Driver hand release detection method, device and equipment and storage medium
By obtaining the torque detection value and capacitance parameters of the steering wheel, estimating and comprehensive judgment, the problem of driver's hand-off detection in the auxiliary driving system is solved, and the accuracy of detection and system reliability are improved.
Patent Information
- Application Number
- CN202411445244.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-16
- Publication Date
- 2024-12-03
AI Technical Summary
The existing auxiliary driving system has inaccuracy when detecting whether the driver is off-handed, especially the inability to evenly arrange the capacitive sensing device within the 360-degree range, resulting in detection blind spots and false alarms on the off-handed.
By obtaining the torque detection value and capacitance parameters of the steering wheel, the real directional torque input by the driver is estimated, and the capacitance signal is combined with the capacitance signal to comprehensively determine whether the driver is off-handed from multiple angles, and the interference signal of the torque detection value is eliminated to improve the accuracy of detection.
It effectively improves the accuracy of driver's decision on hand-out, reduces false alarms, and enhances the reliability of assisted driving systems.
Smart Images

Figure CN119058718A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle control technology, and in particular to a driver's hands-off detection method, device, equipment and storage medium. Background Art
[0002] The current assisted driving system will detect the driver's hands-off state when controlling the vehicle. It usually relies on the capacitive sensor module of the capacitive steering wheel to detect the driver's hand position through capacitance changes. When it is detected that the driver is holding the steering wheel, it is judged that the driver has not taken his hands off the steering wheel. Conversely, if the driver's hands are not detected on the steering wheel, it is judged that the driver has taken his hands off the steering wheel.
[0003] Capacitive steering wheels cannot have capacitive sensing devices evenly arranged within a 360-degree range, so there is a certain detection blind spot. Even if the driver holds the steering wheel in a special position, it cannot be detected. The assisted driving system often has a certain probability of false alarms due to inaccurate input information.
[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention
[0005] The main purpose of this application is to provide a driver's hands-off detection method, device, equipment and storage medium, aiming to solve the technical problem that the prior art is not accurate enough in detecting whether the driver has taken his hands off the steering wheel while driving.
[0006] To achieve the above objectives, the present application proposes a driver's hands-off detection method, which comprises:
[0007] Get the torque detection value and capacitance parameters of the steering wheel;
[0008] estimating the actual directional torque input by the driver according to the torque detection value to obtain a reference torque;
[0009] A driving state is obtained according to the capacitance parameter and the reference torque, where the driving state includes normal driving and hands-free driving.
[0010] In one embodiment, estimating the actual directional torque input by the driver according to the torque detection value to obtain the reference torque includes:
[0011] Obtain the moment of inertia, angular displacement and torsion bar stiffness of the steering wheel;
[0012] Obtaining observation parameters according to the moment of inertia, the angular displacement and the torsion bar stiffness;
[0013] A reference torque is obtained according to the observed parameter and the torque detection value.
[0014] In one embodiment, obtaining the observation parameter according to the moment of inertia, the angular displacement and the torsion bar stiffness includes:
[0015] Taking the moment of inertia, the angular displacement and the torsion bar stiffness as initial parameters;
[0016] Obtaining a reference matrix according to the initial parameters;
[0017] Obtaining an expanded matrix according to the reference matrix and the initial parameters;
[0018] The initial parameters, the reference matrix and the expanded matrix are used as observation parameters.
[0019] In one embodiment, obtaining the reference torque according to the observed parameter and the torque detection value comprises:
[0020] Calculating the torque according to the observed parameters and the torque detection value to obtain an estimated torque;
[0021] Get sensor compensation torque;
[0022] The estimated torque is corrected according to the sensor hardware error compensation torque to obtain a reference torque.
[0023] In one embodiment, the step of calculating the torque according to the observed parameter and the torque detection value to obtain the estimated torque includes:
[0024] Obtaining preset restriction conditions, and obtaining an observation gain matrix according to the observation parameters;
[0025] Obtaining a torque estimation function according to the observation parameters, the torque detection value and the observation gain matrix;
[0026] When the preset restriction condition is met, the estimated torque is obtained based on the torque estimation function.
[0027] In one embodiment, the driving state is obtained according to the capacitance parameter and the reference torque, and the driving state includes normal driving and hands-free driving, including:
[0028] obtaining the driver's hand contact state according to the capacitance parameter;
[0029] A driving state is obtained according to the contact state and the reference torque, and the driving state includes a hands-free driving state and a normal driving state.
[0030] In one embodiment, obtaining the driving state according to the contact state and the reference torque includes:
[0031] When the driver's hand contact state is a non-contact state, a hands-free driving state is used as the driving state;
[0032] When the driver's hand contact state is in the contact state, a reference time when the reference torque is less than a torque threshold is obtained, and when the reference time is greater than or equal to the time threshold, a hands-free driving state is used as the driving state.
[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a driver's hands-off detection device, the driver's hands-off detection device comprising:
[0034] A parameter acquisition module, used to obtain the torque detection value and capacitance parameters of the steering wheel;
[0035] A torque estimation module, used for estimating the real directional torque input by the driver according to the torque detection value to obtain a reference torque;
[0036] The hands-free driving judgment module is used to obtain a driving state according to the capacitance parameter and the reference torque, wherein the driving state includes normal driving and hands-free driving.
[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a driver hands-off detection device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the driver hands-off detection method as described above.
[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the driver's hands-off detection method described above are implemented.
[0039] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the driver's hands-off detection method as described above are implemented.
[0040] One or more technical solutions proposed in this application have at least the following technical effects:
[0041] The detection torque of the steering wheel is obtained through the detector, and the interference signal of the steering wheel torque detection value is further eliminated, and an accurate reference torque that can better represent the driver's input torque is extracted. Then, combined with the driver's contact capacitance signal at the steering wheel, it is comprehensively judged from multiple angles whether the driver is driving with his hands off, effectively improving the accuracy of the judgment on the driver's hands-off driving. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0044] Figure 1 A flowchart of the first embodiment of the driver's hands-off detection method of the present application is provided;
[0045] Figure 2 A schematic diagram of a hands-off determination process flow provided in Embodiment 1 of the driver's hands-off detection method of the present application;
[0046] Figure 3 A schematic diagram of a process flow provided for the second embodiment of the driver's hands-off detection method of the present application;
[0047] Figure 4 This is a schematic diagram of the module structure of the driver's hands-off detection device according to an embodiment of the present application;
[0048] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the driver's hands-off detection method in the embodiment of the present application. DETAILED DESCRIPTION
[0049] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0050] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0051] The main solution of the embodiment of the present application is: obtaining the torque detection value and capacitance parameters of the steering wheel; estimating the actual directional torque input by the driver based on the torque detection value to obtain a reference torque; obtaining the driving state based on the capacitance parameters and the reference torque, and the driving state includes normal driving and hands-free driving.
[0052] In this embodiment, for the convenience of description, the following description is made by taking the identification device for detecting the driver's hands-off function as the execution subject.
[0053] Because the current assisted driving system in the prior art will detect the driver's hands-off state when controlling the vehicle, it usually relies on the capacitive sensor module of the capacitive steering wheel to detect the driver's hand position through capacitance changes. When it is detected that the driver is holding the steering wheel, it is determined that the driver has not taken the hands off. On the contrary, if it is not detected that the driver is holding the steering wheel, it is determined that the driver has taken the hands off. The capacitive steering wheel cannot be arranged with capacitive sensing devices within a 360-degree range, and there is a certain detection blind spot. The driver's hands on the steering wheel in a special position cannot be detected. The assisted driving system often has a certain probability of false alarming of hands-off due to inaccurate input information.
[0054] The present application provides a solution, which obtains the detection torque of the steering wheel through a detector, further eliminates the interference signal of the steering wheel torque detection value, extracts an accurate reference torque that can better represent the driver's input torque, and then combines the driver's contact capacitance signal at the steering wheel to comprehensively judge from multiple angles whether the driver is driving with his hands off, thereby effectively improving the accuracy of the judgment on the driver's hands-off driving.
[0055] It can be seen from the above embodiments that the present application discloses a driver hands-off detection method, device, equipment and storage medium, which relates to the field of vehicle control technology, and discloses a driver hands-off detection method, including: obtaining a torque detection value and a capacitance parameter of a steering wheel; estimating the actual directional torque input by the driver according to the torque detection value to obtain a reference torque; obtaining a driving state according to the capacitance parameter and the reference torque, and the driving state includes normal driving and hands-off driving; the method obtains the detection torque of the steering wheel through a detector, further eliminates the interference signal of the steering wheel torque detection value, extracts an accurate reference torque that can better represent the driver's input torque, and then combines the driver's contact capacitance signal at the steering wheel to comprehensively judge whether the driver is driving with his hands off from multiple angles, thereby effectively improving the accuracy of the judgment on the driver's hands-off.
[0056] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a driver's hands-off detection device, etc. The following takes the driver's hands-off detection device as an example to illustrate this embodiment and the following embodiments.
[0057] Based on this, the embodiment of the present application provides a method for detecting a driver's hands-off behavior. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the driver's hands-off detection method of the present application.
[0058] In this embodiment, the driver's hands-off detection method includes steps S10 to S40:
[0059] Step S10, acquiring the torque detection value and capacitance parameter of the steering wheel.
[0060] It is understandable that the torque detection value can be obtained by a torque detector. The torque detection value can be the torque value of the steering wheel measured by the detector. The torque value may be different from the detection value and the actual torque given by the driver due to inertia, detector influence factors, etc.
[0061] It should be understood that a vehicle steering wheel torque detector is a device used to measure the moment (i.e. torque) applied by the driver when turning the steering wheel. This device is usually installed on the steering column and can be mechanical or electronic. It can detect the driver's operating force on the steering wheel and convert this information into an electrical signal to obtain a torque value.
[0062] It is understandable that the capacitance parameter may be obtained by setting a capacitance sensor module on the steering wheel according to the capacitance change on the steering wheel.
[0063] It should be understood that the capacitance on the steering wheel will change due to the driver's contact and non-contact. For example, the capacitance signal is 1 when the driver contacts the steering wheel, and the capacitance signal is 0 when the driver does not contact the steering wheel.
[0064] Step S20: estimating the actual directional torque input by the driver according to the torque detection value to obtain a reference torque.
[0065] It can be understood that the actual directional torque input by the driver is the torque applied to the steering wheel by the force input by the driver, and the torque detection value is the torque obtained by the torque detector according to the torque of the force of steering wheel rotation.
[0066] It should be understood that the actual directional torque input by the driver will be affected by the interference from the lower end of the steering wheel torsion bar. In dynamic situations, there is a gap between the torque detection value and the actual directional torque input by the driver, and the torque detection value cannot be directly used as the actual directional torque input by the driver.
[0067] It should be noted that the torque detection value may be a steering wheel torsion bar torque value, and the steering wheel torsion bar torque may be calculated by measuring the relative angular displacement between the steering wheel and the lower end of the torsion bar. At the same time, attention should also be paid to the influence of the stiffness of the steering wheel torsion bar on the steering wheel torque.
[0068] In a specific implementation, the driver input torque is estimated based on the measurement value of the torque sensing module, so that the output driver input torque is almost free from interference from the lower end of the torsion bar. A steering wheel dynamics model is constructed to explain the limitations of using the torsion bar signal as an approximation of the driver torque. The Euler equation of the steering wheel is as follows:
[0069]
[0070] Among them, T d is the driver torque, T tb is the torsion bar torque; J sw is the moment of inertia of the steering wheel, θ sw is the angular displacement of the steering wheel.
[0071] Furthermore, T tb The steering torque measurement module measures the relative angular displacement θ between the steering wheel and the lower end of the torsion bar. tbl To calculate, if only the stiffness K of the torsion bar is considered tb , ignoring the damping and friction effects, the following formula is obtained:
[0072]
[0073] Furthermore, considering the angular acceleration of the steering wheel in the dynamic formula of the steering wheel in a static state is 0, therefore, the torsion bar torque is equal to the driver torque, and the following formula can be obtained:
[0074] T d =T tb
[0075] Under dynamic conditions, the torsion bar torque is a function of the driver torque and the steering wheel inertia effect, resulting in the following formula:
[0076]
[0077] Furthermore, the assumption that the driver torque is equal to the torsion bar torque only holds true under static conditions. In dynamic conditions, the inertial effect of the steering wheel is captured by the torsion bar, so the driver's true directional torque can be estimated by compensating for the inertia effect of the steering wheel.
[0078] Step S30, obtaining a driving state according to the capacitance parameter and the reference torque, wherein the driving state includes normal driving and hands-free driving.
[0079] It is understandable that normal driving can be when the driver holds the steering wheel with his hands, and hands-free driving can be when the driver drives the vehicle with both hands off the steering wheel.
[0080] It should be understood that the driving state obtained according to the capacitance parameter and the reference torque can be determined by comprehensively judging the capacitance parameter and the reference torque, which is more accurate than judging whether the driving is hands-free only by the capacitance parameter.
[0081] In a feasible implementation, step S30 may include steps A31 to A32:
[0082] Step A31, obtaining the driver's hand contact state according to the capacitance parameter.
[0083] It is understandable that a plurality of capacitive sensors may be provided on the steering wheel. Since the capacitive sensors generate corresponding capacitive signals when the driver's hands touch the sensors, the state of the driver's hands may be determined based on the sensors that generate the capacitive signals. That is, it can be understood that if a capacitive signal is generated, the driver is in a contact state, and if no capacitive signal is generated, the driver is in a non-contact state.
[0084] It should be emphasized that multiple capacitive sensors can be set on the steering wheel, but the capacitive sensors cannot completely cover the steering wheel. It is possible that there is no capacitive sensor at the position where the driver touches the steering wheel, and the capacitive signal cannot be detected. In this case, the reference torque can be further used to make a hands-off judgment.
[0085] It should be noted that the driving state obtained according to the contact state and the reference torque includes: when the driver's hand contact state is a non-contact state, taking a hands-free driving state as the driving state; when the driver's hand contact state is a contact state, obtaining a reference time when the reference torque is less than a torque threshold, and when the reference time is greater than or equal to a time threshold, taking the hands-free driving state as the driving state.
[0086] Among them, it should be noted that when the setting range of the capacitive sensor is comprehensive, the hands-free driving state can be directly used as the driving state when the driver's hand contact state is in a non-contact state; the reference torque can also be obtained when the driver's hand contact state is in a non-contact state. If the reference torque is greater than the preset minimum torque, normal driving can be used as the driving state.
[0087] Among them, it needs to be further explained that when the driver's hand contact state is in the contact state, it is also possible that the driver just places his hands on the steering wheel and does not apply force to the steering wheel. This should also fall within the scope of hands-free driving. A reference torque can be obtained. If the reference torque is less than the torque threshold and the duration is greater than or equal to the time threshold, it is considered to be in the hands-free state.
[0088] Step A32, obtaining a driving state according to the contact state and the reference torque, wherein the driving state includes a hands-free driving state and a normal driving state.
[0089] It should be noted that if the driver does not hold the steering wheel, the driver torque is still judged. If the reference torque is less than the torque threshold, and the duration is greater than or equal to the time threshold and lasts for a certain time t, the driver is judged to have taken the hands off the wheel; otherwise, it is not judged to have taken the hands off the wheel. The auxiliary driving system has been set to avoid or not tolerate false alarms when judging the hands off, so the threshold must be set higher than the difference range that cannot be compensated by the above method. The driver input torque threshold for hands off judgment can be obtained through actual vehicle calibration, usually set to less than 0.3Nm, and the time threshold t<15s.
[0090] It should be emphasized that if the driver has his hands on the steering wheel, if the reference torque is less than the torque threshold and it lasts for a certain time t, it is determined that the driver has taken his hands off the steering wheel; otherwise it is not determined to be hands off; when the hands-off determination is established, the auxiliary driving system issues a hands-off alarm warning; the on-board display device receives the hands-off alarm warning request from the auxiliary driving system and issues an acoustic / optical warning message.
[0091] In this embodiment, the capacitance parameters are used to intuitively determine whether the driver has touched the steering wheel. When the driver touches the steering wheel, the driver's input torque is used to further determine whether the driver has applied torque to the steering wheel. The size of the applied torque is used to accurately determine whether the driver has effectively touched and controlled the steering wheel, thereby more accurately determining whether the driver has let go of the steering wheel.
[0092] The above are only feasible implementations of step S30 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S30.
[0093] In the specific implementation, the flow chart of the hands-off determination can refer to Figure 2 In the figure, the torsional moment measurement value is received, and the detection information of the position of the driver's hand contacting the steering wheel is received by the capacitive sensing module; the driver's input torque is estimated based on the detection value of the steering torque measurement module, and whether the driver is holding the steering wheel is determined by the contact position of the capacitive sensing module. When it is determined by the capacitive module that the driver is holding the steering wheel, it is determined that the driver has not let go of the steering wheel; when it is determined by the capacitive module that the driver does not hold the steering wheel, the driving input torque is determined to be greater than the preset torque threshold. If it is greater than the preset torque threshold, it is determined that the driver is not driving with his hands. If it is less than or equal to the preset torque threshold, it is determined that the driver is driving with his hands, and the auxiliary driving system issues a warning message.
[0094] It is worth noting that the steering torque measurement module measures the driver's steering torque value in real time; the capacitive sensing module detects the driver's hand position information through capacitance changes to determine whether the driver touches the steering wheel. The auxiliary driving module, which includes sensors, inertial measurement units, etc., can realize automatic control of the vehicle; the on-board display device receives the hands-off warning request of the auxiliary driving system, and the on-board display device informs the driver through acoustic and optical methods.
[0095] The present embodiment provides a method for detecting a driver's hands-off driving, which obtains a detection torque of the steering wheel through a detector, further eliminates interference signals of the steering wheel torque detection value, extracts an accurate reference torque that is more representative of the driver's input torque, and then combines the driver's contact capacitance signal at the steering wheel to comprehensively judge from multiple angles whether the driver is driving with his hands off, thereby effectively improving the accuracy of the judgment on the driver's hands-off driving.
[0096] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 Before step S10, the driver's hands-off detection method further includes steps S21 to S23:
[0097] Step S21, obtaining the moment of inertia, angular displacement and torsion bar stiffness of the steering wheel.
[0098] It is understood that the moment of inertia is a measure of an object's ability to resist rotation about its axis of rotation. For a steering wheel, it describes the inertia of the steering wheel when it rotates around its center of rotation. The moment of inertia of the steering wheel can be obtained by experimental testing in advance or by other methods.
[0099] It is understood that angular displacement refers to the change in the angle of rotation of an object around a point or axis. In a car, this can be directly measured by a sensor (such as an angle encoder). When you turn the steering wheel, the angular displacement refers to the angle the steering wheel turns relative to its initial position. The unit is usually radians or degrees.
[0100] It is understood that the stiffness of a torsion bar refers to the torque required to produce a unit angle of twist in the bar when a torque is applied to the bar. It is an indicator of the torsion bar's ability to resist twisting deformation. It can be determined experimentally, such as fixing one end and applying torque to the other end, measuring the resulting angular displacement, and then calculating it according to Hooke's law.
[0101] Step S22, obtaining observation parameters according to the moment of inertia, the angular displacement and the torsion bar stiffness.
[0102] It can be understood that the present application is to construct an observer model to determine the relationship between the steering wheel detected torque and the driver's actual torque.
[0103] It should be understood that the observation parameter may be a parameter related to the actual input torque of the driver that can be calculated based on the model when the observer model is constructed.
[0104] In a feasible implementation, step S22 may include steps A221 to A223:
[0105] Step A221, taking the moment of inertia, the angular displacement and the torsion bar stiffness as initial parameters, and obtaining a reference matrix according to the initial parameters.
[0106] It should be noted that the observer is constructed with the input of the observer being the angle of the lower end of the torsion bar (known) and the driver torque (unknown), and its output being the signal of the torque sensing module. The state space expressions of the steering wheel dynamics Euler equation and the torsion bar torque can refer to the following formula:
[0107]
[0108] Among them, x is the state vector, u1 is the vector containing known inputs, u2 is the vector containing unknown inputs (driver torque), and y is the output (the signal of the torque sensing module, i.e., the detected torque).
[0109] Furthermore, the initial parameters may include: u1=θ tbl 、u2=T d ,y=T tb .
[0110] It should be emphasized that the reference matrix in the reference matrix obtained according to the initial parameters may include: Since C and D are output matrices, considering a linear time-invariant system, they can be set to C = [1 0], D = [1 0].
[0111] Step A222: obtaining an expanded matrix according to the reference matrix and the initial parameters.
[0112] It can be understood that in order to be estimated by the state observer, the unknown input vector u2 is combined with the state vector x to generate an extended state vector, and then the expansion matrix is obtained based on the state extended vector.
[0113] In a specific implementation, the extended state vector can be expressed as:
[0114] Furthermore, based on the extended state vector, the system state space expansion formula is obtained, which can be specifically referred to in the following formula 6:
[0115]
[0116] Among them, the expansion matrix is obtained by expanding according to the reference matrix, as follows:
[0117]
[0118] C e =[C 0] =[K tb 0 0]
[0119] Step A223, taking the initial parameters, the reference matrix and the expanded matrix as observation parameters.
[0120] It is understandable that when the initial parameters, the reference matrix and the expanded matrix are used as observation parameters based on the observation of the extended state space (ESS) model state and the observation conditions of the Romberg state observer are met, the original system state and the unknown input can be estimated.
[0121] In this embodiment, by combining the moment of inertia representing the ability of an object to resist changes in rotational motion, the angular displacement, and the torsion bar stiffness reflecting the ability of the material to resist torsional deformation, a more accurate dynamic observer model is established, which can capture more factors that affect the behavior of the system, thereby making the model closer to the actual situation and more accurately estimating the driver's input torque.
[0122] The above are only feasible implementations of step S22 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S22.
[0123] Step S23: obtaining a reference torque according to the observation parameter and the torque detection value.
[0124] In a feasible implementation, step S23 may include steps A231 to A233:
[0125] Step A231, performing torque calculation based on the observed parameters and the torque detection value to obtain an estimated torque.
[0126] It is understandable that the observer is pre-built successfully, and real-time torque estimation can be performed through the observer according to the parameters and torque detection values observed each time.
[0127] It should be noted that the torque calculation based on the observation parameters and the torque detection values to obtain the estimated torque includes: obtaining preset restriction conditions and obtaining an observation gain matrix based on the observation parameters; obtaining a torque estimation function based on the observation parameters, the torque detection values and the observation gain matrix; and obtaining the estimated torque based on the torque estimation function when the preset restriction conditions are met.
[0128] It should be noted that the observation gain matrix obtained according to the observation parameters can be obtained according to the observation parameters A e and C e The observed gain matrix K can be obtained. e By configuring A e -K e C e The poles are used to calculate and characterize the stability and convergence of the system. That is, the bandwidth of the observer can be adjusted by placing the poles at the required cutoff frequency (the solution of the Romberg observer belongs to a general calculation method and is not elaborated in detail in the present invention).
[0129] It should be noted that the preset restriction condition may be a condition that the DTE must satisfy based on the observation of the state of the extended state space (ESS) model, and for this purpose, the observability conditions of the ESS models 9 and 10 must be met. For details, refer to the following formula:
[0130]
[0131] Among them, it can be understood that this restriction condition is due to the rank of the observable matrix O being equal to the size of the state vector, so the Romberg state observer can be designed to estimate the original system state and unknown input. Therefore, the torque estimation function based on this restriction condition is as follows:
[0132]
[0133] Furthermore, based on the Romberg observer and This is the actual driver torque after the required error is eliminated.
[0134] Step A232, obtaining sensor compensation torque.
[0135] It is understandable that, generally speaking, the torque sensor will have a certain degree of sensor deviation or a certain friction effect on the torque transmission link, which will also cause deviation in the measurement value of the torque sensing module.
[0136] It should be noted that the sensor compensation torque can be used to compensate for the hardware error of the torque sensor. The consideration of the hardware error of the torque sensor can be analyzed based on the static condition where the torque measured by the torque sensing module is equal to the driver input torque.
[0137] In a specific implementation, if the sensor has a steady-state hardware error T dev , T under static leveling conditions tb =T d +T dev When it is determined to be a static condition and the capacitive sensing module determines that the driver's hand is not in contact with the steering wheel, T is set. d =0, then T tb The feedback value is the sensor hardware error.
[0138] Furthermore, for a certain period of time, T that meets the above conditions tb The values are screened and the values that meet the 3sigma distribution are selected to find the average value, and T is obtained. dev .
[0139] Step A233, correcting the estimated torque according to the sensor hardware error compensation torque to obtain a reference torque.
[0140] It is understandable that the reference torque may be obtained by subtracting the sensor hardware error compensation torque from the estimated torque.
[0141] In this implementation, by obtaining the sensor compensation torque and correcting the estimated torque, the measurement error caused by these hardware factors can be effectively reduced, thereby improving the reliability and accuracy of the driver input torque estimation.
[0142] The above are only feasible implementations of step S23 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S23.
[0143] The present embodiment provides a driver hands-off detection method, which can more effectively separate the actual driver input torque from the measurement value of the EPS torque sensor by acquiring physical parameters such as the steering wheel's moment of inertia, angular displacement, and torsion bar stiffness, thereby achieving high-precision extraction of the driver input torque and ensuring the accuracy of hands-off / no-hands-off judgment in the event of a sensor failure, greatly improving the performance and safety of the EPS system.
[0144] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the driver's hands-off detection method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.
[0145] This application also provides a driver's hands-off detection device, please refer to Figure 4 , the driver's hands-off detection device comprises:
[0146] A parameter acquisition module 10 is used to acquire a torque detection value and a capacitance parameter of a steering wheel;
[0147] The torque estimation module 20 is used to estimate the real directional torque input by the driver according to the torque detection value to obtain a reference torque;
[0148] The hands-free driving judgment module 30 is used to obtain a driving state according to the capacitance parameter and the reference torque, wherein the driving state includes normal driving and hands-free driving.
[0149] The driver's hands-off detection device provided by the present application adopts the driver's hands-off detection method in the above embodiment, which can solve the technical problem of the prior art that the detection of whether the driver has taken his hands off the steering wheel while driving is not accurate enough. Compared with the prior art, the beneficial effects of the driver's hands-off detection device provided by the present application are the same as the beneficial effects of the driver's hands-off detection method provided by the above embodiment, and other technical features of the driver's hands-off detection device are the same as the features disclosed in the above embodiment method, which will not be repeated here.
[0150] The present application provides a driver hands-off detection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the driver hands-off detection method in the above-mentioned embodiment one.
[0151] Reference below Figure 5 , which shows a schematic diagram of the structure of a driver's hands-off detection device suitable for implementing the embodiment of the present application. The driver's hands-off detection device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The illustrated driver's hands-off detection device is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0152] like Figure 5As shown, the driver's hands-off detection device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the driver's hands-off detection device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the driver's hands-off detection device to communicate wirelessly or wired with other devices to exchange data. Although the driver's hands-off detection device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided alternatively.
[0153] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0154] The driver's hands-off detection device provided by the present application adopts the driver's hands-off detection method in the above embodiment, which can solve the technical problem of the prior art that the detection of whether the driver has taken his hands off the steering wheel while driving is not accurate enough. Compared with the prior art, the beneficial effects of the driver's hands-off detection device provided by the present application are the same as the beneficial effects of the driver's hands-off detection method provided by the above embodiment, and the other technical features of the driver's hands-off detection device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0155] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0156] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0157] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the driver's hands-off detection method in the above-mentioned embodiment.
[0158] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0159] The computer-readable storage medium may be included in the hands-off driver detection device; or may exist independently without being assembled into the hands-off driver detection device.
[0160] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the driver's hands-off detection device, the driver's hands-off detection device: obtains the torque detection value and capacitance parameter of the steering wheel; estimates the actual directional torque input by the driver based on the torque detection value to obtain a reference torque; and obtains a driving state based on the capacitance parameter and the reference torque, wherein the driving state includes normal driving and hands-off driving.
[0161] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0162] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0163] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0164] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned driver's hands-off detection method, and can solve the technical problem of the prior art that the detection of whether the driver has taken his hands off the steering wheel while driving is not accurate enough. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the driver's hands-off detection method provided in the above-mentioned embodiment, and will not be repeated here.
[0165] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned driver's hands-off detection method when executed by a processor.
[0166] The computer program product provided by the present application can solve the technical problem that the prior art is not accurate enough in detecting whether the driver has taken his hands off the steering wheel while driving. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the driver's hands-off detection method provided by the above embodiment, and will not be elaborated here.
[0167] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A method for detecting a driver's hands-off behavior, characterized in that: The driver's hands-off detection method comprises: Get the torque detection value and capacitance parameters of the steering wheel; estimating the actual directional torque input by the driver according to the torque detection value to obtain a reference torque; A driving state is obtained according to the capacitance parameter and the reference torque, where the driving state includes normal driving and hands-free driving.
2. The method for detecting a driver's hands-off behavior according to claim 1, wherein: The method of estimating the real directional torque input by the driver according to the torque detection value to obtain a reference torque includes: Obtain the moment of inertia, angular displacement and torsion bar stiffness of the steering wheel; Obtaining observation parameters according to the moment of inertia, the angular displacement and the torsion bar stiffness; A reference torque is obtained according to the observed parameter and the torque detection value.
3. The method for detecting a driver's hands-off behavior according to claim 2, wherein: The obtaining of observation parameters according to the moment of inertia, the angular displacement and the torsion bar stiffness includes: Taking the moment of inertia, the angular displacement and the torsion bar stiffness as initial parameters, and obtaining a reference matrix according to the initial parameters; Obtaining an expanded matrix according to the reference matrix and the initial parameters; The initial parameters, the reference matrix and the expanded matrix are used as observation parameters.
4. The method for detecting a driver's hands-off behavior according to claim 2, wherein: The obtaining of the reference torque according to the observation parameter and the torque detection value comprises: Calculating the torque according to the observed parameters and the torque detection value to obtain an estimated torque; Get sensor compensation torque; The estimated torque is corrected according to the sensor hardware error compensation torque to obtain a reference torque.
5. The method for detecting a driver's hands-off behavior according to claim 4, wherein: The step of calculating the torque according to the observation parameter and the torque detection value to obtain the estimated torque includes: Obtaining preset restriction conditions, and obtaining an observation gain matrix according to the observation parameters; Obtaining a torque estimation function according to the observation parameters, the torque detection value and the observation gain matrix; When the preset restriction condition is met, the estimated torque is obtained based on the torque estimation function.
6. The method for detecting a driver's hands-off behavior according to claim 1, wherein: The obtaining of a driving state according to the capacitance parameter and the reference torque, wherein the driving state includes normal driving and hands-free driving, comprises: obtaining the driver's hand contact state according to the capacitance parameter; A driving state is obtained according to the contact state and the reference torque, and the driving state includes a hands-free driving state and a normal driving state.
7. The method for detecting a driver's hands-off behavior according to claim 6, wherein: The obtaining the driving state according to the contact state and the reference torque comprises: When the driver's hand contact state is a non-contact state, a hands-free driving state is used as the driving state; When the driver's hand contact state is in the contact state, a reference time when the reference torque is less than a torque threshold is obtained, and when the reference time is greater than or equal to the time threshold, a hands-free driving state is used as the driving state.
8. A driver's hands-off detection device, characterized in that: The driver's hands-off detection device comprises: A parameter acquisition module, used to obtain the torque detection value and capacitance parameters of the steering wheel; A torque estimation module, used for estimating the real directional torque input by the driver according to the torque detection value to obtain a reference torque; The hands-free driving judgment module is used to obtain a driving state according to the capacitance parameter and the reference torque, wherein the driving state includes normal driving and hands-free driving.
9. A driver's hands-off detection device, characterized in that: The device comprises: a memory, a processor, and a driver's hands-off detection program stored in the memory and executable on the processor, wherein the driver's hands-off detection program is configured to implement the driver's hands-off detection method according to any one of claims 1 to 7.
10. A storage medium, characterized in that: The storage medium stores a driver's hands-off detection program, which, when executed by the processor, implements the driver's hands-off detection method according to any one of claims 1 to 7.
Citation Information
Cited By
Steering wheel out-of-hand detection device, vehicle, out-of-hand detection method and storage medium
CN120702643A
