Hand-off detection method and apparatus

Abstract

The application relates to a hand-off detection method and device. The method comprises the following steps: acquiring a hand force torque value corresponding to a steering wheel and a response torque value; acquiring a zero offset compensation value, which is used for offsetting the influence of zero point bias of a torque sensor on a resultant torque of the hand force torque value and the response torque value; determining a target resultant torque according to the hand force torque value, the response torque value and the zero offset compensation value; judging whether the target resultant torque is greater than a first threshold value; and if not, determining that a driver has taken off the steering wheel. The scheme provided by the application can overcome the difference between different vehicles, improve the accuracy of hand-off detection, and reduce the false positive rate and the false negative rate.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a method and device for detecting hands-free driving. Background Technology

[0002] When advanced driver assistance systems (ADAS) are activated, the driver needs to keep their hands on the steering wheel, pay attention to road conditions, and be ready to take over the steering at any time. If the system detects that the driver is not holding the steering wheel, it should alert the driver or even disengage the ADAS. From a safety perspective, it's undesirable for the hands-off detection algorithm to fail to recognize that the driver is not holding the steering wheel. From a driver comfort perspective, it's undesirable for the system to falsely report that the driver is not holding the steering wheel when they are actually holding it, thus continuously triggering unnecessary warnings. Therefore, the accuracy of the method for detecting whether the driver is holding the steering wheel is crucial, and the false alarm rate (hands on the steering wheel but prompting "not holding the steering wheel") and false negative rate (not holding the steering wheel but not prompting "not holding the steering wheel") of hands-off detection are two important indicators for assessing its accuracy. Summary of the Invention

[0003] To address or partially address the problems existing in related technologies, this application provides a hands-free detection method and apparatus that can overcome the differences in vehicle conditions, improve the accuracy of hands-free detection, and reduce its false alarm rate and false alarm rate.

[0004] The first aspect of this application provides a method for detecting hand release, comprising:

[0005] Obtain the corresponding hand torque value and response torque value of the steering wheel;

[0006] Obtain a zero-bias compensation value, which is used to offset the influence of the zero-point bias of the torque sensor on the resultant torque of the hand force torque value and the response torque value;

[0007] The target resultant torque is determined based on the hand force torque value, the response torque value, and the zero-bias compensation value;

[0008] Determine whether the target resultant torque is greater than a first threshold.

[0009] If not, then it is determined that the driver has taken their hands off the steering wheel.

[0010] In some implementations, obtaining the zero-bias compensation value based on the hand force torque value includes:

[0011] Determine the zero-bias compensation value based on the stated hand force torque value;

[0012] or,

[0013] Read the zero bias compensation value.

[0014] In some implementations, determining the zero-bias compensation value based on the hand force torque value includes:

[0015] The target hand force torque value is obtained by filtering the hand force torque value.

[0016] Determine the offset of the waveform corresponding to the target hand force torque value for several consecutive time periods;

[0017] Determine the average offset corresponding to the plurality of offsets;

[0018] The zero-bias compensation value is determined based on the average offset.

[0019] In some implementations, determining the target resultant torque based on the hand force torque value, the response torque value, and the zero-bias compensation value includes:

[0020] Calculate the first resultant torque corresponding to the hand force torque value, the response torque value, and the zero offset compensation value;

[0021] Calculate the target resultant moment corresponding to the first resultant moment and the lateral force compensation value.

[0022] In some implementations, the calculation of the hand force torque value, and the first resultant torque corresponding to the response torque value and the zero-bias compensation value, includes:

[0023] The first parameter is obtained by subtracting the zero bias compensation value from the target hand force torque value, and the target hand force torque value is obtained after filtering the hand force torque value.

[0024] The second parameter is obtained by multiplying the target response torque value by a preset coefficient. The target response torque value is obtained after filtering the response torque value.

[0025] The absolute value of the difference between the first parameter and the second parameter is determined as the first resultant torque.

[0026] A second aspect of this application provides a hand-removal detection device, comprising:

[0027] The first acquisition module is used to acquire the hand force torque value and response torque value corresponding to the steering wheel;

[0028] The second acquisition module is used to acquire the zero-bias compensation value, which is used to offset the influence of the zero-point bias of the torque sensor on the resultant torque of the hand force torque value and the response torque value.

[0029] The first determining module is used to determine the target resultant torque based on the hand force torque value, the response torque value, and the zero bias compensation value;

[0030] The judgment module is used to determine whether the target resultant torque is greater than a first threshold.

[0031] The second determining module is used to determine when the target resultant torque is not greater than the first threshold, that the driver has taken off the steering wheel.

[0032] In some implementations, the second acquisition module includes:

[0033] The determining unit is used to determine the zero-bias compensation value based on the hand force torque value;

[0034] or,

[0035] The read unit is used to read the zero bias compensation value.

[0036] In some implementations, the determining unit includes:

[0037] A filtering subunit is used to filter the hand force torque value to obtain the target hand force torque value;

[0038] The first determining subunit is used to determine the offset of the waveform corresponding to the target hand force torque value for several consecutive time periods;

[0039] The second determining subunit is used to determine the average offset corresponding to the plurality of offsets;

[0040] The third determining subunit is used to determine the zero-bias compensation value based on the average offset.

[0041] In some implementations, the first determining module includes:

[0042] The first calculation unit is used to calculate the hand force torque value, the response torque value and the first resultant torque corresponding to the zero bias compensation value;

[0043] The second calculation unit is used to calculate the target resultant moment corresponding to the first resultant moment and the lateral force compensation value.

[0044] In some implementations, the first computing unit includes:

[0045] The first calculation subunit is used to subtract the zero bias compensation value from the target hand force torque value to obtain the first parameter, wherein the target hand force torque value is obtained after filtering the hand force torque value.

[0046] The second calculation subunit is used to multiply the target response torque value by a preset coefficient to obtain the second parameter, wherein the target response torque value is obtained after filtering the response torque value.

[0047] The third calculation subunit is used to determine the absolute value of the difference between the first parameter and the second parameter as the first resultant torque.

[0048] A third aspect of this application provides an electronic device, comprising:

[0049] Processor; and

[0050] A memory that stores executable code, which, when executed by the processor, causes the processor to perform the method described above.

[0051] A fourth aspect of this application provides a computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0052] This invention, after acquiring the hand torque value and response torque value corresponding to the steering wheel, can obtain a zero-bias compensation value. Based on the hand torque value, response torque value, and zero-bias compensation value, a target resultant torque is determined. The driver's hand-to-hand torque is then used to determine whether the driver has taken their hands off the steering wheel. The zero-bias compensation value is used to offset the influence of the torque sensor on the resultant torque of the hand torque value and response torque value. In other words, this invention can compensate for the resultant torque based on the zero-point offset of different vehicles. Then, based on the compensated resultant torque (target resultant torque), it determines whether the driver has taken their hands off the steering wheel. This uses the same threshold for different vehicles, avoiding situations where some vehicles have high accuracy while others have low accuracy. It overcomes the differences between vehicles in different conditions, improves the accuracy of hand-to-hand detection, and reduces false alarm and false negative rates.

[0053] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0054] The above and other objects, features and advantages of this application will become more apparent from the description of exemplary embodiments of this application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of this application.

[0055] Figure 1 It is a waveform diagram of the hand force torque value and response torque value in the hands-free state;

[0056] Figure 2 This is a waveform diagram of the hand force torque values ​​of vehicles A and B when the hands are off;

[0057] Figure 3 This is a schematic flowchart illustrating the hand-removal detection method in an embodiment of this application;

[0058] Figure 4 This is another schematic flowchart of the hand-removal detection method shown in the embodiments of this application;

[0059] Figure 5 This is a schematic diagram of the waveform corresponding to the target hand force torque value shown in the embodiments of this application;

[0060] Figure 6 This is a schematic diagram of the structure of the hand-removal detection device shown in the embodiments of this application;

[0061] Figure 7 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application. Detailed Implementation

[0062] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0063] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0064] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0065] For ease of understanding, the vocabulary used in the embodiments of this application will be introduced below.

[0066] Torque: A special type of torque that causes an object to rotate.

[0067] Electric Power Steering (EPS): A power steering system that relies directly on an electric motor to provide auxiliary torque. It mainly consists of a torque sensor, a vehicle speed sensor, an electric motor, a reduction gear, and an electronic control unit (ECU).

[0068] Hand torque value: The torque value applied to the steering wheel. When the driver places their hands on the steering wheel of the car, the driver's hands will apply a certain torque to the steering wheel. This torque can be collected and expressed in the form of torque value.

[0069] Response torque value: The torque generated by the vehicle's electric power steering system in response to the torque on the steering wheel, which is used to assist steering.

[0070] Offset: The deviation of the waveform of the hand force torque value from the corresponding sine curve. Specifically, the sine curve can be represented as... In the formula, k represents the offset. In related technologies, hands-off detection devices use the resultant torque corresponding to the torque of a torque sensor and the response torque to determine whether the driver's hands are on the steering wheel. When the resultant torque is greater than a threshold, it is considered that the driver has not taken off the steering wheel; when the resultant torque is less than the threshold, it is considered that the driver has taken off the steering wheel.

[0071] However, the torque sensor in an electric power steering system may have varying fixed zero-point offsets, and these offsets can drift due to different environmental factors, usage duration, and driving habits. In other words, different vehicles will have different zero-point offsets. If the above solution uses the same threshold to judge different vehicles, some vehicles will perform better and have higher accuracy, while others will perform worse and have lower accuracy.

[0072] like Figure 1 These are the hand torque values ​​(TBT) and EPS response torque values ​​(T) collected by the hands-free detection device when the driver is in a hands-free state. r The following relationship exists between the two: T r ×a1 + TBT = 0. When a user grips the steering wheel, the change in the hand torque value TBT becomes irregular, disrupting the balance between the two. Therefore, when the response torque T... r When ×a1+TBT≠0, it can be considered that the driver is holding the steering wheel. Based on the above principle, technicians set a threshold T1 based on experience. When the hand torque value TBT is close to the response torque T... r The corresponding resultant torque T c =T r If ×a2+TBT is greater than T1, then the driver is considered to be holding the steering wheel. a1 and a2 are calibration coefficients.

[0073] Figure 2These are waveforms of the torque values ​​(TBT) corresponding to the hands-on torque when vehicles A and B are no longer under the steering wheel. Vehicle A's torque value has a zero-point offset of approximately +0.07 Nm, while vehicle B's torque value has a zero-point offset of -0.15 Nm. The significant difference in zero-point offset between the two vehicles means that the calculated resultant torque will also differ considerably under the same conditions (e.g., both vehicles are no longer under the steering wheel and have the same speed). Using the same threshold T1 to distinguish between the two vehicles can easily lead to inconsistent judgments. For example, if T1 is set too high, it might be judged that vehicle A is holding the steering wheel while vehicle B is no longer under the steering wheel, which is clearly inaccurate.

[0074] To address the aforementioned issues, this application introduces a zero-bias compensation value to compensate for the resultant torque and overcome the influence of zero-point offset. Specifically, this application provides a hands-off detection method that can overcome the differences between vehicles in different conditions, improve the accuracy of hands-off detection, and reduce its false alarm rate and false negative rate.

[0075] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0076] Please see Figure 3 , Figure 3 This is a flowchart illustrating a hands-free detection method disclosed in an embodiment of the present invention. This method is applicable to scenarios where the driver has a bad driving habit of taking their hands off the wheel while the car is on the road. The method is executed by a hands-free detection device, which can be implemented by software and / or hardware and integrated into the vehicle's interior. Figure 3 As shown, the method for detecting hand loss may include the following steps:

[0077] 301. The hands-off detection device acquires the corresponding hand force torque value and response torque value of the steering wheel;

[0078] After the vehicle is started, the torque sensor collects the torque value of the hand force applied by the driver on the steering wheel, the EPS calculates the response torque value corresponding to the hand force torque value, the hands-off detection device obtains the hand force torque value from the torque sensor, and obtains the response torque value from the EPS.

[0079] It should be understood that in this embodiment, the torque sensor can be an internal torque sensor of the EPS or an external torque sensor of the EPS; this embodiment does not limit the specific type. The release detection device can obtain the response torque value uploaded by the EPS through the Controller Area Network (CAN), or it can obtain the response torque value through other means; this embodiment does not limit the specific type.

[0080] 302. The zero-bias compensation value is obtained by the hand-off detection device;

[0081] After the release detection device acquires the hand force torque value and the response torque value, it acquires a zero-bias compensation value. This zero-bias compensation value is used to compensate for the resultant torque corresponding to the hand force torque value and the response torque value, so as to counteract the influence of the zero-point bias of the torque sensor on the resultant torque of the hand force torque value and the response torque value.

[0082] In some embodiments, the zero-bias compensation value is related to the currently acquired hand force torque value. Specifically, after the release detection device acquires the currently acquired hand force torque value and response torque value from the torque sensor, it determines the zero-bias compensation value based on the hand force torque value.

[0083] In some embodiments, the zero-bias compensation value is related to historical hand force torque values. Specifically, before implementing this scheme, the release detection device first calculates the zero-bias compensation value based on historical hand force torque values ​​and stores the zero-bias compensation value in a memory. After obtaining the hand force torque value and response torque value currently collected by the torque sensor, the release detection device reads the zero-bias compensation value from the memory.

[0084] The hand-off detection device can also obtain the zero bias compensation value through other means, which are not limited in this embodiment.

[0085] 303. The release detection device determines the target resultant torque based on the hand force torque value, the response torque value, and the zero-bias compensation value;

[0086] 304. The release detection device determines whether the target resultant torque is greater than the first threshold. If not, proceed to step 305.

[0087] After the release detection device determines the target resultant torque, it determines whether the target resultant torque is greater than the first threshold. If not, step 305 is executed.

[0088] It should be understood that the first threshold is a calibrated value, set by technicians based on experience. This experience is based on specific experimental results and can be any value.

[0089] 305. The hands-off detection device determines when the driver has taken their hands off the steering wheel.

[0090] When the hands-off detection device determines that the target resultant torque is greater than a first threshold, it confirms that the driver has taken their hands off the steering wheel. Specifically, after confirming that the driver has taken their hands off the steering wheel, the driver can be reminded and / or the driver assistance function can be discontinued to ensure driving safety. The methods for reminding the driver may include one or more of the following: broadcasting "Please keep your hands on the steering wheel" via loudspeaker, flashing warning lights inside the vehicle, and displaying a warning icon on the instrument panel.

[0091] This invention, after acquiring the hand torque value and response torque value corresponding to the steering wheel, can obtain a zero-bias compensation value. Based on the hand torque value, response torque value, and zero-bias compensation value, a target resultant torque is determined. The driver's hand-to-hand torque is then used to determine whether the driver has taken their hands off the steering wheel. The zero-bias compensation value is used to offset the influence of the torque sensor on the resultant torque of the hand torque value and response torque value. In other words, this invention can compensate for the resultant torque based on the zero-point offset of different vehicles. Then, based on the compensated resultant torque (target resultant torque), it determines whether the driver has taken their hands off the steering wheel. This uses the same threshold for different vehicles, avoiding situations where some vehicles have high accuracy while others have low accuracy. It overcomes the differences between vehicles in different conditions, improves the accuracy of hand-to-hand detection, and reduces false alarm and false negative rates.

[0092] To understand the hand-drop detection method in the embodiments of the present invention, a detailed description of the hand-drop detection method in the embodiments of the present invention is provided below. Please refer to [link / reference]. Figure 4 Another embodiment of the slip-out detection method of the present invention includes:

[0093] 401. The hands-off detection device acquires the corresponding hand force torque value and response torque value of the steering wheel;

[0094] After the vehicle is started, the torque sensor collects the torque value of the hand force applied by the driver on the steering wheel, the EPS calculates the response torque value corresponding to the hand force torque value, the hands-off detection device obtains the hand force torque value from the torque sensor, and obtains the response torque value corresponding to the hand force torque value from the EPS.

[0095] It should be understood that in this embodiment, the torque sensor can be an internal torque sensor of the EPS or an external torque sensor of the EPS; this embodiment does not limit the specific type. The release detection device can obtain the response torque value uploaded by the EPS through the Controller Area Network (CAN), or it can obtain the response torque value through other means; this embodiment does not limit the specific type.

[0096] It should also be understood that before acquiring the hand torque value and response torque value, the hands-free detection device can determine whether the vehicle's driver assistance function is activated. When it is determined that the driver assistance function is activated, the hands-free detection process is initiated, and the steps of acquiring the hand torque value and response torque value corresponding to the steering wheel are executed.

[0097] 402. The release detection device determines the zero-bias compensation value based on the hand force torque value;

[0098] After the release detection device acquires the current hand force torque value collected by the torque sensor, it can determine the zero-bias compensation value corresponding to that hand force torque value.

[0099] Specifically, the process by which the release detection device determines the zero-bias compensation value corresponding to the hand force torque value may include the following steps:

[0100] S1. Filter the hand force torque value to obtain the target hand force torque value;

[0101] Specifically, the release detection device performs a first-order filter on the hand force torque value to obtain the target hand force torque value. First-order filtering generally refers to a first-order low-pass filter, and the characteristics of a first-order low-pass filter are typically represented by a first-order linear differential equation. Besides first-order filtering, other filtering methods with similar effects, such as Kalman filtering, can also be used; this embodiment does not limit the specific method used.

[0102] This embodiment determines the zero bias compensation value based on the filtered hand force torque value (target hand force torque value), which can avoid periodic interference and improve the accuracy of zero bias identification.

[0103] S2. Determine the offset of the waveform corresponding to the target hand force torque value for several consecutive time periods;

[0104] It should be understood that when the driver is not holding the steering wheel, the steering wheel angle is basically 0, and the hand torque, EPS response torque, lateral torque, etc. should be in a dynamic equilibrium state. The waveform corresponding to the hand torque value is a sinusoidal waveform with a certain offset. The waveform corresponding to the target hand torque value obtained after filtering the hand torque value is a sinusoidal waveform with a certain offset.

[0105] The release detection device divides the waveform corresponding to the target hand force torque value into several sine waves and calculates the offset corresponding to each sine wave. The time periods corresponding to the several sine waves are continuous, and the time length corresponding to each time period is preset and can be any value.

[0106] For example, the duration of each time slot is set to 20 seconds, such as... Figure 5 As shown, the release detection device divides the waveform corresponding to the target hand force torque value acquired within 80 seconds into four sine waveforms with a corresponding time length of 20 seconds. The release detection device determines the offsets of these four sine waveforms as 0.065Nm, 0.075Nm, 0.07Nm, and 0.07Nm, respectively.

[0107] S3. Determine the average offset corresponding to several offsets.

[0108] Calculate the average offset corresponding to the offset of the waveform corresponding to the target hand force value for several consecutive time periods. In some embodiments, the average offset corresponding to several offsets is the average value of several offsets.

[0109] For example, in the above scenario, the calculated offsets for the four consecutive time periods are 0.065Nm, 0.075Nm, 0.07Nm, and 0.07Nm, respectively. The average offset corresponding to these four offsets is calculated as: k = (0.75Nm + 0.065Nm + 0.07Nm + 0.07Nm) / 4 = 0.07Nm.

[0110] S4. Determine the zero-bias compensation value based on the average offset.

[0111] In some embodiments, after determining the average offset, the release detection device sets the average offset as the zero-offset compensation value. This embodiment determines the zero-offset compensation value by using the average offset of the waveform over a certain time period, which can improve the accuracy of identification.

[0112] In some embodiments, before determining the zero-bias compensation value corresponding to the hand force torque value, the release detection device may perform at least one of the following:

[0113] (1) Receive zero bias identification command;

[0114] When the user determines that the current scenario requires zero-bias recognition, they trigger a zero-bias recognition command, and the off-hand detection device receives the zero-bias recognition command triggered by the user.

[0115] Specifically, scenarios requiring zero-bias recognition can include vehicles traveling on long, straight, and flat roads. In such cases, users can trigger zero-bias recognition commands via one or more buttons, including buttons on the touchscreen and / or physical buttons on the vehicle's central control unit. Users can also trigger zero-bias recognition commands via one or more headlight controllers, including interior and / or exterior lights. Users can also trigger recognition commands via voice instructions, such as "Start zero-bias recognition." Users can also trigger zero-bias recognition commands via specific facial expressions, postures, or gestures. Correspondingly, the hands-free detection device can receive zero-bias recognition commands via sensors such as the touchscreen, central control buttons, headlight controllers, microphones, and cameras.

[0116] Zero-bias identification can also be performed in hub inspection. Inspectors can use a diagnostic instrument to send a diagnostic instruction to trigger a zero-bias identification command, and the off-hand inspection device receives the zero-bias identification command triggered by the diagnostic instrument.

[0117] Users can also trigger zero-bias recognition commands in other scenarios, which are not limited in this embodiment. In addition to being triggered by users, zero-bias recognition commands can also be received from other devices, which are not limited in this embodiment.

[0118] In this embodiment, the user can trigger the zero-bias recognition command in an environment with less interference, such as a long, straight, flat test road or a rotating hub, to start the process of the hands-off detection device identifying the zero-bias compensation value (determining the zero-bias compensation value corresponding to the hand force torque value), thereby improving the accuracy of zero-bias recognition.

[0119] (2) Determine whether the vehicle meets the preset conditions. If not, proceed with the step of determining the zero offset compensation value based on the hand torque value. The preset conditions include at least one of the following: the hand torque value fluctuates significantly, the vehicle changes lanes, or the vehicle brakes.

[0120] In this embodiment, the hands-off detection device will only identify the zero-bias compensation value when the hand torque value fluctuates little, the vehicle does not change lanes, and the vehicle does not brake. This avoids interference from special circumstances with the zero-bias compensation value and improves the accuracy of zero-bias identification.

[0121] 403. The release detection device calculates the hand force torque value, the response torque value, and the first resultant torque corresponding to the zero bias compensation value;

[0122] In some embodiments, the release detection device can calculate the hand force torque value, the response torque value, and the first resultant torque corresponding to the zero bias compensation value in the following manner: subtract the zero bias compensation value from the target hand force torque value to obtain a first parameter, multiply the target response torque value by a preset coefficient to obtain a second parameter, and then determine the absolute value of the difference between the first parameter and the second parameter as the first resultant torque. The target hand force torque value is obtained after filtering the acquired hand force torque value, and the target response torque value is obtained after filtering the acquired response torque value. The filtering process is a first-order filter, a Kalman filter, or other filters, which are not limited in this embodiment.

[0123] In some embodiments, after the release detection device acquires the hand force torque value and the response torque value, it can filter the hand force torque value and the response torque value to obtain the target hand force torque value TBT and the target response torque value T. r Then, based on the target hand force torque value TBT, the target response torque value T r The first resultant torque is calculated using the zero-bias compensation value x. Specifically, the first resultant torque T can be calculated using the following formula: offset =|TBT-x)-T r ·a|, where a is a preset coefficient. The release detection device can also calculate the first resultant torque through a modified formula of the above formula, but this embodiment does not limit the specific calculation.

[0124] 404. The release detection device calculates the target resultant moment corresponding to the first resultant moment and the lateral force compensation value;

[0125] After the release detection device determines the first resultant torque, it adds the lateral force compensation value to the first resultant torque to obtain the target resultant torque, that is, it performs lateral force compensation on the first resultant torque to obtain the target resultant torque.

[0126] It should be understood that when a vehicle is in a curve, the lateral force from the road surface will offset part of the EPS power assist motor torque through the steering mechanism. Therefore, a lateral force compensation value is added in this embodiment. To achieve universality, that is, regardless of whether the vehicle is on a straight road or a curve, this embodiment assumes that the vehicle needs to perform lateral force compensation on the first resultant torque. However, it is understood that the lateral force compensation value should be zero on a straight road.

[0127] Specifically, the magnitude of the lateral force compensation value is related to several factors, the two most important of which are the curvature of the vehicle's driving lane and the vehicle speed. A graph showing the relationship between the lateral force compensation value and the curvature and speed can be obtained through calibration. Therefore, before calculating the target resultant torque, the hands-off detection device can obtain the curvature and speed of the current vehicle's driving lane, and then use this curvature and speed to query the graph to obtain the corresponding lateral force compensation value.

[0128] In addition to considering the influence of zero-point offset on the torque value and performing zero-offset compensation, this embodiment also considers the influence of lateral force on the torque value in the curve and performs lateral force compensation, making the calculated target resultant torque more accurate and improving the accuracy of release detection.

[0129] 405. The release detection device determines whether the target resultant torque is greater than the first threshold. If not, proceed to step 406; if yes, proceed to step 407.

[0130] It should be understood that the first threshold is a calibrated value, set by technicians based on experience. This experience is based on specific experimental results and can be any value.

[0131] In some embodiments, since the road quality varies across different road grades, the first threshold can be appropriately lowered for highways and urban expressways with better road quality, while the first threshold can be appropriately increased for other roads such as national highways and main roads with relatively poorer road quality. This not only improves the adaptability of the algorithm, but also improves the accuracy of off-hand detection.

[0132] 406. The hands-off detection device determines when the driver has taken their hands off the steering wheel;

[0133] When the hands-off detection device determines that the target resultant torque is greater than a first threshold, it confirms that the driver has taken their hands off the steering wheel. Specifically, after confirming that the driver has taken their hands off the steering wheel, the driver can be reminded and / or the driver assistance function can be discontinued to ensure driving safety. The methods for reminding the driver may include one or more of the following: broadcasting "Please keep your hands on the steering wheel" via loudspeaker, flashing warning lights inside the vehicle, and displaying a warning icon on the instrument panel.

[0134] 407. The hand-removal detection device performs other procedures.

[0135] When the hands-off detection device determines that the target resultant torque is not greater than the first threshold, the hands-off detection device executes other processes, such as determining that the driver has not taken his hands off the steering wheel, and judging whether the hand torque value meets other conditions, etc., the specifics are not limited here.

[0136] In some embodiments, after the release detection device completes step 402, that is, after the release detection device determines the zero bias compensation value, the zero bias compensation value can be stored. The zero bias compensation value can be used by the release detection device to compensate for the hand force torque value in the next release detection.

[0137] In some embodiments, the release detection device may skip step 402 and instead perform the following steps: reading the zero-bias compensation value. That is, in addition to determining the zero-bias compensation value based on the current hand force torque value, the release detection device may also read a pre-stored zero-bias compensation value from the memory, wherein the zero-bias compensation value may be the zero-bias compensation value calculated in the previous release detection.

[0138] This embodiment can store the zero-bias compensation value determined based on the target hand force torque value. The next time the hand-off detection device is tested, it can directly call the zero-bias compensation value without recalculation, which improves the detection speed and avoids the situation where the zero-bias compensation cannot be calculated due to the driving environment, thus preventing detection.

[0139] This invention, after acquiring the hand torque value and response torque value corresponding to the steering wheel, can determine the target resultant torque based on the hand torque value, response torque value, and zero-bias compensation value. It then uses this target resultant torque to determine whether the driver has taken their hands off the steering wheel. The zero-bias compensation value is used to offset the influence of the torque sensor on the resultant torque of the hand torque value and response torque value. In other words, this invention can compensate for the resultant torque based on the zero-point offset of different vehicles, and then determine whether the driver has taken their hands off the steering wheel based on the compensated resultant torque (target resultant torque). This uses the same threshold for different vehicles, avoiding situations where some vehicles have high accuracy while others have low accuracy. It overcomes the differences between vehicles in different conditions, improves the accuracy of hands-off detection, and reduces its false alarm rate and false negative rate.

[0140] Secondly, this embodiment can determine the zero-bias compensation value based on the real-time hand force torque value, making the identified zero-bias compensation value more accurate and improving the accuracy of the release detection.

[0141] Furthermore, in addition to zero-bias compensation for the hand force torque value, this embodiment also performs lateral force compensation for the hand force torque value during curves, making the calculated resultant torque more accurate and improving the accuracy of the release detection.

[0142] Furthermore, this embodiment performs zero-bias identification on a long, straight, flat test road or in a turning environment, without the vehicle changing lanes or braking, making the identified zero-bias compensation value more accurate and further improving the accuracy of hands-off detection.

[0143] Corresponding to the aforementioned application function implementation method embodiments, this application also provides a hand-removal detection device, an electronic device, and corresponding embodiments.

[0144] Figure 6 This is a schematic diagram of the structure of the hand-removal detection device shown in the embodiments of this application.

[0145] See Figure 6 The hand-release detection device 600 includes:

[0146] The first acquisition module 601 is used to acquire the hand force torque value and response torque value corresponding to the steering wheel;

[0147] The second acquisition module 602 is used to acquire the zero-bias compensation value, which is used to offset the influence of the zero-point bias of the torque sensor on the resultant torque of the manual torque value and the response torque value.

[0148] The first determining module 603 is used to determine the target resultant torque based on the hand force torque value, the response torque value and the zero bias compensation value;

[0149] The judgment module 604 is used to determine whether the target resultant torque is greater than the first threshold.

[0150] The second determining module 605 is used to determine when the driver takes off the steering wheel when the target resultant torque is not greater than the first threshold.

[0151] As an optional approach, the second acquisition module may include:

[0152] A determination unit is used to determine the zero-bias compensation value based on the hand force torque value;

[0153] or,

[0154] The read unit is used to read the zero bias compensation value.

[0155] As an optional approach, determining the unit may include:

[0156] The filtering subunit is used to filter the hand force torque value to obtain the target hand force torque value.

[0157] The first determining subunit is used to determine the offset of the waveform corresponding to the target hand force torque value for several consecutive time periods;

[0158] The second determining subunit is used to determine the average offset corresponding to several offsets;

[0159] The third determining sub-unit is used to determine the zero-bias compensation value based on the average offset.

[0160] As an optional approach, the first determining module may include:

[0161] The first calculation unit is used to calculate the first resultant torque corresponding to the hand force torque value, the response torque value, and the zero bias compensation value.

[0162] The second calculation unit is used to calculate the target resultant moment corresponding to the first resultant moment and the lateral force compensation value.

[0163] As an optional approach, the first computing unit may include:

[0164] The first calculation subunit is used to subtract the zero bias compensation value from the target hand force torque value to obtain the first parameter. The target hand force torque value is obtained after filtering the hand force torque value.

[0165] The second calculation subunit is used to multiply the target response torque value by a preset coefficient to obtain the second parameter. The target response torque value is obtained after filtering the response torque value.

[0166] The third calculation subunit is used to determine the absolute value of the difference between the first parameter and the second parameter as the first resultant torque.

[0167] As an alternative, the hand-removal detection device may also include:

[0168] The storage module is used to store the zero-bias compensation value.

[0169] As an alternative, the hand-removal detection device may also include:

[0170] The receiving module is used to receive zero-bias identification commands;

[0171] The condition judgment module is used to respond to the zero bias recognition command, determine whether the vehicle has preset conditions, and when it is determined that the preset conditions are not met, trigger the determination unit to determine the zero bias compensation value based on the hand force torque value. The preset conditions include at least one of the following: the hand force torque value fluctuates greatly, the vehicle changes lanes, and the vehicle brakes.

[0172] In this embodiment of the invention, after the first acquisition module 601 acquires the hand torque value and response torque value corresponding to the steering wheel, the second acquisition module 603 can acquire the zero-bias compensation value. The first determination module 603 can determine the target resultant torque based on the hand torque value, response torque value, and zero-bias compensation value. The judgment module 604 can determine whether the driver has taken their hands off the steering wheel based on the target resultant torque. The zero-bias compensation value is used to offset the influence of the torque sensor on the resultant torque of the hand torque value and response torque value. In other words, this embodiment of the invention can compensate for the resultant torque based on the zero-point offset of different vehicles, and then determine whether the driver has taken their hands off the steering wheel based on the compensated resultant torque (target resultant torque). This way, different vehicles use the same threshold for judgment, avoiding situations where some vehicles have high accuracy while others have low accuracy. It overcomes the differences between vehicles in different conditions, improves the accuracy of hands-off detection, and reduces its false alarm rate and false negative rate.

[0173] Secondly, this embodiment can determine the zero-bias compensation value based on the real-time hand force torque value, making the identified zero-bias compensation value more accurate and improving the accuracy of the release detection.

[0174] Furthermore, in addition to zero-bias compensation for the hand force torque value, this embodiment also performs lateral force compensation for the hand force torque value during curves, making the calculated resultant torque more accurate and improving the accuracy of the release detection.

[0175] Furthermore, this embodiment performs zero-bias identification on a long, straight, flat test road or in a turning environment, without the vehicle changing lanes or braking, making the identified zero-bias compensation value more accurate and further improving the accuracy of hands-off detection.

[0176] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0177] Figure 7 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application.

[0178] See Figure 7 The electronic device 700 includes a memory 710 and a processor 720.

[0179] The processor 720 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0180] Memory 710 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by the processor 720 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). System memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 710 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, memory 710 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital multifunction optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, a high-density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0181] The memory 710 stores executable code, which, when processed by the processor 720, can cause the processor 720 to execute part or all of the methods described above.

[0182] Furthermore, the method according to this application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the method described above.

[0183] Alternatively, this application may be implemented as a computer-readable storage medium (or a non-transitory machine-readable storage medium or a machine-readable storage medium) storing executable code (or computer program or computer instruction code) thereon, which, when executed by a processor of an electronic device (or server, etc.), causes the processor to perform part or all of the steps of the methods described above according to this application.

[0184] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for detecting hand slippage, characterized in that, include: Obtain the corresponding hand torque value and response torque value of the steering wheel; Obtain a zero-bias compensation value, which is used to offset the influence of the zero-point bias of the torque sensor on the resultant torque of the hand force torque value and the response torque value; The process of obtaining the zero-bias compensation value includes: filtering the hand force torque value to obtain the target hand force torque value; determining the offset of the waveform corresponding to the target hand force torque value for several consecutive time periods; determining the average offset corresponding to the several offsets; and determining the zero-bias compensation value based on the average offset. The target resultant torque is determined based on the hand force torque value, the response torque value, and the zero-bias compensation value; Determine whether the target resultant torque is greater than a first threshold. If not, then it is determined that the driver has taken their hands off the steering wheel.

2. The method for detecting hand loss according to claim 1, characterized in that, The process of obtaining the zero-bias compensation value includes: Determine the zero-bias compensation value based on the stated hand force torque value; or, Read the zero bias compensation value.

3. The method for detecting hand removal according to claim 1 or 2, characterized in that, The step of determining the target resultant torque based on the hand force torque value, the response torque value, and the zero-bias compensation value includes: Calculate the first resultant torque corresponding to the hand force torque value, the response torque value, and the zero offset compensation value; Calculate the target resultant moment corresponding to the first resultant moment and the lateral force compensation value.

4. The method for detecting hand loss according to claim 3, characterized in that, The calculation of the hand force torque value, the first resultant torque corresponding to the response torque value and the zero offset compensation value includes: The first parameter is obtained by subtracting the zero bias compensation value from the target hand force torque value, and the target hand force torque value is obtained after filtering the hand force torque value. The second parameter is obtained by multiplying the target response torque value by a preset coefficient. The target response torque value is obtained after filtering the response torque value. The absolute value of the difference between the first parameter and the second parameter is determined as the first resultant torque.

5. A hand-removal detection device, characterized in that, include: The first acquisition module is used to acquire the hand force torque value and response torque value corresponding to the steering wheel; The second acquisition module is used to acquire the zero-bias compensation value, which is used to offset the influence of the zero-point bias of the torque sensor on the resultant torque of the hand force torque value and the response torque value. The process of obtaining the zero-bias compensation value includes: filtering the hand force torque value to obtain the target hand force torque value; determining the offset of the waveform corresponding to the target hand force torque value for several consecutive time periods; determining the average offset corresponding to the several offsets; and determining the zero-bias compensation value based on the average offset. The first determining module is used to determine the target resultant torque based on the hand force torque value, the response torque value, and the zero bias compensation value; The judgment module is used to determine whether the target resultant torque is greater than a first threshold. The second determining module is used to determine when the target resultant torque is not greater than the first threshold, that the driver has taken off the steering wheel.

6. The hand-removal detection device according to claim 5, characterized in that, The second acquisition module includes: The determining unit is used to determine the zero-bias compensation value based on the hand force torque value; or, The read unit is used to read the zero bias compensation value.

7. The hand-removal detection device according to claim 5 or 6, characterized in that, The first determining module includes: The first calculation unit is used to calculate the hand force torque value, the response torque value and the first resultant torque corresponding to the zero bias compensation value; The second calculation unit is used to calculate the target resultant moment corresponding to the first resultant moment and the lateral force compensation value.

8. The hand-removal detection device according to claim 7, characterized in that, The first computing unit includes: The first calculation subunit is used to subtract the zero bias compensation value from the target hand force torque value to obtain the first parameter, wherein the target hand force torque value is obtained after filtering the hand force torque value. The second calculation subunit is used to multiply the target response torque value by a preset coefficient to obtain the second parameter, wherein the target response torque value is obtained after filtering the response torque value. The third calculation subunit is used to determine the absolute value of the difference between the first parameter and the second parameter as the first resultant torque.

9. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-4.

10. A computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method as described in any one of claims 1-4.

Images