Vehicle control method and device

Abstract

The invention provides a vehicle control method and device, and relates to the technical field of vehicle control. The method comprises the following steps: receiving driving operation data of a driver for a vehicle; based on the driving operation data and a control system of the vehicle, a control instruction for the vehicle is determined; wherein the control parameters of the control system are determined based on the driving style of the driver; the driving style is determined by the target model based on historical driving operation data of a driver and corresponding historical vehicle driving data; and controlling the driving of the vehicle based on the control instruction. According to the vehicle control method and device, the intelligent degree of vehicle control can be improved.

Description

Technical Field

[0001] This application relates to the technical field of vehicle control, and particularly to a vehicle control method and device. Background Art

[0002] Driving style refers to the specific behaviors and habits demonstrated by a driver during the driving process, including characteristics such as acceleration, braking, and steering. Drivers with different driving styles adapt to different vehicle control parameters. For example, drivers with an aggressive driving style tend to select higher vehicle speeds and may frequently perform rapid acceleration and deceleration operations. Therefore, such drivers may require a more sensitive acceleration and braking system response, as well as higher torque output. Conservative drivers, on the other hand, place more emphasis on stability and safety. They may choose lower vehicle speeds and avoid rapid acceleration and deceleration. Such drivers may require smoother acceleration and braking characteristics, as well as lower torque output.

[0003] Currently, the recognition of a driver's driving style is not accurate enough. That is to say, the current vehicle control methods have a low level of intelligence. Summary of the Invention

[0004] This application provides a vehicle control method to solve the defect of the low level of intelligence in the existing vehicle control methods and improve the intelligence level of vehicle control.

[0005] In a first aspect, this application provides a vehicle control method, including:

[0006] Receiving driving operation data of the driver for the vehicle;

[0007] Based on the driving operation data and the vehicle control system, determining a control instruction for the vehicle; wherein, the control parameters of the control system are determined based on the driving style of the driver; the driving style is determined by a target model based on the driver's historical driving operation data and the corresponding historical vehicle driving data;

[0008] Controlling the driving of the vehicle based on the control instruction.

[0009] Optionally, the determination of the driving style is triggered based on at least one of the following conditions:

[0010] At intervals of a preset period;

[0011] Detecting that the cumulative driving distance of the vehicle reaches a preset condition;

[0012] Receiving a detection instruction for the driving style.

[0013] Optionally, the vehicle control method further includes:

[0014] If a driver switching instruction is received, query the driving style corresponding to the driver indicated by the driver switching instruction from the control system;

[0015] If the driving style corresponding to the driver indicated by the driver switching instruction is queried, directly use the control parameters corresponding to the queried driving style as the control parameters of the control system;

[0016] If the driving style corresponding to the driver indicated by the driver switching instruction is not queried, re-determine the driving style corresponding to the driver indicated by the driver switching instruction; and use the control parameters corresponding to the re-determined driving style as the control parameters of the control system.

[0017] Optionally, the vehicle control method further includes:

[0018] If a driving style change is detected, re-determine the control parameters based on the changed driving style and the previous driving style.

[0019] Optionally, the re-determining the control parameters based on the changed driving style and the previous driving style includes:

[0020] If the conservativeness of the changed driving style is higher than that of the previous driving style, directly use the control parameters corresponding to the changed driving style as the re-determined control parameters;

[0021] If the conservativeness of the changed driving style is lower than that of the previous driving style, determine a parameter increment based on the changed driving style and the previous driving style; and re-determine the control parameters based on the parameter increment.

[0022] Optionally, the historical driving operation data includes at least one of the extreme value of the steering wheel angle and the extreme value of the steering wheel angle change rate; the historical vehicle driving data includes at least one of the extreme value of the longitudinal vehicle speed, the extreme value of the lateral speed, and the extreme value of the yaw rate.

[0023] Optionally, the target model is trained in the following manner:

[0024] Perform at least one training operation on the initial model based on a sample training set until the training end condition is met, and use the initial model that meets the training end condition as the target model;

[0025] Wherein, the training operation includes:

[0026] Input the sample data in the sample training set into the initial model to obtain a predicted style; the sample data has a corresponding sample style;

[0027] For each sample data, determine the difference information between the predicted style and the sample style;

[0028] Based on the difference information corresponding to each sample data, determine the training loss;

[0029] If the training loss does not meet the training end condition, adjust the parameters of the initial model based on the training loss, and use the initial model with adjusted parameters as the initial model corresponding to the next training operation.

[0030] In a second aspect, the present application further provides a vehicle control device, including:

[0031] A receiving module, configured to receive driving operation data of a driver for a vehicle;

[0032] A determining module, configured to determine a control instruction for the vehicle based on the driving operation data and the control system of the vehicle; wherein, the control parameters of the control system are determined based on the driving style of the driver; the driving style is determined by a target model based on the historical driving operation data of the driver and the corresponding historical vehicle driving data;

[0033] A control module, configured to control the driving of the vehicle based on the control instruction.

[0034] In a third aspect, the present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the method described in the first aspect is implemented.

[0035] In a fourth aspect, the present application further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0036] In a fifth aspect, the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0037] The vehicle control method and device provided by the present application determine the driving style through historical driving operation data and the corresponding historical vehicle driving data, determine the control parameters of the control system through the driving style, determine the control instruction through the driving operation data and the control system, and thus control the driving of the vehicle, which can accurately identify the driving style of the driver, make the driving of the vehicle adapt to the driving habits of the driver, improve the intelligence level of vehicle control, and improve the driving experience. Description of the Drawings

[0038] To more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0039] Figure 1 is a schematic flowchart of a vehicle control method provided by an embodiment of the present application;

[0040] Figure 2 is a schematic structural diagram of a vehicle control device provided by an embodiment of the present application;

[0041] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0042] To make the objectives, technical solutions, and advantages of the present application clearer, the following will clearly and completely describe the technical solutions in the present application with reference to the drawings in the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present application.

[0043] Figure 1 is a schematic flowchart of a vehicle control method provided by an embodiment of the present application. Refer to Figure 1 , an embodiment of the present application provides a vehicle control method, the execution subject of which can be a control system. The control system can be set in a terminal or in a server. The terminal can include an in-vehicle terminal and a user terminal. The server can be a server that communicates with the vehicle, and the specific is not limited. The following will take the execution subject as the control system as an example for illustration. The method can include:

[0044] Step 110: Receive driving operation data of the driver for the vehicle;

[0045] Step 120: Determine a control command for the vehicle based on the driving operation data and the control system of the vehicle; wherein, the control parameters of the control system are determined based on the driving style of the driver; the driving style is determined by a target model based on the historical driving operation data of the driver and the corresponding historical vehicle driving data;

[0046] Step 130: Control the driving of the vehicle based on the control command.

[0047] In step 110, the control system can receive the driving operation data of the driver for the vehicle.

[0048] In step 120, the control system can determine a control command for the vehicle based on the driving operation data and the vehicle's own control system. Specifically, the driving operation data is the vehicle control command issued by the driver. The control system can receive the driver's vehicle control command and then convert it into a vehicle control command.

[0049] Among them, the control system can obtain the historical driving operation data of the driver driving the vehicle and the corresponding historical vehicle driving data. Specifically, the historical driving operation data and the corresponding historical vehicle driving data can be the data obtained when the driver makes a turn. The historical driving operation data is, for example, the extreme value of the steering wheel angle. The historical vehicle driving data is, for example, the extreme value of the yaw rate. By inputting the historical driving operation data and the corresponding historical vehicle driving data into the target model, the control system can obtain the driving style.

[0050] The target model can be a supervised training neural network model, such as a BP neural network model. The BP neural network can learn and store a large number of input-output pattern mapping relationships without revealing the mathematical equations describing this mapping relationship in advance. Its learning rule is to use the steepest descent method and continuously adjust the weights and thresholds of the network through backpropagation to minimize the sum of squared errors of the network.

[0051] The control system can determine the control parameters of the vehicle's control system based on the driving style. Specifically, it can be achieved by establishing a matching mapping relationship between the driving style and the control parameters. This part conducts cross-experiments based on different style drivers, different steering conditions, and different combinations of control parameters, and constructs the matching mapping relationship of the control parameters through subjective evaluation. Specifically, the driving style can include conservative, general, and aggressive types. Different driving styles correspond to different control parameters. Specifically, the control parameters can include understeer gradient, natural frequency, damping ratio, etc. The corresponding relationship between the driving style and the control parameters can be shown in the following table:

[0052] Understeer gradient Natural frequency Damping ratio Conservative type K1 ωn1 <![CDATA[ξ1]]> General type K2 ωn2 <![CDATA[ξ2]]> Aggressive type K3 ωn3 <![CDATA[ξ3]]>

[0053] In step 130, the control system can control the driving of the vehicle based on the control command.

[0054] The vehicle control method provided by the embodiments of the present application determines the driving style through the historical driving operation data and the corresponding historical vehicle driving data, determines the control parameters of the control system through the driving style, determines the control command through the driving operation data and the control system, and thus controls the driving of the vehicle. It can accurately identify the driver's driving style, make the driving of the vehicle adapt to the driver's driving habits, improve the intelligence level of vehicle control, and improve the driving experience.

[0055] In one embodiment, the determination of the driving style is triggered based on at least one of the following conditions: at intervals of a preset period; detecting that the cumulative driving distance of the vehicle reaches a preset condition; receiving a detection instruction for the driving style.

[0056] At intervals of a preset period (for example: 7 days), or detecting that the cumulative driving distance of the vehicle reaches a preset condition (for example: 20 km), or receiving a detection instruction for the driving style, or when any of the above conditions are met, the control system can determine the driving style based on the historical driving operation data of the driver and the corresponding historical vehicle driving data.

[0057] The vehicle control method provided by the embodiments of the present application triggers the detection process of the driving style through different conditions, so as to accurately and timely detect the driving style according to the actual needs of the driver, and then obtain control parameters to control the driving of the vehicle, making the driving of the vehicle adapt to the driving habits of the driver and improving the driving experience.

[0058] In one embodiment, the vehicle control method further includes: if a driver switching instruction is received, query the driving style corresponding to the driver indicated by the driver switching instruction from the control system; if the driving style corresponding to the driver indicated by the driver switching instruction is queried, directly use the control parameters corresponding to the queried driving style as the control parameters of the control system; if the driving style corresponding to the driver indicated by the driver switching instruction is not queried, re-determine the driving style corresponding to the driver indicated by the driver switching instruction; and use the control parameters corresponding to the re-determined driving style as the control parameters of the control system.

[0059] In practical applications, there may be a situation where the driver is changed. After receiving the driver switching instruction, the control system can quickly determine the driving style and update the control parameters according to the driving style. Specifically, if the driving style of the switched driver can be queried in the control system, the control parameters corresponding to the driving style can be directly used as the control parameters of the control system. If it cannot be queried, it is necessary to re-determine the driving style and update the control parameters.

[0060] The vehicle control method provided by the embodiments of the present application defines how to determine the control parameters in the case of driver switching to control the driving of the vehicle, making the vehicle control method more universal and improving the driving experience of the driver.

[0061] In one embodiment, the vehicle control method further includes: if a change in the driving style is detected, re-determine the control parameters based on the changed driving style and the driving style before the change.

[0062] After the driver is switched, or when the driving style of the same driver changes, a driving style change may occur. When the control system detects a driving style change, it can re-determine the control parameters based on the changed driving style and the driving style before the change.

[0063] The vehicle control method provided by the embodiments of the present application defines how to determine the control parameters in the case of a driving style change, controls the driving of the vehicle, makes the vehicle control method more universal, and improves the driving experience of the driver.

[0064] In one embodiment, re-determining the control parameters based on the changed driving style and the driving style before the change includes: if the conservativeness of the changed driving style is higher than that of the driving style before the change, directly using the control parameters corresponding to the changed driving style as the re-determined control parameters; if the conservativeness of the changed driving style is lower than that of the driving style before the change, determining a parameter increment based on the changed driving style and the driving style before the change; and re-determining the control parameters based on the parameter increment.

[0065] For example, if the changed driving style is a conservative type and the driving style before the change is an aggressive type, the control system can directly use the control parameters corresponding to the changed driving style as the re-determined control parameters.

[0066] If the changed driving style is an aggressive type and the driving style before the change is a conservative type, the control parameters can be re-determined based on the parameter increment.

[0067] Since each valid steering driving data (historical driving operation data and corresponding historical vehicle driving data) can output a driving style identification result, and then output corresponding control parameters, the expected yaw response characteristics of the whole vehicle can be reconfigured after one effective steering driving. However, considering that the recognition accuracy of the driving style recognition result cannot reach completely correct, the intentional or unintentional steering fluctuation of the driver or the style recognition error will cause the mutation of the control parameters, and correspondingly will cause the mutation of the expected yaw angular velocity, which is extremely likely to cause danger. In addition, this mutation is uncomfortable for the driver, and the frequent switching of the expected yaw characteristics makes it difficult for the driver and the vehicle to find a balance in mutual adaptation, deteriorating the driving experience. On the contrary, accumulating enough driving style recognition results and obtaining the mean value of the control expectation gain parameters, and configuring them as a stable steering mode, can better meet the expectations of a certain type of driver.

[0068] Taking into comprehensive consideration the stability and real-time adaptability of the expected yaw response, the present application can adopt the method of a style sliding window to achieve the smooth switching of the expected yaw response.

[0069] Let the number of driving style identifications in the style sliding window be N ds(That is, the number of characteristic data in the historical driving operation data and the corresponding historical vehicle driving data. For example, the historical driving operation data and the corresponding historical vehicle driving data include five data: the extreme value of the steering wheel angle, the extreme value of the longitudinal vehicle speed, the extreme value of the steering wheel angle change rate, the extreme value of the lateral speed, and the extreme value of the yaw rate. The number of driving style identifications is 5), and the single style identification result is S i (That is, the style identification result obtained from one of the extreme value of the steering wheel angle, the extreme value of the longitudinal vehicle speed, the extreme value of the steering wheel angle change rate, the extreme value of the lateral speed, and the extreme value of the yaw rate), then the driving style identification result output by the single style sliding window (that is, the driving style identified by the target model for the five driving characteristic data of the extreme value of the steering wheel angle, the extreme value of the longitudinal vehicle speed, the extreme value of the steering wheel angle change rate, the extreme value of the lateral speed, and the extreme value of the yaw rate for one effective steering) S is:

[0070]

[0071] As the number of effective steering operations of the driver increases, the driving style identification result based on the style sliding window will be continuously evolved and updated. Denote the update cycle of the current style sliding window as m, and the corresponding driving style (that is, the driving style before change) identification result as S m (That is, the driving style obtained from the five driving characteristic data of the extreme value of the steering wheel angle, the extreme value of the longitudinal vehicle speed, the extreme value of the steering wheel angle change rate, the extreme value of the lateral speed, and the extreme value of the yaw rate obtained from one effective steering); after a style sliding window cycle, the driving style identification result (that is, the driving style after change) is updated to S m+1 (That is, the driving style obtained from the five driving characteristic data of the extreme value of the steering wheel angle, the extreme value of the longitudinal vehicle speed, the extreme value of the steering wheel angle change rate, the extreme value of the lateral speed, and the extreme value of the yaw rate obtained from another effective steering). Then the parameter increment ΔP m can be expressed as:

[0072] ΔP m =f1(S m ,S m+1 )

[0073] where f1 is a cyclic period function.

[0074] Denote the control parameter (the control parameter corresponding to the driving style before change) under the current style sliding window as P m , then the control parameter (the control parameter corresponding to the driving style after change) P m+1 after a style sliding window cycle can be expressed as:

[0075] P m+1 =P m +ΔP m

[0076] As the driving styles converge, the control parameters will also converge, thereby completing the self-evolution update process of the control expected parameters for the changed driving styles.

[0077] The changed driving style is aggressive, and the driving style before the change is conservative. After driving for a period of time, the driving style will be recognized as an aggressive style from a conservative style. At the same time, control parameters such as the understeer gradient, natural frequency, and damping ratio gradually evolve from K1, ωn1, ξ1 to K2, ωn2, ξ2, thus completing the online self-evolution of the control parameters.

[0078] The vehicle control method provided by the embodiments of the present application can control the driving of the vehicle by updating the control parameters when the driving style changes, enabling the driving of the vehicle to fully adapt to the driver's habits, improving the intelligence level of vehicle control, and enhancing the driving experience.

[0079] In one embodiment, the historical driving operation data includes at least one of the extreme value of the steering wheel angle and the extreme value of the steering wheel angle change rate; the historical vehicle driving data includes at least one of the extreme value of the longitudinal vehicle speed, the extreme value of the lateral speed, and the extreme value of the yaw rate.

[0080] Through data analysis, variables that can fully characterize the driver's steering characteristics can be determined as the historical driving operation data and the corresponding historical vehicle driving data. For the driver input variables, the extreme value of the driver's steering wheel angle, the extreme value of the longitudinal vehicle speed, and the extreme value of the steering wheel angle change rate can be selected; for the vehicle state variables, the extreme value of the yaw rate and the extreme value of the lateral speed can be selected, and both are used as the historical driving operation data and the corresponding historical vehicle driving data.

[0081] The vehicle control method provided by the embodiments of the present application uses the extreme value of the steering wheel angle, the extreme value of the longitudinal vehicle speed, the extreme value of the steering wheel angle change rate, the extreme value of the lateral speed, and the extreme value of the yaw rate as historical data, and then obtains the driving style through the target model, which can improve the accuracy of driving style recognition and the intelligence level of vehicle control.

[0082] In one embodiment, the target model is trained in the following manner: performing at least one training operation on the initial model based on the sample training set until the training end condition is met, and using the initial model that meets the training end condition as the target model; wherein, the training operation includes: inputting the sample data in the sample training set into the initial model to obtain the predicted style; the sample data has a corresponding sample style; for each sample data, determining the difference information between the predicted style and the sample style; based on the difference information corresponding to each sample data, determining the training loss; if the training loss does not meet the training end condition, adjusting the parameters of the initial model based on the training loss, and using the initial model with adjusted parameters as the initial model corresponding to the next training operation.

[0083] Specifically, the sample data can be the model input vector of the initial model, the predicted style can be the model prediction output, the sample style can be the model expected output, the difference information can be the model prediction error, and the training loss can be the model average error.

[0084] The target model can be trained in the following way: based on the model input vector, the first connection weight, the hidden layer bias, and the hidden layer non-linear activation function, determine the hidden layer output; based on the hidden layer output, the second connection weight, and the output layer bias, determine the model prediction output; based on the model prediction output and the model expected output, determine the model prediction error; based on the model prediction error, update the first connection weight, the second connection weight, the hidden layer bias, and the output layer bias; and based on the model prediction error, determine the model average error; when the model average error meets the training end condition, obtain the target model.

[0085] This application can establish a mapping and matching relationship between the historical driving operation data of the driver and the corresponding historical vehicle driving data and driving style. For example, select drivers with different driving styles (such as aggressive, balanced, and conservative), and collect driving data under different working condition designs (such as different driving behaviors (such as single lane change, double lane change, right-angle turn, etc.)) by means of a driving simulator or a real vehicle. Select characteristic parameters (such as maximum steering angle, maximum vehicle speed, steering wheel angle and angular velocity, etc.) to realize the feature extraction of the driving data, and obtain the historical driving operation data and the corresponding historical vehicle driving data. Since the driver style that generates the historical driving operation data and the corresponding historical vehicle driving data is known, a data set with driving style labels can be constructed accordingly. Based on this data set, a supervised learning neural network can be built, with the input being the historical driving operation data and the corresponding historical vehicle driving data, and the output being the driving style.

[0086] The historical driving operation data and the corresponding historical vehicle driving data obtained based on the above situation are high-dimensional time-domain driving data, and the number of sampling points is determined by the sampling time and the total working condition duration. This high-dimensional data cannot be used for subsequent driving style recognition, so it is necessary to perform a dimensionality reduction operation on the high-dimensional time-domain driving data. Specifically, variables that can fully characterize the driver's steering characteristics can be selected as samples of the historical driving operation data and the corresponding historical vehicle driving data to obtain a low-dimensional database, and this part can be performed offline.

[0087] In the low-dimensional database, the model input vector, that is, the historical driving operation data and the corresponding historical vehicle driving data sample X is:

[0088]

[0089] Wherein, is the extreme value of the steering wheel angle, is the extreme value of the longitudinal vehicle speed, is the extreme value of the steering wheel angle change rate, is the extreme value of the lateral speed, γ ep is the extreme value of the yaw rate.

[0090] The expected output of the model, i.e., the driving style label Y, is:

[0091] Y = [0, 1, 2] T

[0092] Among them, the definition example of the driving style identification result is as follows:

[0093] Driving style Identification result Conservative type 0 General type 1 Aggressive type 2

[0094] Therefore, the reconstructed low-dimensional database, i.e., the sample database Ω, can be expressed as:

[0095] Ω = {(x i , y i ) | x i ∈X, y i ∈Y, i = 1, 2, …, m}

[0096] Among them, x i is the sample of the sample database, i.e., the historical driving operation data and the corresponding historical vehicle driving data sample, y i is the label of the sample database, i.e., the driving style label, and m is the number of samples in a style sliding window.

[0097] The sample database provides a sample training set for the training of the target model.

[0098] First, the number of input layer nodes, the number of hidden layer nodes, and the number of output layer nodes of the initial model can be determined according to the input and output of the sample database. Then, the first connection weight V ik between the input layer and the hidden layer, and the second connection weight W kj between the output layer and the hidden layer are initialized. Finally, the hidden layer bias a k , the output layer bias b j are initialized, and the learning rate η and the hidden layer non-linear activation function are determined.

[0099] Then, according to the model input vector x i , the first connection weight V ik , the hidden layer bias a k and the hidden layer non-linear activation function f2, the hidden layer output z k is calculated as follows:

[0100]

[0101] Among them, n is the number of input layer nodes and q is the number of hidden layer nodes.

[0102] Then, according to the output z of the hidden layer k , the second connection weight W kj and the output layer bias b j , calculate the predicted output O of the model j :

[0103]

[0104] where q is the number of hidden layer nodes and l is the number of output layer nodes.

[0105] According to the predicted output O of the model j and the expected output Y of the model j , calculate the prediction error e of the model j :

[0106] e j = Y j - O j , j = 1, 2, …, l

[0107] where l is the number of output layer nodes.

[0108] According to the prediction error e of the model j , the first connection weight V ik can be updated to V ik ′, and the second connection weight W kj can be updated to W kj ′:

[0109]

[0110] W kj ′ = W kj + ηz k e j

[0111] i = 1, 2, …, n

[0112] k = 1, 2, …, q

[0113] j = 1, 2, …, l

[0114] where η is the learning rate, n is the number of input layer nodes, q is the number of hidden layer nodes, and l is the number of output layer nodes.

[0115] According to the prediction error e of the model j , the hidden layer bias a k can be updated to a k ′, and the output layer bias b j can be updated to b j ′:

[0116]

[0117] b j ′ = b j + e j

[0118] i = 1, 2, …, n

[0119] k = 1, 2, …, q

[0120] j = 1, 2, …, l

[0121] Among them, η is the learning rate, n is the number of nodes in the input layer, q is the number of nodes in the hidden layer, and l is the number of nodes in the output layer.

[0122] According to the model prediction error e j Calculate the model average error E:

[0123]

[0124] Among them, m is the number of samples in a style sliding window.

[0125] According to the calculated model average error, determine whether the algorithm iteration process can end. When the model average error meets the training end condition, obtain the target model. If the training end condition is not met, recalculate the output of the hidden layer.

[0126] The vehicle control method provided by the embodiments of the present application can improve the accuracy of driving style recognition and the robustness of the model by training the initial model to obtain the target model.

[0127] Based on the descriptions of the above embodiments, the vehicle control method provided by the present application serves as a pre-module of a distributed drive control torque vector multi-objective optimization controller, and realizes the self-evolution of the "vehicle adapting to people" control system by adjusting control parameters. This function first constructs an offline database (i.e., a sample database) and constructs a mapping and matching relationship between driving styles and control parameters. Then, by online collecting effective driving data for the current driver, online analyze the personalized driving style of the driver and extract the control parameters corresponding to the driving style of the current driver. These control parameters will be sent as characteristic parameters matching the driving style and driving expectations of the current driver to the reference target calculation module, thereby adjusting the vehicle controller to evolve in the direction that meets the driving needs of the current driver, so as to achieve the development goal of "vehicle adapting to people".

[0128] The vehicle control device provided by the present application is described below. The vehicle control device described below can be mutually referred to the vehicle control method described above.

[0129] Figure 2 is a schematic structural diagram of the vehicle control device provided by the embodiments of the present application. Refer toFigure 2 , the vehicle control device provided by the embodiment of the present application may include:

[0130] A receiving module 210, configured to receive driving operation data of a driver for a vehicle;

[0131] A determining module 220, configured to determine a control instruction for the vehicle based on the driving operation data and the control system of the vehicle; wherein, the control parameters of the control system are determined based on the driving style of the driver; the driving style is determined by a target model based on the historical driving operation data of the driver and the corresponding historical vehicle driving data;

[0132] A control module 230, configured to control the driving of the vehicle based on the control instruction.

[0133] The vehicle control device provided by the embodiment of the present application determines the driving style through the historical driving operation data and the corresponding historical vehicle driving data, determines the control parameters of the control system through the driving style, determines the control instruction through the driving operation data and the control system, and thus controls the driving of the vehicle, which can accurately identify the driving style of the driver, make the driving of the vehicle adapt to the driving habits of the driver, improve the intelligence level of vehicle control, and improve the driving experience.

[0134] Specifically, the above vehicle control device provided by the embodiment of the present application can implement all the method steps implemented by the above method embodiment, and can achieve the same technical effects. The same parts and beneficial effects as those in the method embodiment will not be specifically described herein.

[0135] Figure 3 is a schematic structural diagram of an electronic device provided by the embodiment of the present application. As Figure 3 shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 complete mutual communication through the communication bus 340. The processor 310 may call logic instructions in the memory 330 to execute a vehicle control method, for example, including:

[0136] Receiving driving operation data of a driver for a vehicle;

[0137] Based on the driving operation data and the control system of the vehicle, determining a control instruction for the vehicle; wherein, the control parameters of the control system are determined based on the driving style of the driver; the driving style is determined by a target model based on the historical driving operation data of the driver and the corresponding historical vehicle driving data;

[0138] Control the driving of the vehicle based on the control instruction.

[0139] In addition, when the logical instructions in the above-mentioned memory 330 can be implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0140] On the other hand, this application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is used to execute the steps of the vehicle control method provided by the above-mentioned various methods, for example, including:

[0141] Receive driving operation data of the vehicle from the driver;

[0142] Based on the driving operation data and the control system of the vehicle, determine a control instruction for the vehicle; wherein, the control parameters of the control system are determined based on the driving style of the driver; the driving style is determined by a target model based on the historical driving operation data of the driver and the corresponding historical vehicle driving data;

[0143] Control the driving of the vehicle based on the control instruction.

[0144] On yet another aspect, this application also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the steps of the vehicle control method provided by the above-mentioned various methods, for example, including:

[0145] Receive driving operation data of the vehicle from the driver;

[0146] Based on the driving operation data and the control system of the vehicle, determine a control instruction for the vehicle; wherein, the control parameters of the control system are determined based on the driving style of the driver; the driving style is determined by a target model based on the historical driving operation data of the driver and the corresponding historical vehicle driving data;

[0147] Control the driving of the vehicle based on the control instruction.

[0148] The device embodiments described above are merely illustrative. 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 to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

[0149] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0150] In addition, it should be noted that: In the embodiments of the present application, terms such as "first" and "second" are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are usually of the same type, and the number of objects is not limited. For example, the first object can be one or multiple.

[0151] In the embodiments of the present application, the term "and / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0152] "Determining B based on A" in the embodiments of this application means that the factor A should be considered when determining B. It is not limited to "determining B only based on A", but also includes: "determining B based on A and C", "determining B based on A, C, and E", "determining C based on A and further determining B based on C", etc. Additionally, it may also include using A as a condition for determining B. For example, "when A meets the first condition, use the first method to determine B"; for another example, "when A meets the second condition, determine B"; for yet another example, "when A meets the third condition, determine B based on the first parameter", etc. Of course, it can also be that A is used as a condition for the factor of determining B. For example, "when A meets the first condition, use the first method to determine C and further determine B based on C", etc.

[0153] In the embodiments of this application, the term "a plurality of" means two or more, and other quantifiers are similar.

[0154] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of this application, rather than to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A vehicle control method, characterized in that, Including: Receiving driving operation data of the vehicle by the driver; Based on the driving operation data and the control system of the vehicle, determining a control instruction for the vehicle; wherein, the control parameters of the control system are determined based on the driving style of the driver; the driving style is determined by a target model based on the historical driving operation data of the driver and the corresponding historical vehicle driving data; Controlling the driving of the vehicle based on the control instruction.

2. The vehicle control method according to claim 1, wherein The determination of the driving style is triggered based on at least one of the following conditions: An interval of a preset period; Detecting that the cumulative driving distance of the vehicle reaches a preset condition; Receiving a detection instruction for the driving style.

3. The vehicle control method according to claim 1, characterized in that Further including: If a driver switching instruction is received, querying the driving style corresponding to the driver indicated by the driver switching instruction from the control system; If the driving style corresponding to the driver indicated by the driver switching instruction is queried, directly using the control parameters corresponding to the queried driving style as the control parameters of the control system; If the driving style corresponding to the driver indicated by the driver switching instruction is not queried, re-determining the driving style corresponding to the driver indicated by the driver switching instruction; And using the control parameters corresponding to the re-determined driving style as the control parameters of the control system.

4. The vehicle control method according to claim 1, wherein, Further including: If a driving style change is detected, re-determining the control parameters based on the changed driving style and the previous driving style.

5. The vehicle control method according to claim 4, wherein, The re-determining the control parameters based on the changed driving style and the previous driving style includes: If the conservativeness of the changed driving style is higher than that of the previous driving style, directly using the control parameters corresponding to the changed driving style as the re-determined control parameters; If the conservativeness of the changed driving style is lower than that of the previous driving style, determining a parameter increment based on the changed driving style and the previous driving style; and re-determining the control parameters based on the parameter increment.

6. The vehicle control method according to claim 1, characterized in that The historical driving operation data includes at least one of the extreme value of the steering wheel angle and the extreme value of the steering wheel angle change rate; the historical vehicle driving data includes at least one of the extreme value of the longitudinal vehicle speed, the extreme value of the lateral speed, and the extreme value of the yaw rate.

7. The vehicle control method according to claim 1, wherein The target model is trained in the following manner: Performing at least one training operation on the initial model based on a sample training set until the training end condition is met, and using the initial model that meets the training end condition as the target model; Wherein, the training operation includes: Inputting the sample data in the sample training set into the initial model to obtain a predicted style; the sample data has a corresponding sample style; For each sample data, determining the difference information between the predicted style and the sample style; Determining a training loss based on the difference information corresponding to each sample data; If the training loss does not meet the training end condition, adjusting the parameters of the initial model based on the training loss, and using the initial model with adjusted parameters as the initial model corresponding to the next training operation.

8. A vehicle control device, characterized in that, Including: A receiving module for receiving driving operation data of the vehicle by the driver; A determination module, configured to determine a control instruction for the vehicle based on the driving operation data and the control system of the vehicle; wherein, a control parameter of the control system is determined based on the driving style of the driver; the driving style is determined by a target model based on the historical driving operation data of the driver and the corresponding historical vehicle driving data; A control module, configured to control the driving of the vehicle based on the control instruction.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the vehicle control method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing a computer program thereon, characterized in that, When the computer program is executed by a processor, it implements the vehicle control method according to any one of claims 1 to 7.

Images