Brake control method and vehicle

Abstract

The invention provides a braking control method and a vehicle, and relates to the technical field of vehicle braking. The method comprises the following steps: acquiring braking parameters and driving parameters of a vehicle and biological data of a driver at the current moment; determining a driving style, a driving intention and a driving state of the driver at the current moment according to the driving parameters and the biological data; wherein the driving style is used for representing the preference of the driving behavior of the driver, the driving intention is used for representing the driving behavior of the driver in a preset scene, and the driving state is used for representing the physiological and psychological states of the driver; according to the driving style, the driving intention and the driving state, a braking control instruction corresponding to the braking parameters is determined; according to the technical scheme, braking control is conducted on the vehicle on the basis of the braking control instruction, braking control can be effectively adjusted according to the actual driving condition, and therefore the actual braking effect adapts to the driving behavior of a driver, the driving comfort is improved, and the driving safety is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle braking, in particular to a braking control method and a vehicle. BACKGROUND

[0002] With the continuous improvement of people's travel needs, cars have become the first choice for most people to go out. The braking system of the vehicle is an important part to ensure the safe driving of the car, mainly including driving braking and parking braking. In driving braking, the driver steps on the brake pedal to generate braking force to realize braking of the vehicle during driving.

[0003] In the related art, during the process of the driver stepping on the brake pedal for deceleration braking, the brake pedal feel provided by the braking system depends on the pedal feel curve calibrated in advance during development to implement the braking process. The pedal feel curve is fixed and only a single pedal feel can be provided, which is difficult to fully meet the braking needs of the driver during driving. SUMMARY

[0004] The embodiments of the present application provide a braking control method and a vehicle to perform braking control on the basis of considering the driving behavior of the driver, improve the comfort and safety of driving.

[0005] In a first aspect, the embodiments of the present application provide a braking control method, comprising: obtaining braking parameters, driving parameters and biological data of the driver of the vehicle at the current time; determining the driving style, driving intention and driving state of the driver at the current time according to the driving parameters and the biological data; wherein the driving style is used to represent the preference of the driving behavior of the driver, the driving intention is used to represent the driving behavior of the driver in the preset scene, and the driving state is used to represent the physiological and psychological state of the driver; determining the braking control instruction corresponding to the braking parameters according to the driving style, the driving intention and the driving state; performing braking control on the vehicle based on the braking control instruction.

[0006] Based on the above technical content, the driving style, the driving intention and the driving state of the driver at the current time are determined by the driving parameter and the biological data of the driver at the current time, the driving behavior of the driver can be analyzed, and the braking needs of the driver are clear. The driving style is used to represent the preference of the driving behavior of the driver, the preference of the driver to the brake control can be analyzed through the driving style, and the braking characteristics of the driver are clear. The driving intention is used to represent the driving behavior of the driver in the preset scene, the purpose of the braking expected by the driver in the preset scene can be analyzed through the driving intention, and the braking target of the driver is clear. The driving state is used to represent the physiological and psychological state of the driver, the influence of the state of the driver on the accuracy and timeliness of the braking behavior can be analyzed through the driving state. The braking control instruction corresponding to the braking parameter is determined through the driving style, the driving intention and the driving state, the braking control can be effectively adjusted according to the actual driving condition of the driver, the actual braking effect is adapted to the driving behavior of the driver, the braking needs of the driver are met, and thus, a safer, more comfortable and more in line with the current driving expectation driving experience is provided, the driving comfort is improved, and the driving safety is improved.

[0007] In a possible implementation, the braking control instruction corresponding to the braking parameter is determined according to the driving style, the driving intention and the driving state, including: The parameter change amount corresponding to the braking parameter is determined according to the driving style, the driving intention and the driving state. The braking control instruction corresponding to the braking parameter is generated by adjusting the braking parameter by using the parameter change amount.

[0008] In the embodiment of the application, the driving style, the driving intention and the driving state of the driver at the current time can indicate the driving behavior of the driver. In order to fully meet the driving behavior of the driver, the parameter change amount matched with the driving behavior of the driver can be selected. The braking parameter is adjusted according to the parameter change amount, so that the adjusted parameter meets the driving demand of the driver, and thus the corresponding braking control instruction is obtained to perform the braking control, meet the driving expectation of the driver, and improve the driving comfort.

[0009] In a possible implementation, the parameter change amount corresponding to the braking parameter is determined according to the driving style, the driving intention and the driving state, including: The driving label with the highest priority is determined from the driving style, the driving intention and the driving state according to the priority of the preset driving label. According to a preset correspondence relationship, a parameter change amount corresponding to the driving label is determined as the parameter change amount corresponding to the brake parameter, wherein the correspondence relationship is a correspondence relationship between different driving labels and parameter change amounts.

[0010] Here, the driving style, the driving intention and the driving state are sorted according to the priority of the driving label, the driving label with the highest priority is determined, and the driving label that is most consistent with the driving behavior of the driver can be found; and the brake parameter is adjusted by using the parameter change amount corresponding to the driving label, so that the adjusted brake parameter can meet the driving needs of the driver at the current moment, and the driving experience is improved.

[0011] In a possible implementation, before the driving label with the highest priority is determined from the driving style, the driving intention and the driving state according to the priority of the preset driving label, the method further includes: determining the relevance of each driving style, each driving intention and each driving state to driving safety; determining the priority of the driving label of each driving style, each driving intention and each driving state based on the relevance.

[0012] According to the relevance of the driving label to driving safety, the priority of the driving label can be determined, so that the driving label that is most relevant to driving safety or has a great impact on driving safety has a higher priority, so that the driving label that is most relevant to driving safety can be given priority, and the brake control of the vehicle can fully meet the driving needs of the driver at the current moment, and the driving safety is improved.

[0013] In a possible implementation, the driving style of the driver at the current moment is determined according to the driving parameter, including: extracting the driving feature of the driver from the driving parameter; determining the driving style of the driver at the current moment according to the driving feature, a first style recognition model, a second style recognition model and a third style recognition model, wherein the first style recognition model, the second style recognition model and the third style recognition model are trained according to the driving feature of different driving styles and corresponding driving styles.

[0014] The embodiments of the present application can extract the driving feature of the driver from the driving parameter, and determine the driving style of the driver at the current moment according to the driving feature, the first style recognition model, the second style recognition model and the third style recognition model, so that the driving feature can be analyzed according to three independently trained style recognition models, the driving style of the driver can be accurately obtained, the prediction performance of the model as a whole is improved, and the accuracy of the determination of the driving style is improved.

[0015] In a possible implementation, the determining the driving style of the driver at the current moment according to the driving feature, the first style recognition model, the second style recognition model and the third style recognition model comprises: inputting the driving feature into the first style recognition model to obtain a first driving style of the driver output by the first style recognition model; inputting the driving feature into the second style recognition model to obtain a second driving style of the driver output by the second style recognition model; inputting the driving feature into the third style recognition model to obtain a third driving style of the driver output by the third style recognition model; performing weighted voting based on the first driving style, the second driving style and the third driving style to obtain the driving style of the driver at the current moment.

[0016] Based on the above technical content, the driving feature is processed by the first style recognition model, the second style recognition model and the third style recognition model respectively to obtain the driving style output by each style recognition model, the driving style of the driver can be predicted in different ways; and the first driving style, the second driving style and the third driving style are obtained to perform weighted voting, the prediction results of the various style recognition models can be comprehensively considered, the accuracy and stability of the driving style of the driver obtained finally are improved, and the deviation of the prediction result of the driving style is reduced.

[0017] In a possible implementation, the determining the driving style of the driver at the current moment according to the driving feature, the first style recognition model, the second style recognition model and the third style recognition model comprises: the determining the initial driving style of the driver at the current moment according to the driving feature, the first style recognition model, the second style recognition model and the third style recognition model; determining the driving style of the driver at the current moment according to the historical initial driving styles corresponding to the first preset number of moments before the current moment, the previous driving style of the current moment and the initial driving style of the driver at the current moment.

[0018] In the embodiments of the present application, considering that the driving style of the driver is generally stable, after the driving features are processed by using the first style recognition model, the second style recognition model and the third style recognition model to obtain the initial driving style of the driver at the current moment, the initial driving style of the driver at the current moment is further smoothed according to the historical initial driving styles corresponding to the continuous first preset number of moments before the current moment, and the previous driving style at the current moment, the fluctuation of the determined initial driving style at the current moment is reduced by considering the historical driving behavior of the driver, and the driving style of the driver at the current moment is accurately determined, so as to ensure the accuracy and stability of the obtained driving style.

[0019] In a possible implementation, the determining the driving style of the driver at the current moment according to the historical initial driving styles of the driver corresponding to the continuous first preset number of moments before the current moment, the previous driving style at the current moment, and the initial driving style of the driver at the current moment comprises: when the number of the initial driving styles of the current moment in the historical initial driving styles is greater than or equal to the second preset number, the initial driving style of the driver at the current moment is determined as the driving style of the driver at the current moment; when the number of the initial driving styles of the current moment in the historical initial driving styles is less than the second preset number, the previous driving style of the driver at the current moment is determined as the driving style of the driver at the current moment.

[0020] Here, when the number of the initial driving styles of the current moment in the historical initial driving styles is greater than or equal to the second preset number, it means that the driving style of the driver is predicted as the initial driving style of the current moment for multiple times, and then the driving style of the driver is likely to be the initial driving style; when the number of the initial driving styles of the current moment in the historical initial driving styles is less than the second preset number, it means that the driving style of the driver is predicted as the initial driving style of the current moment for a small number of times, and it is possible that only part of the driving behavior leads to the deviation of the driving style prediction, and then the driving style of the driver at the current moment can be continued as the previous driving style at the current moment.

[0021] In a possible implementation, the driving parameters include steering wheel parameters and lane parameters, and the biological data includes facial data and biological signal data of the driver. The determining the driving state of the driver at the current moment according to the driving parameters and the biological data comprises: extracting, from the driving parameters and the biological data, steering wheel features, lane features, facial features and biological signal features of the driver at the current moment; determine at least one driving state of the driver at the current time based on the steering wheel feature, the lane feature, the face feature and the biological signal feature; According to a preset priority of the driving state, a driving state with the highest priority in the at least one driving state is determined as the driving state of the driver at the current time.

[0022] Wherein, the steering wheel feature and the lane feature of the driver at the current time are extracted from the driving parameter, so as to obtain the control of the driver on the steering wheel and the control of the vehicle; the face feature and the biological signal feature of the driver at the current time are extracted from the biological data, so as to obtain the state of the driver at the current time; according to the above features, at least one driving state of the driver at the current time is determined; by the preset priority of the driving state, a driving state with the highest priority in the at least one driving state is determined as the driving state of the driver at the current time, so that the brake control of the driver can be adjusted according to the driving state with the highest priority, to ensure the driving safety of the driver.

[0023] In a second aspect, an embodiment of the present application provides a brake control device, comprising: An acquisition module is configured to acquire a brake parameter, a driving parameter and biological data of a driver of a vehicle at a current time; A determination module is configured to determine a driving style, a driving intention and a driving state of the driver at the current time according to the driving parameter and the biological data; wherein, the driving style is used to represent the preference of the driving behavior of the driver, the driving intention is used to represent the driving behavior of the driver in a preset scene, and the driving state is used to represent the physiological and psychological state of the driver; An adjustment module is configured to determine a brake control instruction corresponding to the brake parameter according to the driving style, the driving intention and the driving state; A control module is configured to perform brake control on the vehicle based on the brake control instruction.

[0024] In a third aspect, an embodiment of the present application provides a vehicle, comprising a memory and a processor, the memory stores a computer program capable of running on the processor, and the processor implements the brake control method of any one of the first aspect when executing the computer program.

[0025] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the brake control method of any one of the first aspect.

[0026] It can be understood that the beneficial effects of the above-mentioned second aspect to fourth aspect can be referred to the related description in the first aspect, which will not be repeated here.

[0027] It should be understood that the above general description and the following detailed description are only exemplary and explanatory and are not restrictive of the present specification. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0029] Figure 1 is an application scenario diagram provided by an embodiment of the present application; Figure 2 is a signal transmission diagram of the brake control method provided by an embodiment of the present application; Figure 3 is a flow diagram of the brake control method provided by an embodiment of the present application; Figure 4 is a flow diagram of the brake control method provided by another embodiment of the present application; Figure 5 is a structural diagram of the brake control device provided by an embodiment of the present application; Figure 6 is a structural diagram of the vehicle provided by an embodiment of the present application. DETAILED DESCRIPTION

[0030] The present application will be described more clearly in connection with specific embodiments. The following embodiments will help those skilled in the art to further understand the role of the present application, but do not limit the present application in any form. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made. These all belong to the protection scope of the present application.

[0031] It should be understood that when used in the present application specification and the appended claims, the term "comprising" indicates the presence of the described features, whole, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0032] It should also be understood that the term "and / or" used in the present application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0033] In the description of the present application and the appended claims, the terms "first", "second", "third", etc. are used merely to distinguish descriptions and cannot be understood as indicating or implying relative importance.

[0034] In the present application, the reference to "one embodiment" or "some embodiments" means that the specific features, structures or characteristics described in connection with the embodiment are included in one or more embodiments of the present application. Therefore, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in further some embodiments" and the like appearing in the present specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "include", "contain", "have" and their variants mean "including but not limited to", unless otherwise specifically emphasized.

[0035] In addition, the "multiple" mentioned in the embodiments of the present application should be interpreted as two or more.

[0036] The present applicant finds that during the process of deceleration braking by the driver stepping on the brake pedal, the brake system can only provide a single brake pedal feeling, and cannot provide the customer with a multi-state, multi-scene pedal feeling according to the actual driving situation. Therefore, it is necessary to consider a new method to control the braking of the driver.

[0037] In the embodiments of the present application, in order to improve the driving experience, the driving style, driving intention and driving state of the driver at the current time are determined through the driving parameters of the vehicle and the biological data of the driver, the driving behavior of the driver can be comprehensively analyzed, the braking needs of the driver are determined, and the braking control instruction corresponding to the braking parameter is determined, the braking control is effectively adjusted, the actual braking effect is adapted to the driving behavior of the driver, the driving comfort is improved, and the driving safety is improved.

[0038] Firstly refer to Figure 1 , Figure 1 The application scenario provided by the embodiments of the present application is schematically shown, which involves devices including a brake system 101 and a controller 102.

[0039] When the application scenario is brake control, the controller 102 can determine the brake control instruction corresponding to the brake parameter according to the driving style, the driving intention and the driving state, and then control the brake system 101 to perform brake control of the vehicle.

[0040] Optionally, the devices involved in the application scenario can also include a server.

[0041] In the application scenario of brake control, the driving parameters of the vehicle and the biological data of the driver are stored on the server, and the trained model is deployed on the server. The driving style, driving intention and driving state of the driver at the current time can be obtained on the server based on the driving parameters of the vehicle, the biological data of the driver and the trained model. The server and the controller 102 can communicate through the network. The controller 102 can receive the driving style, driving intention and driving state of the driver at the current time sent by the server, and then determine the brake control instruction corresponding to the brake parameter to realize the brake control of the vehicle. In addition, the driving parameters of the vehicle and the biological data of the driver can also be stored on the controller 102 and the trained model can be deployed on the controller 102, so that the adjustment of brake control can still be realized when the network is not smooth.

[0042] In addition, referring to the signal transmission schematic diagram shown in FIG. 2, in the application scenario of the embodiment, a vehicle body monitoring module, an environment perception module and a biological recognition module are also involved. The vehicle body monitoring module can monitor the parameters of the vehicle itself, such as the steering wheel angle signal, the steering wheel speed signal, the accelerator pedal opening signal, the brake pedal opening signal and the vehicle speed signal, etc. The environment perception module can include a laser radar, an ultrasonic radar, a millimeter wave radar and a front camera module, etc., for obtaining the environmental information around the vehicle body. The biological recognition module can include an in-vehicle camera, an infrared sensor, a seat integrated heart rate sensor and a steering wheel grip force sensor, etc. Figure 2

[0043] The driving label determination module and the brake control instruction generation module are arranged in the controller of the vehicle.

[0044] The driving parameters and the biological data monitored by the vehicle body monitoring module, the environment perception module and the biological recognition module are transmitted to the driving label determination module. The driving label determination module can determine the driving style, the driving intention and the driving state of the driver at the current time according to the driving parameters and the biological data, and transmit them to the brake control instruction generation module. The brake control instruction generation module can generate the brake control instruction corresponding to the brake parameter according to the driving style, the driving intention and the driving state of the driver at the current time, and send it to the corresponding brake system, so that the brake system outputs the actual brake force to perform brake control.

[0045] The brake control method provided by the example embodiment of the present application will be described below in combination with the application scenario of FIG. 1 and the signal transmission schematic diagram of FIG. 2, and with reference to FIG. 3. It should be noted that the above-mentioned application scenario is only shown for the purpose of facilitating the understanding of the spirit and principles of the present application, and the embodiments of the present application are not limited in this respect. On the contrary, the embodiments of the present application can be applied to any applicable scenario. Figure 1 Figure 2 Figures 3-4

[0046] ​​​​It should be noted that the embodiments of the present application can be applied to a vehicle, which can be a server or a controller of the vehicle, i.e., the brake control method provided by the exemplary embodiments of the present application can be executed on the server or the controller of the vehicle.

[0047] The server can be a monolithic server or a distributed server across multiple computers or computer data centers. The server can also be of various categories, such as but not limited to, a web server, an application server, or a database server, or a proxy server.

[0048] Optionally, the server can include hardware, software, or an embedded logic component or a combination of two or more such components for performing suitable functions supported or implemented by the server. For example, the server, such as a blade server, a cloud server, etc., or a server group composed of multiple servers, can include one or more of the above-mentioned categories of servers, etc.

[0049] It should be noted that the brake control method provided by the exemplary embodiments of the present application can be executed on the same device or on different devices.

[0050] Reference Figure 3 , Figure 3 is a flowchart of the brake control method provided by an embodiment of the present application. As shown in Figure 3 , the method in the embodiment of the present application can include: Step 301, obtaining brake parameters, driving parameters and biological data of the driver of the vehicle at the current time.

[0051] Here, the brake parameters can include parameters of the brake pedal controlled by the driver, such as the opening degree of the brake pedal, or control parameters corresponding to the brake system of the vehicle when the driver controls the brake of the vehicle.

[0052] The driving parameters are parameters controlled by the driver during driving of the vehicle, which can include the steering wheel angle, the steering wheel angular velocity, the steering wheel angular acceleration, the accelerator pedal opening degree, the opening degree change rate, the accelerator pedal stepping frequency, the brake pedal opening degree, the opening degree change rate, the stepping frequency, the vehicle speed, the longitudinal acceleration, the lateral acceleration, the gear information, and the lane deviation information, etc. of the vehicle. The parameters of the vehicle itself can be obtained through a body monitoring module, and the lane deviation information can be obtained and recognized through devices such as laser radar, ultrasonic radar, millimeter wave radar, and front vision camera installed on the periphery of the vehicle body.

[0053] The biological data is state data of the driver himself during driving, which can include head state, heart rate, skin conductance, steering wheel grip, etc. The head state can include head posture, eye state, and mouth state, the head posture can include posture such as looking up and looking down, the eye state can include parameters such as blink frequency, eye closure time ratio, and line of sight deviation, and the mouth state can include parameters such as yawning frequency and mouth opening frequency. The mental state of the driver such as head posture can be obtained by an in-vehicle camera or an infrared sensor, the heart rate data can be obtained by a heart rate sensor integrated in the seat, and the steering wheel grip can be obtained by a sensor arranged on the steering wheel.

[0054] In step 302, the driving style, driving intention, and driving state of the driver at the current moment are determined according to the driving parameters and the biological data; wherein the driving style is used to represent the preference of the driving behavior of the driver, the driving intention is used to represent the driving behavior of the driver in the preset scene, and the driving state is used to represent the physiological and psychological state of the driver.

[0055] In this embodiment, the driving behavior of the driver can be analyzed by the driving parameters and the biological data to obtain the driving label corresponding to the driver at the current moment, which can include the driving style, the driving intention, and the driving state of the driver. That is, by analyzing the driving parameters and the biological data, one driving style, one driving intention, and one driving state corresponding to the driver can be obtained.

[0056] Here, the driving style is used to represent the preference of the driving behavior of the driver. The driving style is the relatively fixed behavior preference and operation mode of the driver, which determines the operation tendency of the driver in the conventional scene. For example, the driving style can include aggressive, moderate, normal, and economical, etc. For the driving behavior of overtaking, the driver with aggressive driving style may accelerate quickly and overtake at a close distance. While the driver with moderate driving style may accelerate slowly and overtake with a safe distance.

[0057] Correspondingly, the drivers with different driving styles have different force and timing of brake operation, and the brake effect obtained and the driving feeling brought to the driver are different. For example, the driver with aggressive driving style may brake urgently to make the vehicle stop quickly in a short distance, which is easy to bring impact and frustration to the driver. The driver with moderate driving style may be used to step on the brake gently to make the vehicle decelerate smoothly in a long distance, so that the driving is more inclined to be smooth. Therefore, the drivers with different driving styles also have different needs for brake control and feedback.

[0058] Driving intention is used to characterize a driver's driving behavior in a pre-defined scenario. Driving intention is the specific operational goal a driver wants to achieve in the current driving scenario; it is short-term and dynamically changing. For example, driving intention can include emergency avoidance, congested driving, track maneuvering, and normal driving. Driving intention directly affects the purpose and intensity of the driver's braking behavior, determining whether the braking effect achieves the expected result. For instance, under the driving intention of emergency avoidance, the driver may brake suddenly to slow the vehicle to a safe state; in this case, the vehicle's braking control needs to reduce risk and ensure driving safety. Under the driving intention of congested driving, the driver may frequently apply the brakes to slow the vehicle forward; in this case, the vehicle's braking control needs to optimize smoothness to ensure a stable driving experience. Therefore, drivers will have different braking control and feedback needs under different driving intentions.

[0059] Driving state is used to characterize the driver's physiological and psychological state. Focusing on the driver's own condition, driving state is a core prerequisite affecting the effectiveness of driving behavior. For example, driving state can include fatigue, distraction, tension, and normal state. When a driver is in a fatigued state, slower reaction times may lead to delayed operations, making it impossible to achieve the desired driving behavior in a timely and accurate manner.

[0060] Correspondingly, the driver's driving state directly affects the reaction speed and operational precision of braking behavior, that is, the timeliness and accuracy of braking, which in turn determines the reliability and safety of the braking effect. For example, when a driver is fatigued and performs braking operations, there will be a reaction delay, with the brakes applied 1-2 seconds later than under normal conditions, which may lead to a longer braking distance and increase the risk of collision. Therefore, drivers require different braking control and feedback under different driving conditions to ensure driving safety.

[0061] Based on this, this embodiment analyzes the driver's driving behavior by determining the driver's driving style, driving intention, and driving state at the current moment, and clarifies the driver's braking needs so as to accurately carry out subsequent braking control and ensure the safety of vehicle driving.

[0062] Step 303: Determine the braking control command corresponding to the braking parameters based on driving style, driving intention and driving state.

[0063] In this embodiment, different driving styles, driving intentions, and driving states require different braking control. For example, when the driving intention is to make an emergency maneuver, the driver's braking control needs to respond quickly to reduce driving risks. When the driving state is tense, smooth control is needed to avoid over-response. Therefore, by determining the driver's driving style, driving intention, and driving state at the current moment, the braking parameters can be adjusted to obtain corresponding braking control commands for subsequent braking control.

[0064] At step 304, the vehicle is controlled to brake based on the brake control instruction.

[0065] In this embodiment, after the brake control instruction is determined, the brake system of the vehicle can perform corresponding brake control according to the brake control instruction, so that the actual brake effect of the driver's brake operation is adapted to the driving behavior of the driver. The brake system of the vehicle can be an electronic mechanical brake system (EMB).

[0066] In the embodiments of the present application, the driving style, the driving intention and the driving state of the driver at the current time are determined through the driving parameters and the biological data of the driver at the current time, the driving behavior of the driver is analyzed, and the brake needs of the driver are determined. The driving style is used to represent the preference of the driving behavior of the driver, the preference of the brake control of the driver is analyzed through the driving style, and the brake characteristics of the driver are determined. The driving intention is used to represent the driving behavior of the driver in the preset scene, the purpose of the brake expected to be achieved by the driver in the preset scene is analyzed through the driving intention, and the brake target of the driver is determined. The driving state is used to represent the physiological and psychological state of the driver, the influence of the state of the driver on the accuracy and timeliness of the brake behavior is analyzed through the driving state. The brake control instruction corresponding to the brake parameter is determined through the driving style, the driving intention and the driving state, the brake control is effectively adjusted according to the actual driving condition of the driver, the actual brake effect is adapted to the driving behavior of the driver, the brake needs of the driver are met, and a safer, more comfortable and more expected driving experience is provided, the driving comfort is improved, and the driving safety is improved.

[0067] In some embodiments, determining the brake control instruction corresponding to the brake parameter according to the driving style, the driving intention and the driving state can be determining the parameter change corresponding to the brake parameter according to the driving style, the driving intention and the driving state; and adjusting the brake parameter by using the parameter change to generate the brake control instruction corresponding to the brake parameter.

[0068] In this embodiment, the driving style, the driving intention and the driving state of the driver at the current time indicate the needs of the driving behavior of the driver. In order to fully meet the needs of the driving behavior of the driver, the brake parameter can be adjusted according to the parameter change corresponding to the driving style, the driving intention and the driving state of the driver at the current time, so that the adjusted parameter meets the driving needs of the driver, and the corresponding brake control instruction is obtained to perform brake control.

[0069] Optionally, the driving style, the driving intention and the driving state of the driver constitute the driving behavior of the driver at the current moment, and thus each driving behavior constituted by the driving style, the driving intention and the driving state can correspond to a parameter variation quantity which matches the driving behavior.

[0070] In another possible implementation, each driving style can correspond to a parameter variation quantity, each driving intention can correspond to a parameter variation quantity, and each driving state can also correspond to a parameter variation quantity. The driving style, the driving intention and the driving state of the driver can be comprehensively selected to select a parameter variation quantity in the driving style, the driving intention and the driving state. For example, a parameter variation quantity corresponding to a driving label which best matches the driving behavior of the driver can be selected, or a parameter variation quantity corresponding to a driving label which is most relevant to driving safety can be selected.

[0071] Here, the parameter variation quantity can be a variation quantity of a braking parameter. The braking parameter can be directly adjusted by using the parameter variation quantity, and a corresponding braking control instruction can be generated according to the adjusted braking parameter.

[0072] In addition, the parameter variation quantity can also be a variation quantity of a braking control parameter of a braking system. The braking system of the vehicle involves braking control parameters such as pedal feeling, braking response, Vehicle Running Dynamic Control System (VDC) control and Cooperative Regenerative Braking System (CRBS) control. The braking control parameter of the vehicle can be adjusted by using the parameter variation quantity, and the braking parameter can be adaptively adjusted based on the adjusted braking control parameter, so as to obtain a corresponding braking control instruction to accurately control the braking of the vehicle.

[0073] In some embodiments, according to the driving parameter, the driving style of the driver at the current moment can be determined by first extracting the driving feature of the driver from the driving parameter, and then determining the driving style of the driver at the current moment according to the driving feature, a first style recognition model, a second style recognition model and a third style recognition model. The first style recognition model, the second style recognition model and the third style recognition model are trained according to the driving feature of different driving styles and the corresponding driving style.

[0074] In this embodiment, the driving feature of the driver in the driving process can be extracted from the driving parameter of the driver, so that the driving style of the driver can be analyzed according to the driving feature.

[0075] The driving features can include acceleration features, brake features, steering wheel features, speed features, power features, etc. The acceleration features can specifically include maximum acceleration, minimum acceleration, average acceleration, and standard deviation of acceleration, etc. The brake features can specifically include maximum brake pressure, average brake pressure, and number of emergency braking, etc. The steering wheel features can specifically include steering wheel operation amplitude, steering wheel deflection, and steering wheel change rate, etc. The speed features can specifically include maximum speed, average speed, and speed change rate, etc. The power features can specifically include average rotation speed, throttle opening, and throttle change rate, etc.

[0076] Here, the driving parameters of the driver within the first preset time length before the current time can be extracted through the analysis window of the first preset time length, and the driving features can be obtained by using the driving parameters within the first preset time length. For example, the analysis window of the first preset time length can be set to 5 seconds, and the data acquisition frequency can be set to 10 Hz. The driving parameters collected within 5 seconds can be obtained, and the driving features can be obtained by performing feature extraction on the driving parameters.

[0077] In this embodiment, the three models can be independently trained by using the driving features of different driving styles and the corresponding driving styles, to obtain a first style recognition model, a second style recognition model, and a third style recognition model.

[0078] The first style recognition model, the second style recognition model, and the third style recognition model described above can be obtained by training different types of models. For example, the neural network model, the deep learning model, the machine learning model, and the support vector machine can be used for training to obtain different style recognition models.

[0079] For example, the first style recognition model can be obtained by training a random forest model, the second style recognition model can be obtained by training a neural network model, and the third style recognition model can be obtained by training a support vector machine.

[0080] The driving style of the driver at the current time can be determined by processing the driving features through the three style recognition models. The prediction results of the three independently trained models can be used to obtain better overall prediction performance, and the accuracy of the driving style determination can be improved.

[0081] Optionally, the embodiment determines the driving style of the driver at the current moment according to the driving feature, the first style recognition model, the second style recognition model and the third style recognition model. The driving feature can be input into the first style recognition model to obtain the first driving style of the driver output by the first style recognition model. The driving feature can be input into the second style recognition model to obtain the second driving style of the driver output by the second style recognition model. The driving feature can be input into the third style recognition model to obtain the third driving style of the driver output by the third style recognition model. Then, the first driving style, the second driving style and the third driving style are used for weighted voting to obtain the driving style of the driver at the current moment.

[0082] In the embodiment, the first style recognition model, the second style recognition model and the third style recognition model can be used to process the driving feature respectively, so as to obtain the driving style output by each style recognition model respectively. The driving style of the driver is predicted in different ways. The first driving style, the second driving style and the third driving style are used for weighted voting, which can improve the accuracy and stability of the driving style of the driver obtained finally, reduce the deviation of the driving style prediction result and improve the prediction accuracy.

[0083] Here, the weights corresponding to the prediction results of the first style recognition model, the second style recognition model and the third style recognition model can be the same or different.

[0084] When the weights are the same, the weights corresponding to the prediction results of the first style recognition model, the second style recognition model and the third style recognition model can all be 1 / 3.

[0085] When the weights are different, for example, the first style recognition model is obtained by training a random forest model, the second style recognition model is obtained by training a neural network model, and the third style recognition model is obtained by training a support vector machine. The weight corresponding to the first style recognition model can be 40%, the weight corresponding to the second style recognition model can be 30%, and the weight corresponding to the third style recognition model can be 30%. Then, the driving style of the driver at the current moment can be calculated according to the first driving style, the second driving style, the third driving style and the corresponding weights. For example, the first driving style is ordinary, the second driving style is aggressive, and the third driving style is aggressive. Then, the driving style can be 40% ordinary + 30% aggressive + 30% aggressive = 40% ordinary + 60% aggressive. The probability of the driving style being aggressive is higher, so it can be determined that the driving style of the driver at the current moment is aggressive.

[0086] The neural network model can be a sequence model, such as a long short-term memory network model, which includes two hidden layers and an output layer. The hidden layers are 64 and 32 neurons respectively, and a ReLU activation function can be used. The output layer can be 4 neurons, and a Softmax activation function is used.

[0087] In another implementation, the first, second, and third style recognition models also output probabilities corresponding to the driving styles. When determining the driving style of the driver at the current time, the probabilities of the driving styles output by the models can also be considered.

[0088] In the following case, the weight corresponding to the first style recognition model can be 40%, the weight corresponding to the second style recognition model can be 30%, the weight corresponding to the third style recognition model can be 30%, the first driving style is ordinary and the probability is 80%, the second driving style is aggressive and the probability is 60%, and the third driving style is aggressive and the probability is 60%. The driving style can be 40% x 80% x ordinary + 30% x 60% x aggressive + 30% x 60% x aggressive = 32% ordinary + 36% aggressive, and it can be determined that the driving style of the driver at the current time is aggressive.

[0089] Here, the first, second, and third style recognition models can also output probabilities corresponding to each driving style. For each driving style, the probabilities of the driving style output by the first, second, and third style recognition models are weighted to obtain the final probability of the driving style, and the driving style with the highest final probability is selected as the driving style of the driver at the current time.

[0090] In addition, the third style recognition model trained by the support vector machine can be used for detection of whether the driving style is aggressive. When training the support vector machine, aggressive and non-aggressive can be used as labels for training, i.e., the driving style is aggressive as one label, and the remaining driving styles as another label. The support vector is trained to obtain the third style recognition model. Correspondingly, the prediction result output by the third style recognition model is also aggressive or non-aggressive.

[0091] When performing weighted voting, if the prediction result output by the third style recognition model is aggressive, the calculation is performed in the above manner.

[0092] If the prediction result output by the third style recognition model is non-aggressive, when the prediction results output by the first and second style recognition models are not aggressive, the output of the third style recognition model can not be considered, and the driving style of the driver at the current time is determined according to the prediction results output by the first and second style recognition models.

[0093] When the prediction results output by the first style recognition model and the second style recognition model are both aggressive, due to the sum of the weights of the first style recognition model and the second style recognition model being greater than the weight of the third style recognition model, it is determined that the driving style of the driver at the current time is aggressive.

[0094] When one of the prediction results output by the first style recognition model and the second style recognition model is aggressive and the other is not aggressive, the prediction result output by the third style recognition model can be considered to support the prediction result that is not aggressive, and corresponding calculation is performed to obtain the driving style of the driver at the current time. For example, the first driving style is aggressive, the second driving style is ordinary, and the third driving style is non-aggressive, so the driving style = 40% aggressive + 30% ordinary + 30% non-aggressive = 40% aggressive + 60% ordinary, that is, it can be considered that the driving style of the driver at the current time is ordinary.

[0095] In addition, for the convenience of model representation, a mapping matrix of the driving style can be defined, where 0 represents aggressive, 1 represents moderate, 2 represents ordinary, and 3 represents economic.

[0096] In some embodiments, considering that the driving style of the driver is generally stable and does not change abruptly, the driving style obtained according to the first style recognition model, the second style recognition model, and the third style recognition model can be smoothed to ensure the stability of the determined driving style.

[0097] In this embodiment, the driving style of the driver at the current time is determined according to the driving feature, the first style recognition model, the second style recognition model, and the third style recognition model. It can be that: first, the initial driving style of the driver at the current time is determined according to the driving feature, the first style recognition model, the second style recognition model, and the third style recognition model; and then, the driving style of the driver at the current time is determined according to the historical initial driving styles corresponding to the first preset number of continuous time points before the current time, the previous driving style at the current time, and the initial driving style of the driver at the current time.

[0098] In this embodiment, the driving feature is processed by using the first style recognition model, the second style recognition model, and the third style recognition model, and the initial driving style of the driver at the current time can be obtained. For details, reference can be made to the description in the above embodiments.

[0099] The initial driving style of the driver at the current time is smoothed according to the historical initial driving styles corresponding to the first preset number of continuous time points before the current time and the previous driving style at the current time, which can consider the historical driving behavior of the driver, accurately determine the driving style of the driver at the current time, and ensure the accuracy and stability of the determination of the driving style.

[0100] Here, the historical initial driving style is an initial driving style corresponding to a first preset number of time instants consecutively before the current time instant. The previous driving style of the current time instant is the driving style of the driver determined at a time instant immediately before the current time instant. The first preset number can be determined according to the variation of the driving style of the driver, for example, the first preset number can be 5, 6, 7, 8, 9, etc. The above are merely illustrative and not restrictive.

[0101] Optionally, the embodiment determines the driving style of the driver at the current time instant according to the historical initial driving style of the driver at a first preset number of time instants consecutively before the current time instant, the previous driving style of the current time instant, and the initial driving style of the driver at the current time instant. The determination can be: when the number of the initial driving styles of the current time instant in the historical initial driving styles is greater than or equal to a second preset number, the initial driving style of the driver at the current time instant is determined as the driving style of the driver at the current time instant; or when the number of the initial driving styles of the current time instant in the historical initial driving styles is less than the second preset number, the previous driving style of the driver at the current time instant is determined as the driving style of the driver at the current time instant.

[0102] In the embodiment, when the number of the initial driving styles of the current time instant in the historical initial driving styles is greater than or equal to the second preset number, it indicates that the driving style of the driver is predicted as the initial driving style of the current time instant for multiple times, and the driving style of the driver is likely to be the initial driving style. Therefore, the initial driving style of the driver at the current time instant can be determined as the driving style of the driver at the current time instant, so as to ensure the stability and accuracy of the determination of the driving style.

[0103] When the number of the initial driving styles of the current time instant in the historical initial driving styles is less than the second preset number, it indicates that the number of times that the driving style of the driver is predicted as the initial driving style of the current time instant is small, and the prediction deviation of the driving style is likely to be caused by only part of the driving behavior, rather than the change of the driving style of the driver. Therefore, the previous driving style of the driver at the current time instant can be determined as the driving style of the driver at the current time instant, so as to ensure the continuity and stability of the driving style of the driver.

[0104] Here, the second preset number can be determined according to the value of the first preset number, so that the second preset number is less than the first preset number, and the second preset number is greater than or equal to 1 / 2 of the first preset number. For example, when the first preset number is 6, the second preset number can be 3, 4, or 5.

[0105] The first preset number is 5, the second preset number is 3, the current time is 10, the initial driving style corresponding to time 5 is aggressive, the initial driving style corresponding to time 6 is aggressive, the initial driving style corresponding to time 7 is ordinary, the initial driving style corresponding to time 8 is ordinary, the initial driving style corresponding to time 9 is ordinary, and the driving style corresponding to time 9 is ordinary.

[0106] If the initial driving style corresponding to the current time 10 is aggressive, the number of aggressive in the historical initial driving style is 2, which is less than 3, the driving style of the driver at the current time is determined as the initial driving style of the driver at the current time, and the driving style corresponding to time 9 is determined as the driving style of the driver at the current time. The corresponding driving style corresponding to the current time 10 is ordinary.

[0107] If the initial driving style corresponding to the current time 10 is ordinary, the number of ordinary in the historical initial driving style is 3, which is equal to 3, the driving style of the driver at the current time is determined as the initial driving style of the driver at the current time, and the corresponding driving style corresponding to the current time 10 is ordinary.

[0108] In some embodiments, the driving features include driving mode, steering wheel speed, throttle opening, vehicle speed, brake pedal opening, and brake switching frequency.

[0109] According to the driving parameters, the driving intention of the driver at the current time can be determined by extracting the driving features of the driver from the driving parameters. If the steering wheel speed is greater than the first preset speed, the throttle opening is greater than the first preset throttle opening, and the brake pedal opening is greater than the preset pedal opening, the driving intention of the driver at the current time is determined to be emergency avoidance. If the vehicle speed is less than the first preset vehicle speed, the steering wheel speed is less than the second preset speed, and the brake switching frequency is greater than the preset frequency, the driving intention of the driver at the current time is determined to be congestion crawling. If the driving mode is race mode, the vehicle speed is greater than the second preset vehicle speed, and the throttle opening is greater than the second preset throttle opening, the driving intention of the driver at the current time is determined to be race operation. If any of the above conditions is not met, the driving intention of the driver at the current time is determined to be normal driving. Wherein, the first preset speed is greater than the second preset speed, the first preset throttle opening is less than the second preset throttle opening, and the first preset vehicle speed is less than the second preset vehicle speed.

[0110] In this embodiment, the key features are extracted from the driving parameters, and different conditions are judged, so that the driving behavior of the driver can be accurately analyzed, and the driving intention of the driver at the current time can be determined.

[0111] Here, if the steering wheel rotation speed is greater than the first preset rotation speed, the accelerator opening degree is greater than the first preset accelerator opening degree, and the brake pedal opening degree is greater than the preset pedal opening degree, it indicates that the driver is driving at a high speed at the current moment, quickly rotates the steering wheel, and brakes to slow down, which may be that the driver encounters an emergency situation to avoid, and it is considered that the driving intention of the driver at this moment is emergency avoidance.

[0112] For example, the first preset rotation speed can be 200 degrees per second, the first preset accelerator opening degree can be 70%, and the preset pedal opening degree can be 45%.

[0113] If the vehicle speed is less than the first preset vehicle speed, the steering wheel rotation speed is less than the second preset rotation speed, and the brake switching frequency is greater than the preset frequency, it indicates that the driver is driving at a low speed at the current moment, and the steering wheel is rotated less frequently, and the driver is in a congested state and is slowly driving, and it is considered that the driving intention of the driver at the current moment is congestion crawling.

[0114] For example, the first preset vehicle speed can be 20 kph, the second preset rotation speed can be 50 degrees per second, and the preset frequency can be 2 Hz.

[0115] If the driving mode is a track mode, the vehicle speed is greater than the second preset vehicle speed, and the accelerator opening degree is greater than the second preset accelerator opening degree, it indicates that the driver actively enters the track mode and drives at a high speed, and it can be considered that the driving intention of the driver at the current moment is track operation.

[0116] For example, the second preset vehicle speed can be 60 kph, and the second preset accelerator opening degree can be 80%.

[0117] In the analysis of the driving intention by using the driving parameters, the driving parameters of the driver within a second preset time length before the current moment can be extracted through a second preset time length analysis window, and the driving intention of the driver at the current moment is analyzed by using the driving parameters within the second preset time length. For example, a second preset time length analysis window of 500 milliseconds and a data acquisition frequency of 100 Hz can be set, and the driving parameters collected within 500 milliseconds are obtained, and there are 50 samples under the 100 Hz sampling frequency. In addition, a new data sample can be received every 10 milliseconds, and the analysis of the driving intention is triggered when the analysis window is filled with 50 samples.

[0118] In some embodiments, the driving parameters include steering wheel parameters and lane parameters, and the biological data includes facial data and biological signal data of the driver.

[0119] The embodiment determines the driving state of the driver at the current moment according to the driving parameter and the biological data. The steering wheel feature, the lane feature, the face feature and the biological signal feature of the driver at the current moment can be extracted from the driving parameter and the biological data. At least one driving state of the driver at the current moment is determined based on the steering wheel feature, the lane feature, the face feature and the biological signal feature. Finally, the driving state with the highest priority in the at least one driving state is determined as the driving state of the driver at the current moment according to the preset priority of the driving state.

[0120] Here, the driving state of the driver will affect the driving of the vehicle, and the driver himself will also have some performance, so when determining the driving state of the driver at the current moment, the driving parameter and the biological data can be considered to analyze the operation of the driver to the vehicle and the biological data of the driver.

[0121] In the embodiment, the steering wheel feature and the lane feature of the driver at the current moment can be extracted from the driving parameter to obtain the control of the driver to the steering wheel and the control of the vehicle. The face feature and the biological signal feature of the driver at the current moment can be extracted from the biological data to obtain the state of the driver at the current moment.

[0122] Since the driver himself may have multiple driving states at the same time, such as the driver may be in a state of fatigue and distraction at the same time, by analyzing the above extracted steering wheel feature, lane feature, face feature and biological signal feature, at least one driving state of the driver at the current moment can be obtained, and multiple driving states of the driver can be obtained comprehensively and accurately.

[0123] Since different driving states have different effects on driving safety, the priorities of different driving states are also different. Among them, the greater the impact on driving safety, the higher the priority of the corresponding driving state. By presetting the priority of the driving state, the driving state with the highest priority in the at least one driving state can be determined as the driving state of the driver at the current moment, and the brake control of the driver can be adjusted with the driving state with the highest priority to ensure the driving safety of the driver.

[0124] In a specific embodiment, the driving state can include fatigue, distraction, tension and normal, and the priorities can be fatigue, distraction, tension and normal in descending order. When the driving state of the driver is determined to include fatigue and distraction, the driving state of the driver at the current moment can be finally determined as fatigue.

[0125] In the analysis of the driving state by using the driving parameters and the biological data, the data of various devices need to be acquired, including a visual camera, a steering wheel operation sensor, a biological signal sensor, a lane departure detection device, and the like. The sampling frequencies of each device are different, wherein the sampling frequency of the visual camera can be 30fps, the sampling frequency of the steering wheel operation sensor can be 20Hz, the sampling frequency of the biological signal sensor can be 1Hz, and the sampling frequency of the lane departure detection device can be 10Hz.

[0126] The data of each device can be stored by using an independent sliding analysis window, and the length of the analysis window can be a third preset length. For example, the third preset length can be set as an analysis window of 5 seconds, and then the window corresponding to the visual camera has 150 frames, the window corresponding to the steering wheel operation sensor has 100 samples, the window corresponding to the biological signal sensor has 5 samples, and the window corresponding to the lane departure detection device has 50 samples.

[0127] Optionally, the steering wheel features can include a micro correction frequency and a grip change rate, the lane features can include a lane offset rate, the face features can include an eye closure time ratio, a yaw frequency and a visual line offset standard deviation, and the biological signal features can include an average heart rate, a heart rate variability and a skin electricity reaction.

[0128] In the embodiment, for the micro correction operation in the steering wheel features, if the steering wheel angle change is less than 5 degrees, but the steering wheel speed change is greater than 5 degrees / second, it can be determined that the micro correction operation is performed. The steering wheel grip change is monitored, the grip change rate is calculated by the grip change, and if the change exceeds 5N, it is considered as a significant change.

[0129] For the lane features, if the lateral offset of the vehicle and the lane exceeds 0.3 meters, it is determined that the lane is deviated, and the offset number and the duration are recorded.

[0130] For the face features, the aspect ratio of the eyes can be calculated to monitor the blinking, and if it is less than 0.2, it is determined that the eyes are closed. The aspect ratio of the mouth can be calculated to monitor the yawning, and if it is higher than 0.5, it is determined that the mouth is opened. The head posture and the visual line direction are identified, and if the head lowering time is greater than 3s, it is determined that the visual line is deviated.

[0131] For the biological signal features, the heart rate and the heart rate variability can be calculated, and the skin electricity reaction can also be analyzed to calculate the skin conductance response.

[0132] Further, in the embodiment, the driver's at least one driving state at the current time is determined based on the steering wheel feature, the lane feature, the face feature, and the biological signal feature. If the eye-closed time ratio is greater than a preset eye-closed time ratio and the yawning frequency is greater than a preset yawning frequency, it is determined that the driver's driving state at the current time is fatigue. If the line-of-sight deviation standard deviation is greater than a preset line-of-sight deviation standard deviation, the lane deviation rate is greater than a preset deviation rate, and the micro-correction frequency is less than a first preset micro-correction frequency, it is determined that the driver's driving state at the current time is distraction. If the heart rate is greater than a preset heart rate, the grip force change rate is greater than a preset grip force change rate, and the micro-correction frequency is greater than a second preset micro-correction frequency, it is determined that the driver's driving state at the current time is tension. If none of the above conditions is met, it is determined that the driver's driving state at the current time is normal. The first preset micro-correction frequency is less than the second preset micro-correction frequency.

[0133] Here, if the eye-closed time ratio is greater than a preset eye-closed time ratio and the yawning frequency is greater than a preset yawning frequency, it indicates that the driver frequently closes eyes and yawns during driving, which may be that the driver is tired. Therefore, it is considered that the driver's driving state at the current time is fatigue.

[0134] For example, the preset eye-closed time ratio can be 30%, and the preset yawning frequency can be 0.1 times per second.

[0135] Here, if the line-of-sight deviation standard deviation is greater than a preset line-of-sight deviation standard deviation, the lane deviation rate is greater than a preset deviation rate, and the micro-correction frequency is less than a first preset micro-correction frequency, it indicates that the driver's line of sight deviates during driving, the vehicle deviates from the lane, and there is no timely correction, which may be that the driver does not observe the road conditions in time and control. Therefore, it can be considered that the driver's driving state at the current time is distraction.

[0136] For example, the preset line-of-sight deviation standard deviation can be 15 degrees, the preset deviation rate can be 20%, and the first preset micro-correction frequency can be 0.5 Hz.

[0137] Here, if the heart rate is greater than a preset heart rate, the grip force change rate is greater than a preset grip force change rate, and the micro-correction frequency is greater than a second preset micro-correction frequency, it indicates that the driver is excited and frequently changes the control of the steering wheel, and frequently makes small corrections to the vehicle direction, which may be that the driver is highly concentrated. Therefore, it can be considered that the driver's driving state at the current time is tension.

[0138] The preset heart rate can be 100 beats per minute, the preset grip force change rate can be 50%, and the second preset micro-correction frequency can be 2 Hz.

[0139] In the embodiments of the present application, the driving style, the driving intention and the driving state of the driver at the current time are determined through the driving parameters and the biological data of the driver at the current time, the driving behavior of the driver can be analyzed, and the braking needs of the driver are clear. The driving style is used to represent the preference of the driving behavior of the driver, the preference of the driver for brake control can be analyzed through the driving style, and the braking characteristics of the driver are clear. The driving intention is used to represent the driving behavior of the driver in the preset scene, the purpose of the driver in the preset scene can be analyzed through the driving intention, and the braking target of the driver is clear. The driving state is used to represent the physiological and psychological state of the driver, the influence of the state of the driver on the accuracy and timeliness of the braking behavior can be analyzed through the driving state. The braking control instruction corresponding to the braking parameter is determined through the driving style, the driving intention and the driving state, the braking control can be effectively adjusted according to the actual driving condition of the driver, the actual braking effect is adapted to the driving behavior of the driver, the braking needs of the driver are met, and thus a safer, more comfortable and more suitable driving experience for the current driving expectation is provided, the driving comfort is improved, and the driving safety is improved. The parameter variation quantity matched with the driving style, the driving intention and the driving state of the driver at the current time can be selected, the braking parameter is adjusted according to the parameter variation quantity, the adjusted parameter meets the driving demand of the driver, and thus the corresponding braking control instruction is obtained to perform the braking control, meet the driving expectation of the driver, and improve the driving comfort. In addition, the driving features of the driver are extracted from the driving parameters, and the driving style of the driver at the current time is determined according to the driving features, the first style recognition model, the second style recognition model and the third style recognition model. The driving features can be analyzed according to the three independently trained style recognition models, the driving style of the driver is accurately obtained, the prediction performance of the model is improved, and thus the accuracy of the driving style determination is improved. The first driving style, the second driving style and the third driving style are weighted and voted, the prediction results of the various style recognition models can be comprehensively considered, the accuracy and stability of the driving style of the driver finally obtained are improved, and the deviation degree of the prediction result of the driving style is reduced. Considering that the driving style of the driver is usually stable, the initial driving style of the driver at the current time is smoothed according to the historical initial driving style corresponding to the first preset number of time points before the current time and the previous driving style at the current time. The historical driving behavior of the driver is considered, the volatility of the initial driving style at the current time is reduced, the driving style of the driver at the current time is accurately determined, and thus the accuracy and stability of the obtained driving style are ensured.The steering wheel feature and the lane feature of the driver at the current moment are extracted from the driving parameter, so that the control of the driver on the steering wheel and the control of the vehicle are obtained. The face feature and the biological signal feature of the driver at the current moment are extracted from the biological data, so that the self-state of the driver at the current moment is obtained. According to the above features, at least one driving state of the driver at the current moment is determined. Through the priority of the preset driving state, the driving state with the highest priority in the at least one driving state is taken as the driving state of the driver at the current moment. The brake control of the driver can be adjusted according to the driving state with the highest priority, so as to ensure the driving safety of the driver.

[0140] In addition, in the determination of the brake control instruction corresponding to the brake parameter, the priority of the determined driving style, driving intention and driving state of the driver at the current moment is also considered, so as to brake the vehicle according to the driving label most related to the driving safety of the vehicle, to ensure that the brake control of the vehicle fully meets the driving demand of the driver and improves the driving safety. Figure 4 The flowchart of the brake control method provided by another embodiment of the application is shown in Figure 4 The method comprises the following steps: Step 401, obtaining the brake parameter, driving parameter and biological data of the driver of the vehicle at the current moment.

[0141] Step 402, determining the driving style, driving intention and driving state of the driver at the current moment according to the driving parameter and the biological data; wherein the driving style is used to represent the preference of the driving behavior of the driver, the driving intention is used to represent the driving behavior of the driver in the preset scene, and the driving state is used to represent the physiological and psychological state of the driver.

[0142] Here, the implementation of steps 401-402 is described in the related description of Figure 3 the embodiment, which will not be repeated here.

[0143] Step 403, determining the driving label with the highest priority from the driving style, driving intention and driving state according to the priority of the preset driving label.

[0144] Step 404, determining the parameter change amount corresponding to the driving label as the parameter change amount corresponding to the brake parameter according to the preset corresponding relationship; wherein the corresponding relationship is the corresponding relationship between different driving labels and parameter change amounts.

[0145] In the embodiment, each driving label corresponds to a parameter variation. The driver has three driving labels at the current time, including a driving style, a driving intention and a driving state, the driving style corresponds to a parameter variation, the driving intention corresponds to a parameter variation, and the driving state corresponds to a parameter variation. Correspondingly, there are three different parameter variations, and it may not be determined which parameter variation is selected. Therefore, all driving labels can be prioritized, and the highest priority driving label of the driver at the current time is determined from the driving style, the driving intention and the driving state, and the parameter variation corresponding to the driving label is selected.

[0146] In the embodiment, each driving label corresponds to a parameter variation. The parameter variation can be related to the parameters including the idle stroke, the force gradient, the pressure building rate, the delay, the forward collision warning (FCW) threshold, the autonomous emergency braking (AEB) threshold, the recovery intensity, the pre-charge pressure, the electronic stability controller (ESC) intervention intensity and the drag feeling. The correspondence table of the driving label and the parameter variation is shown in Table 1. Table 1 Correspondence table of driving label and parameter variation

[0147] Here, the parameter variation can be a variation based on the default parameter.

[0148] Optionally, before determining the driving label with the highest priority from the driving style, the driving intention and the driving state according to the priority of the preset driving label, the correlation of each driving style, each driving intention and each driving state with the driving safety can be determined first, and then the priority of the driving label of each driving style, each driving intention and each driving state is determined based on the correlation.

[0149] In the embodiment, considering that the brake control of the vehicle is closely related to the driving safety, the priority of the driving label can be determined according to the correlation of each driving style, each driving intention and each driving state with the driving safety. The driving label related to or greatly affecting the driving safety has a higher priority, so that the driving label most related to the driving safety can be considered first when determining the parameter variation in the subsequent process, so as to ensure that the brake control of the vehicle fully meets the driving demand of the driver at the current time and improve the driving safety.

[0150] Among the driving tags mentioned above, emergency avoidance has the strongest correlation with driving safety and is of the highest urgency. Therefore, the driving intention to avoid emergency situations can be regarded as the highest priority driving tag.

[0151] Secondly, fatigued, distracted, and tense driving conditions can also seriously affect driving safety. Therefore, fatigued, distracted, and tense driving conditions can be considered the second highest priority driving label.

[0152] Furthermore, the driving intentions of congested crawling and track maneuvering significantly affect driving safety during the driving process, and can be ranked as the third highest priority driving label.

[0153] In addition, a driver's aggressive, mild, or economical driving style can also affect driving safety during the driving process. Aggressive, mild, and economical driving styles can be ranked as the fourth highest priority driving labels.

[0154] Finally, normal driving style, normal driving intention, and normal driving state can be considered the fifth highest priority driving label.

[0155] For example, if the driver's driving style is normal, the driving intention is to crawl in traffic, and the driving state is tense, then the parameter changes corresponding to the tense driving state can be determined as the parameter changes corresponding to the braking parameters, and subsequent control commands can be generated.

[0156] Step 405: Adjust the braking parameters using the parameter changes to generate braking control commands corresponding to the braking parameters.

[0157] Step 406: Based on the braking control command, brake control is applied to the vehicle.

[0158] For the implementation of steps 405-406, please refer to [link / reference]. Figure 3 The relevant descriptions in the embodiments will not be repeated here.

[0159] In the embodiment of the present application, the driving style, the driving intention and the driving state of the driver at the current time are determined through the driving parameters and the biological data of the driver of the vehicle at the current time, the driving behavior of the driver can be analyzed, and the braking needs of the driver are clear. The driving style is used to represent the preference of the driving behavior of the driver, the preference of the driver for brake control can be analyzed through the driving style, and the braking characteristics of the driver are clear. The driving intention is used to represent the driving behavior of the driver in the preset scene, the purpose of the driver in the preset scene can be analyzed through the driving intention, and the braking target of the driver is clear. The driving state is used to represent the physiological and psychological state of the driver, the influence of the state of the driver on the accuracy and timeliness of the braking behavior can be analyzed through the driving state. The braking control instruction corresponding to the braking parameter is determined through the driving style, the driving intention and the driving state, the braking control can be effectively adjusted according to the actual driving condition of the driver, the actual braking effect is adapted to the driving behavior of the driver, and the braking needs of the driver are met, so that a safer, more comfortable and more in line with the current driving expectation driving experience is provided, and the driving comfort or the driving safety is improved. The driving style, the driving intention and the driving state are sorted according to the priority of the driving label, the driving label with the highest priority is determined, and the driving label most consistent with the driving behavior of the driver can be found. The braking parameter is adjusted by using the parameter change amount corresponding to the driving label, the adjusted braking parameter can meet the driving needs of the driver at the current time, and the driving experience is improved. In addition, the priority of the driving label is determined according to the correlation between the driving label and the driving safety, the priority of the driving label related to the driving safety or having a great influence on the driving safety is higher, so that the driving label most related to the driving safety can be given priority, and the driving safety is improved.

[0160] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0161] Figure 5 is a structural schematic diagram of the brake control device provided by an embodiment of the present application. As shown in Figure 5 The brake control device provided by the embodiment of the present application can include an acquisition module 501, a determination module 502, an adjustment module 503 and a control module 504.

[0162] The acquisition module 501 is configured to acquire the braking parameter, the driving parameter and the biological data of the driver of the vehicle at the current time.

[0163] The determining module 502 is configured to determine a driving style, a driving intention and a driving state of the driver at the current moment according to the driving parameter and the biological data; the driving style is used to represent the preference of the driving behavior of the driver, the driving intention is used to represent the driving behavior of the driver preset scene, and the driving state is used to represent the physiological and psychological state of the driver. The adjusting module 503 is configured to determine a brake control instruction corresponding to the brake parameter according to the driving style, the driving intention and the driving state. The control module 504 is configured to perform brake control on the vehicle based on the brake control instruction.

[0164] In a possible implementation, the adjusting module 503 is specifically configured to: determine a parameter change amount corresponding to the brake parameter according to the driving style, the driving intention and the driving state; adjust the brake parameter by using the parameter change amount to generate the brake control instruction corresponding to the brake parameter.

[0165] In a possible implementation, the adjusting module 503 is specifically configured to: determine a driving label with the highest priority from the driving style, the driving intention and the driving state according to the priority of the preset driving label; determine the parameter change amount corresponding to the driving label as the parameter change amount corresponding to the brake parameter according to the preset corresponding relationship; the corresponding relationship is a corresponding relationship between different driving labels and the parameter change amount.

[0166] In a possible implementation, the adjusting module 503 is further configured to: determine the relevance of each driving style, each driving intention and each driving state to the driving safety; determine the priority of the driving label of each driving style, each driving intention and each driving state based on the relevance.

[0167] In a possible implementation, the determining module 502 is specifically configured to: extract a driving feature of the driver from the driving parameter; determine the driving style of the driver at the current moment according to the driving feature, a first style recognition model, a second style recognition model and a third style recognition model; the first style recognition model, the second style recognition model and the third style recognition model are trained according to the driving feature of different driving styles and the corresponding driving style.

[0168] In a possible implementation, the determining module 502 is specifically configured to: input the driving feature into the first style recognition model to obtain a first driving style of the driver output by the first style recognition model; input the driving features into the second style recognition model to obtain a second driving style of the driver output by the second style recognition model; input the driving features into the third style recognition model to obtain a third driving style of the driver output by the third style recognition model; perform weighted voting based on the first driving style, the second driving style and the third driving style to obtain the driving style of the driver at the current time.

[0169] In a possible implementation, the determining module 502 is specifically configured to: determine an initial driving style of the driver at the current time according to the driving features, the first style recognition model, the second style recognition model and the third style recognition model; determine the driving style of the driver at the current time according to the historical initial driving styles corresponding to the first preset number of times before the current time, the previous driving style at the current time and the initial driving style of the driver at the current time.

[0170] In a possible implementation, the determining module 502 is specifically configured to: when the number of the initial driving styles of the current time in the historical initial driving styles is greater than or equal to the second preset number, determine the initial driving style of the driver at the current time as the driving style of the driver at the current time; when the number of the initial driving styles of the current time in the historical initial driving styles is less than the second preset number, determine the previous driving style of the driver at the current time as the driving style of the driver at the current time.

[0171] In a possible implementation, the driving parameters include steering wheel parameters and lane parameters, and the biological data includes facial data and biological signal data of the driver; The determining module 502 is specifically configured to: extract steering wheel features, lane features, facial features and biological signal features of the driver at the current time from the driving parameters and the biological data; determine at least one driving state of the driver at the current time based on the steering wheel features, the lane features, the facial features and the biological signal features; determine the driving state with the highest priority in the at least one driving state as the driving state of the driver at the current time according to the preset priority of the driving state.

[0172] It should be noted that the information interaction, execution process and the like among the above apparatuses / units are based on the same concept as the method embodiments of the present application, and the specific functions and the technical effects brought by the same can be referred to the method embodiments part, which will not be described here in detail.

[0173] Figure 6 This is a schematic diagram of the structure of a vehicle provided in one embodiment of this application. Figure 6 As shown, the vehicle 600 in this embodiment includes a processor 610 and a memory 620, wherein the memory 620 stores a computer program 621 that can run on the processor 610. When the processor 610 executes the computer program 621, it implements the steps in any of the above method embodiments, for example... Figure 2 Steps 201-204 are shown. Alternatively, when processor 610 executes computer program 621, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 5 The functions of modules 501-504 are shown.

[0174] For example, computer program 621 may be divided into one or more modules / units, one or more of which are stored in memory 620 and executed by processor 610 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 621 in vehicle 600.

[0175] Those skilled in the art will understand that Figure 6 This is merely an example of a vehicle and does not constitute a limitation on the vehicle. It may include more or fewer components than shown, or combinations of certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0176] The processor 610 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0177] The memory 620 can be an internal storage unit of the vehicle, such as a hard disk or a memory of the vehicle, or an external storage device of the vehicle, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, or the like. The memory 620 can include both the internal storage unit and the external storage device. The memory 620 is used to store computer programs and other programs and data required by the vehicle. The memory 620 can also be used to temporarily store data that has been output or will be output.

[0178] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, 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. In addition, the specific names of the functional units and modules are only for the convenience of mutual distinction, and do not limit the protection scope of the application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0179] An embodiment of the application further provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the brake control method.

[0180] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0181] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or in a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0182] In the embodiments of the present application, it should be understood that the disclosed apparatus / vehicle and method can be implemented in other manners. For example, the described apparatus / vehicle embodiments are merely schematic. For example, the division of the modules or units is merely logical function division. There can be another division manner for the actual implementation. 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 displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0183] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0184] In addition, each functional unit 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.

[0185] The integrated module / 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 this understanding, all or part of the processes in the above-described embodiment methods can also be completed by computer programs instructing related hardware, and the computer programs can be stored in a computer readable storage medium. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0186] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A braking control method, characterized in that, include: Obtain the vehicle's braking parameters, driving parameters, and the driver's biometric data at the current moment; Based on the driving parameters and the biological data, the driver's driving style, driving intention, and driving state at the current moment are determined; wherein, the driving style is used to characterize the driver's driving behavior preferences, the driving intention is used to characterize the driver's driving behavior in a preset scenario, and the driving state is used to characterize the driver's physiological and psychological state. Based on the driving style, driving intention, and driving state, determine the braking control command corresponding to the braking parameters; Based on the braking control command, the vehicle is braked.

2. The braking control method according to claim 1, characterized in that, Based on the driving style, driving intention, and driving state, determine the braking control command corresponding to the braking parameters, including: Based on the driving style, driving intention, and driving state, determine the parameter change corresponding to the braking parameters; The braking parameters are adjusted using the changes in the aforementioned parameters to generate braking control commands corresponding to those parameters.

3. The braking control method according to claim 2, characterized in that, The step of determining the parameter change corresponding to the braking parameter based on the driving style, driving intention, and driving state includes: Based on the preset priority of driving tags, the driving tag with the highest priority is determined from the driving style, the driving intention and the driving state; According to a preset correspondence, the parameter change corresponding to the driving tag is determined as the parameter change corresponding to the braking parameter; wherein, the correspondence is the correspondence between different driving tags and parameter changes.

4. The braking control method according to claim 3, characterized in that, Before determining the highest-priority driving tag from the driving style, driving intention, and driving state based on the preset priority of driving tags, the method further includes: Determine the correlation between each driving style, driving intention, and driving state and driving safety; Based on the aforementioned correlations, the priority of driving tags for each driving style, each driving intention, and each driving state is determined.

5. The braking control method according to any one of claims 1 to 4, characterized in that, Based on the driving parameters, determine the driver's driving style at the current moment, including: Extract the driver's driving characteristics from the driving parameters; Based on the driving characteristics, the first style recognition model, the second style recognition model, and the third style recognition model, the driver's driving style at the current moment is determined; wherein, the first style recognition model, the second style recognition model, and the third style recognition model are trained based on the driving characteristics of different driving styles and the corresponding driving styles.

6. The braking control method according to claim 5, characterized in that, Determining the driver's driving style at the current moment based on the driving characteristics, the first style recognition model, the second style recognition model, and the third style recognition model includes: The driving characteristics are input into the first style recognition model to obtain the first driving style of the driver output by the first style recognition model; The driving characteristics are input into the second style recognition model to obtain the second driving style of the driver output by the second style recognition model; The driving characteristics are input into the third style recognition model to obtain the driver's third driving style output by the third style recognition model; The driver's driving style at the current moment is obtained by weighted voting based on the first driving style, the second driving style, and the third driving style.

7. The braking control method according to claim 5, characterized in that, Determining the driver's driving style at the current moment based on the driving characteristics, the first style recognition model, the second style recognition model, and the third style recognition model includes: The driver's initial driving style at the current moment is determined based on the driving characteristics, the first style recognition model, the second style recognition model, and the third style recognition model. The driver's driving style at the current moment is determined based on the driver's historical initial driving style corresponding to a first preset number of consecutive moments before the current moment, the previous driving style at the current moment, and the driver's initial driving style at the current moment.

8. The braking control method according to claim 7, characterized in that, The step of determining the driver's driving style at the current moment based on the driver's historical initial driving style corresponding to a first preset number of consecutive moments before the current moment, the previous driving style at the current moment, and the driver's initial driving style at the current moment includes: When the number of initial driving styles at the current moment in the historical initial driving styles is greater than or equal to the second preset number, the driver's initial driving style at the current moment is used to determine the driver's driving style at the current moment. If the number of initial driving styles at the current moment in the historical initial driving styles is less than the second preset number, the driver's previous driving style at the current moment is used to determine the driver's driving style at the current moment.

9. The braking control method according to any one of claims 1 to 4, characterized in that, The driving parameters include steering wheel parameters and lane parameters, and the biodata includes the driver's facial data and biosignal data. Based on the driving parameters and the biological data, the driver's driving state at the current moment is determined, including: From the driving parameters and the biological data, the driver's steering wheel features, lane features, facial features and biosignal features at the current moment are extracted; Based on the steering wheel features, lane features, facial features, and biosignal features, determine at least one driving state of the driver at the current moment; Based on the preset priority of driving states, the driving state with the highest priority among the at least one driving states is taken as the driving state of the driver at the current moment.

10. A vehicle comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the braking control method as described in any one of claims 1 to 9.

Images