fusing geographical features provided in the above embodiments.

[0149] Furthermore, the electronic device further includes:

[0150] A communication interface 703 for communication between the memory 701 and the processor 702.

[0151] The memory 701 is used to store a computer program executable on the processor 702.

[0152] The memory 701 may include a high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0153] If the memory 701, the processor 702, and the communication interface 703 are implemented independently, the communication interface 703, the memory 701, and the processor 702 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0154] Optionally, in a specific implementation, if the memory 701, the processor 702, and the communication interface 703 are integrated on a single chip, the memory 701, the processor 702, and the communication interface 703 can communicate with each other through an internal interface.

[0155] The processor 702 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0156] The embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the above-mentioned full-scenario driving condition development method integrating geographical features is implemented.

[0157] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or N embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0158] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0159] Any process or method description in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more N executable instructions for implementing a customized logical function or process. The scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the art of the embodiments of the present application.

[0160] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following well-known technologies in the art or a combination of them can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits with suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0161] Those of ordinary skill in the art can understand that all or part of the steps carried out in implementing the above-mentioned embodiment methods can be completed by instructing relevant hardware through a program. The said program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

Claims

1. A full-scenario driving condition development method integrating geographical features, characterized in that, The method includes the following steps: Obtain the current operation data of the vehicle and the current geographical information data of the location where the vehicle is located; Based on the current operation data and the current geographical information data, determine a first set of alternative operating conditions that meet the preset characteristic parameter deviations from a preset road scenario database, where the preset road scenario database is obtained based on a dynamically adjusted multi-dimensional Markov model, and the dynamically adjusted multi-dimensional Markov model is obtained through the division of state variables dynamically generated by historical operation data and historical geographical information data; Based on the current operation data and the current geographical information data, determine the target driving condition of the vehicle from the first set of alternative operating conditions.

2. The method according to claim 1, wherein Before determining, based on the current operation data and the current geographical information data, a first set of alternative operating conditions that meet the preset characteristic parameter deviations from a preset road scenario database, it further includes: Obtain the historical operation data of the vehicle and the historical geographical information data corresponding to the historical operation data; Obtain multiple scenario combinations based on the historical operation data and the historical geographical information data; Based on short travel segments of the multiple scenario combinations, transform the historical operation data and the historical geographical information data into state variables, dynamically adjust the division of the state variables, and construct the dynamically adjusted multi-dimensional Markov model; Generate multiple state sequences based on the Markov model, and screen the multiple state sequences through low-pass filtering to obtain multiple single driving conditions, and based on the multiple scenario combinations, combine the multiple driving conditions to obtain the preset road scenario database.

3. The method according to claim 2, wherein The obtaining multiple scenario combinations based on the historical operation data and the historical geographical information data includes: Based on the historical operation data, determine multiple driving speed intervals; Based on the historical geographical information data, determine multiple driving altitude intervals and multiple driving slope intervals; Based on the multiple driving speed intervals, the multiple driving altitude intervals, and the multiple driving slope intervals, combine to obtain the multiple scenario combinations.

4. The method according to claim 2, characterized in that, The calculation formula of the low-pass filtering is: y c = α × x c + (1 - α) × y c-1 ; where y c is the value of the filtered signal at the c-th moment, α is the filtering coefficient, and x c is the value of the original input vehicle speed or slope sequence at the c-th moment.

5. The method according to claim 1, wherein The current operation data includes a speed parameter and an acceleration parameter, and the current geographical information data includes a slope parameter and an altitude parameter.

6. The method according to claim 5, characterized in that, The determining, based on the current operation data and the current geographical information data, a first set of alternative operating conditions that meet the preset characteristic parameter deviations from a preset road scenario database includes: Based on the speed parameter, the acceleration parameter, the slope parameter, and the altitude parameter, screen out driving conditions from the preset road scenario database whose overall characteristic parameter deviation value from the current operation data and the current geographical information data is less than a first deviation threshold and whose characteristic parameter deviation values are less than a second preset threshold; Generate the first set of alternative operating conditions according to the driving conditions whose overall characteristic parameter deviation value is less than the first deviation threshold and whose characteristic parameter deviation values are less than the second preset threshold.

7. The method according to claim 6, wherein The determining, based on the current operation data and the current geographical information data, the target driving condition of the vehicle from the first set of alternative operating conditions includes: Based on the slope parameter in the current geographic information data, determine whether the vehicle is in a preset flat road condition; If the vehicle is in the preset flat road condition, based on the speed parameter and acceleration parameter in the current operation data, select the driving condition with the smallest cumulative deviation from the speed distribution parameter of the current operation data from the first alternative condition set as the target driving condition; And, if the vehicle is not in the preset flat road condition, select a second alternative condition set whose speed distribution parameter satisfies a preset cumulative deviation from the current operation data from the first alternative condition set, and select the condition with the smallest cumulative deviation from the slope distribution parameter of the current geographic information data from the second alternative condition set as the target driving condition.

8. A full-scenario driving condition development device integrating geographical features, characterized in that Comprising: An acquisition module, configured to acquire the current operation data of the vehicle and the current geographic information data of the location where the vehicle is located; An alternative module, configured to determine a first alternative condition set that satisfies a preset characteristic parameter deviation from a preset road scene database based on the current operation data and the current geographic information data, wherein the preset road scene database is obtained based on a dynamically adjusted multi-dimensional Markov model, and the dynamically adjusted multi-dimensional Markov model is obtained by dividing state variables dynamically generated by historical operation data and historical geographic information data; A determination module, configured to determine the target driving condition of the vehicle from the first alternative condition set based on the current operation data and the current geographic information data.

9. An electronic device, characterized in that, Comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the method for developing a full-scenario driving condition integrating geographic features according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to be used to implement the method for developing a full-scenario driving condition integrating geographic features according to any one of claims 1-7.

Images