Hand release detection method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a hand release detection method and device, equipment, a storage medium and a program product, and relates to the technical field of automatic driving. The method comprises the steps that when it is detected that a vehicle is in an automatic driving state, steering state information of the vehicle is obtained; wherein the steering state information is at least used for indicating the torque of a steering column; determining a matched torque compensation dimension according to the steering state information, and determining torque compensation information according to target compensation information under the matched torque compensation dimension; correcting the torque of the steering column according to the torque compensation information to obtain corrected torque of the steering column; and determining a hand release detection result according to the corrected torque of the steering column. The method is used for achieving the effect of improving the hand release detection precision under the condition that the vehicle cost is not increased.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, and in particular to a hand-off detection method and device, equipment, a storage medium and a program product. BACKGROUND

[0002] In the technical field of automatic driving, hand-off detection is a core link of driver state monitoring.

[0003] For example, for an L2-level assisted driving system, in the semi-automatic driving state of a vehicle, the driver still needs to maintain the monitoring and supervision ability of the vehicle. At this time, the hand-off detection can be used to determine whether the driver's hands are away from the steering wheel, so as to avoid safety accidents caused by the driver's inattention or misoperation.

[0004] In the related art, a capacitive steering wheel can be equipped in a vehicle to achieve accurate hand-off detection. However, the cost of the capacitive steering wheel is high, which increases the cost of the vehicle. SUMMARY

[0005] The embodiments of the present application provide a hand-off detection method, device, equipment, storage medium and program product, so as to achieve the effect of improving the hand-off detection precision without increasing the cost of the vehicle.

[0006] In a first aspect, the embodiments of the present application provide a hand-off detection method, comprising:

[0007] When it is detected that the vehicle is in an automatic driving state, steering state information of the vehicle is acquired; wherein the steering state information is used at least to indicate a steering column torque;

[0008] According to the steering state information, a matched torque compensation dimension is determined, and torque compensation information is determined according to target compensation information in the matched torque compensation dimension;

[0009] The steering column torque is corrected according to the torque compensation information to obtain a corrected steering column torque;

[0010] According to the corrected steering column torque, a hand-off detection result is determined.

[0011] In a possible implementation, the steering state information is also used to indicate a steering speed and a steering angle; according to the steering state information, the matched torque compensation dimension is determined, comprising:

[0012] If it is determined that the preset torque offset compensation requirement is met according to the steering column torque, the steering speed and the steering angle, it is determined that the matched torque compensation dimension includes a torque offset compensation dimension and a dynamic friction compensation dimension; and / or, if it is determined that the preset damping compensation requirement is met according to the steering column torque, the steering speed and the steering angle, it is determined that the matched torque compensation dimension includes a damping compensation dimension and the dynamic friction compensation dimension.

[0013] In a possible implementation, the matched torque compensation dimension indicates a torque offset compensation dimension; and the target compensation information under the matched torque compensation dimension is determined according to the following steps:

[0014] obtaining column torque offset data;

[0015] performing a difference operation on the steering column torque and the column torque offset data to obtain the target compensation information under the torque offset compensation dimension.

[0016] In a possible implementation, the method further includes:

[0017] performing low-pass filtering and moving average filtering on the target compensation information to obtain new offset data;

[0018] updating the column torque offset data according to the new offset data.

[0019] In a possible implementation, the steering state information is further used to indicate a steering speed; the matched torque compensation dimension indicates a damping compensation dimension; and the target compensation information under the matched torque compensation dimension is determined according to the following steps:

[0020] obtaining historical steering speed and historical steering column torque;

[0021] determining average speed information included in a preset sliding window according to the historical steering speed, and determining average torque information included in the preset sliding window according to the historical steering column torque;

[0022] determining a current damping coefficient according to the average torque information and the average speed information;

[0023] determining the target compensation information under the damping compensation dimension according to the current damping coefficient and the steering speed.

[0024] In a possible implementation, the steering state information is further used to indicate a steering speed; the matched torque compensation dimension indicates a dynamic friction compensation dimension; and the target compensation information under the matched torque compensation dimension is determined according to the following steps:

[0025] acquire preset friction torque amplitude data and transition coefficient information;

[0026] determine target compensation information in the dynamic friction compensation dimension according to the friction torque amplitude data, the transition coefficient information, and the steering speed.

[0027] In a possible implementation, the steering column torque is corrected according to the torque compensation information to obtain a corrected steering column torque, including:

[0028] The steering column torque is subtracted from the torque compensation information to obtain the corrected steering column torque.

[0029] In a possible implementation, the hand-off detection result indicates a hand-off state; the hand-off detection result is determined according to the corrected steering column torque, including:

[0030] acquire a preset torque threshold and a preset time threshold matched with the vehicle;

[0031] If it is determined that the corrected steering column torque is less than the preset torque threshold and the duration is greater than the preset time threshold, it is determined that the hand-off detection result indicates a hand-off state.

[0032] In a second aspect, an embodiment of the present application provides a hand-off detection device, including:

[0033] An acquisition unit is configured to acquire steering state information of the vehicle when it is detected that the vehicle is in an automatic driving state, wherein the steering state information is used at least to indicate a steering column torque.

[0034] A determination unit is configured to determine a matched torque compensation dimension according to the steering state information, and determine torque compensation information according to target compensation information in the matched torque compensation dimension.

[0035] A correction unit is configured to correct the steering column torque according to the torque compensation information to obtain a corrected steering column torque.

[0036] A detection unit is configured to determine a hand-off detection result according to the corrected steering column torque.

[0037] In a possible implementation, the steering state information is also used to indicate a steering speed and a steering angle; at this time, the determination unit is configured to:

[0038] If it is determined that the preset torque offset compensation requirement is met according to the steering column torque, the steering speed and the steering angle, it is determined that the matched torque compensation dimension includes a torque offset compensation dimension and a dynamic friction compensation dimension; and / or, if it is determined that the preset damping compensation requirement is met according to the steering column torque, the steering speed and the steering angle, it is determined that the matched torque compensation dimension includes a damping compensation dimension and the dynamic friction compensation dimension.

[0039] In a possible implementation, the matched torque compensation dimension indicates a torque offset compensation dimension; and the target compensation information under the matched torque compensation dimension is determined according to the following steps:

[0040] obtaining column torque offset data;

[0041] performing a difference operation on the steering column torque and the column torque offset data to obtain the target compensation information under the torque offset compensation dimension.

[0042] In a possible implementation, the device is further configured to:

[0043] performing low-pass filtering and moving average filtering on the target compensation information to obtain new offset data;

[0044] updating the column torque offset data according to the new offset data.

[0045] In a possible implementation, the steering state information is further configured to indicate a steering speed; the matched torque compensation dimension indicates a damping compensation dimension; and the target compensation information under the matched torque compensation dimension is determined according to the following steps:

[0046] obtaining historical steering speed and historical steering column torque;

[0047] determining average speed information included in a preset sliding window according to the historical steering speed, and determining average torque information included in the preset sliding window according to the historical steering column torque;

[0048] determining a current damping coefficient according to the average torque information and the average speed information;

[0049] determining the target compensation information under the damping compensation dimension according to the current damping coefficient and the steering speed.

[0050] In a possible implementation, the steering state information is further configured to indicate a steering speed; the matched torque compensation dimension indicates a dynamic friction compensation dimension; and the target compensation information under the matched torque compensation dimension is determined according to the following steps:

[0051] acquire preset friction torque amplitude data and transition coefficient information;

[0052] determine target compensation information under the dynamic friction compensation dimension according to the friction torque amplitude data, the transition coefficient information and the steering speed.

[0053] In a possible implementation, the correction unit is configured to:

[0054] perform difference operation on the steering column torque and the torque compensation information to obtain the corrected steering column torque.

[0055] In a possible implementation, the hand-off detection result indicates a hand-off state; at this time, the detection unit is configured to:

[0056] acquire a preset torque threshold and a preset time threshold matched with the vehicle;

[0057] if it is determined that the corrected steering column torque is less than the preset torque threshold and the duration is greater than the preset time threshold, it is determined that the hand-off detection result indicates a hand-off state.

[0058] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0059] the memory stores computer execution instructions;

[0060] the processor executes the computer execution instructions stored in the memory, so that the processor executes the first aspect and / or various possible implementations of the first aspect.

[0061] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the first aspect and / or various possible implementations of the first aspect.

[0062] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and the computer program is executed by a processor to implement the first aspect and / or various possible implementations of the first aspect.

[0063] The hands-free detection method, apparatus, device, storage medium, and program product provided in this application can acquire the vehicle's steering state information when the vehicle is detected to be in autonomous driving mode; wherein, the steering state information is used to indicate at least the steering column torque. In this case, hands-free detection can be performed based on the steering state information, eliminating the need to integrate a capacitive sensor in the steering wheel, thus avoiding increased hardware costs. Subsequently, a matching torque compensation dimension can be determined based on the steering state information, and torque compensation information can be determined based on the target compensation information under the matching torque compensation dimension. In this implementation, the matching torque compensation dimension can be dynamically determined based on the steering state information, and the torque compensation information can be determined based on the target compensation information under the matching torque compensation dimension, improving the flexibility and accuracy of the torque compensation information. Next, the steering column torque can be corrected based on the torque compensation information to obtain a corrected steering column torque, and the hands-free detection result can be determined based on the corrected steering column torque. This implementation can correct the steering column torque based on the torque compensation information, thereby reducing friction and damping interference, thus improving the accuracy and reliability of the hands-free detection result, and meeting the hands-free detection requirements of the assisted driving system. Attached Figure Description

[0064] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0065] Figure 1 A schematic flowchart illustrating a method for detecting hand removal provided in an embodiment of this application;

[0066] Figure 2 A flowchart illustrating another method for detecting hand release provided in an embodiment of this application;

[0067] Figure 3 This application provides a schematic diagram of the process for determining target compensation information in the dimension of torque offset compensation, as illustrated in an embodiment of the present application.

[0068] Figure 4 This application provides a schematic diagram of the process for determining target compensation information in the dimension of damping compensation.

[0069] Figure 5 A schematic diagram illustrating the relationship between preset transition coefficient information and dynamic friction torque of the steering column, provided in an embodiment of this application;

[0070] Figure 6 This application provides a schematic diagram of the process for determining target compensation information under the dynamic friction compensation dimension.

[0071] Figure 7A schematic diagram illustrating the implementation process of a hand-removal detection method provided in this application embodiment;

[0072] Figure 8 This is a schematic diagram of the structure of a hand-removal detection device provided in an embodiment of this application;

[0073] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0074] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0075] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0076] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0077] In the field of autonomous driving technology, hands-free detection is a core component of driver status monitoring.

[0078] For example, for Level 2 driver assistance systems, even in a semi-autonomous driving mode, the driver still needs to maintain monitoring and oversight of the vehicle. In this situation, hands-free detection can determine whether the driver's hands have left the steering wheel. When the driver's hands are off the steering wheel, ADAS (Advanced Driver Assistance Systems) can provide audible and visual warnings and exit or terminate the autonomous driving mode, forcing the driver to regain control of the vehicle, thereby preventing accidents caused by driver inattention or misoperation.

[0079] In related technologies, capacitive steering wheels can be installed in vehicles to enable hands-free detection. However, capacitive steering wheels are expensive, which is why they are generally not installed in vehicles.

[0080] Therefore, how to achieve high-precision hand-drop detection at low cost has become an urgent technical problem to be solved.

[0081] Research has shown that when a traditional hydraulic steering system is upgraded to an electro-hydraulic steering system (EHPS) with an electronic control module, the status of the steering column can be monitored through the electronic control module and torque angle sensor, and used for hands-free detection.

[0082] Generally, when directly performing a hands-off detection based on the steering column torque collected by the sensor, there are significant errors in the hands-off detection due to the influence of factors such as static friction, dynamic friction, and damping force.

[0083] The hands-off detection method provided in this application acquires vehicle steering state information using a torque angle sensor and determines target compensation information in at least one torque compensation dimension based on this information, thereby obtaining torque compensation information. Then, the steering column torque can be corrected based on the torque compensation information to reduce interference from factors such as friction and damping, resulting in a corrected steering column torque that accurately represents the torque applied by the driver. Subsequently, hands-off detection is performed based on the corrected steering column torque to obtain the hands-off detection result, thus improving hands-off detection accuracy without increasing vehicle costs.

[0084] The technology presented in this application can serve as an alternative to hands-off detection for capacitive steering wheels, thereby reducing costs. However, it should be understood that the technology presented in this application can also be used in combination with hands-off detection for capacitive steering wheels. In fact, the technology presented in this application is independent of whether a capacitive steering wheel is used, and this application does not impose any limitations on this.

[0085] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0086] Figure 1 This is a flowchart illustrating a method for detecting hand removal provided in an embodiment of this application, as shown below. Figure 1 As shown, the method includes:

[0087] S101. When the vehicle is detected to be in an autonomous driving state, the vehicle's steering status information is obtained; wherein the steering status information is used to indicate at least the steering column torque.

[0088] In one example, the vehicle's steering state information can be obtained from the torque and angle sensors of the vehicle's steering system. Alternatively, the vehicle's steering state information can be obtained from both the torque and angle sensors of the vehicle's steering system. The type of sensor used to collect the vehicle's steering state information is not limited here.

[0089] At this point, the vehicle's steering status information can be determined based on the torque signal and steering angle information collected by the sensors from the steering column.

[0090] In one example, the torque signal from the steering column can be used to determine the steering column torque, and the steering angle information can be used to determine the steering angle, steering speed, and steering acceleration, etc.

[0091] S102. Based on the steering status information, determine the matching torque compensation dimension, and based on the target compensation information under the matching torque compensation dimension, determine the torque compensation information.

[0092] In one example, in a vehicle's steering system, factors such as component assembly, aging, deformation, and maintenance can cause uneven friction in the steering column. At the same time, the steering column torque is also affected by dynamic damping, which means that the steering column torque cannot directly reflect whether the driver is applying torque.

[0093] Based on this, the embodiments of this application can correct the directly obtained steering column torque by matching the torque compensation dimension.

[0094] In one example, the matched torque compensation dimension may include at least one of the torque offset compensation dimension, dynamic friction compensation dimension, and damping compensation dimension.

[0095] Among them, the target compensation information under the torque offset compensation dimension can indicate torque offset compensation information; the target compensation information under the dynamic friction compensation dimension can indicate friction compensation information; and the target compensation information under the damping compensation dimension can indicate damping compensation information.

[0096] S103. Correct the steering column torque based on the torque compensation information to obtain the corrected steering column torque.

[0097] In one example, the modified steering column torque can be used to characterize the torque applied by the driver.

[0098] S104. Determine the hand-off detection result based on the corrected steering column torque.

[0099] In one example, the release detection result can indicate whether the hand is released or not.

[0100] As described above, the embodiments of this application can acquire the vehicle's steering state information upon detecting that the vehicle is in an autonomous driving state; wherein, the steering state information is at least used to indicate the steering column torque. At this time, hands-off detection can be performed based on the steering state information, eliminating the need to integrate a capacitive sensor in the steering wheel, thus avoiding increased hardware costs. Subsequently, a matching torque compensation dimension can be determined based on the steering state information, and torque compensation information can be determined based on the target compensation information under the matching torque compensation dimension. In this implementation, the matching torque compensation dimension can be dynamically determined based on the steering state information, and torque compensation information can be determined based on the target compensation information under the matching torque compensation dimension, improving the flexibility and accuracy of the torque compensation information. Next, the steering column torque can be corrected based on the torque compensation information to obtain a corrected steering column torque, and the hands-off detection result can be determined based on the corrected steering column torque. This implementation can correct the steering column torque based on the torque compensation information, thereby reducing friction and damping interference, thus improving the accuracy and reliability of the hands-off detection result, thereby meeting the hands-off detection requirements of the assisted driving system.

[0101] Figure 2 This is a flowchart illustrating another method for detecting hand removal provided in an embodiment of this application, as shown below. Figure 2 As shown, in this embodiment... Figure 1 Based on the examples, the method for detecting hand slippage is described in detail, and the method includes:

[0102] S201. When the vehicle is detected to be in an autonomous driving state, obtain the vehicle's steering status information; wherein the steering status information is used to indicate at least the steering column torque.

[0103] In one example, this step can be referred to the content described in S101 above, and will not be repeated in detail here.

[0104] In one example, when the steering status information indicates the steering column torque, steering speed, and steering angle, the matching torque compensation dimension can be determined based on the steering status information. In this case, the torque compensation dimension that meets the hands-off detection scenario can be determined through the steering status information, thereby determining the matching torque compensation dimension. See the process described below for details.

[0105] S202. If the preset torque offset compensation requirement is met based on the steering column torque, steering speed, and steering angle, then the matching torque compensation dimension is determined to include the torque offset compensation dimension and the dynamic friction compensation dimension; and / or, if the preset damping compensation requirement is met based on the steering column torque, steering speed, and steering angle, then the matching torque compensation dimension is determined to include the damping compensation dimension and the dynamic friction compensation dimension.

[0106] Optionally, the preset torque offset compensation requirement can be used to indicate the static friction compensation requirement. In this case, the preset torque offset compensation requirement can be: steering speed less than or equal to the speed threshold, steering angle less than or equal to the angle threshold, and steering column torque less than or equal to the torque threshold.

[0107] Optionally, preset damping compensation requirements can be used to indicate dynamic damping compensation requirements. In this case, the preset damping compensation requirements can be: steering acceleration less than or equal to an acceleration threshold, steering angle less than or equal to an angle threshold, and steering column torque less than or equal to a torque threshold. The steering acceleration is determined based on the steering speed.

[0108] The content of the preset torque offset compensation requirements and preset damping compensation requirements is not limited here, and should be based on actual needs.

[0109] At this point, the current vehicle's hands-free detection scenario can be determined based on the preset torque offset compensation requirements and preset damping compensation requirements.

[0110] In one possible implementation, if the steering status information does not meet the preset torque offset compensation requirements and / or does not meet the preset damping compensation requirements, it is determined that the current vehicle does not meet the hands-off detection scenario. In this case, hands-off detection can be terminated, which not only saves resources but also reduces the false judgment rate.

[0111] In the above embodiments, the matching torque compensation dimension can be dynamically selected according to the preset torque offset compensation requirements and / or the preset damping compensation requirements, which improves the diversity and flexibility of the torque compensation dimension, thereby meeting the hand-off detection requirements under different working conditions, expanding the application scenarios of hand-off detection, and thus improving the accuracy of hand-off detection.

[0112] S203. Determine the target compensation information under the matching torque compensation dimension.

[0113] In one example, different target compensation information can be determined under different torque compensation dimensions.

[0114] For example, if the matched torque compensation dimension indicates the torque offset compensation dimension, then the target compensation information under the matched torque compensation dimension can be determined according to the following steps:

[0115] First, obtain the tubing torque offset data.

[0116] Then, the difference between the steering column torque and the column torque offset data is calculated to obtain the target compensation information in the torque offset compensation dimension.

[0117] In one example, the column torque offset data can be obtained by using the offset data calibrated on the actual vehicle as the initial value and updating it based on the online compensation data.

[0118] Among them, the online compensation data can indicate the target compensation information under the torque offset compensation dimension determined in each hand-off detection cycle.

[0119] Based on this, in this embodiment of the application, after determining the target compensation information under the torque offset compensation dimension, the target compensation information can be subjected to low-pass filtering and moving average filtering to obtain new offset data; then, the tubing torque offset data is updated according to the new offset data.

[0120] Optionally, the target compensation information can be low-pass filtered, where the cutoff frequency of the low-pass filter can be 0.01Hz.

[0121] Optionally, the target compensation information can be processed by a moving average filter, wherein the moving average filter can be a filter with a length of 1000 seconds and a sampling period of 1 second.

[0122] In one example, after obtaining the new offset data, the new offset data can be summed with the tubing torque offset data to update the tubing torque offset data.

[0123] Optional, see Figure 3 , Figure 3 This application provides a schematic diagram of a process for determining target compensation information in the dimension of torque offset compensation, as illustrated in the embodiments of this application. Figure 3 As shown, on one hand, the column torque offset data stored in the memory can be acquired, and the target compensation information in the torque offset compensation dimension can be obtained by subtracting the steering column torque and column torque offset data. On the other hand, after obtaining the target compensation information, low-pass filtering and moving average filtering can be applied to the target compensation information to obtain new offset data; then, the new offset data and the acquired column torque offset data are summed to obtain new column torque offset data, which is saved to the memory to update the column torque offset data. At this time, the updated column torque offset data can be used for the next hand-off detection process.

[0124] This implementation method can extract the long-term trend of target compensation information based on low-pass filtering and moving average filtering, thereby accurately reflecting the cumulative effect of mechanical friction. This allows the obtained tubing torque offset data to accurately reflect the uneven friction of the current tubing, thus improving the accuracy of the target compensation information in the torque offset compensation dimension.

[0125] In one example, the damping force is determined based on the steering speed and the damping coefficient; therefore, the damping coefficient can be calculated based on the steering torque and steering speed of the steering column.

[0126] Based on this, if the matched torque compensation dimension indicates the damping compensation dimension, then the target compensation information under the matched torque compensation dimension is determined according to the following steps:

[0127] First, obtain the historical steering speed and historical steering column torque.

[0128] Then, based on the historical steering speed, the average speed information included in the preset sliding window is determined, and based on the historical steering column torque, the average torque information included in the preset sliding window is determined.

[0129] In this embodiment, after determining the vehicle's steering speed, a high-pass filter can be applied to the steering speed to remove low-frequency interference and baseline drift in the signal, thus obtaining an accurate steering speed. Then, the acquired steering speed and steering column torque can be averaged to obtain average speed information and average torque information.

[0130] Next, the current damping coefficient is determined based on the average torque and average speed information.

[0131] In one example, as described above, if the preset damping compensation requirements are met, it can be determined that the vehicle is in a constant speed steering state. At this time, the current damping coefficient can be determined by performing linear regression calculation on the average torque information and average speed information, and obtaining the slope of the straight line based on the linear regression calculation.

[0132] Finally, based on the current damping coefficient and steering speed, the target compensation information under the damping compensation dimension is determined.

[0133] See one example. Figure 4 , Figure 4 This application provides a schematic diagram of a process for determining target compensation information in the dimension of damping compensation, as illustrated in the embodiments of this application. Figure 4As shown, after acquiring the steering speed, a high-pass filter can be applied to it. Based on the filtered steering speed, the vehicle's steering state information is determined. If the preset damping compensation requirements are met, the average value of the steering speed and steering column torque is calculated to obtain the average speed information Vn and average torque information Tn at the current sampling time. Then, based on historical steering speeds, historical steering column torques, and a preset sliding window, the average speed information included within the preset sliding window can be determined (e.g., ...). Figure 4 The values ​​of Vn, Vn-1, Vn-2, Vn-3, Vn-4, Vn-5, Vn-6, and Vn-7 are shown, along with average torque information (e.g., Figure 4 The values ​​Tn, Tn-1, Tn-2, Tn-3, Tn-4, Tn-5, Tn-6, and Tn-7 are shown. At this point, linear regression calculations can be performed on the average speed and average torque information included within the preset sliding window to obtain a straight line with the horizontal axis representing steering speed and the vertical axis representing steering column torque. The current damping coefficient can then be determined based on the slope of the straight line. Subsequently, the target compensation information under the damping compensation dimension can be determined based on the product of the current damping coefficient and the steering speed.

[0134] In the above implementation, a linear regression model can be used to capture the dynamic relationship between torque and speed when the vehicle's steering system automatically adjusts the steering direction. This allows the determination of the damping torque generated by the steering system, which is then identified as the target compensation information under the damping compensation dimension. When correcting the steering column torque based on this target compensation information, the interference of automatic control on hands-off detection can be reduced, further improving the accuracy of hands-off detection.

[0135] In one example, when the dynamic friction of the steering column fluctuates near zero, it generates high-frequency noise, which in turn affects the accuracy of the hands-off detection.

[0136] Based on this, in determining the dynamic friction torque, the embodiments of this application can use the Coulomb friction model combined with the transition function to smooth the friction fluctuations near the zero point, thereby improving the accuracy of the release detection.

[0137] For example, the dynamic friction torque of the steering column can be determined according to the following formula (1).

[0138] (1)

[0139] in, This represents the dynamic friction torque of the steering column. This represents the preset friction torque amplitude data. This indicates the preset transition coefficient information. Indicates the turning speed.

[0140] In one example, the preset friction torque amplitude data and preset transition coefficient information are actual vehicle calibration data.

[0141] See one example. Figure 5 , Figure 5 This application provides a schematic diagram illustrating the relationship between preset transition coefficient information and the dynamic friction torque of the steering column, as shown in the embodiments. Figure 5 As shown, with the friction torque amplitude data fixed, dynamic friction torque diagrams corresponding to transition coefficient information 1 and transition coefficient information 2 can be obtained, where transition coefficient information 1 is greater than transition coefficient information 2. As can be seen from the diagram, the smaller the preset transition coefficient information, the smoother the fluctuation of the dynamic friction torque of the steering column. Therefore, friction fluctuations near the zero point can be smoothed by calibrating a smaller transition coefficient information.

[0142] Based on this, when the matched torque compensation dimension indicates the dynamic friction compensation dimension, the target compensation information under the matched torque compensation dimension is determined according to the following steps:

[0143] First, obtain the preset friction torque amplitude data and transition coefficient information.

[0144] Then, based on the friction torque amplitude data, transition coefficient information, and steering speed, the target compensation information under the dynamic friction compensation dimension is determined.

[0145] See one example. Figure 6 , Figure 6 This application provides a schematic diagram of a process for determining target compensation information in the dimension of dynamic friction compensation, as illustrated in the embodiments of this application. Figure 6 As shown, after obtaining the preset friction torque amplitude data and the preset transition coefficient information, the preset friction torque amplitude data, the preset transition coefficient information and the steering speed can be input into the dynamic friction torque formula shown in the above formula (1) to calculate the target compensation information under the dynamic friction compensation dimension.

[0146] S204. Determine the torque compensation information based on the target compensation information under the matched torque compensation dimension.

[0147] As can be seen from the above description, the number of matching torque compensation dimensions provided in the embodiments of this application is at least one. When the number of target compensation information under the matching torque compensation dimension is at least one, the target compensation information under the matching torque compensation dimension can be summed to obtain torque compensation information.

[0148] In one example, after obtaining the torque compensation information, the steering column torque can be corrected based on the torque compensation information to obtain the corrected steering column torque. For details, please refer to the process described below.

[0149] S205. Perform a difference calculation on the steering column torque and torque compensation information to obtain the corrected steering column torque.

[0150] This implementation method can subtract torque compensation information from the steering column torque, thereby accurately determining the torque applied by the driver, and making the obtained corrected steering column torque more accurate for hands-off detection.

[0151] S206. Determine the hand-off test result based on the corrected steering column torque.

[0152] In one possible implementation, after obtaining the corrected steering column torque, a preset torque threshold and a preset time threshold for performing hands-off detection can be obtained to match the current vehicle. At this time, the hands-off detection result can be determined by comparing the corrected steering column torque with the preset torque threshold and combining it with the preset time threshold.

[0153] For example, if it is determined that the corrected steering column torque is less than a preset torque threshold and the duration is greater than a preset time threshold, then the hand-off detection result indicates a hand-off state.

[0154] Otherwise, the detection result indicates that the hand has not been released.

[0155] In the above embodiments, the accuracy of release detection can be improved and misjudgment can be avoided by combining preset torque threshold and preset time threshold.

[0156] See one example. Figure 7 , Figure 7 This is a schematic diagram illustrating the implementation process of a hand-removal detection method provided in an embodiment of this application, as shown below. Figure 7 As shown, during the hands-off detection, the vehicle's steering column torque can be acquired, and torque offset compensation information, damping compensation information, and dynamic friction compensation information can be calculated. Then, by combining the torque offset compensation information, damping compensation information, and dynamic friction compensation information, the steering column torque is corrected to obtain the corrected steering column torque. Finally, hands-off detection is performed by combining a preset torque threshold, a preset time threshold, and the corrected steering column torque to obtain the hands-off detection result.

[0157] It should be understood that the corrected steering column torque does not always have to be based on all of the torque offset compensation information, damping compensation information, and dynamic friction compensation information, but can be based on one or more of them. Compared with the uncorrected steering column torque, the steering column torque corrected based on any one of the torque offset compensation information, damping compensation information, and dynamic friction compensation information can provide a more accurate representation of the steering column torque applied by the driver, thereby providing a more accurate hand-off detection result.

[0158] Figure 8 This is a schematic diagram of the structure of a hand-removal detection device provided in an embodiment of this application, as shown below. Figure 8 As shown, the hand-drop detection device 80 provided in this embodiment includes:

[0159] The acquisition unit 801 is used to acquire the vehicle's steering status information when the vehicle is detected to be in an autonomous driving state; wherein the steering status information is used to indicate at least the steering column torque.

[0160] The determining unit 802 is used to determine the matching torque compensation dimension based on the steering state information, and to determine the torque compensation information based on the target compensation information under the matching torque compensation dimension.

[0161] The correction unit 803 is used to correct the steering column torque based on the torque compensation information to obtain the corrected steering column torque.

[0162] The detection unit 804 is used to determine the hand-off detection result based on the corrected steering column torque.

[0163] In one possible implementation, the steering status information is also used to indicate steering speed and steering angle; in this case, the determining unit 802 is used to:

[0164] If the preset torque offset compensation requirements are met based on the steering column torque, steering speed, and steering angle, then the matching torque compensation dimensions include the torque offset compensation dimension and the dynamic friction compensation dimension; and / or, if the preset damping compensation requirements are met based on the steering column torque, steering speed, and steering angle, then the matching torque compensation dimensions include the damping compensation dimension and the dynamic friction compensation dimension.

[0165] In one possible implementation, the matched torque compensation dimension indicates the torque offset compensation dimension; the target compensation information under the matched torque compensation dimension is determined according to the following steps:

[0166] Obtain the tubing string torque offset data;

[0167] The target compensation information in the torque offset compensation dimension is obtained by performing a subtraction operation on the steering column torque and steering column torque offset data.

[0168] In one possible implementation, the device is also used for:

[0169] The target compensation information is subjected to low-pass filtering and moving average filtering to obtain new offset data;

[0170] Update the column torque offset data based on the new offset data.

[0171] In one possible implementation, the steering state information is also used to indicate the steering speed; the matched torque compensation dimension indicates the damping compensation dimension; the target compensation information under the matched torque compensation dimension is determined according to the following steps:

[0172] Obtain historical steering speed and historical steering column torque;

[0173] Based on historical steering speeds, determine the average speed information included in the preset sliding window, and based on historical steering column torques, determine the average torque information included in the preset sliding window.

[0174] The current damping coefficient is determined based on the average torque and average speed information;

[0175] Based on the current damping coefficient and steering speed, determine the target compensation information under the damping compensation dimension.

[0176] In one possible implementation, the steering state information is also used to indicate the steering speed; the matched torque compensation dimension indicates the dynamic friction compensation dimension; the target compensation information under the matched torque compensation dimension is determined according to the following steps:

[0177] Obtain preset friction torque amplitude data and transition coefficient information;

[0178] Based on the friction torque amplitude data, transition coefficient information, and steering speed, the target compensation information under the dynamic friction compensation dimension is determined.

[0179] In one possible implementation, the correction unit 803 is used for:

[0180] The corrected steering column torque is obtained by performing a subtraction operation on the steering column torque and torque compensation information.

[0181] In one possible implementation, the release detection result indicates a release state; at this time, the detection unit 804 is used for:

[0182] Obtain preset torque thresholds and preset time thresholds that match the vehicle;

[0183] If it is determined that the corrected steering column torque is less than the preset torque threshold and the duration is greater than the preset time threshold, then the hand-off detection result indicates a hand-off state.

[0184] The hand-drop detection device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0185] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 9 As shown, the electronic device 90 provided in this embodiment includes at least one processor 901 and a memory 902. Optionally, the electronic device 90 further includes a communication component 903. The processor 901, memory 902, and communication component 903 are connected via a bus 904.

[0186] In a specific implementation, at least one processor 901 executes computer execution instructions stored in memory 902, causing at least one processor 901 to perform the above-described method.

[0187] The specific implementation process of processor 901 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0188] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0189] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0190] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0191] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0192] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0193] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0194] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0195] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0196] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0197] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0198] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0199] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0200] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for detecting hand slippage, characterized in that, include: When the vehicle is detected to be in autonomous driving mode, the vehicle's steering status information is acquired; wherein the steering status information is used to indicate at least the steering column torque; Based on the steering state information, determine the matching torque compensation dimension, and based on the target compensation information under the matching torque compensation dimension, determine the torque compensation information; The steering column torque is corrected based on the torque compensation information to obtain the corrected steering column torque. The result of the hands-off detection is determined based on the corrected steering column torque.

2. The method according to claim 1, characterized in that, The steering status information is also used to indicate steering speed and steering angle; Based on the steering state information, the matching torque compensation dimension is determined, including: If, based on the steering column torque, the steering speed, and the steering angle, a preset torque offset compensation requirement is determined to be met, then the matched torque compensation dimension is determined to include a torque offset compensation dimension and a dynamic friction compensation dimension; and / or, if, based on the steering column torque, the steering speed, and the steering angle, a preset damping compensation requirement is determined to be met, then the matched torque compensation dimension is determined to include a damping compensation dimension and a dynamic friction compensation dimension.

3. The method according to claim 1, characterized in that, The matched torque compensation dimension indicates the torque offset compensation dimension; the target compensation information under the matched torque compensation dimension is determined according to the following steps: Obtain the tubing string torque offset data; The target compensation information under the torque offset compensation dimension is obtained by performing a difference operation on the steering column torque and the steering column torque offset data.

4. The method according to claim 3, characterized in that, The method further includes: The target compensation information is subjected to low-pass filtering and moving average filtering to obtain new offset data; The string torque offset data is updated based on the new offset data.

5. The method according to claim 1, characterized in that, The steering state information is also used to indicate steering speed; the matched torque compensation dimension indicates the damping compensation dimension; the target compensation information under the matched torque compensation dimension is determined according to the following steps: Obtain historical steering speed and historical steering column torque; Based on the historical steering speed, determine the average speed information included in the preset sliding window, and based on the historical steering column torque, determine the average torque information included in the preset sliding window; The current damping coefficient is determined based on the average torque information and the average speed information; Based on the current damping coefficient and the steering speed, the target compensation information under the damping compensation dimension is determined.

6. The method according to claim 1, characterized in that, The steering state information is also used to indicate steering speed; the matched torque compensation dimension indicates the dynamic friction compensation dimension; the target compensation information under the matched torque compensation dimension is determined according to the following steps: Obtain preset friction torque amplitude data and transition coefficient information; Based on the friction torque amplitude data, the transition coefficient information, and the steering speed, the target compensation information under the dynamic friction compensation dimension is determined.

7. The method according to any one of claims 1-6, characterized in that, The steering column torque is corrected based on the torque compensation information to obtain the corrected steering column torque, including: The corrected steering column torque is obtained by performing a difference operation between the steering column torque and the torque compensation information.

8. The method according to claim 7, characterized in that, The release detection result indicates the release status; Based on the corrected steering column torque, the hand-off detection result is determined, including: Obtain a preset torque threshold and a preset time threshold that match the vehicle; If it is determined that the corrected steering column torque is less than the preset torque threshold and the duration is greater than the preset time threshold, then the hand-off detection result indicates a hand-off state.

9. A hand-removal detection device, characterized in that, include: An acquisition unit is configured to acquire steering state information of the vehicle when it is detected that the vehicle is in an autonomous driving state; wherein the steering state information is used to indicate at least the steering column torque; The determining unit is used to determine the matching torque compensation dimension based on the steering state information, and to determine the torque compensation information based on the target compensation information under the matching torque compensation dimension. The correction unit is used to correct the steering column torque according to the torque compensation information to obtain the corrected steering column torque. The detection unit is used to determine the hand-off detection result based on the corrected steering column torque.

10. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-8.

12. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-8.

Images