Vehicle cruise control method and device and storage medium
By acquiring and processing platform cruise data, training road conditions models, and optimizing vehicle cruise control, the problem of low vehicle cruise fuel saving rate under congested road conditions is solved, and the operating costs of commercial vehicles are reduced.
Patent Information
- Application Number
- CN202411222707.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-11-12
AI Technical Summary
The existing predicted cruise control scheme has a low fuel saving rate when cruising under congested road conditions and requires the addition of multiple sensors, resulting in high operating costs for commercial vehicles.
By obtaining platform cruise data for preprocessing, training road conditions models, obtaining target congestion levels, and calculating predicted cruise optimization information based on preset planning optimization algorithms, reducing the number of brakes and shifting times, and realizing vehicle cruise control.
Reduce fuel consumption in congested road conditions, reduce the number of vehicle cruising and backward times, and reduce the operating costs of commercial vehicles.
Smart Images

Figure CN118928394A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle intelligent driving technology, and in particular to a vehicle cruise control method, device and storage medium. Background Art
[0002] The fuel cost of commercial vehicles has a significant impact on vehicle operations, so vehicle fuel-saving control is very important. The existing predictive cruise control scheme allows the vehicle speed to fluctuate within a certain range by considering the slope information of the road ahead, and makes full use of the kinetic energy of the vehicle and the potential energy of the road, which can effectively avoid fuel-inefficient driving behavior.
[0003] The current predictive cruise control solution can improve fuel efficiency in non-congested road conditions compared to driver driving; however, in congested road conditions, due to the need to frequently brake to maintain a safe distance from the vehicle in front, repeated forward and backward cruising, the fuel efficiency is lower than that of driver driving. In addition, the existing predictive cruise control solution is based on equipment such as radar and cameras, and is not suitable for low-cost commercial vehicles.
[0004] Therefore, the existing solution has a low fuel saving rate when the vehicle is cruising in congested road conditions, and requires the addition of various sensors, which leads to high operating costs for commercial vehicles. Summary of the invention
[0005] The embodiments of the present application provide a vehicle cruise control method, device and storage medium to solve the defects of the existing solution in that the fuel saving rate is low when the vehicle is cruising in congested road conditions, and various sensors need to be added, resulting in high operating costs for commercial vehicles.
[0006] In a first aspect, an embodiment of the present application provides a vehicle cruise control method, comprising:
[0007] Acquire platform cruise data, pre-process the platform cruise data to obtain a training data set, train the training data set by a clustering algorithm to obtain a road condition model, the road condition model is used to indicate a congestion level of a road condition, and the platform cruise data is used to indicate a plurality of fleet data;
[0008] Acquire current driving information and cruise control speed of the vehicle, input the current driving information into the road condition model to acquire a target congestion level, acquire coordinated vehicle information according to the target congestion level and the cruise control speed, and acquire predicted cruise optimization information according to the coordinated vehicle information based on a preset planning optimization algorithm;
[0009] Acquire initial cruise state information and braking state information, and acquire initial cruise demand information according to the initial cruise state information, and acquire predicted braking information according to the braking state information, wherein the initial cruise state information is used to indicate whether the vehicle enters a first cruise state, and the braking state information is used to indicate whether the vehicle enters a braking state;
[0010] Predicted cruise control information is acquired according to the predicted cruise optimization information, the initial cruise demand information and the predicted braking information, and a cruise control torque is calculated based on the predicted cruise control information. Vehicle cruising is achieved by outputting the cruise control torque.
[0011] In a possible implementation manner, a download interval time of each vehicle data in the fleet data is obtained, wherein the vehicle data includes vehicle speed, braking percentage, cruising speed and road positioning signal, and the road positioning signal is used to indicate different road categories;
[0012] If the download interval is greater than a preset time, the fleet data is marked as sparse fleet data, and data interpolation processing is performed based on the data of each vehicle in the sparse fleet data to generate qualified fleet data;
[0013] If the download interval is less than a preset time, marking the fleet data as qualified fleet data;
[0014] The qualified fleet data in the platform cruise data is obtained, and the qualified fleet data is used as the training data set.
[0015] In a possible implementation manner, it is detected whether there are non-team vehicle in the sparse team data, and if not, the sparse team data is used as the qualified team data;
[0016] If so, the average vehicle speed is obtained according to the speed of each vehicle in the sparse vehicle fleet data, and the sparse vehicle fleet data is interpolated based on the average vehicle speed to generate new vehicle fleet data, and the new vehicle fleet data is used as the qualified vehicle fleet data.
[0017] In a possible implementation manner, a predicted cruising reference speed is obtained according to the target congestion level, and the coordinated vehicle speed upper limit and the coordinated vehicle speed lower limit are obtained according to the predicted cruising reference speed;
[0018] Based on the preset map, according to the current driving information, the current vehicle speed, the predicted slope angle and the predicted gear are obtained, and the predicted cruise basic acceleration is obtained according to the predicted slope angle and the predicted gear, the vehicle speed deviation acceleration coefficient is obtained according to the current vehicle speed and the predicted cruise reference speed, and the predicted coasting acceleration coefficient is obtained according to the vehicle weight;
[0019] The product of the predicted cruise basic acceleration, the vehicle speed deviation acceleration coefficient and the predicted coasting acceleration coefficient is used as the coordinated acceleration.
[0020] In a possible implementation manner, if the target congestion level is basically unblocked or unblocked, the cruise speed is used as the predicted cruise reference speed, and the cruise speed is used to indicate the cruising speed set by the driver;
[0021] If the target congestion level is severe congestion, moderate congestion or mild congestion, the average congestion vehicle speed within the preset congestion time before the target congestion level is obtained, and the average congestion vehicle speed is used as the predicted cruise reference speed.
[0022] In a possible implementation, a congestion impact upper limit coefficient and a predicted cruise allowable upper deviation threshold are obtained according to the target congestion level, an upper limit product of the congestion impact upper limit coefficient and the predicted cruise allowable upper deviation threshold is obtained, and a sum of the upper limit product and an upper limit of the predicted cruise reference speed is used as the coordinated vehicle speed upper limit;
[0023] The congestion impact lower limit coefficient and the predicted cruise allowable lower deviation threshold are obtained according to the target congestion level, the lower limit product of the congestion impact lower limit coefficient and the predicted cruise allowable lower deviation threshold is obtained, and the sum of the lower limit product and the lower limit of the predicted cruise reference speed is used as the coordinated vehicle speed lower limit.
[0024] In a possible implementation manner, if the initial cruise state information indicates that the vehicle enters the first cruise state, and the cruise speed is greater than the current vehicle speed, the current road section and the gear position at the time of entering cruise are obtained according to the current driving information, and the gear position at the time of entering cruise and the highest gear are polled to obtain the initial cruise required gear position;
[0025] If the current road section is a flat road or an uphill road section, the cruise speed is used as the initial cruise required speed;
[0026] If the current road section is a downhill section, the vehicle speed at the bottom of the slope is calculated based on the current vehicle speed. If the vehicle speed at the bottom of the slope is less than the cruise speed, the cruise speed is used as the initial cruise requirement speed. If the vehicle speed at the bottom of the slope is equal to or greater than the cruise speed, the initial cruise requirement speed is obtained through a preset vehicle speed optimization algorithm.
[0027] In a possible implementation manner, if the braking state information indicates that the vehicle enters a braking state, the current vehicle speed is obtained according to the current driving information, and the predicted braking demand gear is obtained according to the current vehicle speed;
[0028] Obtaining a predicted downhill slope through a preset map, and obtaining a maximum free-gliding speed of the downhill section according to the predicted downhill slope and the target congestion level;
[0029] The maximum braking force of the vehicle is obtained, and the maximum braking capacity speed is calculated based on the maximum braking force of the vehicle; if the maximum braking capacity speed is greater than the maximum free sliding speed in the downhill section, the maximum free sliding speed in the downhill section is used as the predicted braking demand speed; otherwise, the maximum braking capacity speed is used as the predicted braking demand speed.
[0030] In a second aspect, an embodiment of the present application provides a vehicle cruise control device, comprising:
[0031] an acquisition module, used to acquire platform cruise data, pre-process the platform cruise data to acquire a training data set, train the training data set by a clustering algorithm to acquire a road condition model, wherein the road condition model is used to indicate a congestion level of a road condition, and the platform cruise data is used to indicate data of multiple fleets;
[0032] a processing module, configured to obtain current driving information and a cruise control speed of the vehicle, input the current driving information into the road condition model to obtain a target congestion level, obtain coordinated vehicle information according to the target congestion level and the cruise control speed, and obtain predicted cruise optimization information according to the coordinated vehicle information based on a preset planning optimization algorithm;
[0033] The processing module is further used to obtain initial cruising state information and braking state information, and obtain initial cruising demand information according to the initial cruising state information, and obtain predicted braking information according to the braking state information, wherein the initial cruising state information is used to indicate whether the vehicle enters a first cruising state, and the braking state information is used to indicate whether the vehicle enters a braking state;
[0034] The control module is used to obtain predicted cruise control information according to the predicted cruise optimization information, the initial cruise demand information and the predicted braking information, and calculate and obtain the cruise control torque based on the predicted cruise control information, and realize vehicle cruising by outputting the cruise control torque.
[0035] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementations of the first aspect.
[0036] The vehicle cruise control method provided in the embodiment of the present application performs preprocessing based on the acquired platform cruise data to obtain a training data set, trains the training data set through a clustering algorithm to obtain a road condition model, obtains a target congestion level through the road condition model, obtains coordinated vehicle information according to the target congestion level and the cruise control speed, obtains predicted cruise optimization information according to the coordinated vehicle information based on a preset planning optimization algorithm, reduces the number of forward and backward cruises in congested road conditions, obtains initial cruise demand information according to initial cruise state information, obtains predicted braking information according to braking state information, obtains predicted cruise control information according to the predicted cruise optimization information, the initial cruise demand information and the predicted braking information, reduces the number of braking and shifting, calculates and obtains the cruise control torque based on the predicted cruise control information, and realizes vehicle cruising by outputting the cruise control torque, thereby reducing high fuel consumption when cruising under congested road conditions, thereby reducing the operating cost of commercial vehicles. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0038] Figure 1 Schematic diagram of the vehicle cruise control method provided in this application Figure 1 ;
[0039] Figure 2 Schematic diagram of the vehicle cruise control method provided in this application Figure 2 ;
[0040] Figure 3 A schematic diagram of the vehicle cruise control architecture provided for this application;
[0041] Figure 4 Schematic diagram of the vehicle cruise control method provided in this application Figure 3 ;
[0042] Figure 5 A schematic diagram of the structure of a vehicle cruise control device provided in this application;
[0043] Figure 6 A schematic diagram of the structure of the electronic device provided in this application.
[0044] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0045] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0046] According to the requirements of the fourth-stage fuel consumption regulations and the current situation that commercial vehicle fuel costs account for a high proportion of operating costs, vehicle fuel-saving control is very important. Traditional commercial vehicle cruise control usually considers maintaining a constant vehicle speed and ignores the influence of road and traffic information; as a result, when the vehicle encounters conditions with undulating road slopes, in order to maintain a constant vehicle speed, it will accelerate sharply when going uphill and decelerate sharply when going downhill, resulting in fuel-inefficient driving effects. The predictive cruise control solution combines the slope information of the road ahead, allows the vehicle speed to fluctuate within a certain range, and makes full use of the kinetic energy of the vehicle and the potential energy of the road, which can effectively avoid fuel-inefficient driving behavior.
[0047] The current predictive cruise control solution can improve fuel savings by 4-6% in non-congested road conditions compared to driver driving; however, in congested road conditions, due to the need to frequently brake to maintain a safe distance from the vehicle in front, repeated forward and backward cruising, the fuel savings are lower than that of driver driving. In addition, existing predictive cruise control solutions are generally based on radar, cameras, lane lines, etc. to first determine congested road conditions, and then adjust the threshold for the adaptive cruise algorithm. They are not suitable for low-cost commercial vehicles without radar and cameras.
[0048] Therefore, the present application provides a vehicle cruise control method, which performs preprocessing based on the acquired platform cruise data to obtain a training data set, trains the training data set through a clustering algorithm to obtain a road condition model, obtains a target congestion level through the road condition model, obtains coordinated vehicle information according to the target congestion level and the cruise control speed, obtains predicted cruise optimization information according to the coordinated vehicle information based on a preset planning optimization algorithm, reduces the number of forward and backward cruises in congested road conditions, obtains initial cruise demand information according to initial cruise state information, obtains predicted braking information according to braking state information, obtains predicted cruise control information according to the predicted cruise optimization information, the initial cruise demand information and the predicted braking information, reduces the number of braking and shifting, calculates and obtains the cruise control torque based on the predicted cruise control information, and realizes vehicle cruising by outputting the cruise control torque, thereby reducing high fuel consumption when cruising under congested road conditions, thereby reducing the operating cost of commercial vehicles.
[0049] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0050] Figure 1 The process diagram of the vehicle cruise control method provided in this application is as follows Figure 1 ,like Figure 1 As shown, the method includes:
[0051] S101, obtaining platform cruise data, preprocessing the platform cruise data to obtain a training data set, training the training data set by a clustering algorithm to obtain a road condition model, the road condition model is used to indicate a congestion level of a road condition, and the platform cruise data indicates a plurality of fleet data;
[0052] Specifically, multiple different fleet data are obtained through traffic big data platforms such as Smart Pass, where the fleet data includes multiple vehicle data. Each vehicle data is used to indicate the passing speed, braking percentage, cruise speed, GPS signal and current slope of each vehicle in the fleet. The congestion levels include severe congestion, moderate congestion, mild congestion, basically unobstructed and unobstructed. Each congestion level corresponds to 10-0, and the larger the value, the more congested it is. Each degree corresponds to a numerical interval of 2, that is, 0-2 represents unobstructed traffic, and 8-10 represents severe congestion. Overlapping values are attributed to a large range of congestion levels;
[0053] Furthermore, before preprocessing the platform cruise data, it is detected whether the vehicles in the fleet in the platform cruise data are all on the same straight road. If so, the fleet data is preprocessed. If not, that is, if the first vehicle to the last vehicle in the fleet are not on the same straight road, no data preprocessing is performed.
[0054] S102, obtaining current driving information and cruise control speed of the vehicle, inputting the current driving information into the road condition model to obtain a target congestion level, obtaining coordinated vehicle information according to the target congestion level and the cruise control speed, and obtaining predicted cruise optimization information according to the coordinated vehicle information based on a preset planning optimization algorithm;
[0055] Specifically, after obtaining the road condition model, the current driving information including the vehicle speed, braking percentage, cruise control speed and GPS is obtained, wherein the GPS indicates the road positioning signal, and the current driving information is input into the road condition model to obtain the target congestion level, and the coordinated vehicle information is calculated according to the target congestion level;
[0056] Among them, the coordinated vehicle information also includes the coordinated gear shift speed. Based on the coordinated upper and lower limits of the vehicle speed, the coordinated acceleration and the coordinated gear shift speed, the predicted cruise optimization information is obtained through road network reconstruction, vehicle modeling and preset planning optimization algorithm. Among them, the predicted cruise optimization information indicates the predicted cruise optimization vehicle speed and the predicted cruise optimization gear.
[0057] S103, acquiring initial cruise state information and braking state information, and acquiring initial cruise demand information according to the initial cruise state information, and acquiring predicted braking information according to the braking state information, wherein the initial cruise state information is used to indicate whether the vehicle enters a first cruise state, and the braking state information is used to indicate whether the vehicle enters a braking state;
[0058] Specifically, the initial cruise state information and braking state information of the current vehicle settings are obtained, wherein the initial cruise demand information includes the initial cruise demand vehicle speed and the initial cruise demand gear, and the braking state information includes the predicted braking demand vehicle speed and the predicted braking demand gear, wherein for the predicted braking demand gear, if the braking state information indicates that the vehicle enters a braking state, the predicted braking demand gear is obtained based on the braking optimal engine speed and the current vehicle speed.
[0059] S104, acquiring predicted cruise control information according to the predicted cruise optimization information, the initial cruise demand information and the predicted braking information, and calculating and acquiring a cruise control torque based on the predicted cruise control information, and achieving vehicle cruising by outputting the cruise control torque;
[0060] Specifically, the predicted cruise optimization information, initial cruise demand information and predicted braking information are coordinated and calculated to obtain the predicted cruise control information. The predicted cruise control information includes the predicted cruise vehicle speed, the predicted cruise gear and the predicted cruise gear control state. The torque is calculated based on the predicted cruise vehicle speed to obtain the cruise control torque, and the cruise control torque is output through the actuator to achieve cruise control of the vehicle.
[0061] The vehicle cruise control method provided in the embodiment of the present application performs preprocessing based on the acquired platform cruise data to obtain a training data set, trains the training data set through a clustering algorithm to obtain a road condition model, obtains a target congestion level through the road condition model, obtains coordinated vehicle information according to the target congestion level and the cruise control speed, obtains predicted cruise optimization information according to the coordinated vehicle information based on a preset planning optimization algorithm, reduces the number of forward and backward cruises in congested road conditions, obtains initial cruise demand information according to initial cruise state information, obtains predicted braking information according to braking state information, obtains predicted cruise control information according to the predicted cruise optimization information, the initial cruise demand information and the predicted braking information, reduces the number of braking and shifting, calculates and obtains the cruise control torque based on the predicted cruise control information, and realizes vehicle cruising by outputting the cruise control torque, thereby reducing high fuel consumption when cruising under congested road conditions, thereby reducing the operating cost of commercial vehicles.
[0062] Figure 2 The process diagram of the vehicle cruise control method provided in this application is as follows Figure 2 , Figure 3 The vehicle cruise control architecture diagram provided for this application is combined with Figure 2 and Figure 3 As shown, in this embodiment Figure 2 Based on the embodiment, a vehicle cruise control method is described in detail, and the method includes:
[0063] S201, obtaining platform cruise data indicating a plurality of fleet data, and obtaining a download interval time of each vehicle data in the fleet data;
[0064] Specifically, after obtaining the platform cruise data, the download interval of each vehicle data in each fleet data is used to detect whether the data source of the corresponding fleet data is sparse. If the data source is sparse, only the vehicle data in the fleet is obtained, and the data of each vehicle in the fleet are interpolated and combined to obtain the original value of the training data.
[0065] S202: if the download interval is greater than a preset time, marking the fleet data as sparse fleet data, and performing data interpolation processing based on the data of each vehicle in the sparse fleet data to generate qualified fleet data;
[0066] Specifically, for each fleet data, if there is a vehicle whose download interval is greater than a preset time, such as one second, the fleet data is marked as sparse fleet data, wherein the vehicle data includes vehicle speed, braking percentage, cruising speed and road positioning signal, i.e., GPS. The road positioning signal is used to indicate different road categories. According to the road positioning signal, speed and vehicle spacing of each vehicle in the fleet, it is determined whether other non-team vehicles are added to the fleet, that is, whether there are non-team vehicles in the sparse fleet data. If not, the original data data1, data2...data uploaded by each vehicle in the fleet from the first vehicle to the last vehicle on the same road at the same time are saved. n , that is, the sparse fleet data is regarded as qualified fleet data;
[0067] Furthermore, if there are non-team vehicles in the sparse team, save the original data data1, data2, ..., data uploaded by each vehicle in the team from the first vehicle to the last vehicle on the same road at the same time m , where the original data m Indicate the data of the last vehicle in the fleet, then obtain the average speed according to the speed of each vehicle in the sparse fleet data, and interpolate the sparse fleet data according to the average speed according to the GPS position, speed and vehicle spacing of each vehicle in the fleet to generate new fleet data after filling data1, data2...data n , and use the new fleet data as qualified fleet data {data n ,data n-1 ...data1}.
[0068] S203, if the download interval is less than a preset time, marking the fleet data as qualified fleet data;
[0069] Specifically, for each fleet data, if there are vehicles whose download interval is less than or equal to the preset time, such as one second, the data source interval is considered normal, and the data downloaded from the Smart Communication Platform is directly used as the original value of the training data.
[0070] S204, obtaining the data of each qualified fleet in the platform cruise data, and using the data of each qualified fleet as a training data set, and training the training data set by a clustering algorithm to obtain a road condition model;
[0071] Specifically, after obtaining the training data set, the principal component analysis method is used to perform data correlation analysis on the training data set to obtain the training input related to the judgment of road congestion under cruising conditions, that is, the speed, braking percentage, cruise speed and GPS of each vehicle, among which GPS is used as a classification for different road identification to distinguish different clustering algorithm training;
[0072] Furthermore, during training, the training data set is divided according to the presence of congestion degree labels in the training data set. The data with congestion degree labels are stored as the first training data set, and the data without congestion degree labels are stored as the second training data set. The second training data set is normalized and then trained using the k-means method. The first training data set is normalized and then the trained k-means method clustering center is tested and verified to obtain a road condition model, thereby achieving low-cost road condition congestion degree recognition with different data sparsity levels under a vehicle configuration without a radar camera.
[0073] S205, obtaining current driving information and cruise control speed of the vehicle, and inputting the current driving information into the road condition model to obtain a target congestion level;
[0074] Specifically, after obtaining the road condition model, the cruise control speed and current driving information periodically collected by the controller are obtained, namely the vehicle speed, braking percentage, cruise control speed and GPS signal, and the cruise control speed and current driving information are normalized to obtain characteristic parameters, which are then input into the road condition model to obtain the target congestion level.
[0075] S206: If the target congestion level is basically unblocked or unblocked, the cruise speed is used as the predicted cruise reference speed, and the cruise speed is used to indicate the cruise speed set by the driver;
[0076] Specifically, after obtaining the target congestion level, the predicted cruise reference speed is obtained according to the target congestion level. When the congestion level is basically unobstructed or unobstructed, the predicted cruise reference speed is the fixed-speed cruise speed, that is, the reference speed under unobstructed road conditions is the fixed-speed cruise speed set by the driver.
[0077] S207: If the target congestion level is severe congestion, moderate congestion or mild congestion, obtaining an average congestion vehicle speed during a preset congestion time before the target congestion level, and using the average congestion vehicle speed as the predicted cruise reference speed;
[0078] Specifically, when the congestion level is severe congestion, moderate congestion or mild congestion, the predicted cruise reference speed is the average speed of the previous preset congestion time under the current congestion level, such as 10s, that is, the average congestion speed. The preset congestion time can of course also be set to other reasonable time periods, as long as it can indicate the average speed of the previous period under the current congestion level.
[0079] S208, obtaining the coordinated vehicle speed upper limit, the coordinated vehicle speed lower limit and the coordinated acceleration according to the predicted cruise reference vehicle speed;
[0080] Specifically, after obtaining the predicted cruise reference speed, for the coordinated speed upper limit, the congestion impact upper limit coefficient and the predicted cruise allowable upper deviation threshold are obtained according to the target congestion level, and the upper limit product of the congestion impact upper limit coefficient and the predicted cruise allowable upper deviation threshold is obtained. The upper limit product and the upper limit of the predicted cruise reference speed are used as the coordinated speed upper limit, and are obtained through the coordinated speed upper limit calculation formula. The coordinated speed upper limit calculation formula is as follows:
[0081] V Up =V Ref +fac 拥堵影响上限 ×V UpDe ;
[0082] Among them, V Ref is the predicted cruising reference speed, fac 拥堵影响上限 To allow the upper threshold correction factor, V UpDe For predicting the upper deviation threshold allowed by cruise control, the correction coefficient of the upper deviation threshold allowed is obtained from the upper deviation threshold correction coefficient table according to the target congestion level, the upper deviation threshold correction coefficient table pre-stores a negative correlation mapping relationship between the upper deviation threshold correction coefficient and the target congestion level, and the calibration range of the upper deviation threshold correction coefficient allowed is between [0,1], the upper deviation threshold allowed by cruise control is obtained from the upper deviation threshold table according to the target congestion level and the cruise speed, and the upper deviation threshold table pre-stores a negative correlation mapping relationship between the upper deviation threshold and the target congestion level;
[0083] Furthermore, for the lower speed limit after coordination, the lower limit coefficient of congestion impact and the lower deviation threshold of predicted cruise are obtained according to the target congestion level, the lower limit product of the lower limit coefficient of congestion impact and the lower deviation threshold of predicted cruise are obtained, and the sum of the lower limit product and the lower limit of predicted cruise reference speed is used as the lower speed limit after coordination, and is obtained through the upper speed limit calculation formula after coordination. The upper speed limit calculation formula after coordination is as follows:
[0084] V Lo =V Ref +fac 拥堵影响下限 ×V LoDe ;
[0085] Among them, V Ref is the predicted cruising reference speed, fac 拥堵影响下限 V is the correction factor for the lower threshold. LoDeTo predict the cruise control's allowed lower deviation threshold, the allowed lower deviation threshold correction coefficient is obtained from the lower deviation threshold correction coefficient table according to the target congestion level, the lower deviation threshold correction coefficient table pre-stores a positive correlation mapping relationship between the lower deviation threshold correction coefficient and the target congestion level, and the allowed lower deviation threshold correction coefficient calibration range is between [-1,0], the predicted cruise control's allowed lower deviation threshold is obtained from the lower deviation threshold table according to the target congestion level and the cruise control vehicle speed, and the lower deviation threshold table pre-stores a positive correlation mapping relationship between the lower deviation threshold and the target congestion level;
[0086] Further, for the coordinated acceleration in the coordinated vehicle information, based on the preset map and according to the current driving information, the current vehicle speed, predicted slope angle and predicted gear are obtained, and the predicted cruise basic acceleration is obtained according to the predicted slope angle and the predicted gear, the speed deviation acceleration coefficient is obtained according to the current vehicle speed and the predicted cruise reference speed, and the predicted coasting acceleration coefficient is obtained according to the vehicle weight, and the product of the predicted cruise basic acceleration, the speed deviation acceleration coefficient and the predicted coasting acceleration coefficient is used as the coordinated acceleration, which is obtained through the coordinated acceleration calculation formula. The coordinated acceleration calculation formula is as follows:
[0087] a Pred =a Bas ×fac 车速偏差 ×fac 预测滑行 ;
[0088] Among them, a Pred is the acceleration after coordination, a Bas To predict the basic cruise acceleration, query the basic acceleration table according to the predicted slope angle and predicted gear. The predicted slope angle is positive and the acceleration is negative. The smaller the positive slope angle, the greater the acceleration. The larger the positive slope, the smaller the acceleration. The predicted slope angle is negative and the acceleration is positive. The smaller the negative slope angle, the greater the acceleration. The larger the negative slope, the smaller the acceleration. fac 车速偏差 is the speed deviation acceleration coefficient, based on the current speed and the predicted cruise reference speed V Ref Deviation query deviation acceleration coefficient table to obtain, when the current speed and the predicted cruise reference speed deviation is positive, the calibration is greater than 1; when the current speed and the predicted cruise reference speed deviation is negative, the calibration is less than 1, fac 预测滑行 To predict the coasting acceleration coefficient, when the vehicle is on an uphill road, a table is looked up based on the distance to the top of the slope and the vehicle weight. The shorter the distance to the top of the slope, the larger the coefficient calibration, and the heavier the vehicle weight, the smaller the coefficient calibration. When the vehicle is on a flat road, a table is looked up based on the distance to the downhill and the vehicle weight. The shorter the distance to the downhill, the larger the coefficient calibration, and the heavier the vehicle weight, the smaller the coefficient calibration. When the vehicle is on a downhill road, the predicted coasting acceleration coefficient is 1, so that the predicted acceleration adjustment of the function cost in predictive cruising under congested road conditions is implemented to meet the comprehensive needs of uphill drivers for time efficiency and fuel consumption.
[0089] Furthermore, the post-coordinated shift speed in the post-coordinated vehicle information is obtained through a speed formula, and the speed formula is as follows:
[0090] n gr =n grBs ×fac 拥堵程度2n ;
[0091] Among them, n gr To coordinate the shift speed, n grBs is the basic speed for shifting gears. The basic speed for shifting gears is obtained by querying the preset speed table based on the current vehicle speed and the predicted gear position. 拥堵程度2n is the influence coefficient of congestion degree on the basic speed of gear shifting, which is calibrated by the congestion degree. The calibration range is [facmin,1]; the more serious the congestion, the smaller the influence coefficient. Among them, facmin is the influence coefficient of ensuring the minimum engine shift speed to prevent engine shutdown, which is calibrated by num gr The gear shift prediction section number indicates the section for gear shifting. When the engine speed calculated by the gear position under the predicted vehicle speed is lower than the coordinated gear shift speed in the gear shift prediction section, it is considered that gear shifting is required. The gear shift prediction section number is obtained by the following prediction section formula:
[0092] num gr =num grBs ×fac 拥堵程度2Num ;
[0093] Among them, n grB s is the basic speed for shifting gears, which is obtained by looking up the table based on the current vehicle speed and the predicted gear position. 拥堵程度2Num The coefficient of influence of congestion level on the number of gear shift prediction sections is calibrated by the congestion level;
[0094] Furthermore, after obtaining the coordinated vehicle information including the coordinated upper and lower speed limits, the coordinated acceleration and the coordinated gear shift speed, the optimal upper and lower speed limits and the optimal gear upper and lower limits are calculated through road network reconstruction and vehicle modeling, and then the fuel consumption and comfort in the vehicle model are comprehensively calculated optimally according to the preset planning optimization algorithm in the predicted speed planning to obtain predictive cruise optimization information including predicted cruise optimization speed and predicted cruise optimization gear, and the predictive cruise speed upper and lower limit thresholds are adjusted in congested road conditions to reduce the number of forward and backward cruises in congested road conditions and improve driving comfort.
[0095] Figure 4 The process diagram of the vehicle cruise control method provided in this application is as follows Figure 3 As shown in 4, in this embodiment Figure 2 Based on the embodiment, a vehicle cruise control method is described in detail, and the method includes:
[0096] S401, obtaining initial cruising state information and braking state information, if the initial cruising state information indicates that the vehicle enters the first cruising state, and the cruise control speed is greater than the current speed, obtaining the current road section and the gear position at the time of entering the cruise control according to the current driving information;
[0097] Specifically, for the initial cruise state information, when any of the following conditions is met, the initial cruise state information indicates that the vehicle enters the first cruise state:
[0098] a. The driver who enters the current road presses the cruise switch for the first time to enter the cruise;
[0099] b. After turning around on the same road, the driver presses the cruise switch to enter cruise control;
[0100] c. After turning on the same road, the driver presses the cruise switch to enter cruise control;
[0101] d. On the same road, when the cruise control is turned off and there is no U-turn, the driver presses the cruise switch to enter cruise control after the vehicle speed drops below the lower speed limit threshold after the cruise control is turned off. The lower speed limit threshold is obtained by looking up the table based on the congestion level and the last cruise control speed;
[0102] e. When switching from one road to another, the driver presses the cruise switch to re-enter the cruise mode;
[0103] Among them, when the initial cruise state information indicates that the vehicle enters the first cruise state, the initial cruise demand speed and the initial cruise demand gear are used as the predicted cruise speed and predicted cruise gear in the predictive cruise control information. At this time, the driver's power demand will be responded to first. The road U-turn and turning can be obtained by calculating the curvature information in the map. When switching from one road to another, it can be obtained by calculating the updated state of the new road section in the map. Through the logical judgment of the first cruise, the driver's time efficiency demand when exiting cruise and re-entering cruise under congested road conditions is realized;
[0104] Furthermore, when the cruise speed is lower than the current speed, the first cruise demand speed, i.e. the initial cruise demand speed, is controlled according to the dynamically optimized optimal speed. When the cruise speed is equal to the current speed, when it is a flat road or an uphill section, the initial cruise demand speed is set to the cruise speed; when it is a downhill section, the initial cruise demand speed is controlled according to the dynamically optimized optimal speed.
[0105] Further, for the initial cruise demand gear in the initial cruise demand information, when the cruise control vehicle speed is greater than the current vehicle speed, poll from the gear at the time of entering cruise to the highest gear in sequence to find the comprehensive optimal gear, and shift up in sequence to obtain the initial cruise demand gear; when the cruise control vehicle speed is less than the current vehicle speed, poll from the gear at the time of entering cruise to the lowest gear for exiting cruise in sequence to find the comprehensive optimal gear, and shift down in sequence to obtain the initial cruise demand gear; when the cruise control vehicle speed is similar to the current vehicle speed, poll the current gear at the time of entering cruise, the current gear plus 1 gear; the current gear minus 1 gear to find the comprehensive optimal gear; otherwise, maintain the current gear.
[0106] S402: If the current road section is a flat road or an uphill road section, use the cruise control speed as the initial cruise required speed;
[0107] Specifically, when the cruise control speed is greater than the current vehicle speed and the current road section is a flat road or an uphill section, the first cruise demand speed is entered, that is, the initial cruise demand speed, and the current vehicle speed is controlled to slowly increase to the cruise control speed as the initial cruise demand speed.
[0108] S403: if the current road section is a downhill road section, calculate the vehicle speed at the bottom of the slope according to the current vehicle speed; if the vehicle speed at the bottom of the slope is less than the cruise speed, use the cruise speed as the initial cruise required speed;
[0109] Specifically, when the cruise control speed is greater than the current speed and the current road section is a downhill section, the speed from the downhill to the bottom of the downhill is calculated first. If the speed at the bottom of the downhill can reach the cruise control speed, the initial cruise demand speed is controlled according to the dynamically optimized optimal speed; if the speed at the bottom of the downhill is less than the cruise control speed, the initial cruise demand speed is controlled according to the cruise control speed.
[0110] S404: if the braking state information indicates that the vehicle enters a braking state, obtaining predicted braking information according to the current driving information;
[0111] Specifically, for the braking status information, when the following conditions are met at the same time, the braking status information indicates that the vehicle enters the braking state: a. not in neutral; b. downhill, the current vehicle speed is greater than the braking demand speed; c. the map is valid; d. not in the acceleration stage before the next uphill; e. cruising; f. the downhill length is greater than the threshold; g. the distance to the lowest flat road section is greater than the road section threshold;
[0112] Further, the predicted braking information includes a predicted braking demand speed and a predicted braking demand gear. For the predicted braking demand speed, the current vehicle speed is obtained according to the current driving information, and the predicted braking demand gear is obtained according to the current vehicle speed. The predicted slope of the downhill section and the actual vehicle speed at the top of the uphill section are obtained through a preset map to calculate the ideal maximum vehicle speed when free sliding in the downhill section. The maximum vehicle speed for free sliding in the downhill section under the current road conditions is obtained according to the ideal maximum vehicle speed when free sliding in the downhill section and the target congestion level.
[0113] The maximum braking force of the vehicle is obtained, and the maximum braking capacity speed is calculated according to the maximum braking force of the vehicle. If the maximum braking capacity speed is greater than the maximum free sliding speed of the downhill section, the maximum free sliding speed of the downhill section is used as the predicted braking demand speed. Otherwise, the maximum braking capacity speed is used as the predicted braking demand speed, that is, the maximum braking capacity speed and the maximum free sliding speed of the downhill section are taken as the smaller one to obtain the predicted braking demand speed.
[0114] Further, for predicting the brake demand gear, the predicted brake demand gear is obtained by looking up the table based on the optimal engine speed for braking and the current vehicle speed. When the braking state information indicates that the vehicle is switching from entering the braking state to exiting the braking state, the predicted brake demand gear is obtained based on the comprehensive optimal calculation of fuel consumption and comfort.
[0115] Furthermore, by adjusting the predicted braking demand gear and the predicted braking demand vehicle speed, the number of brake applications can be reduced in congested road conditions, and by adjusting the speed during predictive cruise downshifts in congested road conditions, the number of gear shifts can be reduced. By resuming the gear calculation and adjustment after predictive cruise braking in congested road conditions, the number of gear shifts can be reduced, thereby achieving the comprehensive optimal fuel consumption and comfort under congested road conditions.
[0116] S405, acquiring predicted cruise control information according to the predicted cruise optimization information, the initial cruise demand information and the predicted braking information, and calculating and acquiring a cruise control torque based on the predicted cruise control information, and achieving vehicle cruising by outputting the cruise control torque;
[0117] Specifically, after obtaining the predicted cruise optimization information including the predicted cruise optimization vehicle speed and the predicted cruise optimization gear, the initial cruise requirement information including the initial cruise requirement vehicle speed and the initial cruise requirement gear, and the predicted braking information including the predicted braking requirement vehicle speed and the predicted braking requirement gear, the predicted cruise optimization information, the initial cruise requirement information and the predicted braking information are coordinated and calculated according to the priority to obtain the predicted cruise control information including the predicted cruise vehicle speed, the predicted cruise gear and the predicted cruise gear control state, wherein the priority of the predicted braking information, the initial cruise requirement information and the predicted cruise optimization information decreases in sequence.
[0118] The vehicle cruise control method provided in the embodiment of the present application performs preprocessing based on the acquired platform cruise data to obtain a training data set, trains the training data set through a clustering algorithm to obtain a road condition model, obtains a target congestion level through the road condition model, obtains coordinated vehicle information according to the target congestion level and the cruise control speed, obtains predicted cruise optimization information according to the coordinated vehicle information based on a preset planning optimization algorithm, reduces the number of forward and backward cruises in congested road conditions, obtains initial cruise demand information according to initial cruise state information, obtains predicted braking information according to braking state information, obtains predicted cruise control information according to the predicted cruise optimization information, the initial cruise demand information and the predicted braking information, reduces the number of braking and shifting, calculates and obtains the cruise control torque based on the predicted cruise control information, and realizes vehicle cruising by outputting the cruise control torque, thereby reducing high fuel consumption when cruising under congested road conditions, thereby reducing the operating cost of commercial vehicles.
[0119] Figure 5 The structural diagram of the vehicle cruise control device provided by this application is as follows: Figure 5 As shown, the vehicle cruise control device 50 provided in this embodiment includes:
[0120] An acquisition module 501 is used to acquire platform cruise data, pre-process the platform cruise data to acquire a training data set, train the training data set by a clustering algorithm to acquire a road condition model, wherein the road condition model is used to indicate a congestion level of a road condition, and the platform cruise data is used to indicate data of multiple fleets;
[0121] The processing module 502 is used to obtain the current driving information and the cruise speed of the vehicle, input the current driving information into the road condition model to obtain the target congestion level, obtain the coordinated vehicle information according to the target congestion level and the cruise speed, and obtain the predicted cruise optimization information according to the coordinated vehicle information based on a preset planning optimization algorithm;
[0122] The processing module 502 is further used to obtain initial cruising state information and braking state information, and obtain initial cruising demand information according to the initial cruising state information, and obtain predicted braking information according to the braking state information, wherein the initial cruising state information is used to indicate whether the vehicle enters a first cruising state, and the braking state information is used to indicate whether the vehicle enters a braking state;
[0123] The control module 503 is used to obtain predicted cruise control information according to the predicted cruise optimization information, the initial cruise demand information and the predicted braking information, and calculate the cruise control torque based on the predicted cruise control information, and realize vehicle cruising by outputting the cruise control torque.
[0124] Furthermore, the acquisition module 501 is specifically used to acquire the download interval time of each vehicle data in the fleet data, wherein the vehicle data includes vehicle speed, braking percentage, cruising speed and road positioning signal, and the road positioning signal is used to indicate different road categories;
[0125] If the download interval is greater than a preset time, the fleet data is marked as sparse fleet data, and data interpolation processing is performed based on the data of each vehicle in the sparse fleet data to generate qualified fleet data;
[0126] If the download interval is less than a preset time, marking the fleet data as qualified fleet data;
[0127] The qualified fleet data in the platform cruise data is obtained, and the qualified fleet data is used as the training data set.
[0128] Furthermore, the acquisition module 501 is specifically used to detect whether there are non-team vehicles in the sparse team data, and if not, the sparse team data is used as the qualified team data;
[0129] If so, the average vehicle speed is obtained according to the speed of each vehicle in the sparse vehicle fleet data, and the sparse vehicle fleet data is interpolated based on the average vehicle speed to generate new vehicle fleet data, and the new vehicle fleet data is used as the qualified vehicle fleet data.
[0130] Further, the processing module 502 is specifically configured to obtain a predicted cruising reference speed according to the target congestion level, and obtain the coordinated vehicle speed upper limit and the coordinated vehicle speed lower limit according to the predicted cruising reference speed;
[0131] Based on the preset map, according to the current driving information, the current vehicle speed, the predicted slope angle and the predicted gear are obtained, and the predicted cruise basic acceleration is obtained according to the predicted slope angle and the predicted gear, the vehicle speed deviation acceleration coefficient is obtained according to the current vehicle speed and the predicted cruise reference speed, and the predicted coasting acceleration coefficient is obtained according to the vehicle weight;
[0132] The product of the predicted cruise basic acceleration, the vehicle speed deviation acceleration coefficient and the predicted coasting acceleration coefficient is used as the coordinated acceleration.
[0133] Further, the processing module 502 is specifically configured to use the cruise speed as the predicted cruise reference speed if the target congestion level is basically unblocked or unblocked, and the cruise speed is used to indicate the cruise speed set by the driver;
[0134] If the target congestion level is severe congestion, moderate congestion or mild congestion, the average congestion vehicle speed within the preset congestion time before the target congestion level is obtained, and the average congestion vehicle speed is used as the predicted cruise reference speed.
[0135] Further, the processing module 502 is specifically configured to obtain a congestion impact upper limit coefficient and a predicted cruise allowable upper deviation threshold according to the target congestion level, obtain an upper limit product of the congestion impact upper limit coefficient and the predicted cruise allowable upper deviation threshold, and use the upper limit product and the upper limit of the predicted cruise reference speed as the coordinated vehicle speed upper limit;
[0136] The congestion impact lower limit coefficient and the predicted cruise allowable lower deviation threshold are obtained according to the target congestion level, the lower limit product of the congestion impact lower limit coefficient and the predicted cruise allowable lower deviation threshold is obtained, and the sum of the lower limit product and the lower limit of the predicted cruise reference speed is used as the coordinated vehicle speed lower limit.
[0137] Further, the processing module 502 is specifically configured to obtain the current road section and the gear position at the time of entering the cruise according to the current driving information if the initial cruise state information indicates that the vehicle enters the first cruise state and the cruise speed is greater than the current vehicle speed, and to poll the gear position between the gear position at the time of entering the cruise and the highest gear to obtain the initial cruise required gear;
[0138] If the current road section is a flat road or an uphill road section, the cruise speed is used as the initial cruise required speed;
[0139] If the current road section is a downhill section, the vehicle speed at the bottom of the slope is calculated based on the current vehicle speed. If the vehicle speed at the bottom of the slope is less than the cruise speed, the cruise speed is used as the initial cruise requirement speed. If the vehicle speed at the bottom of the slope is equal to or greater than the cruise speed, the initial cruise requirement speed is obtained through a preset vehicle speed optimization algorithm.
[0140] Further, the processing module 502 is specifically configured to obtain a current vehicle speed according to the current driving information if the braking state information indicates that the vehicle enters a braking state, and obtain a predicted braking demand gear according to the current vehicle speed;
[0141] Obtaining a predicted downhill slope through a preset map, and obtaining a maximum free-gliding speed of the downhill section according to the predicted downhill slope and the target congestion level;
[0142] The maximum braking force of the vehicle is obtained, and the maximum braking capacity speed is calculated based on the maximum braking force of the vehicle; if the maximum braking capacity speed is greater than the maximum free sliding speed in the downhill section, the maximum free sliding speed in the downhill section is used as the predicted braking demand speed; otherwise, the maximum braking capacity speed is used as the predicted braking demand speed.
[0143] The vehicle cruise control device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.
[0144] Figure 6 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 6 As shown, the electronic device 60 provided in this embodiment includes: at least one processor 601 and a memory 602. Optionally, the device 60 also includes a communication component 603. The processor 601, the memory 602 and the communication component 603 are connected via a bus 604.
[0145] In a specific implementation process, at least one processor 601 executes the computer execution instructions stored in the memory 602, so that at least one processor 601 executes the above method.
[0146] The specific implementation process of the processor 601 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.
[0147] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.
[0148] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.
[0149] 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, the bus in the drawings of the present application is not limited to only one bus or one type of bus.
[0150] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.
[0151] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.
[0152] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.
[0153] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.
[0154] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.
[0155] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0156] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0157] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0158] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.
[0159] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.
Claims
1. A vehicle cruise control method, It is characterized in that include: Acquire platform cruise data, pre-process the platform cruise data to obtain a training data set, train the training data set by a clustering algorithm to obtain a road condition model, the road condition model is used to indicate a congestion level of a road condition, and the platform cruise data is used to indicate a plurality of fleet data; Acquire current driving information and cruise control speed of the vehicle, input the current driving information into the road condition model to acquire a target congestion level, acquire coordinated vehicle information according to the target congestion level and the cruise control speed, and acquire predicted cruise optimization information according to the coordinated vehicle information based on a preset planning optimization algorithm; Acquire initial cruise state information and braking state information, and acquire initial cruise demand information according to the initial cruise state information, and acquire predicted braking information according to the braking state information, wherein the initial cruise state information is used to indicate whether the vehicle enters a first cruise state, and the braking state information is used to indicate whether the vehicle enters a braking state; Predicted cruise control information is acquired according to the predicted cruise optimization information, the initial cruise demand information and the predicted braking information, and a cruise control torque is calculated based on the predicted cruise control information. Vehicle cruising is achieved by outputting the cruise control torque.
2. The method according to claim 1, It is characterized in that The preprocessing of the platform cruise data to obtain a training data set includes: Obtaining a download interval of each vehicle data in the fleet data, wherein the vehicle data includes vehicle speed, braking percentage, cruising speed and road positioning signal, and the road positioning signal is used to indicate different road categories; If the download interval is greater than a preset time, the fleet data is marked as sparse fleet data, and data interpolation processing is performed based on the data of each vehicle in the sparse fleet data to generate qualified fleet data; If the download interval is less than a preset time, marking the fleet data as qualified fleet data; The qualified fleet data in the platform cruise data is obtained, and the qualified fleet data is used as the training data set.
3. The method according to claim 2, It is characterized in that The performing data interpolation processing based on each vehicle data in the sparse fleet data to generate qualified fleet data includes: Detecting whether there are non-team vehicles in the sparse team data, and if not, using the sparse team data as the qualified team data; If so, the average vehicle speed is obtained according to the speed of each vehicle in the sparse vehicle fleet data, and the sparse vehicle fleet data is interpolated based on the average vehicle speed to generate new vehicle fleet data, and the new vehicle fleet data is used as the qualified vehicle fleet data.
4. The method according to claim 1, It is characterized in that The coordinated vehicle information includes a coordinated vehicle speed upper limit, a coordinated vehicle speed lower limit, and a coordinated acceleration, and the obtaining of the coordinated vehicle information according to the target congestion level and the cruise control speed includes: Acquire a predicted cruising reference speed according to the target congestion level, and acquire the coordinated vehicle speed upper limit and the coordinated vehicle speed lower limit according to the predicted cruising reference speed; Based on the preset map, according to the current driving information, the current vehicle speed, the predicted slope angle and the predicted gear are obtained, and the predicted cruise basic acceleration is obtained according to the predicted slope angle and the predicted gear, the vehicle speed deviation acceleration coefficient is obtained according to the current vehicle speed and the predicted cruise reference speed, and the predicted coasting acceleration coefficient is obtained according to the vehicle weight; The product of the predicted cruise basic acceleration, the vehicle speed deviation acceleration coefficient and the predicted coasting acceleration coefficient is used as the coordinated acceleration.
5. The method according to claim 4, It is characterized in that The obtaining of a predicted cruising reference speed according to the target congestion level includes: If the target congestion level is basically unblocked or unblocked, the cruise speed is used as the predicted cruise reference speed, and the cruise speed is used to indicate the cruising speed set by the driver; If the target congestion level is severe congestion, moderate congestion or mild congestion, the average congestion vehicle speed within the preset congestion time before the target congestion level is obtained, and the average congestion vehicle speed is used as the predicted cruise reference speed.
6. The method according to claim 4, It is characterized in that The obtaining the coordinated vehicle speed upper limit and the coordinated vehicle speed lower limit according to the predicted cruise reference vehicle speed includes: Obtaining a congestion impact upper limit coefficient and a predicted cruise allowable upper deviation threshold according to the target congestion level, obtaining an upper limit product of the congestion impact upper limit coefficient and the predicted cruise allowable upper deviation threshold, and taking the upper limit product and the upper limit of the predicted cruise reference speed as the coordinated vehicle speed upper limit; The congestion impact lower limit coefficient and the predicted cruise allowable lower deviation threshold are obtained according to the target congestion level, the lower limit product of the congestion impact lower limit coefficient and the predicted cruise allowable lower deviation threshold is obtained, and the sum of the lower limit product and the lower limit of the predicted cruise reference speed is used as the coordinated vehicle speed lower limit.
7. The method according to claim 1, It is characterized in that The initial cruise demand information includes an initial cruise demand vehicle speed and an initial cruise demand gear. The acquiring the initial cruise demand information according to the initial cruise state information includes: If the initial cruise state information indicates that the vehicle enters the first cruise state, and the cruise speed is greater than the current vehicle speed, the current road section and the gear position at the time of entering cruise are obtained according to the current driving information, and the gear position at the time of entering cruise and the highest gear are polled to obtain the initial cruise required gear position; If the current road section is a flat road or an uphill road section, the cruise speed is used as the initial cruise required speed; If the current road section is a downhill section, the vehicle speed at the bottom of the slope is calculated based on the current vehicle speed. If the vehicle speed at the bottom of the slope is less than the cruise speed, the cruise speed is used as the initial cruise requirement speed. If the vehicle speed at the bottom of the slope is equal to or greater than the cruise speed, the initial cruise requirement speed is obtained through a preset vehicle speed optimization algorithm.
8. The method according to claim 1, It is characterized in that The predicted braking information includes a predicted braking requirement vehicle speed and a predicted braking requirement gear, and the obtaining of the predicted braking information according to the braking state information includes: If the braking state information indicates that the vehicle enters a braking state, the current vehicle speed is obtained according to the current driving information, and the predicted braking demand gear is obtained according to the current vehicle speed; Obtaining a predicted downhill slope through a preset map, and obtaining a maximum free-gliding speed of the downhill section according to the predicted downhill slope and the target congestion level; The maximum braking force of the vehicle is obtained, and the maximum braking capacity speed is calculated based on the maximum braking force of the vehicle; if the maximum braking capacity speed is greater than the maximum free sliding speed in the downhill section, the maximum free sliding speed in the downhill section is used as the predicted braking demand speed; otherwise, the maximum braking capacity speed is used as the predicted braking demand speed.
9. A vehicle cruise control device, It is characterized in that include: an acquisition module, used to acquire platform cruise data, pre-process the platform cruise data to acquire a training data set, train the training data set by a clustering algorithm to acquire a road condition model, wherein the road condition model is used to indicate a congestion level of a road condition, and the platform cruise data is used to indicate data of multiple fleets; a processing module, configured to obtain current driving information and a cruise control speed of the vehicle, input the current driving information into the road condition model to obtain a target congestion level, obtain coordinated vehicle information according to the target congestion level and the cruise control speed, and obtain predicted cruise optimization information according to the coordinated vehicle information based on a preset planning optimization algorithm; The processing module is further used to obtain initial cruising state information and braking state information, and obtain initial cruising demand information according to the initial cruising state information, and obtain predicted braking information according to the braking state information, wherein the initial cruising state information is used to indicate whether the vehicle enters a first cruising state, and the braking state information is used to indicate whether the vehicle enters a braking state; The control module is used to obtain predicted cruise control information according to the predicted cruise optimization information, the initial cruise demand information and the predicted braking information, and calculate and obtain the cruise control torque based on the predicted cruise control information, and realize vehicle cruising by outputting the cruise control torque.
10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.
