A vehicle following control method and related device
By combining fluid dynamics simulation and neural network training, a wake vortex simulation model can accurately calculate the simulated following position by incorporating vehicle speed, wind speed, and vehicle shape information. This solves the problem that existing following methods cannot accurately determine the wake vortex region, and achieves more efficient and energy-saving following.
Patent Information
- Application Number
- CN202210850527.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-19
- Publication Date
- 2026-02-27
- Estimated Expiration
- 2042-07-19
AI Technical Summary
Existing vehicle-following methods cannot accurately determine the impact of different vehicle models on the exhaust vortex region, resulting in poor energy-saving performance.
A wake vortex simulation model trained using fluid dynamics simulation and neural network methods is adopted. Combined with vehicle speed, wind speed and vehicle shape information, the simulated following position is accurately calculated. The model is then optimized through iterative training of neural networks to improve the following accuracy.
It achieves a more precise following strategy, reduces energy consumption, and improves the speed and accuracy of following, especially in the case of strong crosswinds, it can effectively avoid the wake vortex area.
Smart Images
Figure CN115195723B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present specification relates to the field of vehicle control, and more specifically, to a follow vehicle control method and related device. BACKGROUND
[0002] Aerodynamic drag is generally characterized by the drag coefficient. For a fuel vehicle, a 10% reduction in the drag coefficient results in a 3% reduction in fuel consumption. For an electric vehicle, a 0.02 reduction in the drag coefficient results in a 10 km increase in driving range. Vehicle platooning can significantly reduce the drag experienced by each vehicle, because the total pressure in the wake region is small. Therefore, when a vehicle travels within the wake region of a preceding vehicle, it will experience less pressure drag. This reduction in drag means less fuel consumption, higher fuel efficiency, and less pollution. In some current follow vehicle schemes, the wake region is usually calculated based on the speed of the preceding vehicle, and the following vehicle is controlled to enter the wake region to save fuel. However, the current follow vehicle method cannot accurately determine the wake region based on wind speed and different vehicle models, and the energy-saving effect is greatly reduced. SUMMARY
[0003] A series of simplified concepts are introduced in the summary section, which will be further described in detail in the detailed description section. The summary section of the present application does not mean to attempt to limit the key features and essential technical features of the claimed technical solutions, nor to determine the protection scope of the claimed technical solutions.
[0004] In order to provide a more energy-saving and convenient follow vehicle method, in a first aspect, the present application provides a follow vehicle control method, the method comprising:
[0005] obtaining driving information of a to-be-followed vehicle, wherein the driving information comprises vehicle speed information and wind speed information;
[0006] inputting the vehicle speed information and the wind speed information into a wake simulation model to obtain a simulation follow position of a target vehicle, wherein the wake simulation model is obtained based on fluid dynamics simulation and neural network method through iterative training;
[0007] determining a relative position relationship between the simulation follow position and the to-be-followed vehicle based on lane line information;
[0008] controlling the target vehicle to follow the to-be-followed vehicle based on the relative position relationship.
[0009] Optionally, the driving information further comprises vehicle shape information;
[0010] inputting the wind speed information and the vehicle speed information into a wake simulation model to obtain a simulation follow position of a target vehicle, comprising:
[0011] determining a vehicle shape parameter of the vehicle to be followed based on the vehicle shape information in a vehicle shape library of the wake vortex simulation model;
[0012] determining a wind speed parameter and a wind direction parameter based on the wind speed information in a wind speed library of the wake vortex simulation model;
[0013] determining a vehicle speed parameter based on the vehicle speed information in a vehicle speed library of the wake vortex simulation model;
[0014] performing simulation calculation based on the vehicle shape parameter, the wind speed parameter, the wind direction parameter and the vehicle speed parameter as inputs of the wake vortex simulation model to obtain a simulation following position.
[0015] Optionally, the method further comprises:
[0016] constructing a plurality of three-dimensional flow field simulation models based on a fluid mechanics simulation method and a vehicle shape database;
[0017] performing simulation based on a vehicle speed database, a wind speed database and the three-dimensional flow field simulation models to obtain a preset simulation following position;
[0018] iteratively training the wake vortex simulation model based on neural network method through the wake vortex measurement data of the following test and the preset simulation following position.
[0019] Optionally, the method further comprises:
[0020] obtaining vehicle head pressure data and vehicle tail pressure data of the target vehicle at different positions in the wake vortex area corresponding to the vehicle to be followed;
[0021] obtaining the wake vortex measurement data of the following test based on the vehicle head pressure data and the vehicle tail pressure data.
[0022] Optionally, the controlling the target vehicle to follow based on the relative position relationship comprises:
[0023] when the simulation following position is in a current driving lane of the vehicle to be followed and the distance between the simulation following position and the vehicle to be followed is greater than a statutory distance, obtaining road information of a current driving lane behind the vehicle to be followed, wherein the statutory distance is the shortest following distance allowed under the current road condition and the current vehicle speed;
[0024] when there is no other vehicle driving within a first following distance behind the vehicle to be followed, controlling the target vehicle to drive to the simulation following position to follow, wherein the first following distance is determined based on the simulation following position and the shape size of the target vehicle.
[0025] Optionally, the controlling the target vehicle to follow the vehicle based on the relative position relationship comprises:
[0026] In a case that the simulation following position is on a lane adjacent to the vehicle to be followed, acquiring road information of a lane adjacent to the rear of the vehicle to be followed;
[0027] In a case that no other vehicle is running within a second following distance of the adjacent lane behind the vehicle to be followed, controlling the target vehicle to run to the simulation following position to follow the vehicle, wherein the second following distance is determined based on the simulation following position, the size of the target vehicle and the width of the lane.
[0028] Optionally, the controlling the target vehicle to follow the vehicle based on the relative position relationship comprises:
[0029] In a case that the simulation following position is on a lane adjacent to the vehicle to be followed, acquiring road information of a lane adjacent to the rear of the vehicle to be followed;
[0030] In a case that no other vehicle is running within a third following distance of the adjacent lane and the current running lane of the vehicle to be followed, controlling the target vehicle to run to the simulation following position to follow the vehicle;
[0031] Monitoring vehicle running information behind the target vehicle;
[0032] In a case that other vehicles appear within a preset safety distance behind the target vehicle, controlling the target vehicle to run to the current running lane of the vehicle to be followed.
[0033] In a second aspect, the present application further provides a following control device, comprising:
[0034] A first acquisition unit is configured to acquire running information of a vehicle to be followed, wherein the running information comprises vehicle speed information and wind speed information;
[0035] A second acquisition unit is configured to input the vehicle speed information and the wind speed information into a wake vortex simulation model to acquire a simulation following position of a target vehicle, wherein the wake vortex simulation model is obtained by iterative training based on fluid dynamics simulation method and neural network method;
[0036] A determination unit is configured to determine a relative position relationship between the simulation following position and the vehicle to be followed based on lane line information;
[0037] A control unit is configured to control the target vehicle to follow the vehicle based on the relative position relationship.
[0038] In a third aspect, an electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor configured to implement the steps of the following vehicle control method according to any one of the first aspect when executing the computer program.
[0039] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, the computer program executable by a processor to implement the following vehicle control method according to any one of the first aspect.
[0040] In summary, the following vehicle control method according to the embodiments of the present application includes: obtaining driving information of a to-be-followed vehicle, wherein the driving information includes vehicle speed information and wind speed information; taking the vehicle speed information and the wind speed information as inputs of a wake vortex simulation model to obtain a simulation following position of the target vehicle, wherein the wake vortex simulation model is obtained based on an iterative training of a fluid dynamics simulation method and a neural network method; determining a relative position relationship between the simulation following position and the to-be-followed vehicle based on lane line information; and controlling the target vehicle to follow the to-be-followed vehicle based on the relative position relationship. The following vehicle control method according to the embodiments of the present application not only considers the influence of the vehicle speed of the preceding vehicle on the wake vortex, but also considers the influence of the wind speed on the wake vortex during the process, and the obtained simulation following position is more accurate. Meanwhile, the wake vortex simulation model trained by the neural network is used to calculate the following position, and the calculation speed is faster, the error of the determined following position and the actual maximum position of the wake vortex intensity is smaller, and a more rapid and accurate following strategy can be implemented.
[0041] The following vehicle control method according to the embodiments of the present application, other advantages, objects and features of the present application will be embodied in part through the following description, and will be understood by those skilled in the art through research and practice of the present application. BRIEF DESCRIPTION OF DRAWINGS
[0042] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of the preferred embodiments and are not intended to limit the scope of the present application. Moreover, the same reference numerals are used throughout the same figures. In the drawings:
[0043] Figure 1 A following vehicle control method flowchart is provided for the embodiments of the present application;
[0044] Figure 2 A following vehicle driving related parameter measurement principle diagram is provided for the embodiments of the present application;
[0045] Figure 3 A wind speed measurement system structure diagram is provided for the embodiments of the present application;
[0046] Figure 4 A follow-up test sensor arrangement mode schematic diagram provided for an embodiment of the present application;
[0047] Figure 5 Another follow-up test sensor arrangement mode schematic diagram provided for an embodiment of the present application;
[0048] Figure 6 A simulation follow-up position schematic diagram provided for an embodiment of the present application;
[0049] Figure 7 A vehicle platooning schematic diagram provided for an embodiment of the present application;
[0050] Figure 8 Another vehicle platooning schematic diagram provided for an embodiment of the present application
[0051] Figure 9 A follow-up control device structure schematic diagram provided for an embodiment of the present application;
[0052] Figure 10 A follow-up control electronic equipment structure schematic diagram provided for an embodiment of the present application. DETAILED DESCRIPTION
[0053] The follow-up control method provided by the embodiment of the present application not only considers the influence of the front vehicle speed on the wake vortex, but also considers the influence of the wind speed on the wake vortex in the process, and the obtained simulation follow-up position is more accurate. Meanwhile, the application uses the wake vortex simulation model trained by the neural network, the calculation speed is faster, the error of the determined follow-up position and the actual maximum position of the wake vortex intensity is smaller, and a more rapid and accurate follow-up strategy can be realized.
[0054] The terms "first", "second", "third", "fourth" and the like in the description, claims, as well as the above-mentioned drawings (if any) of the present application are used to distinguish similar objects, and do not necessarily have to describe a particular order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all embodiments.
[0055] Please refer toFigure 1 This is a schematic flowchart of a vehicle following control method provided in an embodiment of this application, which may specifically include:
[0056] S110. Obtain the driving information of the vehicle to be followed, wherein the driving information includes vehicle speed information and wind speed information;
[0057] For example, the vehicle to be followed is the vehicle in front, such as... Figure 2 As shown, in some target vehicles implementing a following strategy, a 5-hole probe can be installed on the front of the vehicle to connect to a high-precision ALPHA sensor to identify the yaw angle. A pitot tube measures the wind speed facing the vehicle, and the direction and intensity of the crosswind are calculated based on the current vehicle speed. A millimeter-wave radar is installed on the front of the vehicle to identify the position and relative speed of the vehicle in front, and the speed of the vehicle in front is calculated from the current vehicle speed. It is understandable that if the vehicle in front can communicate with the vehicle behind, the speed of the vehicle in front can also be measured by the ECU (Electronic Control Unit) of the vehicle in front, and the measurement result can be transmitted to the vehicle behind or to the cloud for calculating the following strategy. Wind speed information can also be measured by roadside wind speed measuring devices, which can be used as follows: Figure 3 The wind speed is measured in the manner shown. A base 101 is set on an open ground, including two first sliding devices 102 and one second sliding device 103. The second slide rail 1032 of the second sliding device 103 is mounted on the first slider 1021 of the two first sliding devices 102. Guide devices 106 are fixed at both ends of the first slider 1021 and on the base 101. A first motor 1051 and a second motor 1052 are mounted on the base 101. A transmission belt 107 encircles the output shafts of the first motor 1051 and the second motor 1052, and the guide devices 106 mounted on the first slider 1021 and the base 101, forming an "I" shape. By controlling the speed of the motors, the movement direction of the wind measuring component 104, which is fixedly connected to the second slider 1031, can be controlled, thereby controlling the crosswind component to measure wind speed and direction at a designated location.
[0058] (when v≤3m / s)
[0059] R1 represents the rotational speed of the first motor, v represents the measured wind speed, and a and b are constants. The smaller the measured wind speed v, the greater the rotational speed of either the first or second motor, ensuring the rapid movement of the second slider. R2 represents the rotational speed of the second motor. The smaller the measured wind speed v, the smaller the difference between R1 and R2, maintaining the second slider's horizontal or vertical movement; the greater the measured wind speed v, the greater the difference between R1 and R2, resulting in movement along the tilt direction.
[0060] (when v > 3 m / s)
[0061] When v>3m / s, i,j are the rotating directions of the first motor and the second motor, clockwise is positive, n is a constant, the rotating speed and direction of the second motor R2 are adjusted adaptively according to the rotating speed and direction of the first motor, c is the measured wind direction angle, the angle of the horizontal right direction is 0 point, the counterclockwise angle increases (for example, when the wind direction points to the horizontal axis right direction, c=0, n tan c=0, the demand is that the second slider needs to move left or right in the horizontal direction to be parallel to the wind direction, at this time, iR1+jR2=0 is required, which has the physical meaning of equal rotating speed and reverse direction of the first motor and the second motor), n is a proportional coefficient, by this method, the first motor and the second motor control the second slider to slowly translate along the parallel wind direction.
[0062] S120, input the vehicle speed information and the wind speed information as the input of the wake vortex simulation model to obtain the simulation following position of the target vehicle, wherein the wake vortex simulation model is obtained through iterative training based on the fluid mechanics simulation method and the neural network method;
[0063] Exemplarily, the trained wake vortex simulation model can be obtained by iteratively training the neural network constructed by the simulation following position output by the flow field simulation model and the wake vortex measurement data obtained by the following test. The trained wake vortex simulation model can be loaded on the target vehicle or in the cloud. Before the target vehicle follows, the vehicle speed information and the wind speed information recognized as the input are used to calculate the simulation following position by using the wake vortex simulation model. By using the wake vortex simulation model trained by the neural network, the calculation speed is faster, the error of the determined following position and the actual maximum position of the wake vortex intensity is smaller, and a more rapid and accurate following strategy can be realized. When the intensity of the crosswind is large, the wake vortex of the front vehicle will deviate to the adjacent lane, and the simulation following position will also deviate to the adjacent lane to realize close following, and the crosswind is used to avoid the following distance of at least 50m in the same lane on the highway stipulated by the regulations.
[0064] S130, determine the relative position relationship between the simulation following position and the vehicle to be followed based on the lane line information;
[0065] Exemplarily, according to the simulation following position calculated and the lane information on the driving road, there can be three cases, i.e., the simulation following position and the front vehicle are in the same lane, the simulation following position and the front vehicle are in the adjacent lane, and the simulation following position and the front vehicle are located on the lane line of the driving lane of the front vehicle
[0066] S140, control the target vehicle to follow based on the relative position relationship.
[0067] For example, the target vehicle is controlled to follow the preceding vehicle according to the relative position relationship. For example, when the simulation following position is on the lane line, the rear vehicle is not allowed to occupy the lane line for a long time; when the simulation following position is in the same lane as the preceding vehicle, the rear vehicle follows the preceding vehicle in the same lane and maintains a certain safe distance to meet the safety requirements; when the simulation following position is in the adjacent lane of the preceding vehicle, it is observed whether the adjacent lane is available. If the adjacent lane is available and there is no other obstacle vehicle in front and back, the rear vehicle drives in the adjacent lane to the simulation following position.
[0068] In summary, the follow-up control method proposed in the embodiments of the present application not only considers the influence of the speed of the preceding vehicle on the wake vortex, but also considers the influence of the wind speed on the wake vortex during the process. The simulation following position obtained is more accurate. Meanwhile, the present application uses a wake vortex simulation model trained by a neural network, which has faster calculation speed and smaller error between the determined following position and the actual maximum position of the wake vortex intensity, and can realize a more rapid and accurate follow-up strategy.
[0069] In some examples, the driving information further includes vehicle shape information;
[0070] The wind speed information and the vehicle speed information are used as inputs of the wake vortex simulation model to obtain a simulation following position of the target vehicle, including:
[0071] Based on the vehicle shape information, a to-be-followed vehicle shape parameter is determined in a vehicle shape library of the wake vortex simulation model;
[0072] Based on the wind speed information, a crosswind speed parameter and a crosswind direction parameter are determined in a wind speed library of the wake vortex simulation model;
[0073] Based on the vehicle speed information, a vehicle speed parameter is determined in a vehicle speed library of the wake vortex simulation model;
[0074] The simulation following position is obtained by performing simulation calculation on the to-be-followed vehicle shape parameter, the crosswind speed parameter, the crosswind direction parameter, and the vehicle speed parameter as inputs of the wake vortex simulation model.
[0075] Exemplarily, since the shapes of vehicles are different, that is, the length, the style, the height or the shape of the vehicle will affect the flow field formed by the air flowing through the front of the vehicle when the vehicle is driving, the vortex area formed by different shape vehicles under the same driving condition is not the same, and the influence of the shape of the vehicle on the formation of the vortex can be considered in the construction of the vortex model and in the driving process. The vortex simulation model is a model trained by a large amount of data. The trained vortex model provides a vehicle shape library, a wind speed library and a vehicle speed library. After obtaining the shape information, the vehicle speed information and the wind speed information of the vehicle to be followed, the corresponding vehicle shape parameters, the crosswind speed parameters, the crosswind direction parameters and the vehicle speed parameters are selected in the corresponding database as the input of the vortex simulation model for simulation calculation to obtain the simulation following position.
[0076] In summary, the vehicle following control method provided in the application can select the corresponding vehicle shape parameters, crosswind speed parameters, crosswind direction parameters and vehicle speed parameters in the corresponding database of the vortex simulation model based on the vehicle shape information, the wind speed information and the vehicle speed information, and use the above parameters as the input of the vortex simulation model, so that the accurate simulation following position can be quickly simulated and calculated.
[0077] In some examples, the above method further comprises:
[0078] constructing a plurality of three-dimensional flow field simulation models based on the fluid mechanics simulation method and the vehicle shape database;
[0079] obtaining a preset simulation following position by simulation based on the vehicle speed database, the wind speed database and the above three-dimensional flow field simulation models;
[0080] iteratively training the above vortex simulation model based on the vortex measurement data obtained by the vehicle following test and the above preset simulation following position based on the neural network method.
[0081] Exemplarily, the vortex simulation model of the front vehicle is obtained by the method of computational fluid dynamics. The simulation model has a vehicle to be followed shape database, a vehicle speed database and a wind speed database. The input of the vortex simulation model includes crosswind speed and crosswind direction simulation parameters, vehicle speed simulation parameters of the front vehicle, vehicle shape parameters of the front vehicle. The output of the vortex simulation model is the coordinate simulation parameters of the position with strong negative pressure of the vortex of the front vehicle, that is, the simulation following position. The simulation following position output by the flow field simulation model is combined with the vortex measurement data obtained by the vehicle following test to construct a neural network for iterative training to obtain a trained vortex simulation model. The trained vortex simulation model can be loaded on the target vehicle to determine the simulation following position according to the identified front vehicle shape information, vehicle speed information and wind speed information. The vortex simulation model trained by the neural network has faster calculation speed, smaller error of the determined following position and the actual strongest vortex intensity position, and can realize more rapid and accurate following strategy.
[0082] Specifically constructing the trained wake vortex simulation model can include the following steps:
[0083] S210, constructing an initial neural network model;
[0084] With the error between the measurement value of the position of the strong negative pressure of the wake vortex of the preceding vehicle output by the initial neural network model and the actual position of the strong negative pressure of the wake vortex of the preceding vehicle being minimized as the target, the crosswind speed and direction simulation parameters, the vehicle speed simulation parameters of the preceding vehicle, and the shape parameters of the preceding vehicle are input into the initial neural network model for iterative training to obtain a target neural network model for obtaining the measurement value of the position of the strong negative pressure of the wake vortex of the preceding vehicle (simulated following vehicle position). The type of the initial neural network model can be a feedback neural network model, a deep learning neural network model, a convolutional neural network model, etc., which is not limited herein. According to the type of the initial neural network model, the operation of step training can be completed. Specifically, the initial neural network model can be understood as an untrained target neural network model, which can output the measurement value of the initial position of the strong negative pressure of the wake vortex of the preceding vehicle by calculating the input crosswind speed and direction simulation parameters, the vehicle speed simulation parameters of the preceding vehicle through the neural network. Under normal circumstances, the initial neural network model can include an input layer, a hidden layer, and an output layer, wherein the hidden layer is responsible for related calculations of the neural network. By iterative training, the weight parameters in the hidden layer and other related transfer function parameters can be gradually adjusted, so that the initial wheel core vertical displacement measurement signal output by the initial neural network model meets the predetermined training target. At this time, the initial neural network model can be considered as the target neural network model, and the measurement value of the initial position of the strong negative pressure of the wake vortex of the preceding vehicle output by the initial neural network model can be considered as the measurement value of the position of the strong negative pressure of the wake vortex of the preceding vehicle.
[0085] S220, obtaining an initial wake vortex simulation model of the preceding vehicle, including: obtaining an initial wake vortex simulation model of the preceding vehicle, inputting the crosswind speed parameter, the crosswind direction parameter, the vehicle speed parameter of the vehicle to be followed, and the shape parameter of the vehicle to be followed into the wake vortex simulation model for simulation to obtain the coordinate simulation parameter of the position of the strong negative pressure of the wake vortex of the preceding vehicle output by the initial wake vortex simulation model. The wake vortex simulation model of the preceding vehicle is obtained by a method of computational fluid dynamics; wherein the preceding vehicle is a specific vehicle type with known shape size parameters in the database, i.e. a target type vehicle (also referred to as the preceding vehicle), the wake vortex simulation model input includes the crosswind speed and direction simulation parameters, the vehicle speed simulation parameters of the preceding vehicle, and the wake vortex simulation model output is the coordinate simulation value of the position of the strong negative pressure of the wake vortex of the preceding vehicle, i.e. the preset simulation following vehicle position.
[0086] S230, obtain the wake vortex measurement data of the following test, based on the crosswind speed and direction and the vehicle speed of the target type vehicle actually running, and obtain the test sensing signal through the whole vehicle sensor group on the vehicle behind the target type vehicle; wherein the whole vehicle sensor group includes one or more of ALPHA sensor, pitot tube, pressure sensor, millimeter wave radar, camera. Based on the test sensing signal and the simulation output value, the initial wake vortex simulation model of the front vehicle is optimized to the wake vortex simulation model of the front vehicle.
[0087] S240, training the neural network model according to the initial simulation data of the wake vortex and the wake vortex measurement data of the following test to obtain the wake vortex simulation model. The error between the initial simulation data and the wake vortex measurement data of the following test is minimized as the target, the crosswind speed and direction simulation parameters and the vehicle speed simulation parameters of the front vehicle are input into the initial neural network model for iterative training to obtain the target neural network model for measuring the value of the position with strong negative pressure of the wake vortex of the front vehicle. Specifically, the wake vortex simulation model of the front vehicle obtained by step S220 can obtain multiple sets of crosswind speed and direction simulation parameters, vehicle speed simulation parameters of the front vehicle, and coordinate simulation values of the position with strong negative pressure of the wake vortex of the front vehicle (preset simulation following position) and wake vortex measurement data of the following test, so as to construct a training set of the initial neural network model, complete the iterative training of the initial neural network model, and obtain the target neural network model for measuring the value of the position with strong negative pressure of the wake vortex of the front vehicle, i.e. the wake vortex simulation model.
[0088] In summary, the following control method proposed in the embodiment of the application is used to determine the simulation following position according to the recognized front vehicle shape information, vehicle speed information and wind speed information through the trained wake vortex simulation model, the calculation speed is faster, the error of the determined following position and the actual maximum position of the wake vortex intensity is smaller, a more rapid and accurate following strategy can be realized, and the energy consumption of the following vehicle can be effectively saved.
[0089] In some examples, the above method further comprises:
[0090] Obtaining the front head pressure data and the rear pressure data of the target vehicle at different positions of the wake vortex area corresponding to the vehicle to be followed;
[0091] Based on the front head pressure data and the rear pressure data, the wake vortex measurement data of the following test is obtained.
[0092] For example, Figure 4 and Figure 5As shown, in some vehicles, 4 patch pressure sensors are arranged at the position of the vehicle head area, and 8 patch pressure sensors are arranged at the position of the vehicle tail area. Analogous to following a vehicle, the absolute pressure value of the vehicle head at the position where the negative pressure of the front vehicle tail vortex is strong and the front and rear pressure difference are measured. During the test, the position where the negative pressure of the front vehicle tail vortex is strong and the preset range near the position are measured multiple times to test whether the area where the negative pressure of the front vehicle tail vortex is strong is accurate, and the measurement results are summarized to form following test tail vortex measurement data for training the tail vortex simulation model. It can be understood that the following test test can change the shape of the front vehicle, the speed of the front vehicle and the wind speed to obtain more comprehensive following test tail vortex measurement data under different following conditions.
[0093] In summary, the following control method provided by the embodiments of the present application adds pressure sensors to the front end and the rear end of the target vehicle, obtains following test tail vortex measurement data through a following test, and optimizes the tail vortex simulation model based on the neural network according to the following test tail vortex measurement data, so as to obtain a more accurate tail vortex simulation model, which can provide a more accurate simulation following position for the target vehicle in actual following, so that the position where the negative pressure of the tail vortex is strong can be more fully utilized to achieve the purpose of energy-saving following.
[0094] In some examples, the above-mentioned control of the above-mentioned target vehicle to follow the vehicle includes:
[0095] In the case that the simulation following position is in the current driving lane of the vehicle to be followed and the distance between the simulation following position and the vehicle to be followed is greater than a legal distance, the current driving lane road information behind the vehicle to be followed is obtained, wherein the legal distance is the shortest following distance allowed under the current road condition and the current speed.
[0096] In the case that there is no other vehicle driving within a first following distance behind the vehicle to be followed, the target vehicle is controlled to drive to the simulation following position to follow the vehicle, wherein the first following distance is determined based on the simulation following position and the size of the shape of the target vehicle.
[0097] For example, after obtaining the simulation following position through the tail vortex simulation model, the lane line information is obtained through the radar in front of the target vehicle or the radar behind the vehicle to be followed, and the simulation following position and the position of the lane line are judged by the vehicle to be followed, the target vehicle or the cloud. If the simulation following position is in the current driving lane of the vehicle to be followed, for example Figure 6the recommended position A, the distance between the simulation following position and the to-be-followed vehicle is obtained, that is, the car distance of the recommended position A and the to-be-followed vehicle, if the car distance is greater than the legal distance, it is determined whether there is another vehicle within the first following distance behind the to-be-followed vehicle, that is, it is determined whether the target vehicle can interfere with the rear vehicle if the target vehicle drives to the recommended position A, and if there is no other vehicle within the first following distance, the target vehicle is controlled to drive to the recommended position A for following.
[0098] In summary, the embodiment of the present application provides a target vehicle following control method for a simulation following position appearing on the current driving road of a to-be-followed vehicle, which can ensure the safety of the distance from the front vehicle during following and will not affect the normal driving of the rear vehicle.
[0099] In some examples, the above control of the target vehicle for following based on the above relative position relationship includes:
[0100] In the case that the simulation following position is in the adjacent lane of the to-be-followed vehicle, the road information of the adjacent lane behind the to-be-followed vehicle is obtained.
[0101] In the case that there is no other vehicle driving within the second following distance of the adjacent road behind the to-be-followed vehicle, the target vehicle is controlled to drive to the simulation following position for following, wherein the second following distance is determined based on the simulation following position, the size of the target vehicle, and the lane width.
[0102] For example, if the simulation following position is in the adjacent lane of the to-be-followed vehicle, such as Figure 6 the recommended position B in the above, it is determined whether there is another vehicle within the second following distance in the adjacent lane behind the to-be-followed vehicle, that is, it is determined whether the target vehicle can interfere with the rear vehicle if the target vehicle drives to the recommended position B, and if there is no other vehicle within the second following distance, the target vehicle is controlled to drive to the recommended position B for following. It should be noted that the second distance is determined based on the simulation following position, the size of the target vehicle, and the lane width, that is, a distance that can ensure that the target vehicle will not affect the normal driving of the rear vehicle during following the to-be-followed vehicle.
[0103] In summary, the embodiment of the present application provides a target vehicle following control method for a simulation following position appearing on the current driving road of a to-be-followed vehicle, which can ensure the safety of the distance from the front vehicle during following and will not affect the normal driving of the rear vehicle.
[0104] In some examples, the above-mentioned controlling the target vehicle to follow the preceding vehicle based on the relative position relationship comprises:
[0105] In a case where the simulation following position is on a lane line of a current lane and a neighboring lane of the preceding vehicle, acquiring neighboring road information and current road information behind the preceding vehicle;
[0106] In a case where no other vehicle is running within a third following distance of the neighboring lane and the current lane of the preceding vehicle, controlling the target vehicle to run to the simulation following position to follow the preceding vehicle;
[0107] Monitoring vehicle running information behind the target vehicle;
[0108] In a case where other vehicles appear within a preset safety distance behind the target vehicle, controlling the target vehicle to run to a current lane of the preceding vehicle.
[0109] For example, the simulation following position can also appear on a lane line of a current lane and a neighboring lane, in which case it is acquired whether other vehicles are running within a third following distance of the neighboring lane and the current lane of the preceding vehicle, and in a case where no other vehicle is running, the target vehicle is controlled to follow the preceding vehicle to the simulation following position. During the following, the vehicle behind the target vehicle is monitored, and when other vehicles appear within a preset safety distance of the target vehicle, the target vehicle is controlled to run in the same lane as the preceding vehicle to avoid the oncoming vehicle.
[0110] In summary, the embodiment of the present application provides a target vehicle following control method for a simulation following position appearing on a lane line, which can effectively follow the vehicle and will not affect the normal running of the neighboring lane and the current vehicle.
[0111] In some examples, as shown in Figure 7 and Figure 8 , a plurality of vehicles can run in a platoon, and the vehicles in the platoon can be staggered to fully utilize the negative pressure of the vortex at the tail of the preceding vehicle to save fuel or energy consumption when the rear vehicle runs. Two or more vehicles can run in the same or adjacent lanes in a staggered following manner and temporarily occupy the lane line.
[0112] Referring to Figure 9 , one embodiment of the vehicle following control device in the embodiment of the present application can comprise:
[0113] The first acquisition unit 21 is configured to acquire running information of the preceding vehicle, wherein the running information comprises vehicle speed information and wind speed information;
[0114] The second acquisition unit 22 is configured to acquire a simulation following position of the target vehicle by taking the vehicle speed information and the wind speed information as inputs of a wake vortex simulation model, wherein the wake vortex simulation model is obtained by iterative training based on a fluid dynamics simulation method and a neural network method.
[0115] The determination unit 23 is configured to determine a relative position relationship between the simulation following position and the to-be-followed vehicle based on the lane line information.
[0116] The control unit 24 is configured to control the target vehicle to follow the to-be-followed vehicle based on the relative position relationship.
[0117] As shown in Figure 10 The electronic device 300 is used to implement the method for controlling following according to the embodiments of the present application, and the specific implementation of the electronic device 300 and various changes thereof can be understood by those skilled in the art based on the method described in the embodiments of the present application. Therefore, the implementation of the electronic device 300 in the method according to the embodiments of the present application will not be described in detail, and the electronic device used to implement the method according to the embodiments of the present application belongs to the scope of protection of the present application.
[0118] The electronic device 300 is used to implement the method for controlling following according to the embodiments of the present application, and the specific implementation of the electronic device 300 and various changes thereof can be understood by those skilled in the art based on the method described in the embodiments of the present application. Therefore, the implementation of the electronic device 300 in the method according to the embodiments of the present application will not be described in detail, and the electronic device used to implement the method according to the embodiments of the present application belongs to the scope of protection of the present application.
[0119] In the implementation process, the computer program 311 can implement Figure 1 any of the embodiments of the corresponding embodiments.
[0120] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.
[0121] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.
[0122] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks. Figure 1 one or more flowcharts and / or blocks.
[0123] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks. Figure 1 one or more flowcharts and / or blocks.
[0124] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks. Figure 1 one or more flowcharts and / or blocks.
[0125] The embodiments of the present application also provide a computer program product, which comprises computer software instructions, when the computer software instructions are executed on a processing device, causing the processing device to perform the steps of the follow-up control in the corresponding embodiments. the flowchart of the follow-up control in the corresponding embodiments.
[0126] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that the computer can store or be integrated into a data storage device such as a server, data center, etc. containing one or more available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.
[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.
[0128] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.
[0129] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.
[0130] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.
[0131] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in the form of a contribution to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0132] The above, the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some of the technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.
Claims
1. A vehicle following control method, characterized in that, include: Multiple three-dimensional flow field simulation models were constructed based on fluid dynamics simulation methods and vehicle shape databases; Based on the vehicle speed database, wind speed database, and the three-dimensional flow field simulation model, a preset simulation following position is obtained through simulation. By using four patch pressure sensors located at the front of the vehicle and eight patch pressure sensors located at the rear of the vehicle, the front and rear pressure data of the target vehicle at different locations in the wake vortex zone corresponding to the vehicle to be followed are obtained. Based on the vehicle front pressure data and parking space pressure data, obtain the tail vortex measurement data of the following test; The wake vortex simulation model is obtained by iterative training based on a neural network method using the wake vortex measurement data from the following test and the preset simulated following position. Obtain the driving information of the vehicle to be followed, wherein the driving information includes vehicle speed information and wind speed information; The vehicle speed information and the wind speed information are used as inputs to the wake vortex simulation model to obtain the simulated following position of the target vehicle. The wake vortex simulation model is obtained through iterative training based on fluid dynamics simulation and neural network methods. The relative positional relationship between the simulated following position and the vehicle to be followed is determined based on lane line information; The target vehicle is controlled to follow the vehicle based on the relative positional relationship.
2. The method as described in claim 1, characterized in that, The driving information also includes vehicle exterior information; Using the wind speed information and vehicle speed information as inputs to the wake vortex simulation model to obtain the simulated following position of the target vehicle, including: Based on the vehicle shape information, the shape parameters of the vehicle to be followed are determined from the vehicle shape library of the wake vortex simulation model. Based on the wind speed information, the crosswind speed parameters and crosswind direction parameters are determined from the wind speed library of the wake vortex simulation model. Based on the vehicle speed information, the vehicle speed parameters are determined from the vehicle speed library of the wake vortex simulation model; The simulation calculation is performed using the vehicle shape parameters, crosswind speed parameters, crosswind direction parameters, and vehicle speed parameters as inputs to the wake vortex simulation model to obtain the simulated following position.
3. The method as described in claim 1, wherein controlling the target vehicle to follow another vehicle based on the relative positional relationship includes: When the simulated following position is in the current driving lane of the vehicle to be followed and the distance between the simulated following position and the vehicle to be followed is greater than the legal distance, the road information of the current driving lane behind the vehicle to be followed is obtained, wherein the legal distance is the shortest following distance allowed under the current road conditions and current vehicle speed. If no other vehicles are traveling within a first following distance behind the vehicle to be followed, the target vehicle is controlled to travel to the simulated following position to follow the vehicle. The first following distance is determined based on the simulated following position and the external dimensions of the target vehicle.
4. The method as described in claim 1, wherein controlling the target vehicle to follow another vehicle based on the relative positional relationship includes: When the simulated following position is in the adjacent lane of the vehicle to be followed, obtain the road information of the adjacent lane behind the vehicle to be followed; If no other vehicles are traveling within a second following distance on the adjacent road behind the vehicle to be followed, the target vehicle is controlled to travel to the simulated following position to follow the vehicle. The second following distance is determined based on the simulated following position, the external dimensions of the target vehicle, and the lane width.
5. The method as described in claim 1, wherein controlling the target vehicle to follow another vehicle based on the relative positional relationship comprises: When the simulated following position is the lane line between the current driving lane and the adjacent lane of the vehicle to be followed, the adjacent road information and the current driving road information behind the vehicle to be followed are obtained. If there are no other vehicles traveling within a third following distance between the adjacent lane and the current driving lane of the vehicle to be followed, control the target vehicle to drive to the simulated following position to follow the vehicle. Monitor the driving information of vehicles behind the target vehicle; If other vehicles appear within a preset safe distance behind the target vehicle, the target vehicle is controlled to travel in the current lane of the vehicle to be followed.
6. A vehicle following control device, characterized in that, include: The first acquisition unit is used to construct various three-dimensional flow field simulation models based on fluid dynamics simulation methods and vehicle shape databases; to perform simulations based on vehicle speed databases, wind speed databases, and the three-dimensional flow field simulation models to obtain a preset simulated following position; to acquire front and rear pressure data of the target vehicle at different positions in the wake vortex region corresponding to the vehicle to be followed by using four patch pressure sensors installed in the front area of the vehicle and eight patch pressure sensors installed in the rear area of the vehicle; to acquire wake vortex measurement data of the following test based on the front and rear pressure data; and to obtain a wake vortex simulation model by iteratively training the wake vortex measurement data of the following test and the preset simulated following position using a neural network method. Obtain the driving information of the vehicle to be followed, wherein the driving information includes vehicle speed information and wind speed information; The second acquisition unit is used to use the vehicle speed information and the wind speed information as inputs to the wake vortex simulation model to obtain the simulated following position of the target vehicle, wherein the wake vortex simulation model is obtained through iterative training based on fluid dynamics simulation method and neural network method. The determining unit is used to determine the relative positional relationship between the simulated following position and the vehicle to be followed based on lane line information; The control unit is used to control the target vehicle to follow the vehicle based on the relative positional relationship.
7. An electronic device, comprising: The memory and processor are characterized in that the processor is used to implement the steps of the vehicle following control method as described in any one of claims 1-5 when executing a computer program stored in the memory.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the following control method as described in any one of claims 1-5.
Citation Information
Patent Citations
Vehicle driving-support apparatus
CN102548821A
Trailing vehicle positioning system based on detected pressure zones
US20220105934A1