Steering assist control method, system and storage medium based on physiological characteristic perception

Abstract

The application discloses a steering assist control method and system based on physiological feature perception, and a storage medium. The method comprises the following steps: acquiring steering wheel holding force data, physiological state data, head image data and driving operation data of a driver; determining the fatigue degree of the driver according to the head image data, and determining the reaction speed of the driver according to the driving operation data; inputting the steering wheel holding force data, the physiological state data, the fatigue degree and the reaction speed into a pre-trained steering assist demand prediction model to obtain the real-time steering assist demand of the driver; determining the initial steering assist according to the speed signal of the current vehicle and the torque signal of the steering wheel, adjusting the initial steering assist according to the real-time steering assist demand to obtain the target steering assist, and then controlling the steering assist motor to output the target steering assist. The application improves the stability of driving and the driving experience of the driver, and can be widely applied to the technical field of vehicle control.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, and in particular to a steering assist control method and system based on physiological feature perception and a storage medium. BACKGROUND

[0002] When the automobile is steering, the torque sensor can perceive the steering torque and the steering direction, and these signals are sent to the electronic control unit through the data bus. The electronic control unit sends action instructions to the motor controller according to the data signals such as the steering torque and the steering direction, so that the motor outputs steering assist torque of corresponding size and direction, thereby generating auxiliary power to help the driver control the steering of the wheels.

[0003] The current power steering system can only output steering assist torque of corresponding size through analog presetting, and cannot accurately control the current required steering assist according to the real-time physiological condition of the driver, thereby affecting the stability of driving and the driving experience of the driver. SUMMARY

[0004] The present application aims to at least partly solve one of the problems in the prior art.

[0005] To this end, one object of the present application is to provide a steering assist control method based on physiological feature perception, which improves the stability of driving and the driving experience of the driver.

[0006] Another object of the present application is to provide a steering assist control system based on physiological feature perception.

[0007] In order to achieve the above technical objects, the technical solutions adopted by the embodiments of the present application include:

[0008] In a first aspect, the present application provides a steering assist control method based on physiological feature perception, comprising the following steps:

[0009] obtaining steering wheel grip data, physiological state data, head image data and driving operation data of the driver;

[0010] determining the fatigue degree of the driver according to the head image data, and determining the reaction speed of the driver according to the driving operation data;

[0011] inputting the steering wheel grip data, the physiological state data, the fatigue degree and the reaction speed into a pre-trained steering assist demand prediction model to obtain the real-time steering assist demand of the driver;

[0012] The initial steering assist force is determined according to a vehicle speed signal of a current vehicle and a torque signal of a steering wheel, the initial steering assist force is adjusted according to the real-time steering assist force demand to obtain a target steering assist force, and the steering assist motor is controlled to output the target steering assist force.

[0013] Further, in an embodiment of the present application, the driver's steering wheel holding force data, physiological state data, head image data and driving operation data are obtained, which specifically include:

[0014] The steering wheel holding force data are obtained by a holding force sensor arranged in a steering wheel holding area;

[0015] The physiological state data are obtained by a physiological sensor arranged in the steering wheel holding area to obtain the driver's heart rate, blood pressure and blood oxygen data;

[0016] The head image data are obtained by a vehicle-mounted camera;

[0017] The driving operation data of the driver are recorded by a driving assistance system.

[0018] Further, in an embodiment of the present application, the fatigue degree of the driver is determined according to the head image data, which specifically includes:

[0019] Face key point detection is performed on the head image data to obtain eye region images and mouth region images;

[0020] The driver's blinking behavior is identified according to the eye region images, and the blinking frequency of the driver is determined according to continuous multiple frames of the eye region images;

[0021] The driver's yawning behavior is identified according to the mouth region images, and the yawning frequency of the driver is determined according to continuous multiple frames of the mouth region images;

[0022] Posture recognition is performed on the head image data to obtain head posture information;

[0023] The fatigue degree of the driver is determined according to the blinking frequency, the yawning frequency and the head posture information.

[0024] Further, in an embodiment of the present application, the reaction speed of the driver is determined according to the driving operation data, which specifically includes:

[0025] The steering wheel operation frequency of the driver and the response time to a warning signal are determined according to the driving operation data;

[0026] The reaction speed of the driver is determined according to the steering wheel operation frequency and the response time.

[0027] Further, in an embodiment of the present application, the steering assist demand prediction model is trained by the following steps:

[0028] The steering wheel grip sample data, physiological state sample data, fatigue degree sample data and reaction speed sample data of the test personnel are obtained, and the feedback action of the test personnel to the steering assist output of the steering assist motor is recorded;

[0029] The training sample is determined according to the steering wheel grip sample data, the physiological state sample data, the fatigue degree sample data and the reaction speed sample data, and the corresponding steering assist demand label is determined according to the feedback action;

[0030] The training sample is input into a pre-constructed deep learning neural network to obtain a steering assist demand prediction result;

[0031] The loss value is determined according to the steering assist demand prediction result and the steering assist demand label;

[0032] The parameters of the deep learning neural network are updated according to the loss value to obtain the trained steering assist demand prediction model.

[0033] Further, in an embodiment of the present application, the determination of the corresponding steering assist demand label according to the feedback action specifically includes:

[0034] When the feedback action is to increase the torque of the steering wheel, it is determined that the steering assist demand of the test personnel is a strong steering assist demand, and the strong steering assist demand level is determined according to the amplitude of the torque increase, and then the steering assist demand label is determined according to the strong steering assist demand level;

[0035] When the feedback action is to reduce the torque of the steering wheel, it is determined that the steering assist demand of the test personnel is a weak steering assist demand, and the weak steering assist demand level is determined according to the amplitude of the torque reduction, and then the steering assist demand label is determined according to the weak steering assist demand level;

[0036] When the test personnel has no feedback action, the corresponding steering assist demand label is determined to be a standard steering assist demand.

[0037] Further, in an embodiment of the present application, the initial steering assist is determined according to the vehicle speed signal and the torque signal of the steering wheel, the initial steering assist is adjusted according to the real-time steering assist demand to obtain a target steering assist, and then the target steering assist is controlled to be output by the steering assist motor, which specifically includes:

[0038] The vehicle speed signal is acquired by a vehicle body controller, and the torque signal is acquired by a torque sensor;

[0039] The initial steering assist is calculated by an electric power steering system according to the vehicle speed signal and the torque signal;

[0040] A steering assist increase / decrease amplitude is determined according to the real-time steering assist demand, and the initial steering assist is adjusted according to the steering assist increase / decrease amplitude to obtain the target steering assist;

[0041] A corresponding motor current is generated according to the target steering assist, and the target steering assist is output by the steering assist motor controlled by the motor current.

[0042] In a second aspect, an embodiment of the present application provides a steering assist control system based on physiological feature perception, comprising:

[0043] A data acquisition module is configured to acquire steering wheel grip data, physiological state data, head image data and driving operation data of a driver;

[0044] A driving feature extraction module is configured to determine a fatigue degree of the driver according to the head image data, and determine a reaction speed of the driver according to the driving operation data;

[0045] A steering assist demand prediction module is configured to input the steering wheel grip data, the physiological state data, the fatigue degree and the reaction speed into a pre-trained steering assist demand prediction model to obtain a real-time steering assist demand of the driver;

[0046] A steering assist adjustment module is configured to determine an initial steering assist according to a vehicle speed signal and a torque signal of a steering wheel of a current vehicle, adjust the initial steering assist according to the real-time steering assist demand to obtain a target steering assist, and then control a steering assist motor to output the target steering assist.

[0047] In a third aspect, an embodiment of the present application provides a steering assist control device based on physiological feature perception, comprising:

[0048] At least one processor;

[0049] At least one memory configured to store at least one program;

[0050] When the at least one program is executed by the at least one processor, the at least one processor is caused to implement the above-mentioned steering assist control method based on physiological feature perception.

[0051] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, which stores a processor executable program, and the processor executable program is used for executing the above-mentioned steering assist control method based on physiological characteristic perception when executed by a processor.

[0052] The advantages and beneficial effects of the present application will be partially given in the following description, partially will become obvious from the following description, or will be understood through the practice of the present application:

[0053] The embodiments of the present application obtain the steering wheel holding force data, physiological state data, head image data and driving operation data of the driver, determine the fatigue degree of the driver according to the head image data, and determine the reaction speed of the driver according to the driving operation data, input the steering wheel holding force data, physiological state data, fatigue degree and reaction speed into the steering assist demand prediction model which is pre-trained, obtain the real-time steering assist demand of the driver, determine the initial steering assist according to the speed signal of the current vehicle and the torque signal of the steering wheel, adjust the initial steering assist according to the real-time steering assist demand, obtain the target steering assist, and then control the steering assist motor to output the target steering assist. The embodiments of the present application predict the real-time steering assist demand of the driver based on the steering wheel holding force data, physiological state data, fatigue degree and reaction speed of the driver, adjust and control the steering assist according to the real-time steering assist demand, can provide more accurate steering assist for the driver, and improve the stability of driving and the driving experience of the driver. BRIEF DESCRIPTION OF DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following introduces the drawings needed to be used in the embodiments of the present application. It should be understood that the drawings in the following introduction are only for the convenience of clearly describing some embodiments in the technical solutions of the present application, and other drawings can also be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0055] Figure 1 A step flow chart of a steering assist control method based on physiological characteristic perception provided by the embodiments of the present application;

[0056] Figure 2 A structural block diagram of a steering assist control system based on physiological characteristic perception provided by the embodiments of the present application;

[0057] Figure 3 A structural block diagram of a steering assist control device based on physiological characteristic perception provided by the embodiments of the present application. DETAILED DESCRIPTION

[0058] Embodiments of the present application are described below in detail with reference to the accompanying drawings, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as a limitation of the present application. For the step numbers in the following embodiments, they are only set for the convenience of setting out the description, and the order between the steps is not limited in any way, and the execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0059] In the description of the present application, the meaning of multiple is two or more, and if the first, the second is described, it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or implicitly indicating the sequence of indicated technical features. In addition, unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art.

[0060] With reference to Figure 1 , the embodiment of the present application provides a steering assist control method based on physiological feature perception, which specifically comprises the following steps:

[0061] S101, acquiring steering wheel grip data, physiological state data, head image data and driving operation data of the driver;

[0062] S102, determining the fatigue degree of the driver according to the head image data, and determining the reaction speed of the driver according to the driving operation data;

[0063] S103, inputting the steering wheel grip data, physiological state data, fatigue degree and reaction speed into a pre-trained steering assist demand prediction model to obtain the real-time steering assist demand of the driver;

[0064] S104, determining the initial steering assist according to the speed signal of the current vehicle and the torque signal of the steering wheel, adjusting the initial steering assist according to the real-time steering assist demand to obtain the target steering assist, and then controlling the steering assist motor to output the target steering assist.

[0065] Specifically, in the existing electric power steering system, when the driver steers the steering wheel, the torque sensor detects the steering of the steering wheel and the size of the torque, and transmits the voltage signal to the electronic control unit. The electronic control unit sends instructions to the electric motor controller according to the torque voltage signal, the rotation direction and the vehicle speed signal detected by the torque sensor, so that the electric motor outputs steering assist torque of corresponding size and direction, thereby generating auxiliary power.

[0066] The embodiment of the application monitors the change of the driver's grip force, physiological state in real time through the sensor integrated on the steering wheel, monitors the fatigue degree of the driver in real time through the vehicle-mounted camera, monitors the reaction speed of the driver in real time through the driving assistance system, inputs the steering wheel grip force data, physiological state data, fatigue degree and reaction speed into the pre-trained steering assist demand prediction model to obtain the real-time steering assist demand of the driver, and adjusts the output of the steering assist motor according to the real-time steering assist demand to provide the driver with appropriate steering assist.

[0067] The embodiment of the application predicts the real-time steering assist demand of the driver based on the steering wheel grip force data, physiological state data, fatigue degree and reaction speed of the driver, adjusts and controls the steering assist according to the real-time steering assist demand, can provide the driver with more accurate steering assist, and improves the stability of driving and the driving experience of the driver.

[0068] Further, as an optional implementation, the steering wheel grip force data, physiological state data, head image data and driving operation data of the driver are obtained, which specifically include:

[0069] S1011, the steering wheel grip force data is obtained through the grip force sensor arranged in the steering wheel holding area;

[0070] S1012, the heart rate, blood pressure and blood oxygen data of the driver are obtained through the physiological sensor arranged in the steering wheel holding area to obtain the physiological state data;

[0071] S1013, the head image data is obtained through the vehicle-mounted camera;

[0072] S1014, the driving operation behavior of the driver is recorded through the driving assistance system to obtain the driving operation data.

[0073] Specifically, the capacitive sensor or elastomer pressure sensor is embedded in the surface of the steering wheel (such as a conductive layer + rubber layer structure), when the driver holds the steering wheel, the sensor detects the grip force size and distribution through the change of capacitance or the deformation of elastomer, generates a pressure distribution map in real time to obtain the steering wheel grip force data; the heart rate, blood pressure and blood oxygen sensors (such as optical sensors covered with light-transmitting materials) are embedded in the steering wheel holding area to obtain the real-time physiological state data of the driver through contact measurement; the head image data of the driver is obtained through the vehicle-mounted camera in the cockpit; the driving operation behavior of the driver is recorded through the driving assistance system, such as steering wheel operation behavior, brake / acceleration behavior, to obtain the driving operation data.

[0074] Further, as an optional implementation, the fatigue degree of the driver is determined according to the head image data, which specifically includes:

[0075] S1021, perform face key point detection on the head image data to obtain an eye region image and a mouth region image;

[0076] S1022, identify the blinking behavior of the driver according to the eye region image, and determine the blinking frequency of the driver according to the continuous multiple frames of eye region images;

[0077] S1023, identify the yawning behavior of the driver according to the mouth region image, and determine the yawning frequency of the driver according to the continuous multiple frames of mouth region images;

[0078] S1024, perform posture recognition on the head image data to obtain head posture information;

[0079] S1025, determine the fatigue degree of the driver according to the blinking frequency, the yawning frequency and the head posture information.

[0080] Specifically, face key point detection is performed on the head image data to obtain the key points of the eye region and the mouth region, so as to extract the eye region image and the mouth region image; the blinking behavior of the driver can be identified based on the eye region image, so as to count the blinking frequency of the driver in the current period; the yawning behavior of the driver can be identified based on the mouth region image, so as to count the yawning frequency of the driver in the current period; the head posture information of the driver is determined through posture recognition, to judge whether the driver has behaviors such as head leaning back and tilting; the fatigue degree of the driver is quantified according to the blinking frequency, the yawning frequency and the head posture information, and quantified and represented through a preset fatigue degree level, for example, represented by numbers 0-5 to represent no fatigue, first-level fatigue,..., fifth-level fatigue.

[0081] Further as an optional implementation, the reaction speed of the driver is determined according to the driving operation data, which specifically includes:

[0082] S1026, determine the steering wheel operation frequency of the driver and the response time to the warning signal according to the driving operation data;

[0083] S1027, determine the reaction speed of the driver according to the steering wheel operation frequency and the response time.

[0084] Specifically, the time from the issuance of the warning signal to the corresponding behavior of the driver is recorded through the driving assistance system, for example, the driving assistance system issues a warning signal of limiting speed in front, and records the interval time of the driver stepping on the brake, so as to obtain the response time of the driver to the warning signal; the reaction speed of the driver is quantified in combination with the steering wheel operation frequency and the response time to the warning signal, and different reaction speed levels can also be represented by numbers.

[0085] As a further optional implementation, the steering assist demand prediction model is trained by the following steps:

[0086] S201, obtaining steering wheel grip sample data, physiological state sample data, fatigue degree sample data, and reaction speed sample data of a test person, and recording feedback actions of the test person on steering assist output of a steering assist motor;

[0087] S202, determining training samples according to the steering wheel grip sample data, the physiological state sample data, the fatigue degree sample data, and the reaction speed sample data, and determining corresponding steering assist demand labels according to the feedback actions;

[0088] S203, inputting the training samples into a pre-constructed deep learning neural network to obtain a steering assist demand prediction result;

[0089] S204, determining a loss value according to the steering assist demand prediction result and the steering assist demand labels;

[0090] S205, updating parameters of the deep learning neural network according to the loss value to obtain a trained steering assist demand prediction model. As a further optional implementation, the corresponding steering assist demand labels are determined according to the feedback actions, which specifically include:

[0091] S2021, when the feedback action is to increase the torque of the steering wheel, it is determined that the steering assist demand of the test person is a strong steering assist demand, and a strong steering assist demand level is determined according to the amplitude of the torque increase, and then a steering assist demand label is determined according to the strong steering assist demand level;

[0092] S2022, when the feedback action is to reduce the torque of the steering wheel, it is determined that the steering assist demand of the test person is a weak steering assist demand, and a weak steering assist demand level is determined according to the amplitude of the torque reduction, and then a steering assist demand label is determined according to the weak steering assist demand level;

[0093] S2023, when the test person has no feedback action, it is determined that the corresponding steering assist demand label is a standard steering assist demand.

[0094] Specifically, the input data of the steering assist demand prediction model includes steering wheel grip sample data, physiological state sample data, fatigue degree sample data and reaction speed sample data of the test personnel when driving the vehicle, the model architecture can adopt a deep learning neural network, and the model output is the steering assist demand. The steering wheel grip sample data, physiological state sample data, fatigue degree sample data and reaction speed sample data of the test personnel when driving the vehicle are obtained, the corresponding steering assist demand label is determined based on the feedback action of the test personnel to the steering assist of the steering assist motor output, and then the steering wheel grip sample data, physiological state sample data, fatigue degree sample data and reaction speed sample data are input as training samples to the deep learning neural network for training.

[0095] It should be noted that when obtaining the training sample, the circuit steering assist system on the vehicle outputs the steering assist based on the existing steering assist logic (i.e., determines the steering assist based on the torque signal and the vehicle speed signal), at this time the test personnel performs feedback operation based on the steering assist, if the test personnel feels that the steering assist is too large, it means that the steering assist demand of the test personnel at this time is weak, then reduce the torque of the steering wheel, if the test personnel feels that the steering assist is too small, it means that the steering assist demand of the test personnel at this time is strong, then increase the torque of the steering wheel. A training data set is formed by collecting training samples and corresponding sample labels of multiple test personnel.

[0096] After the training sample is input to the initialized deep learning neural network, a model output recognition result, i.e., a steering assist demand prediction result, can be obtained. The accuracy of the model recognition can be evaluated according to the steering assist demand prediction result and the aforementioned steering assist demand label, so as to update the parameters of the model. For the steering assist demand prediction model, the accuracy of the model recognition result can be measured by a loss function. The loss function is defined on a single training data and is used to measure the prediction error of a training data. Specifically, the loss value of the training data is determined by the label of the single training data and the prediction result of the model for the training data. In actual training, there are many training data in a training data set, so a cost function is generally used to measure the overall error of the training data set. The cost function is defined on the entire training data set and is used to calculate the average value of the prediction errors of all training data, which can better measure the prediction effect of the model. For a general machine learning model, based on the aforementioned cost function, plus a regular term that measures the complexity of the model, the loss value of the entire training data set can be obtained based on the objective function. There are many commonly used loss functions, such as 0-1 loss function, square loss function, absolute loss function, logarithmic loss function, cross-entropy loss function, etc., which can be used as the loss function of the machine learning model. In this embodiment, any one of the loss functions can be selected to determine the loss value of the training. Based on the loss value of the training, the parameters of the model are updated by using the back propagation algorithm, and after several iterations, a trained steering assist demand prediction model can be obtained. The number of iterations can be pre-set, or the training can be considered to be completed when the test set reaches the accuracy requirement.

[0097] The steering wheel holding force data, physiological state data, fatigue degree and reaction speed of the driver are input to the trained steering assist demand prediction model, and the real-time steering assist demand of the driver inferred by the model can be obtained.

[0098] Further, as an optional embodiment, the initial steering assist is determined according to the vehicle speed signal and the torque signal of the steering wheel, the initial steering assist is adjusted according to the real-time steering assist demand to obtain the target steering assist, and then the target steering assist is output by the steering assist motor. Specifically, it includes:

[0099] S1041, acquiring a vehicle speed signal through a vehicle body controller and acquiring a torque signal through a torque sensor;

[0100] S1042, calculating an initial steering assist by an electric power steering system according to the vehicle speed signal and the torque signal;

[0101] S1043, determine a steering assist increase / decrease amplitude according to the real-time steering assist demand, adjust the initial steering assist according to the steering assist increase / decrease amplitude to obtain a target steering assist;

[0102] S1044, generate a corresponding motor current according to the target steering assist, and control the steering assist motor to output the target steering assist through the motor current.

[0103] Specifically, the vehicle speed signal is obtained through the vehicle body controller, and the torque signal is obtained through the torque sensor, and the initial steering assist is calculated through the electric power steering system according to the vehicle speed signal and the torque signal. The initial steering assist is consistent with the calculation logic of the existing electric power steering system, and will not be repeated here; determine the steering assist increase / decrease amplitude according to the real-time steering assist demand, if the real-time steering assist demand is a strong steering assist demand, determine the steering assist increase amplitude according to the strong steering assist demand level, if the real-time steering assist demand is a weak steering assist demand, determine the steering assist decrease amplitude according to the weak steering assist demand level, adjust the numerical value of the initial steering assist according to the steering assist increase / decrease amplitude to obtain the target steering assist; generate a corresponding motor current according to the target steering assist, and control the steering assist motor to output the target steering assist through the motor current.

[0104] The method steps of the embodiments of the application are described above. It can be understood that the embodiments of the application predict the real-time steering assist demand of the driver based on the steering wheel holding force data, physiological state data, fatigue degree and reaction speed of the driver, adjust and control the steering assist according to the real-time steering assist demand, which can provide more accurate steering assist for the driver, and improve the stability of driving and the driving experience of the driver.

[0105] Referring to Figure 2 The embodiments of the application provide a steering assist control system based on physiological feature perception, comprising:

[0106] A data acquisition module is configured to acquire steering wheel holding force data, physiological state data, head image data and driving operation data of a driver.

[0107] A driving feature extraction module is configured to determine the fatigue degree of the driver according to the head image data, and determine the reaction speed of the driver according to the driving operation data.

[0108] A steering assist demand prediction module is configured to input the steering wheel holding force data, physiological state data, fatigue degree and reaction speed into a pre-trained steering assist demand prediction model to obtain the real-time steering assist demand of the driver.

[0109] The steering assist adjustment module is used for determining an initial steering assist force according to a current vehicle speed signal and a torque signal of a steering wheel, adjusting the initial steering assist force according to a real-time steering assist force demand to obtain a target steering assist force, and then controlling a steering assist motor to output the target steering assist force.

[0110] The contents in the method embodiments are applicable to the system embodiments, the system embodiments specifically realize the functions same as the method embodiments, and achieve the beneficial effects same as the method embodiments.

[0111] Referring to Figure 3 The embodiment of the present application provides a steering assist control device based on physiological characteristic sensing, which comprises:

[0112] At least one processor;

[0113] At least one memory for storing at least one program;

[0114] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned steering assist control method based on physiological characteristic sensing.

[0115] The contents in the method embodiments are applicable to the device embodiments, the device embodiments specifically realize the functions same as the method embodiments, and achieve the beneficial effects same as the method embodiments.

[0116] The embodiment of the present application further provides a computer readable storage medium, wherein a program executable by a processor is stored, and the program executable by the processor is used for executing the above-mentioned steering assist control method based on physiological characteristic sensing when executed by the processor.

[0117] The computer readable storage medium of the embodiment of the present application can execute the steering assist control method based on physiological characteristic sensing provided by the method embodiment of the present application, execute the steps of any combination of the method embodiments, and has the corresponding functions and beneficial effects of the method.

[0118] The embodiment of the present application further discloses a computer program product or a computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of a computer device can read the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method shown in the figure. Figure 1

[0119] ​In alternative embodiments, the functions / operations in the flow diagrams can occur in sequences other than those depicted. For example, two operations shown in succession can in fact be executed substantially concurrently or the operations can sometimes be executed in the reverse order depending upon the functionality / operations involved. Such variations are contemplated to be within the scope of the present application. Embodiments presented and described in the flow diagrams are examples only and are used to provide an enabling teaching for the present application. The processes disclosed are not limited to the order or specific blocks described. Alternative embodiments are contemplated, in which the order of the blocks is changed and where some blocks are performed in parallel rather than sequentially.

[0120] Moreover, while the present application has been described in the context of functional modules, it is to be understood that one or more of the functions and / or features described above can be integrated within a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It will also be appreciated that detailed discussion of the actual implementation of each module is not necessary for an enabling understanding of the application. Rather, the actual implementation is most readily derived from the description of the functionality of the various functional modules, in conjunction with the understanding of the properties, functions and interrelationships of the various functional modules presented in the context of the device disclosed herein. Therefore, the scope of the application is best understood from the appended claims, in conjunction with the full description and examples provided. It is to be understood that the specific concepts presented are merely illustrative of the application and are not intended to limit the scope of the application as defined by the claims. The scope of the application is defined by the claims and the full extent of equivalents to which such claims are entitled.

[0121] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or part of the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods in the embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, etc.

[0122] The logic and / or steps represented in the flow diagrams or otherwise described herein, for example, can be embodied in non-transitory computer- readable media, executed by an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or in conjunction with which the instructions can be executed. In the context of this specification, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium.

[0123] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and stored in a computer memory.

[0124] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, various steps or methods can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any of the following technologies, known in the art, or combinations thereof, can be used: a discrete logic circuit having logic gates for implementing logic functions upon data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), and / or the like.

[0125] In the above description of the present specification, reference has been made to descriptive terms such as "one embodiment / exemplification", "another embodiment / exemplification", or "some embodiments / exemplifications" etc. It is understood that such terms are not intended to mean that the described specific feature, structure, material or characteristic was included in only one embodiment / exemplification. The illustrative descriptions are not intended to limit the scope of the present specification to the described embodiments / exemplifications. Furthermore, the described specific features, structures, materials or characteristics can be combined in any suitable manner in one or more embodiments / exemplifications.

[0126] While the embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely exemplary and are not to be construed as limiting the scope of the application. The scope of the application is defined by the appended claims and their equivalents.

[0127] The above is the specific description of the preferred embodiment of the application, but the application is not limited to the above-mentioned embodiments, and those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the application.

Claims

1. A steering assist control method based on physiological characteristic perception, characterized in that, Includes the following steps: Acquire driver's steering wheel grip force data, physiological state data, head image data, and driving operation data; The driver's fatigue level is determined based on the head image data, and the driver's reaction speed is determined based on the driving operation data; The steering wheel grip force data, the physiological state data, the fatigue level, and the reaction speed are input into a pre-trained steering assist demand prediction model to obtain the driver's real-time steering assist demand. The initial steering assist is determined based on the current vehicle speed signal and the steering wheel torque signal. The initial steering assist is adjusted according to the real-time steering assist demand to obtain the target steering assist, and then the steering assist motor is controlled to output the target steering assist. The steering assist demand prediction model is trained through the following steps: Acquire sample data of the tester's steering wheel grip force, physiological state, fatigue level, and reaction speed, and record the tester's feedback actions to the steering assist output by the steering assist motor. Training samples are determined based on the steering wheel grip force sample data, the physiological state sample data, the fatigue level sample data, and the reaction speed sample data, and corresponding steering assist demand labels are determined based on the feedback actions. The training samples are input into a pre-built deep learning neural network to obtain steering assist demand prediction results; The loss value is determined based on the steering assist demand prediction results and the steering assist demand label; The parameters of the deep learning neural network are updated based on the loss value to obtain the trained steering assist demand prediction model; The step of determining the corresponding steering assist demand label based on the feedback action specifically includes: When the feedback action is to increase the torque of turning the steering wheel, the steering assist demand of the tester is determined to be a strong steering assist demand, and the strong steering assist demand level is determined according to the magnitude of the torque increase, and then the steering assist demand label is determined according to the strong steering assist demand level. When the feedback action is to reduce the torque of turning the steering wheel, the steering assist requirement of the tester is determined to be a weak steering assist requirement, and the weak steering assist requirement level is determined according to the magnitude of the torque reduction, and then the steering assist requirement label is determined according to the weak steering assist requirement level. If the tester does not provide any feedback, the corresponding steering assist requirement label is determined to be a standard steering assist requirement.

2. The steering assist control method based on physiological feature perception according to claim 1, characterized in that, The acquisition of the driver's steering wheel grip force data, physiological state data, head image data, and driving operation data specifically includes: The steering wheel grip force data is acquired by a grip force sensor located in the steering wheel grip area; The driver's heart rate, blood pressure, and blood oxygen data are obtained by a physiological sensor located in the steering wheel grip area to obtain the physiological state data; The head image data is acquired using an in-vehicle camera; The driving operation data is obtained by recording the driver's driving behavior through the driving assistance system.

3. The steering assist control method based on physiological feature perception according to claim 1, characterized in that, Determining the driver's fatigue level based on the head image data specifically includes: Facial landmark detection is performed on the head image data to obtain eye region images and mouth region images; The driver's blinking behavior is identified based on the eye region image, and the driver's blinking frequency is determined based on multiple consecutive frames of the eye region image; The driver's yawning behavior is identified based on the mouth region image, and the driver's yawning frequency is determined based on multiple consecutive frames of the mouth region image. Head pose information is obtained by performing pose recognition on the head image data; The driver's fatigue level is determined based on the blinking frequency, the yawning frequency, and the head posture information.

4. The steering assist control method based on physiological feature perception according to claim 1, characterized in that, Determining the driver's reaction speed based on the driving operation data specifically includes: The driver's steering wheel operation frequency and response time to warning signals are determined based on the driving operation data. The driver's reaction speed is determined based on the steering wheel operation frequency and the response time.

5. A steering assist control method based on physiological characteristic perception according to any one of claims 1 to 4, characterized in that, The process of determining initial steering assist based on the current vehicle speed signal and steering wheel torque signal, adjusting the initial steering assist according to the real-time steering assist demand to obtain target steering assist, and then controlling the steering assist motor to output the target steering assist, specifically includes: The vehicle speed signal is obtained through the body controller, and the torque signal is obtained through the torque sensor; The initial steering assist is calculated by the electric power steering system based on the vehicle speed signal and the torque signal; The steering assist increase / decrease range is determined based on the real-time steering assist demand, and the initial steering assist is adjusted according to the steering assist increase / decrease range to obtain the target steering assist. The corresponding motor current is generated based on the target steering assist, and the steering assist motor is controlled to output the target steering assist through the motor current.

6. A steering assist control system based on physiological characteristic perception, characterized in that, A steering assist control method based on physiological feature perception as described in any one of claims 1 to 5 includes: The data acquisition module is used to acquire the driver's steering wheel grip force data, physiological state data, head image data, and driving operation data; A driving feature extraction module is used to determine the driver's fatigue level based on the head image data and to determine the driver's reaction speed based on the driving operation data. The steering assist demand prediction module is used to input the steering wheel grip force data, the physiological state data, the fatigue level and the reaction speed into a pre-trained steering assist demand prediction model to obtain the driver's real-time steering assist demand. The steering assist adjustment module is used to determine the initial steering assist based on the current vehicle speed signal and the steering wheel torque signal, adjust the initial steering assist according to the real-time steering assist demand to obtain the target steering assist, and then control the steering assist motor to output the target steering assist.

7. A steering assist control device based on physiological characteristic perception, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a steering assist control method based on physiological feature perception as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to perform a steering assist control method based on physiological feature perception as described in any one of claims 1 to 5.

Images