Hand release detection method, controller, medium, product and vehicle

Abstract

The invention relates to a hand release detection method, a controller, a medium, a product and a vehicle, and the method comprises the steps: carrying out the filtering of a hand torque sensed by a steering wheel of a target vehicle, and obtaining a filtered hand torque; and based on the filtered hand torque, performing hand release detection on a driver of the target vehicle. On the basis, the hand torque sensed by the steering wheel of the vehicle is filtered, interference of complex and diverse actual conditions is reduced, the accuracy of hand release detection is improved on the basis of the filtered hand torque, and therefore the driving safety of the vehicle is ensured.

Description

Technical Field

[0001] The present application relates to the field of hands-off detection technology, and in particular to a hands-off detection method, controller, medium, product, and vehicle. Background Art

[0002] Existing hands-off detection solutions for vehicles include torque-sensing solutions, which detect the magnitude of the torque signal emitted by the vehicle's power steering system to determine whether the driver's hands are off the steering wheel.

[0003] However, due to the complexity and diversity of actual situations, the above-mentioned hands-off detection scheme has the problem that the hands-off detection result is inconsistent with the actual situation due to the failure of the triggering conditions of the hands-off detection, thereby causing the hands-off detection to have a low accuracy. Summary of the Invention

[0004] The embodiments of the present application provide a hands-off detection method, device, controller, storage medium, computer program product, and vehicle. By filtering the hand torque sensed by the vehicle's steering wheel, interference from complex and diverse actual situations is reduced, and the accuracy of hands-off detection is improved based on the filtered hand torque, thereby ensuring the vehicle's driving safety.

[0005] The present invention provides a method for detecting a hands-off condition, including:

[0006] Filtering the hand torque sensed from the steering wheel of the target vehicle to obtain a filtered hand torque;

[0007] Based on the filtered hand torque, a hands-off detection is performed on the driver of the target vehicle.

[0008] Accordingly, an embodiment of the present application provides a hands-off detection device, comprising:

[0009] A filtering module, configured to filter the hand torque sensed by the steering wheel of the target vehicle to obtain a filtered hand torque;

[0010] A detection module is used to perform hands-off detection on the driver of the target vehicle based on the filtered hand torque.

[0011] In addition, an embodiment of the present application also provides a controller, including one or more processors and a memory, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the hands-off detection method provided in an embodiment of the present application.

[0012] In addition, an embodiment of the present application further provides a storage medium, which stores a computer program. When the computer program runs on a controller, the computer program is used to enable the controller to execute any one of the hands-off detection methods provided in the embodiments of the present application.

[0013] In addition, an embodiment of the present application also provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements any of the hands-off detection methods provided in the embodiments of the present application.

[0014] In addition, an embodiment of the present application also provides a vehicle, including the above-mentioned controller.

[0015] In an embodiment of the present application, the hand torque sensed on the steering wheel of a target vehicle is filtered to obtain a filtered hand torque. Hands-off detection of the target vehicle's driver is performed based on the filtered hand torque. By filtering the hand torque sensed on the vehicle's steering wheel, interference from complex and diverse real-world conditions is reduced, and the accuracy of hands-off detection is improved based on the filtered hand torque, thereby ensuring vehicle driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a schematic diagram of an implementation environment scenario of the hands-off detection method provided in an embodiment of the present application;

[0018] Figure 2 1 is a flow chart of a hands-off detection method provided in an embodiment of the present application;

[0019] Figure 3 This is a schematic diagram of the trend of the hand torque perceived on the vehicle's steering wheel when the vehicle's assisted driving function is turned on;

[0020] Figure 4 This is a schematic diagram of the trend of the hand torque sensed on the vehicle's steering wheel when the vehicle's assisted driving function is turned off;

[0021] Figure 5 Schematic diagram of the frequency distribution range of the reference environment interference hand torque corresponding to multiple models of reference vehicles in the hands-off detection method provided in the embodiment of the present application;

[0022] Figure 6Schematic diagram of the design process of the IIR low-pass filter provided in the embodiment of the present application;

[0023] Figure 7 Schematic diagram of designing a 4th-order IIR filter provided in an embodiment of the present application;

[0024] Figure 8a 2 is a schematic diagram of simulation results of a second-order IIR low-pass filter provided in an embodiment of the present application;

[0025] Figure 8b 2 is a schematic diagram of simulation results of a second-order FIR low-pass filter provided in an embodiment of the present application;

[0026] Figure 8c 1 is a schematic diagram of simulation results of a third-order IIR low-pass filter provided in an embodiment of the present application;

[0027] Figure 8d 4 is a schematic diagram of simulation results of a 4th-order IIR low-pass filter provided in an embodiment of the present application;

[0028] Figure 8e Schematic diagram of simulation results of a 4th-order FIR low-pass filter provided in an embodiment of the present application;

[0029] Figure 8f 1 is a schematic diagram of simulation results of a 5th-order IIR low-pass filter provided in an embodiment of the present application;

[0030] Figure 8g 10th-order IIR low-pass filter simulation results provided by an embodiment of the present application;

[0031] Figure 8h This is a schematic diagram of simulation results of a 10th-order FIR low-pass filter provided in an embodiment of the present application;

[0032] Figure 9 Schematic diagram of the specific process of the hands-off detection method provided in the embodiment of the present application;

[0033] Figure 10 Schematic diagram of the structure of the hands-off detection device provided in an embodiment of the present application;

[0034] Figure 11 It is a schematic diagram of the structure of the controller provided in the embodiment of the present application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0036] In addition, the term "a plurality of" in the embodiments of the present application refers to two or more than two. The terms "first" and "second" in the embodiments of the present application are used to distinguish descriptions and should not be understood to imply relative importance.

[0037] Research has found that currently, major automobile manufacturers mainly use the steering wheel to detect whether the driver has taken their hands off the steering wheel, and generally adopt the following three mainstream solutions: grip sensing, capacitive sensing and torque sensing.

[0038] The grip-sensing solution uses a grip sensor installed on the steering wheel. When the driver grips the steering wheel and applies a certain amount of pressure, the system detects that their hands have not left the wheel. If the grip is insufficient, the voltage may be disconnected, and the system will determine that the driver has taken their hands off the wheel. Therefore, when the system prompts "Take Over the Steering Wheel," simply grip the wheel slightly harder. However, frequent reminders may reduce the assisted driving experience. Grip sensors are typically installed only in areas where hands are usually gripped, which poses a risk of missed detection and increases hardware costs.

[0039] Capacitive sensing also detects grip force, but it's more accurate at identifying fingers. A capacitive sensing steering wheel consists of an outer layer, a dual-zone capacitive sensing pad, an insulating layer, a PU heating layer, an inner foam layer, and a frame. By detecting microcurrents at the fingertips, this solution can sense the driver's operating intentions. However, its disadvantage is the high hardware cost.

[0040] The torque-sensing solution detects the torque signal output by the power steering system's angular torque sensor to determine if the driver has taken their hands off the wheel. With a simple turn of the steering wheel, the system detects that the hands are still on the wheel. This solution requires no additional sensors, making it easy to implement and low-cost. However, research has shown that when the driver takes their hands off the wheel, varying road conditions can cause the torque output of the power steering system to fluctuate. In particular, bumpy roads can cause the hand torque to exceed the threshold, causing the system to reset the timing, invalidating the trigger condition, and mistakenly assuming that the driver has taken their hands off the wheel, resulting in the system not issuing the "take over the steering wheel" reminder.

[0041] Due to the complexity and changeability of actual conditions, these hands-off detection schemes may cause the detection results to be inconsistent with the actual situation due to the failure of triggering conditions, thereby reducing the detection accuracy.

[0042] To address the aforementioned issues, embodiments of the present application provide a hands-off detection method, device, controller, storage medium, computer program product, and vehicle. The hands-off detection device can be integrated into a controller, which can be a server, such as a hands-off detection system, or a device, such as a terminal, controlled by the hands-off detection system.

[0043] Among them, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, network acceleration services (Content Delivery Network, CDN), as well as big data and artificial intelligence platforms.

[0044] The terminal may be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, etc., but is not limited thereto. The terminal and the server may be connected directly or indirectly via wired or wireless communication, and this application does not impose any restrictions thereon.

[0045] See also Figure 1 , taking the hands-off detection device integrated into the controller as an example, Figure 1 This is a schematic diagram of an implementation scenario for the hands-off detection method provided in an embodiment of the present application. The controller, which can be a terminal device, filters the hand torque sensed by the steering wheel of a target vehicle to obtain a filtered hand torque. Based on the filtered hand torque, hands-off detection is performed on the driver of the target vehicle. By filtering the hand torque sensed by the vehicle's steering wheel, interference from complex and diverse real-world conditions is reduced. Based on the filtered hand torque, the accuracy of hands-off detection is improved, thereby ensuring vehicle driving safety.

[0046] It should be noted that Figure 1 The schematic diagram of the implementation environment scenario of the hands-off detection method shown is merely an example. The implementation environment scenario of the hands-off detection method described in the embodiments of this application is intended to more clearly illustrate the technical solutions of the embodiments of this application and does not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of data processing and the emergence of new business scenarios, the technical solutions provided in this application are equally applicable to similar technical problems.

[0047] The solutions provided in the embodiments of the present application are specifically described by the following embodiments. It should be noted that the description order of the following embodiments does not limit the preferred order of the embodiments.

[0048] This embodiment will be described from the perspective of a hands-off detection device. The hands-off detection device may be integrated into a controller, which may be a terminal and / or a server. This application does not impose any restrictions on this.

[0049] See also Figure 2 , Figure 2: FIG1 is a flow chart of a hands-off detection method provided in an embodiment of the present application. The hands-off detection method may include the following steps S101 to S102:

[0050] S101 : Filter the hand torque sensed from the steering wheel of the target vehicle to obtain a filtered hand torque.

[0051] The target vehicle refers to the vehicle that needs to be tested for hands-free operation.

[0052] The hand torque refers to the twisting force applied to the steering wheel of the target vehicle, which causes the steering wheel to rotate around its rotation axis.

[0053] Specifically, the hand torque can be measured by a steering torque sensor configured in the power steering system of the target vehicle.

[0054] It should be noted that the above hand torque includes the hand torque of the driver of the target vehicle and / or the environmental interference hand torque generated by the environmental interference of the target vehicle.

[0055] The driver's hand torque refers to the torque applied by the driver of the target vehicle to the steering wheel, which causes the steering wheel to rotate around its rotation axis.

[0056] The environmental interference hand torque refers to the torsional force applied to the steering wheel caused by the environmental interference in the target vehicle, which causes the steering wheel to rotate around its rotation axis.

[0057] Environmental interference refers to various dynamic factors, either external or internal to the vehicle, that are not actively applied by the driver. These factors are transmitted to the steering wheel through the steering mechanism or the tire-road interface, thereby interfering with the driver's intended hand torque. These interferences may manifest as steering wheel vibration, deflection, or sudden torque changes, impacting driving comfort and handling stability.

[0058] The specific content of the environmental interference can be adjusted according to actual conditions and is not limited in the embodiments of the present application.

[0059] In some embodiments, the environmental disturbance includes road surface excitation disturbance of the target vehicle.

[0060] Road excitation interference refers to the influencing factors from the road surface where the target vehicle is located.

[0061] The road surface excitation interference is affected by road surface roughness, road surface adhesion coefficient, road surface slope and cross slope, etc. Its specific content can be adjusted according to actual conditions and is not limited in the embodiments of this application.

[0062] In some embodiments, the environmental interference may also include tire interference caused between the vehicle's tires and wheel system. Tire interference is affected by tire pressure, tire stiffness, and the like.

[0063] In some embodiments, the aforementioned environmental interference may also include internal excitation of the power steering system, such as steering mechanism wear, power steering system failure, etc.

[0064] The filtering process is a process for reducing interference from complex and diverse actual conditions in the hand torque sensed by the steering wheel of the target vehicle.

[0065] The filtered hand torque refers to the hand torque after filtering.

[0066] S102: Perform hands-off detection on the driver of the target vehicle based on the filtered hand torque.

[0067] Among them, hands-off detection refers to a method of detecting whether the driver of the target vehicle has taken his hands off the steering wheel.

[0068] It should be noted that the driver's hands being off the steering wheel can be understood as the driver's hands not applying torque to the steering wheel, but the driver's hands may still be on the steering wheel.

[0069] As can be seen, the hands-off detection method provided in the embodiments of the present application filters the hand torque sensed on the steering wheel of a target vehicle to obtain a filtered hand torque; based on the filtered hand torque, hands-off detection is performed on the driver of the target vehicle. Therefore, by filtering the hand torque sensed on the vehicle's steering wheel, interference from complex and diverse actual conditions is reduced, and the accuracy of hands-off detection is improved based on the filtered hand torque, thereby ensuring vehicle driving safety.

[0070] It should be noted that when the vehicle's assisted driving function is enabled, vehicles using a torque-sensing solution typically monitor the torque signal emitted by the assisted steering system's angular torque sensor, and then determine whether the driver has intervened based on the monitored torque value (the torque value is generally set to >0.3Nm). However, during driving without the driver's manual intervention, road excitation on bumpy roads can interfere with the angular torque sensor's signal.

[0071] The actual performance of existing vehicles using torque sensing solutions is that when the vehicle's assisted driving function is activated, the hand torque signal value changes dramatically. When passing through a pit or manhole cover, the steering wheel swings back and forth, and the signal value can be as high as 2.5Nm, causing the hands-off detection system to not alarm for a long time.

[0072] Under the same road conditions, driver and speed, when the assisted driving function is turned on, refer to Figure 3 The trend chart of the hand torque perceived by the vehicle's steering wheel shows that the maximum value of the driver's hand torque can reach about 2Nm. When the assisted driving function is turned off, refer to Figure 4The trend chart of the hand torque sensed on the vehicle's steering wheel shows that the driver's hand torque can reach a maximum of approximately 2 Nm. Meanwhile, the hand torque value when the test vehicle is stationary is approximately 0.2 Nm. Therefore, it can be assumed that the interference signal can be ignored after the hand torque value caused by external interference is attenuated by a factor of 10.

[0073] The fundamental reason for hands-off detection failure is that the steering torque sensor reflects the actual driver's hand torque, influenced by external factors such as the road surface, the vehicle, and the driver's hand. When road conditions are poor, the road exerts greater force on the tires, resulting in a higher hand torque value from the steering torque sensor. In this case, the system mistakenly interprets the driver's hand as being in the vehicle, leading to a lower frequency of hands-off alarms.

[0074] To this end, this application conducts a torque sensing solution hands-off detection failure analysis at different speed ranges for various models such as existing mini cars, A-class sedans, A-class SUVs, B-class sedans, and B-class SUVs. By analyzing the actual vehicle data of different models at different speed ranges, it is found that the frequency distribution range of the road excitation interference of various reference vehicles is summarized in 7Hz-25Hz, such as Figure 5 As shown in FIG, the frequency distribution range of the driver's hand intervention is 0Hz-5Hz. That is, the frequency distribution range of the environmental interference hand torque includes 7Hz-25Hz, and the frequency distribution range of the driver's hand torque includes 0Hz-5Hz.

[0075] Therefore, the frequency in the frequency distribution range corresponding to the environmental interference hand torque is higher than the frequency in the frequency distribution range corresponding to the driver's hand torque.

[0076] Based on this, the above-mentioned process of filtering the hand torque sensed by the steering wheel of the target vehicle to obtain the filtered hand torque includes: performing low-pass filtering on the hand torque sensed by the steering wheel of the target vehicle to obtain the filtered hand torque to attenuate the environmental interference hand torque in the hand torque.

[0077] The low-pass filtering process refers to attenuating the environmental interference hand torque in the hand torque to retain the driver's hand torque.

[0078] The low-pass filtering process is performed based on a low-pass filter configured with a filter frequency threshold, which is determined based on the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range corresponding to the environmental interference hand torque.

[0079] The low-pass filter is a digital filter used for low-pass filtering, which allows signals below the filter frequency threshold to pass smoothly while attenuating signals of other frequencies.

[0080] There are many ways to set the filtering frequency threshold of the low-pass filter, which can be adjusted according to actual conditions and is not limited in the embodiments of the present application.

[0081] For example, the filtering frequency threshold is determined by taking any frequency value between the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range corresponding to the environmental interference hand torque. For another example, the filtering frequency threshold is determined by taking a median value between the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range corresponding to the environmental interference hand torque. For another example, the filtering frequency threshold is determined by taking an average value between the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range corresponding to the environmental interference hand torque.

[0082] It should be noted that the frequency distribution range corresponding to the above-mentioned environmental interference hand torque is determined based on the frequency distribution range corresponding to the reference environmental interference hand torque of reference vehicles of various models.

[0083] The reference vehicles refer to vehicles corresponding to different models, for example, the reference vehicle corresponding to model A, the reference vehicle corresponding to model B, etc.

[0084] The reference environmental interference hand torque refers to the environmental interference hand torque generated based on the environmental interference of the reference vehicle.

[0085] It should be noted that different reference vehicles have different anti-interference capabilities. That is, the frequency distribution ranges corresponding to the reference environmental interference hand torques of different reference vehicles are different. For example, the frequency distribution range of the reference environmental interference hand torques of reference vehicles corresponding to vehicle type A is 10Hz-15Hz, while the frequency distribution range of the reference environmental interference hand torques of reference vehicles corresponding to vehicle type B is 20Hz-25Hz.

[0086] The frequency distribution range corresponding to the reference environment interference hand torque of reference vehicles of different models is determined according to the anti-interference capability of the reference vehicles of the same models.

[0087] Based on this, in some embodiments, the filtering frequency threshold of the low-pass filter can also be set according to the model of the target vehicle.

[0088] Specifically, the filtering frequency threshold is determined based on the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range of the reference environment interference hand torque corresponding to the model of the target vehicle.

[0089] For example, the filtering frequency threshold is determined by taking any frequency value between the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range of the reference environment interference hand torque corresponding to the model of the target vehicle. For another example, the filtering frequency threshold is determined by taking an average value between the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range of the reference environment interference hand torque corresponding to the model of the target vehicle. The filtering frequency threshold is determined by taking a median value between the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range of the reference environment interference hand torque corresponding to the model of the target vehicle.

[0090] Since the frequency distribution range of the driver's hand torque includes 0Hz-5Hz, the frequency distribution range of the environmental interference hand torque includes 7Hz-25Hz.

[0091] In some preferred embodiments, the filtering frequency threshold comprises 6 Hz.

[0092] It should be noted that the selection of the low-pass filter can be determined according to actual conditions.

[0093] Specifically, the low-pass filter used in the embodiment of the present application is a low-pass filter of the target type selected from multiple different types of candidate low-pass filters based on the filtering performance information of the candidate low-pass filters on the simulated hand torque, wherein the simulated hand torque includes at least the simulated driver hand torque and the simulated environmental interference hand torque.

[0094] The candidate low-pass filter refers to a digital filter that can be used for low-pass filtering processing.

[0095] The low-pass filter used in the embodiment of the present application is a digital filter selected from a plurality of candidate low-pass filters and used for low-pass filtering processing in an actual process.

[0096] In some embodiments, the target-type low-pass filter includes an infinite impulse response filter (IIR).

[0097] Among them, the infinite impulse response filter refers to a digital filter whose impulse response can theoretically extend infinitely and will never completely decay to zero.

[0098] Specifically, the infinite impulse response filter includes a 4th-order infinite impulse response filter.

[0099] The fourth-order infinite impulse response filter refers to an infinite impulse response filter including four historical output items in a feedback path.

[0100] In some embodiments, the candidate low-pass filters are obtained by performing low-pass filter simulation based on the filtering configuration information.

[0101] The filter configuration information refers to the relevant parameters used to configure different types of digital filters, such as filter parameters, order, transfer function, bilinear transformation, etc.

[0102] The filtering performance information includes filtering accuracy and / or filtering processing delay.

[0103] The selection process of the low-pass filter is described in detail below.

[0104] Since the frequency distribution range of the driver's hand torque is 0Hz-5Hz and the frequency distribution range of the environmental interference hand torque is 7Hz-25Hz, the filter frequency threshold can be set to 6Hz.

[0105] The low-pass filtering algorithm of the torque-sensing solution mentioned above usually uses an IIR filter. IIR filters have the characteristic of infinite impulse response (if there is a jump in the input, the output will be affected indefinitely). They are usually more suitable for applications that require fast response and smaller order.

[0106] It should be noted that the design of IIR filter involves filter parameters, order, transfer function, bilinear transformation and other processes, such as Figure 6 As shown in Figure 1. This process maps an s-plane (complex frequency plane) to another z-plane (discrete time plane). The bilinear transformation requires careful selection of transformation parameters to ensure filter stability and performance. When designing and implementing IIR filters, special attention must be paid to preventing instability. An unstable IIR filter can result in unlimited amplification of the input signal, leading to distortion of the output hand torque signal. Therefore, stability analysis and testing are often required during the design process.

[0107] First, it is necessary to determine the passband cutoff frequency, stopband cutoff frequency, passband maximum attenuation, and stopband minimum attenuation of the IIR low-pass filter in this application.

[0108] The passband cutoff frequency is the maximum frequency within the passband, at which the filter's attenuation does not exceed a certain maximum value. The stopband cutoff frequency is the minimum frequency within the stopband, at which the filter's attenuation reaches at least a certain minimum value. The maximum passband attenuation is typically the attenuation at the passband cutoff frequency, typically 3dB. The minimum stopband attenuation is typically 40dB or higher, indicating the filter's attenuation within the stopband.

[0109] Specifically, the passband cutoff frequency is designed based on the fact that the frequency distribution of the driver's hand interference mentioned above is between 0Hz and 5Hz. After filtering, the low-pass filter needs to retain the hand torque signal between 0Hz and 5Hz. Therefore, the passband cutoff frequency of the low-pass filter can be set to 5Hz. The stopband cutoff frequency is designed based on the fact that the frequency distribution of the road excitation interference of the above-mentioned vehicle models is between 7Hz and 25Hz. After filtering, the low-pass filter needs to eliminate the road interference signal between 7Hz and 25Hz. Therefore, the stopband cutoff frequency of the low-pass filter can be set to 7Hz. The maximum passband attenuation is determined by empirical values. Generally, for Butterworth filters, the maximum passband attenuation is generally 3dB. Based on previous field tests, the hand torque value of the vehicle at rest is approximately 0.2Nm. Therefore, it can be assumed that after the hand torque value caused by external interference (typically 2-3Nm) is attenuated by 10 times, it is comparable to the hand torque value when the vehicle is at rest. The interference signal can be ignored. Therefore, the minimum stopband attenuation (A_s) is 10dB.

[0110] To this end, the filtering configuration information of the low-pass filter required to be designed in this application is: the sampling frequency T is 50Hz, the passband cutoff frequency (ω_p) is 5Hz, the stopband cutoff frequency (ω_s) is 7Hz, the passband maximum attenuation (A_p) is 3dB, and the stopband minimum attenuation (A_s) is 10dB.

[0111] Based on the above filter configuration information, the Butterworth method is used to design an IIR low-pass filter, which is characterized by a frequency response curve that is as flat as possible within the passband and gradually decreases to zero in the stopband. Figure 7 As shown in Figure 1. A first-order Butterworth filter has an attenuation rate of 6 dB per octave, a second-order Butterworth filter has an attenuation rate of 12 dB per octave, a third-order Butterworth filter has an attenuation rate of 18 dB per octave, and so on. The Butterworth filter's amplitude versus angular frequency decreases monotonically, making it the only filter whose amplitude versus angular frequency curve maintains the same shape regardless of order. Higher-order filters exhibit faster stopband amplitude attenuation. Other filters with higher-order amplitude versus angular frequency have different shapes than those with lower-order filters.

[0112] Based on the above filtering configuration information, the order of the IIR low-pass filter can be calculated according to the following formula:

[0113]

[0114] Where N is the order of the IIR low-pass filter,

[0115] The above k Sp and λ Sp Substitute the calculation formula of N into it and we get:

[0116]

[0117] Therefore, based on the above filtering configuration information, the order of the IIR low-pass filter is 4.

[0118] Furthermore, the poles of the 4th-order IIR low-pass filter can be determined according to the following formula:

[0119]

[0120] Based on this, the transfer function of the 4th-order normalized IIR low-pass filter can be determined according to the following formula:

[0121]

[0122] It should be noted that, since A_p = 3dB, that is:

[0123] Ω c =Ω p =2πω_p·10 3 =π·10 4

[0124] Combining the above content and the transfer function of the 4th-order normalized IIR low-pass filter, the transfer function of the 4th-order IIR low-pass filter can be expressed as follows:

[0125]

[0126] Since bilinear transformation will lead to nonlinear mapping of frequency, that is, there is a distortion relationship between analog frequency and digital frequency, it is necessary to perform pre-distortion processing on the frequency before performing bilinear transformation.

[0127] The purpose of frequency predistortion is to ensure that the frequency response of the analog filter can be correctly mapped to the frequency response of the digital filter when designing the digital filter. The formula for predistortion is:

[0128]

[0129] Among them, Ω1 is the frequency after pre-distortion, Ω is the original frequency, and Ω0 is a reference frequency (usually taken as Ω p or Ω s ).

[0130] However, in practical applications, since the transfer function H of the analog filter is already known a (s), and the distortion characteristics of the bilinear transform are known, so this distortion can be directly considered in the design process without the need for explicit frequency predistortion calculation.

[0131] The transfer function H of the simulated filter a(s) Convert from the s plane to the z plane to obtain the transfer function H of the digital filter a (z). The formula for bilinear transformation is:

[0132]

[0133] Where s is the analog complex frequency variable, z is the digital complex frequency variable, and T is the sampling period.

[0134] H a Replace s in (s) with z in the above formula and make appropriate algebraic transformations to get H a (z), the formula is as follows:

[0135]

[0136] Because Ha(z) is a polynomial, the replacement and transformation process can be complex. In practice, this is typically accomplished using signal processing toolboxes or filter design functions in programming software such as MATLAB and Python.

[0137] Because Ha(z) is a polynomial, the replacement and transformation process can be complex. In practice, this is typically accomplished using signal processing toolboxes or filter design functions in programming software such as MATLAB and Python.

[0138] A low-pass filter simulation model was built using MATLAB / Simulink software. The discrete sinusoidal signal source module in Simulink simulated the low-frequency hand torque signal and the high-frequency road excitation signal. By superimposing these different signal sources, a simulated external torque signal was generated. This simulated torque signal was then input into the low-pass filter designed in this application, completing the construction of the low-pass filter simulation platform. Finally, the accuracy and delay of the filter output signal were analyzed.

[0139] Depend on Figure 8a It can be seen that after filtering by the second-order IIR low-pass filter, the maximum error of the output low-frequency hand torque value signal is 0.64Nm, and the delay error of the signal before and after processing is 26ms. Figure 8b It can be seen that after filtering by a second-order finite impulse response filter (FIR), the maximum error of the output low-frequency hand torque value signal is 0.87Nm, and the delay error of the signal before and after processing is 26ms. Figure 8a and Figure 8b Analysis shows that compared with the second-order FIR low-pass filter, the second-order IIR low-pass filter has a smaller error in the hand torque signal.

[0140] Depend on Figure 8d It can be seen that after filtering by the 4th-order IIR low-pass filter, the maximum error of the output low-frequency hand torque value signal is 0.15Nm, and the delay error of the signal before and after processing is 58ms. Figure 8e It can be seen that after filtering by the 4th-order FIR low-pass filter, the maximum error of the output low-frequency hand torque value signal is 1.13Nm, and the delay error of the signal before and after processing is 39ms. Figure 8d and Figure 8e Analysis shows that compared with the 4th-order FIR low-pass filter, the 4th-order IIR low-pass filter greatly reduces the hand torque signal error, and the delay error is also relatively small.

[0141] Depend on Figure 8g It can be seen that after filtering by the 10th-order IIR low-pass filter, the maximum error of the output low-frequency hand torque value signal is 0.47Nm, and the delay error of the signal before and after processing is 202ms. Figure 8h It can be seen that after filtering by the 10th-order FIR low-pass filter, the maximum error of the output low-frequency hand torque value signal is 0.84Nm, and the delay error of the signal before and after processing is 98ms. Figure 8g and Figure 8h Analysis shows that compared with the 10th-order FIR low-pass filter, the 10th-order IIR low-pass filter greatly reduces the hand torque signal error, but the delay error is too large, resulting in a decrease in the timeliness of hands-off detection.

[0142] From the above analysis, it can be seen that the error and amplitude attenuation 10 times frequency value performance indicators of each order IIR low-pass filter are better than those of the FIR low-pass filter, and the delay error is also smaller. Therefore, this application adopts the IIR low-pass filter.

[0143] Depend on Figure 8c It can be seen that after filtering by the third-order IIR low-pass filter, the maximum error of the output low-frequency hand torque value signal is 0.33Nm, and the delay error of the signal before and after processing is 65ms. Figure 8f It can be seen that after filtering by the 5th-order IIR low-pass filter, the maximum error of the output low-frequency hand torque value signal is 0.05Nm, and the delay error of the signal before and after processing is 85ms. Figure 8b 、 Figure 8c 、 Figure 8d 、 Figure 8f and Figure 8g Analysis shows that compared with the 10th-order FIR low-pass filter, the 10th-order IIR low-pass filter greatly reduces the hand torque signal error, but the delay error is too large, resulting in a decrease in the timeliness of hands-off detection.

[0144] From the above results Figure 8b 、 Figure 8c 、 Figure 8d 、 Figure 8f and Figure 8g It can be seen that while all five designed IIR low-pass filters can filter high-frequency road excitation, each has different filtering effects, affecting low-frequency hand torque values ​​and delays differently. High-frequency road interference is quickly attenuated and filtered out. Analysis shows that the fourth-order IIR low-pass filter minimizes hand torque signal error, the frequency corresponding to a 10-fold amplitude attenuation, and delay after filtering, demonstrating excellent overall performance. This ensures minimal loss of hand torque amplitude in the 0Hz-5Hz low-frequency range and rapid attenuation of hand torque amplitude in the 6Hz-9.8Hz range, ensuring that high-frequency road excitation is filtered out.

[0145] In some embodiments, the process of performing hands-off detection on the driver of the target vehicle based on the filtered hand torque may include: performing hands-off detection on the driver of the target vehicle based on the magnitude relationship between the filtered hand torque and the preset hand torque.

[0146] The preset hand torque indicates the hand torque when the driver of the target vehicle does not release his hand from the steering wheel of the target vehicle, and when the driver of the target vehicle releases his hand from the steering wheel of the target vehicle. The specific hand torque can be adjusted according to actual conditions and is not limited in the present embodiment.

[0147] Specifically, the above-mentioned process of detecting the driver of the target vehicle's hands being out of the steering wheel according to the magnitude relationship between the filtered hand torque and the preset hand torque may include: when the filtered hand torque is greater than the preset hand torque, determining that the driver of the target vehicle's hands have not been out of the steering wheel of the target vehicle; otherwise, determining that the driver of the target vehicle's hands have been out of the steering wheel of the target vehicle.

[0148] Furthermore, the above-mentioned process of detecting the driver of the target vehicle's hands being out of the steering wheel based on the magnitude relationship between the filtered hand torque and the preset hand torque may also include: when the state of the filtered hand torque being greater than the preset hand torque continues for a preset period of time, determining that the driver of the target vehicle's hands have not been out of the steering wheel of the target vehicle; otherwise, determining that the driver of the target vehicle's hands have been out of the steering wheel of the target vehicle.

[0149] Among them, the preset duration can be adjusted according to actual conditions, and the embodiments of this application do not limit it.

[0150] The following combination Figure 9, the hands-off detection method mentioned in this application is explained with a specific embodiment. Torque sensing is performed through the angular torque sensor of the power steering system of the vehicle to obtain an initial hand torque, which includes the vehicle driver's hand torque and / or the environmental interference hand torque generated by the vehicle's environmental interference. The initial hand torque is output to a low-pass filter to perform low-pass filtering on the initial hand torque to obtain a filtered hand torque. Through the auxiliary driving domain controller, based on the size relationship between the filtered hand torque and the preset hand torque, the vehicle driver's hands are detected to be off the steering wheel. When the filtered hand torque is greater than the preset hand torque, it is determined that the vehicle driver's hands have not left the steering wheel of the target vehicle; otherwise, it is determined that the vehicle driver's hands have left the steering wheel of the target vehicle.

[0151] In this way, by filtering the high-frequency ground interference signal in the hand torque signal, the missed detection caused by external interference is reduced, and the hands-off detection accuracy of the torque sensing solution is greatly improved.

[0152] To facilitate better implementation of the hands-off detection method provided in the embodiments of the present application, the embodiments of the present application also provide a device based on the above hands-off detection method. The meanings of the terms herein are the same as those in the above hands-off detection method, and the specific implementation details can be referred to the description in the method embodiment.

[0153] For example, Figure 10 As shown, the hands-off detection device may include a filtering module 201 and a detection module 202, specifically as follows:

[0154] A filtering module 201 is configured to filter the hand torque sensed on the steering wheel of the target vehicle to obtain a filtered hand torque;

[0155] The detection module 202 is configured to perform hands-off detection on the driver of the target vehicle based on the filtered hand torque.

[0156] In some embodiments, the hand torque includes: a hand torque of a driver of the target vehicle, and / or an environmental interference hand torque generated based on environmental interference of the target vehicle.

[0157] In some embodiments, the environmental disturbance includes road surface excitation disturbance of the target vehicle.

[0158] In some embodiments, the frequency in the frequency distribution range corresponding to the environmental interference hand torque is higher than the frequency in the frequency distribution range corresponding to the driver's hand torque.

[0159] In some embodiments, filtering the hand torque sensed on the steering wheel of the target vehicle to obtain the filtered hand torque includes:

[0160] The hand torque sensed from the steering wheel of the target vehicle is subjected to low-pass filtering to obtain a filtered hand torque, so as to attenuate the environmental interference hand torque in the hand torque.

[0161] In some embodiments, the above-mentioned low-pass filtering processing is performed based on a low-pass filter, and the low-pass filter is configured with a filtering frequency threshold. The filtering frequency threshold is determined based on the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range corresponding to the environmental interference hand torque.

[0162] In some embodiments, the above-mentioned filtering frequency threshold is set according to the model of the target vehicle.

[0163] In some embodiments, the frequency distribution range corresponding to the environmental interference hand torque is determined based on the frequency distribution range corresponding to the reference environmental interference hand torque of reference vehicles of various models.

[0164] In some embodiments, the filtering frequency threshold is determined based on the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range of the reference environment interference hand torque corresponding to the model of the target vehicle.

[0165] In some embodiments, the frequency distribution range corresponding to the driver's hand torque includes 0Hz-5Hz, the frequency distribution range corresponding to the environmental interference hand torque includes 7Hz-25Hz, and the filtering frequency threshold includes 6Hz.

[0166] In some embodiments, the above-mentioned low-pass filter includes a low-pass filter of a target type selected from multiple different types of candidate low-pass filters based on the filtering performance information of the candidate low-pass filters on the simulated hand torque, wherein the simulated hand torque includes at least a simulated driver hand torque and a simulated environmental interference hand torque.

[0167] In some embodiments, the filtering performance information includes filtering accuracy and / or filtering processing delay.

[0168] In some embodiments, the candidate low-pass filters are obtained by performing low-pass filter simulation based on the filtering configuration information.

[0169] In some embodiments, the target type low-pass filter comprises an infinite impulse response filter.

[0170] In some embodiments, the IIR filter comprises a 4th-order IIR filter.

[0171] In some embodiments, the above-mentioned hands-off detection of the driver of the target vehicle based on the filtered hand torque includes:

[0172] According to the magnitude relationship between the filtered hand torque and the preset hand torque, the driver of the target vehicle is detected to have taken his hands off the vehicle.

[0173] In some embodiments, the above-mentioned hands-off detection of the driver of the target vehicle based on the magnitude relationship between the filtered hand torque and the preset hand torque includes:

[0174] If the filtered hand torque is greater than the preset hand torque for a preset period of time, it is determined that the driver of the target vehicle has not released his hand from the steering wheel of the target vehicle; otherwise, it is determined that the driver of the target vehicle has released his hand from the steering wheel of the target vehicle.

[0175] As can be seen, the hands-off detection device provided in the embodiment of the present application filters the hand torque sensed by the steering wheel of the target vehicle through filtering module 201 to obtain a filtered hand torque. Detection module 202 then performs hands-off detection on the driver of the target vehicle based on the filtered hand torque. Therefore, by filtering the hand torque sensed by the vehicle's steering wheel, interference from complex and diverse real-world conditions is reduced, and the accuracy of hands-off detection is improved based on the filtered hand torque, thereby ensuring vehicle driving safety.

[0176] During specific implementation, the above modules can be implemented as independent entities, or they can be arbitrarily combined and implemented as the same or several entities. The specific implementation methods and corresponding beneficial effects of the above modules can be found in the previous method embodiments and will not be repeated here.

[0177] The present application also provides a controller, such as Figure 11 , which shows a schematic diagram of the structure of the controller involved in the embodiment of the present application, specifically:

[0178] The controller may include one or more processing core processors 301, one or more storage media memories 302, a power supply 303, an input unit 304 and other components. Those skilled in the art will understand that Figure 11 The controller structure shown in the figure does not constitute a limitation on the controller, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0179] Processor 301 is the controller's control center, connecting all components of the controller using various interfaces and circuits. It executes computer programs and / or modules stored in memory 302 and accesses data stored in memory 302 to perform various controller functions and process data. Optionally, processor 301 may include one or more processing cores. Preferably, processor 301 integrates an application processor and a modem processor. The application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 301.

[0180] The memory 302 can be used to store computer programs and modules. The processor 301 executes various functional applications and hands-off detection by running the computer programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, a computer program required for at least one function (such as an audio and light prompt function, a hands-off detection function, etc.), etc.; the data storage area may store data created according to the use of the controller, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0181] The controller also includes a power supply 303 for supplying power to various components. Preferably, the power supply 303 can be logically connected to the processor 301 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 303 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0182] The controller may further include an input unit 304, which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0183] Although not shown, the controller may further include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 301 in the controller will load the executable files corresponding to one or more computer program processes into the memory 302 according to the following instructions, and the processor 301 will run the computer programs stored in the memory 302 to implement various functions, such as:

[0184] Filtering the hand torque sensed from the steering wheel of the target vehicle to obtain a filtered hand torque;

[0185] Based on the filtered hand torque, the driver of the target vehicle is detected to have hands-off behavior.

[0186] As can be seen, the controller provided in the embodiments of the present application filters the hand torque sensed on the steering wheel of a target vehicle to obtain a filtered hand torque; based on the filtered hand torque, it performs hands-off detection on the driver of the target vehicle. Therefore, by filtering the hand torque sensed on the vehicle's steering wheel, interference from complex and diverse real-world conditions is reduced, and the accuracy of hands-off detection based on the filtered hand torque is improved, thereby ensuring vehicle driving safety.

[0187] The specific implementation methods and corresponding beneficial effects of the above operations can be found in the detailed description of the hands-off detection method above, which will not be elaborated here.

[0188] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by a computer program, or by controlling related hardware through a computer program. The computer program may be stored in a storage medium and loaded and executed by a processor.

[0189] To this end, an embodiment of the present application provides a storage medium storing a computer program that can be loaded by a processor to execute the steps of any of the hands-off detection methods provided in the embodiments of the present application. For example, the computer program can execute the following steps:

[0190] Filtering the hand torque sensed from the steering wheel of the target vehicle to obtain a filtered hand torque;

[0191] Based on the filtered hand torque, the driver of the target vehicle is detected to have hands-off behavior.

[0192] As can be seen, the storage medium provided in the embodiments of the present application filters the hand torque sensed on the steering wheel of a target vehicle to obtain a filtered hand torque; based on the filtered hand torque, hands-off detection is performed on the driver of the target vehicle. Based on this, by filtering the hand torque sensed on the vehicle's steering wheel, interference from complex and diverse actual conditions is reduced, and the accuracy of hands-off detection is improved based on the filtered hand torque, thereby ensuring vehicle driving safety.

[0193] The specific implementation methods and corresponding beneficial effects of the above operations can be found in the previous embodiments and will not be described in detail here.

[0194] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0195] Since the computer program stored in the storage medium can execute the steps of any of the hands-off detection methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the hands-off detection methods provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0196] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a storage medium. A processor of a computer device reads the computer instructions from the storage medium and executes the computer instructions, causing the computer device to perform the above-described hands-off detection method.

[0197] An embodiment of the present application further provides a vehicle, which includes the above-mentioned hands-off detection device, or the above-mentioned controller, or the above-mentioned computer program product.

[0198] Exemplarily, the vehicle includes the aforementioned controller, which filters the hand torque sensed on the steering wheel of a target vehicle to obtain a filtered hand torque. Hands-off detection is then performed on the driver of the target vehicle based on the filtered hand torque. By filtering the hand torque sensed on the vehicle's steering wheel, interference from complex and diverse real-world conditions is reduced, and the accuracy of hands-off detection is improved based on the filtered hand torque, thereby ensuring vehicle driving safety.

[0199] The specific structure of the vehicle is not limited in this application. The specific implementation methods and corresponding beneficial effects of the above-mentioned operations of the control device are also applicable to the vehicle. For details, please refer to the detailed description of the hands-off detection method above, which will not be repeated here.

[0200] The above is a detailed introduction to a hands-off detection method, device, controller, storage medium, computer program product and vehicle provided in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A hands-off detection method, characterized in that: The method comprises: Filtering the hand torque sensed from the steering wheel of the target vehicle to obtain a filtered hand torque; Based on the filtered hand torque, a hands-off detection is performed on the driver of the target vehicle.

2. The hands-off detection method according to claim 1, wherein: The hand torque includes: a hand torque of a driver of the target vehicle, and / or an environmental interference hand torque generated based on environmental interference of the target vehicle.

3. The hands-off detection method according to claim 2, wherein: The environmental disturbance includes road surface excitation disturbance of the target vehicle.

4. The hands-off detection method according to claim 2, wherein: The frequency in the frequency distribution range corresponding to the environmental interference hand torque is higher than the frequency in the frequency distribution range corresponding to the driver's hand torque.

5. The hands-off detection method according to claim 4, characterized in that: The filtering process of the hand torque sensed from the steering wheel of the target vehicle to obtain the filtered hand torque includes: Low-pass filtering is performed on the hand torque sensed by the steering wheel of the target vehicle to obtain the filtered hand torque, so as to attenuate the environmental interference hand torque in the hand torque.

6. The hands-off detection method according to claim 5, characterized in that: The low-pass filtering processing is performed based on a low-pass filter, and the low-pass filter is configured with a filtering frequency threshold. The filtering frequency threshold is determined based on the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range corresponding to the environmental interference hand torque.

7. The hands-off detection method according to claim 6, wherein: The filtering frequency threshold is set according to the model of the target vehicle.

8. The hands-off detection method according to claim 7, wherein: The frequency distribution range corresponding to the environmental interference hand torque is determined based on the frequency distribution ranges corresponding to the reference environmental interference hand torques of reference vehicles of various models.

9. The hands-off detection method according to claim 8, characterized in that: The filtering frequency threshold is determined based on the highest frequency in the frequency distribution range corresponding to the driver's hand torque and the lowest frequency in the frequency distribution range of the reference environment interference hand torque corresponding to the model of the target vehicle.

10. The hands-off detection method according to claim 6, wherein: The frequency distribution range corresponding to the driver's hand torque includes 0Hz-5Hz, the frequency distribution range corresponding to the environmental interference hand torque includes 7Hz-25Hz, and the filtering frequency threshold includes 6Hz.

11. The hands-off detection method according to claim 6, wherein: The low-pass filter includes a low-pass filter of a target type selected from a plurality of different types of candidate low-pass filters based on filtering performance information of the candidate low-pass filters on simulated hand torque, wherein the simulated hand torque includes at least a simulated driver hand torque and a simulated environmental interference hand torque.

12. The hands-off detection method according to claim 11, wherein: The filtering performance information includes filtering accuracy and / or filtering processing delay.

13. The hands-off detection method according to claim 11, wherein: The candidate low-pass filters are obtained by performing low-pass filter simulation based on the filter configuration information.

14. The hands-off detection method according to claim 11, wherein: The target type of low-pass filter includes an infinite impulse response filter.

15. The hands-off detection method according to claim 14, characterized in that: The infinite impulse response filter includes a 4th-order infinite impulse response filter.

16. The hands-off detection method according to any one of claims 1 to 15, characterized in that: The performing hands-off detection on the driver of the target vehicle based on the filtered hand torque includes: According to the magnitude relationship between the filtered hand torque and the preset hand torque, a hands-off detection is performed on the driver of the target vehicle.

17. The hands-off detection method according to claim 16, wherein: The method of performing hands-off detection on the driver of the target vehicle according to the magnitude relationship between the filtered hand torque and the preset hand torque includes: When the state in which the filtered hand torque is greater than the preset hand torque continues for a preset time period, it is determined that the driver of the target vehicle has not detached his hand from the steering wheel of the target vehicle; otherwise, it is determined that the driver of the target vehicle has detached his hand from the steering wheel of the target vehicle.

18. A controller, characterized in that: The device comprises one or more processors and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the hands-off detection method according to any one of claims 1 to 17.

19. A storage medium, characterized in that The invention comprises a computer program, and when the computer program is run on a controller, the computer program is used to make the controller perform the steps of the hands-off detection method according to any one of claims 1 to 17.

20. A computer program product, characterized in that The method comprises a computer program or instructions, which implements the steps of the hands-off detection method according to any one of claims 1 to 17 when the computer program or instructions are executed by a processor.

21. A vehicle, characterized in that the vehicle comprises the controller according to claim 18.

Images