Hand release detection method and device, electronic equipment and computer program product

Abstract

The invention is suitable for the technical field of automobiles, and provides a hand release detection method and device and electronic equipment, and the method comprises the steps: obtaining a first torque sequence; the first torque sequence comprises a torque signal of a steering wheel in a preset time period; according to the first torque sequence, sequence characteristic parameters are extracted, and the sequence characteristic parameters comprise a power spectrum density estimation result of the first torque sequence; the hand release detection is performed according to the sequence characteristic parameters, whether the driver releases the hand or not is judged based on the power spectrum density estimation result of the torque signal of the steering wheel, and the accuracy of the hand release detection is improved under the conditions that the internal structure of the vehicle is not changed and the implementation cost is not increased.

Description

Technical Field

[0001] This application belongs to the field of automotive technology, and in particular relates to a method, device, electronic equipment, and computer program product for detecting hands-free operation. Background Technology

[0002] Advanced Driving Assistance Systems (ADAS) are designed to assist drivers in operating vehicles. Utilizing sensors, cameras, and computer systems, they enable functions such as road recognition, pedestrian recognition, obstacle recognition, autonomous driving, and automatic parking. To enhance driving safety and ensure the driver can take over the vehicle promptly in emergency situations, the driver's hands must remain on the steering wheel during operation. Therefore, some ADAS systems need to monitor whether the driver's hands are off the wheel and, if so, remind the driver to return them.

[0003] Currently, solutions using capacitive steering wheel detection and vision systems to detect whether the driver has taken their hands off the wheel are too costly to be widely adopted. On the other hand, solutions that only detect whether the steering wheel torque exceeds a preset threshold have the problem of low detection accuracy. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method, apparatus, and electronic device for detecting hands-free driving, which effectively improves the accuracy of detecting when a driver's hands are off the wheel.

[0005] In a first aspect, embodiments of this application provide a method for detecting hand loss, including:

[0006] Obtain the first torque sequence; the first torque sequence includes the torque signal of the steering wheel within a preset time period;

[0007] Sequence feature parameters are extracted based on the first torque sequence, wherein the sequence feature parameters include the power spectral density estimation result of the first torque sequence;

[0008] Hand-drop detection is performed based on sequence feature parameters.

[0009] In this embodiment, the torque signal of the steering wheel within a preset time period is acquired, and the power spectral density estimation result of the torque signal of the steering wheel within the preset time period is calculated. Based on the power spectral density estimation result of the torque signal of the steering wheel, it is determined whether the driver has taken his hands off the wheel, thereby improving the accuracy of hands-off detection without changing the internal structure of the vehicle or increasing the implementation cost.

[0010] In some embodiments, when calibrating the power spectral density threshold, different road condition scenarios can be distinguished to determine the power spectral density threshold corresponding to the road condition.

[0011] In one alternative implementation of the first aspect, the sequence feature parameters include a maximum power spectral density value, and the sequence feature parameters are extracted based on the first torque sequence, including:

[0012] The power spectral density of the first torque sequence is calculated to obtain the power spectral density estimation result of the first torque sequence;

[0013] The maximum power spectral density value is obtained based on the power spectral density estimation result of the first torque sequence.

[0014] In this embodiment, the maximum power spectral density of the first torque sequence is compared with a calibrated first power spectral density threshold. Using the maximum power spectral density for release detection can effectively improve the accuracy of release detection.

[0015] In one implementation of the first aspect, the sequence feature parameters include the maximum power spectral density value, and the sequence feature parameters are extracted based on the first torque sequence, including:

[0016] The first torque sequence is subjected to mean-reduction processing to obtain the second torque sequence;

[0017] The power spectral density of the second torque sequence is calculated to obtain the power spectral density estimation result of the second torque sequence;

[0018] The maximum power spectral density is obtained based on the power spectral density estimation results of the second torque sequence.

[0019] In this embodiment, by performing de-averaging on the torque signal output from the steering wheel, and then using the torque sequence obtained after de-averaging for power spectral density estimation, the data deviation caused by mechanical installation and sensor zeroing in the original signal can be effectively removed. At the same time, the DC component of the power spectral density can also be removed, resulting in a more accurate power spectral density estimation result at low frequencies, thereby improving the accuracy of hands-off detection.

[0020] In one implementation of the first aspect, off-hand detection is performed based on sequence feature parameters, including:

[0021] Compare the maximum power spectral density with the power spectral density threshold;

[0022] If the maximum power spectral density is not less than the power spectral density threshold, it is determined that the driver has not let go of the hands.

[0023] In one implementation of the first aspect, the sequence feature parameters also include the sequence standard deviation, and off-hand detection is performed based on the sequence feature parameters, including:

[0024] Compare the standard deviation of the sequence with the standard deviation threshold;

[0025] If the standard deviation of the sequence is less than the standard deviation threshold, it is determined that the driver has disengaged the vehicle.

[0026] If the standard deviation of the sequence is not less than the standard deviation threshold, it is determined that the driver has not let go of the hands.

[0027] In this embodiment of the application, the accuracy of hand-drop detection is further improved by using the sequence standard deviation.

[0028] In one implementation of the first aspect, the method further includes: calibrating a power spectral density threshold based on a first sample torque sequence and a second sample torque sequence, wherein the first sample torque sequence is the torque signal of the steering wheel when the driver has taken his hands off the wheel, and the second sample torque sequence is the torque signal of the steering wheel when the driver has not taken his hands off the wheel.

[0029] In this embodiment, the power spectral density threshold is determined by calibration, and then the calibrated power spectral density threshold is compared with the sequence characteristic parameters of the first torque sequence. This can adapt to the performance differences between the sensor and the vehicle, thereby improving the accuracy of hands-off detection.

[0030] In one implementation of the first aspect, the method further includes:

[0031] The first sample torque sequence is subjected to mean-reduction processing to obtain the third sample torque sequence;

[0032] The second sample torque sequence is subjected to mean-reduction processing to obtain the fourth sample torque sequence;

[0033] The power spectral density threshold is calibrated based on the third and fourth sample torque sequences.

[0034] In this embodiment, the power spectral density threshold can be calibrated based on the mean-reduced sample torque sequence, which can improve the reliability of the calibrated power spectral density threshold.

[0035] In one implementation of the first aspect, the method further includes:

[0036] The standard deviation threshold is calibrated based on the first sample torque sequence and the fifth sample torque sequence. The first sample torque sequence is the torque signal of the steering wheel when the driver takes his hands off the wheel, and the fifth sample torque sequence is the torque signal of the steering wheel when the driver does not take his hands off the wheel and there is no hand force output.

[0037] In this embodiment, the standard deviation threshold is determined by calibration, and then compared with the sequence characteristic parameters of the first torque sequence based on the calibrated standard deviation threshold. This can adapt to the performance differences between the sensor and the vehicle, thereby improving the accuracy of hands-off detection.

[0038] Secondly, embodiments of this application provide a hand-drop detection device, which includes:

[0039] The sequence acquisition module is used to acquire a first torque sequence; the first torque sequence includes the torque signal of the steering wheel within a preset time period;

[0040] The feature extraction module is used to extract sequence feature parameters based on the first torque sequence, wherein the sequence feature parameters include the power spectral density estimation result of the first torque sequence;

[0041] The detection module is used to perform hand removal detection based on sequence feature parameters.

[0042] Thirdly, an electronic device is provided, including a processor for executing a computer program stored in a memory to implement the method described in the first aspect above.

[0043] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0044] Fifthly, a chip is provided, the chip including a processor and a memory coupled thereto, the processor executing a computer program or instructions stored in the memory to implement the method as described in the first aspect above.

[0045] In a sixth aspect, a computer program product is provided that, when the computer program product is run on an electronic device, causes the electronic device to perform the method described in the first aspect above.

[0046] It is understood that the beneficial effects of the second to sixth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1This is a schematic diagram of the structure of an advanced driver assistance system;

[0049] Figure 2 A schematic diagram illustrating the implementation flow of the hand-removal detection method provided in the embodiments of this application;

[0050] Figure 3 This is a schematic diagram of the structure of an advanced driver assistance system provided in an embodiment of this application;

[0051] Figure 4 A schematic diagram of a power spectral density estimation result provided in an embodiment of this application;

[0052] Figure 5 This is a schematic diagram illustrating another power spectral density estimation result provided in an embodiment of this application;

[0053] Figure 6 A schematic diagram illustrating the implementation process of another hand-release detection method provided in this application embodiment;

[0054] Figure 7 A schematic diagram illustrating the implementation process of another hand-release detection method provided in this application embodiment;

[0055] Figure 8 This is a schematic diagram of the structure of a hand-drop detection device provided in an embodiment of this application;

[0056] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0057] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0058] It should be noted that, unless otherwise specified, all technical terms used in the embodiments of this application have the same meaning as commonly understood by those skilled in the art to which this application belongs. The technical terms used in the embodiments of this application are only used to explain specific embodiments of this application and are not intended to limit this application.

[0059] In the description of the embodiments of this application, the technical terms "comprising," "including," "having," and any variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0060] In the description of the embodiments of this application, unless otherwise stated, the technical term "multiple" means two or more, and the technical terms "at least one" and "one or more" mean one, two or more.

[0061] Technical terms such as “first” and “second” are used only to distinguish different objects and should not be interpreted as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features.

[0062] The technical term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / " in this text generally indicates that the preceding and following related objects have an "or" relationship.

[0063] The term "embodiment" as used in the description of embodiments in this application means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0064] Advanced Driving Assistance Systems (ADAS) are designed to assist drivers in operating vehicles. Utilizing sensors, cameras, and computer systems, they enable functions such as road recognition, pedestrian recognition, obstacle recognition, autonomous driving, and automatic parking. To improve driving safety and enable drivers to take over the vehicle promptly in emergency situations, the driver's hands must remain on the steering wheel during the operation of these driver assistance functions and cannot be removed for extended periods. Therefore, some ADAS systems monitor whether the driver has taken their hands off the steering wheel and, if so, remind the driver to return their hands to the wheel.

[0065] Figure 1 A schematic diagram of the structure of the advanced driver assistance system involved in the embodiments of this application is shown, such as... Figure 1 As shown, the aforementioned advanced driver assistance system may include a detection module, a communication module, and a control module.

[0066] The detection module can use sensors, positioning systems such as GPS, CCD cameras and other devices to collect vehicle data, including vehicle position, speed, distance from other vehicles and so on.

[0067] The communication module enables mobile ad hoc networks formed by the interaction of wireless terminals mounted on the vehicle, without the need for other wired or wireless network support. Of course, other wireless networks can also be used for communication. Mobile ad hoc networks have routing capabilities; using corresponding communication protocols, mobile nodes can discover and maintain routes to other nodes. Data from advanced driver assistance systems can be transmitted via mobile ad hoc networks.

[0068] The control module can specifically be the vehicle controller, which collects vehicle data through a mobile Ad Hoc network and analyzes and processes the obtained vehicle data.

[0069] Among them, the vehicle controller is the core of vehicle control. It can determine the current state of the car based on the input signals (i.e., the signals detected by the detection module), and realize the control of the whole vehicle through certain control logic and control algorithm.

[0070] The vehicle controller can control the vehicle's direction of travel based on the steering torque detected by the steering wheel torque sensor, and also use this value to detect whether the driver has taken their hands off the wheel.

[0071] Current hands-off detection solutions typically use a torque sensor within the steering wheel to detect the steering torque over a period of time and compare it to a set threshold to determine if the hands have been removed. For example, a torque sensor can be installed on the steering column. When the driver rotates the steering wheel, the torque sensor generates a measurement. By detecting whether the detected steering torque is below a set threshold for a certain period, the system can determine if the driver's hands are on the steering wheel. However, due to road surface excitation and steering system friction, false positives and false negatives can occur, resulting in low accuracy in hands-off detection and impacting driving safety and experience. To reduce false positives, a longer time threshold can be set, but this reduces real-time performance and also affects driving safety.

[0072] To improve the accuracy of hands-off detection, capacitive or pressure-sensitive touch sensors can be integrated into the steering wheel to detect whether the driver's hands are on it. Alternatively, a vision system such as a camera can be deployed in the cockpit to acquire images of the driver's hands and the steering wheel, and the image detection results can be used to determine whether the driver's hands are on the steering wheel. These methods require additional components, increasing the cost of hands-off detection and hindering its widespread adoption.

[0073] Therefore, it is urgent to solve the problem of how to improve the accuracy of hands-free detection based on existing vehicle components without changing the vehicle's internal structure or increasing implementation costs.

[0074] Based on this, embodiments of this application provide a method, device control equipment, and vehicle for detecting hands-off driving. By acquiring the torque signal of the steering wheel within a preset time period and calculating the power spectral density estimation result of the steering wheel torque signal within the preset time period, the method determines whether the driver has taken their hands off the steering wheel based on the power spectral density estimation result of the steering wheel torque signal. This improves the accuracy of hands-off detection without changing the internal structure of the vehicle or increasing implementation costs.

[0075] The following will describe in detail the hands-free detection method, apparatus, and vehicle control device provided in the embodiments of this application, with reference to the accompanying drawings:

[0076] Please see Figure 2 , Figure 2 The specific implementation flow of the hand-removal detection method provided in the embodiments of this application is given, such as... Figure 2 As shown, the method for detecting hand loss provided in this application embodiment may specifically include the following steps:

[0077] It should be noted that the execution entity of the hands-free detection method provided in this application embodiment can specifically be a control device equipped with an advanced driver assistance system, such as... Figure 1 In the embodiments of this application, the vehicle controller, etc., are as follows: Figure 3 As shown, the vehicle controller may include a hands-free detection module, which can be used to execute the hands-free detection method provided in the embodiments of this application.

[0078] In S101, the first torque sequence is obtained.

[0079] Here, the aforementioned first torque sequence refers to the torque signal of the steering wheel within a preset time period.

[0080] In practical applications, the torque signal of the steering wheel can be acquired by a torque sensor installed in the steering wheel. Specifically, the torque signal of the steering wheel can be acquired by a torque sensor installed on the steering column tube of the steering wheel.

[0081] Understandably, the torque sensor on the steering wheel has been calibrated before actual use. When the driver does not input torque, that is, when the driver does not turn the steering wheel, the reading of the torque sensor on the steering wheel will be less than the measurement accuracy.

[0082] The torque sensor mentioned above can be selected with a measurement accuracy of not less than 0.05 Nm.

[0083] In practical applications, the torque sensor periodically collects torque signals from the steering wheel and constructs a first torque sequence based on the collection time sequence of the torque signals collected periodically within a preset time period. That is, a first-in-first-out construction method is used to record the torque signals collected by the torque sensor.

[0084] It should be noted that the shorter the acquisition period of the torque sensor, the better the acquired torque signal reflects the steering wheel's twisting behavior. In some embodiments, the acquisition period of the torque sensor can be set to 20ms, meaning that the torque sensor will acquire the steering wheel's torque signal every 20ms.

[0085] Understandably, the measurement accuracy and acquisition cycle of the torque sensor can be selected according to the actual application requirements.

[0086] In practical applications, the duration of the preset time period can also be set according to actual application needs. The duration of the preset time period is affected by the measurement accuracy and acquisition cycle of the torque sensor. In practical applications, the duration of the preset time period can be determined through test calibration.

[0087] For example, in order to improve the resolution of power spectrum estimation and reduce false positives, the shortest duration of the preset time period can be set to 5 seconds, and in order to improve the real-time performance of detection, the longest duration of the preset time period can be set to 15 seconds.

[0088] Taking a preset time period of 10 seconds and a collection period of 20 ms as an example, the first torque sequence records the torque signal detected by the torque sensor every 20 ms interval within these 10 seconds, according to the collection time sequence.

[0089] In S102, sequence feature parameters are extracted based on the first torque sequence.

[0090] Here, the aforementioned sequence characteristic parameters include the power spectral density estimation results of the first torque sequence.

[0091] In practical applications, the above power spectral density estimation results are used to characterize the frequency characteristics of the first torque sequence.

[0092] It should be noted that power spectral density (PSD) is a density function used to describe the distribution of signal power in the frequency domain.

[0093] By extracting the power spectral density estimation result of the first torque sequence, the time-domain and frequency-domain variation characteristics of the steering wheel torque signal can be characterized. Since the driver's hands being on the steering wheel and not on the steering wheel have different effects on the time-domain and frequency-domain characteristics of the steering wheel torque signal, this embodiment can use the power spectral density estimation result of the first torque sequence as a sequence feature parameter. The aforementioned power spectral density estimation result may include, but is not limited to, the mean or maximum power spectral density.

[0094] It is understandable that the sequence characteristic parameters of the first torque sequence mentioned above can also be the sequence standard deviation, sequence mean, etc.

[0095] In S103, hand-drop detection is performed based on sequence feature parameters.

[0096] In practical applications, the extracted sequence feature parameters are compared with the calibrated feature parameter thresholds to determine whether the driver has let go of the hands, thus achieving hands-free detection.

[0097] As can be seen from the above, the embodiments of this application obtain the torque signal of the steering wheel within a preset time period and calculate the power spectral density estimation result of the torque signal of the steering wheel within the preset time period. Based on the power spectral density estimation result of the torque signal of the steering wheel, it determines whether the driver has taken his hands off the wheel, thereby improving the accuracy of hands-off detection without changing the internal structure of the vehicle or increasing the implementation cost.

[0098] Since sensor performance differs from that of the vehicle as a whole, calibration can be used to determine the threshold values ​​of characteristic parameters in order to improve detection accuracy.

[0099] In some embodiments, the steering wheel torque signal when the driver's hands are off and the steering wheel torque signal when the hands are on are recorded. Then, the power spectral density of the first sample torque sequence formed by the steering wheel torque signal when the hands are off is calculated, and the power spectral density of the second sample torque sequence formed by the steering wheel torque signal when the hands are on is calculated. Thus, the power spectral density of the first sample torque sequence when the hands are off and the power spectral density of the second sample torque sequence when the hands are on are obtained. Through comparison and analysis, the power spectral density threshold corresponding to the maximum power spectral density and the power spectral density threshold corresponding to the average power spectral density are determined.

[0100] In some embodiments, when calibrating the power spectral density threshold, different road condition scenarios can be distinguished to determine the power spectral density threshold corresponding to the road condition.

[0101] For example, sample torque sequences can be collected under high-speed road driving conditions, non-high-speed road driving conditions, urban road driving conditions and non-urban road driving conditions, uphill driving conditions, and high-traffic congestion conditions.

[0102] Then, based on the sample torque sequences collected under various road conditions, the power spectral density threshold of the road condition is calibrated. When performing hands-free detection, the power spectral density threshold corresponding to the current road condition can be obtained based on the road condition scenario.

[0103] It should be noted that the above road conditions are merely examples and not limitations.

[0104] The aforementioned characteristic parameter thresholds are determined by calibration. Then, the calibrated characteristic parameter thresholds are compared with the sequence characteristic parameters of the first torque sequence. For example, the maximum power spectral density of the first torque sequence is compared with the aforementioned first power spectral density threshold. If the maximum power spectral density of the first torque sequence is not less than the first power spectral density threshold, it can be confirmed that the driver has not let go of the hands. If the maximum power spectral density of the first torque sequence is less than the first power spectral density threshold, it can be confirmed that the driver has let go of the hands.

[0105] As can be seen above, by determining the power spectral density threshold through calibration, and then comparing the calibrated power spectral density threshold with the sequence characteristic parameters of the first torque sequence, it is possible to adapt to the performance differences between the sensor and the vehicle, thereby improving the accuracy of hands-off detection.

[0106] In one embodiment of this application, after obtaining the first sample torque sequence and the second sample torque sequence, the first sample torque sequence and the second sample torque sequence can be de-meaned, and then the power spectrum density threshold can be calibrated based on the power spectrum density estimation result after de-meaning.

[0107] Calibrling the power spectral density threshold based on the mean-reduced sample torque sequence can improve the reliability of the calibrated power spectral density threshold.

[0108] In one embodiment of this application, the sequence feature parameters may include the maximum power spectral density, and the extraction of sequence feature parameters based on the first torque sequence includes:

[0109] The power spectral density of the first torque sequence is calculated to obtain the power spectral density estimation result of the first torque sequence;

[0110] The maximum power spectral density value is obtained based on the power spectral density estimation results.

[0111] In this embodiment of the application, the power spectral density of the first torque sequence can be calculated based on formula (1):

[0112] PSD1(ω)=|X1(ω)|^2 / T(1);

[0113] Wherein, PSD1(ω) represents the power spectral density function of the first torque sequence (i.e., the power spectral density estimation result mentioned above), X1(ω) represents the Fourier transform of the first torque sequence, and T is the period of the first torque sequence (i.e., the preset time period mentioned above).

[0114] After obtaining the power spectral density estimation result of the first torque sequence, the maximum power spectral density can be obtained, specifically the maximum power spectral density within a preset frequency range.

[0115] It should be noted that the above preset frequency range can be set according to actual application requirements, for example, it can be set to 0-5Hz.

[0116] It is understandable that there are two possible reasons why the driver did not release the hands:

[0117] Scenario 1: The driver lightly grips the steering wheel. At this time, the first torque sequence output by the torque sensor of the steering wheel is an approximately stationary signal, and its power spectral density estimation result is as follows: Figure 4 As shown.

[0118] Scenario 2: The driver places their hands on the steering wheel and applies significant force. The first torque sequence of the steering wheel is a non-stationary signal, and its power spectral density estimation result is as follows: Figure 5 As shown.

[0119] Depend on Figure 4 and Figure 5 It can be seen that when the driver does not release the steering wheel and there is a significant force output, a force will be exerted on the steering wheel. The power spectrum density estimation result has a low-frequency characteristic frequency. The power spectrum density value of this low-frequency characteristic frequency is relatively large. Therefore, by calculating the power spectrum density of the first torque sequence and obtaining the maximum power spectrum density, a basis can be provided for subsequent hands-free detection.

[0120] When the driver takes their hands off the steering wheel, the first torque sequence output by the torque sensor is closer to the calibration value, which is also a near-stable signal.

[0121] In this embodiment, the maximum power spectral density of the first torque sequence can be compared with a calibrated first power spectral density threshold. If the maximum power spectral density of the first torque sequence is not less than the first power spectral density threshold, it can be determined that the driver has not let go of the hands. Using the maximum power spectral density for hands-free detection can effectively improve the accuracy of hands-free detection.

[0122] In another embodiment of this application, please refer to Figure 6 , Figure 6 This illustration shows a schematic diagram of the implementation flow of a hand-drop detection method provided in an embodiment of this application. For example... Figure 6 As shown in the embodiments of this application, the above-mentioned method for detecting hand loss includes the following steps:

[0123] In S601, the first torque sequence is obtained.

[0124] Please refer to the description of S101 for the process of S601, which will not be repeated here.

[0125] In S602, the first torque sequence is de-meaned to obtain the second torque sequence.

[0126] Here, de-meaning refers to subtracting the arithmetic mean of the first torque sequence from each torque signal in the first torque sequence.

[0127] In practical applications, after obtaining the first torque sequence, the arithmetic mean of the first torque sequence is calculated, and then the arithmetic mean is subtracted from each torque signal in the first torque sequence to obtain the second torque sequence mentioned above.

[0128] Understandably, when the driver takes their hands off the wheel, due to the randomness of road excitation, the torque signal of the steering wheel collected by the torque sensor is approximately a stable signal, and its arithmetic mean is a time-independent constant. By using the de-meaning method, the data deviation caused by mechanical installation and sensor zeroing in the original signal can be effectively removed. At the same time, the DC component of the power spectral density can also be removed, resulting in a more accurate power spectral density estimation result at low frequencies.

[0129] In S603, the power spectral density of the second torque sequence is calculated to obtain the power spectral density estimation result of the second torque sequence.

[0130] In practical applications, after obtaining the second torque sequence, the power spectral density of the second torque sequence can be calculated based on formula (2):

[0131] PSD2(ω)=|X2(ω)|^2 / T(2);

[0132] Where PSD2(ω) represents the power spectral density function of the second torque sequence (i.e., the power spectral density estimation result mentioned above), X1(ω) represents the Fourier transform of the second torque sequence, and T is the period of the second torque sequence.

[0133] It is understandable that the period of the second torque sequence is the same as the period of the first torque sequence.

[0134] In S604, the maximum power spectral density is obtained based on the power spectral density estimation result of the second torque sequence.

[0135] In S605, based on the comparison result between the maximum power spectral density and the second power spectral density threshold, it is determined whether the driver has let go of the hands.

[0136] In practical applications, if the maximum power spectral density is not less than the second power spectral density threshold, it is determined that the driver has not let go of the hands.

[0137] In practical applications, the aforementioned second power spectral density threshold is also obtained through calibration. This is achieved by recording the steering wheel torque signals when the driver's hands are off and when the hands are still on the steering wheel. Then, the first sample torque sequence formed by the steering wheel torque signal when the hands are off is de-meaned to obtain a third sample torque sequence. The second sample torque sequence formed by the steering wheel torque signal when the hands are still on the steering wheel is also de-meaned to obtain a fourth sample torque sequence. Power spectral density calculations are then performed on both the third and fourth sample torque sequences to obtain the power spectral density of the third sample torque sequence when the hands are off and the power spectral density of the fourth sample torque sequence when the hands are still on the steering wheel. Through comparative analysis, the power spectral density threshold corresponding to the maximum power spectral density is calibrated; this is the aforementioned second power spectral density threshold.

[0138] Then, the maximum power spectral density obtained from the second torque sequence is compared with the second power spectral density threshold. If the maximum power spectral density of the second torque sequence is not less than the second power spectral density threshold, it can be determined that the driver has not let go of the hands.

[0139] As can be seen from the above, the embodiments of this application perform de-averaging processing on the torque signal output by the steering wheel, and then use the torque sequence obtained after de-averaging to estimate the power spectrum density. This can effectively remove the data deviation caused by mechanical installation and sensor zeroing in the original signal, and also remove the DC component of the power spectrum density, so as to obtain a more accurate power spectrum density estimation result at low frequency, thereby improving the accuracy of hands-off detection.

[0140] In one embodiment of this application, the aforementioned sequence characteristic parameters further include the sequence standard deviation of the first torque sequence, such as... Figure 7 As shown, the above S103 may specifically include:

[0141] S1031: Compare the maximum power spectral density with the power spectral density threshold;

[0142] S1032: If the maximum power spectral density is not less than the power spectral density threshold, it is determined that the driver has not let go of the hands;

[0143] S1033: When the maximum power spectral density is less than the power spectral density threshold, compare the sequence standard deviation of the first torque sequence with the standard deviation threshold.

[0144] S1034: If the standard deviation of the first torque sequence is less than the standard deviation threshold, determine that the driver has disengaged the vehicle;

[0145] S1035: If the standard deviation of the first torque sequence is not less than the standard deviation threshold, it is determined that the driver has not released the hands.

[0146] Here, the aforementioned standard deviation threshold can also be determined through calibration. Due to the different performance of the sensor and the vehicle, in order to improve the accuracy of hands-off detection, the standard deviation threshold is determined through calibration, and then the calibrated standard deviation threshold is used to detect whether the driver has taken their hands off the vehicle.

[0147] In some embodiments, by recording the steering wheel torque signal when the driver has not released the steering wheel and there is no hand force output, and the steering wheel torque signal when the driver has released the steering wheel, the sequence standard deviation of the fifth sample torque sequence corresponding to the steering wheel torque signal when the driver has not released the steering wheel and there is no hand force output is calculated, and the sequence standard deviation of the first sample torque sequence corresponding to the steering wheel torque signal when the driver has released the steering wheel is calculated. Through comparative analysis, the standard deviation threshold is calibrated.

[0148] In some embodiments, when calibrating the standard deviation threshold, different road condition scenarios can be distinguished to determine the standard deviation threshold corresponding to the road condition.

[0149] For example, sample torque sequences can be collected under high-speed road driving conditions, non-high-speed road driving conditions, urban road driving conditions and non-urban road driving conditions, uphill driving conditions, and high-traffic congestion conditions.

[0150] Then, based on the sample torque sequences collected under various road conditions, the standard deviation threshold of the road condition is calibrated. When performing hands-free detection, the standard deviation threshold corresponding to the current road condition can be obtained based on the road condition scenario.

[0151] It should be noted that the above road conditions are merely examples and not limitations.

[0152] In this embodiment of the application, the accuracy of hand-drop detection is further improved by using the sequence standard deviation.

[0153] It is understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0154] Based on the hand-drop detection method provided in the above embodiments, this application further provides embodiments of a hand-drop detection device that implements the above method embodiments. Please refer to... Figure 8 This is a schematic diagram of a control device provided in an embodiment of this application. For ease of explanation, only the parts relevant to this embodiment are shown. Figure 8 As shown, the hand-drop detection device 80 may include: a sequence acquisition module 801, a feature extraction module 802, and a detection module 803. Wherein:

[0155] The sequence acquisition module 801 is used to acquire a first torque sequence; the first torque sequence includes the torque signal of the steering wheel within a preset time period.

[0156] The feature extraction module 802 is used to extract sequence feature parameters based on the first torque sequence, wherein the sequence feature parameters include the power spectral density estimation result of the first torque sequence;

[0157] The detection module 803 is used to perform hand removal detection based on sequence feature parameters.

[0158] In some implementations, the aforementioned sequence feature parameters include the maximum power spectral density value. The aforementioned feature extraction module 802 is specifically used to calculate the power spectral density of the first torque sequence to obtain the power spectral density estimation result of the first torque sequence; and to obtain the maximum power spectral density value based on the power spectral density estimation result of the first torque sequence.

[0159] In some implementations, the sequence feature parameters include the maximum power spectral density value. Specifically, the feature extraction module 802 is used to perform mean-reduction processing on the first torque sequence to obtain the second torque sequence; to calculate the power spectral density of the second torque sequence to obtain the power spectral density estimation result of the second torque sequence; and to obtain the maximum power spectral density based on the power spectral density estimation result of the second torque sequence.

[0160] In some implementations, the detection module 803 is specifically used to compare the maximum power spectral density with a power spectral density threshold; if the maximum power spectral density is not less than the power spectral density threshold, it is determined that the driver has not let go of the hands.

[0161] In some implementations, the sequence feature parameters also include the sequence standard deviation. The detection module 803 is further used to compare the sequence standard deviation with a standard deviation threshold; if the sequence standard deviation is less than the standard deviation threshold, it is determined that the driver has released the hands; if the sequence standard deviation is not less than the standard deviation threshold, it is determined that the driver has not released the hands.

[0162] In some implementations, the aforementioned hand-release detection device also includes a calibration module.

[0163] The calibration module is used to calibrate the power spectral density threshold based on the first sample torque sequence and the second sample torque sequence, wherein the first sample torque sequence is the torque signal of the steering wheel when the driver takes his hands off the wheel, and the second sample torque sequence is the torque signal of the steering wheel when the driver does not take his hands off the wheel.

[0164] In some implementations, the calibration module can also be used to perform mean-reduction processing on the first sample torque sequence to obtain the third sample torque sequence; perform mean-reduction processing on the second sample torque sequence to obtain the fourth sample torque sequence; and calibrate the power spectral density threshold based on the third and fourth sample torque sequences.

[0165] In some implementations, the calibration module is also used to calibrate the standard deviation threshold based on the first sample torque sequence and the fifth sample torque sequence, wherein the first sample torque sequence is the torque signal of the steering wheel when the driver has his hands off the wheel, and the fifth sample torque sequence is the torque signal of the steering wheel when the driver has his hands on the wheel and there is no hand force output.

[0166] It should be noted that the information interaction and execution process between the above-mentioned units are based on the same concept as the method embodiments of this application. Their specific functions and technical effects can be referred to the method embodiments section, and will not be repeated here.

[0167] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules / units is used as an example. In practical applications, the above functions can be assigned to different functional modules / units as needed, that is, the internal structure of the control device can be divided into different functional modules / units to complete all or part of the functions described above. The functional modules / units in the embodiments 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. The integrated unit can be implemented in hardware or as a software functional module / unit. Furthermore, the specific names of the functional modules / units are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of each unit in the above control device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0168] Please see Figure 9 , Figure 9 This is a schematic diagram of the structure of an electronic device provided in another embodiment of this application. For example... Figure 9 As shown, the electronic device 9 provided in this embodiment may include: a processor 90, a memory 91, and a computer program 92 stored in the memory 91 and executable on the processor 90, such as a program corresponding to the inverter operation control method. When the processor 90 executes the computer program 92, it implements the steps in the above-described operation control method embodiment, for example... Figure 2 S101 to S103 are shown. Alternatively, when the processor 90 executes the computer program 92, it implements the functions of each module / unit in the above-described control device embodiment, for example... Figure 8 The functions of units 801 to 802 shown.

[0169] For example, computer program 92 can be divided into one or more modules / units, one or more of which are stored in memory 91 and executed by processor 90 to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of computer program 92 in electronic device 9. For example, computer program 92 can be divided into an acquisition module and a setting module; please refer to the specific functions of each unit. Figure 9 The relevant descriptions in the corresponding embodiments are not repeated here.

[0170] Those skilled in the art will understand that Figure 9 This is merely an example of electronic device 9 and does not constitute a limitation on electronic device 9. It may include more or fewer components than shown, or combine certain components, or use different components.

[0171] The processor 90 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0172] The memory 91 can be an internal storage unit of the electronic device 9, such as a hard disk or RAM. The memory 91 can also be an external storage device of the electronic device 9, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, or flash card. Furthermore, the memory 91 can include both internal and external storage units of the electronic device 9. The memory 91 is used to store computer programs and other programs and data required by the control device. The memory 91 can also be used to temporarily store data that has been output or will be output.

[0173] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the various steps of the operation control method described in the above-described method embodiments.

[0174] This application provides a computer program product that, when run on a control device, causes the control device to perform the steps described in the various method embodiments above.

[0175] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

[0176] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0177] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

[0178] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

[0179] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0180] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for detecting hand slippage, characterized in that, include: Obtain the first torque sequence; The first torque sequence includes the torque signal of the steering wheel within a preset time period; Sequence feature parameters are extracted based on the first torque sequence, wherein the sequence feature parameters include the power spectral density estimation result of the first torque sequence; Hand-drop detection is performed based on the sequence feature parameters.

2. The method for detecting hand loss according to claim 1, characterized in that, The sequence feature parameters include the maximum power spectral density value, and the extraction of sequence feature parameters based on the first torque sequence includes: The power spectral density of the first torque sequence is calculated to obtain the power spectral density estimation result of the first torque sequence; The maximum power spectral density value is obtained based on the power spectral density estimation result of the first torque sequence.

3. The method for detecting hand removal according to claim 1 or 2, characterized in that, The sequence feature parameters include the maximum power spectral density value, and the extraction of sequence feature parameters based on the first torque sequence includes: The first torque sequence is subjected to mean-reduction processing to obtain the second torque sequence; The power spectral density of the second torque sequence is calculated to obtain the power spectral density estimation result of the second torque sequence; The maximum power spectral density is obtained based on the power spectral density estimation result of the second torque sequence.

4. The method for detecting hand removal according to claim 2 or 3, characterized in that, The step of performing hand-drop detection based on the sequence feature parameters includes: The maximum power spectral density is compared with the power spectral density threshold. If the maximum power spectral density is not less than the power spectral density threshold, it is determined that the driver has not let go of the hands.

5. The method for detecting hand slippage according to any one of claims 1 to 4, characterized in that, The sequence feature parameters also include the sequence standard deviation, and the step of performing off-hand detection based on the sequence feature parameters includes: The standard deviation of the sequence is compared with the standard deviation threshold; If the standard deviation of the sequence is less than the standard deviation threshold, it is determined that the driver has disengaged. If the standard deviation of the sequence is not less than the standard deviation threshold, then it is determined that the driver did not release the hands.

6. The method for detecting hand loss according to any one of claims 1 to 5, characterized in that, The method further includes: The power spectral density threshold is calibrated based on the first sample torque sequence and the second sample torque sequence, wherein the first sample torque sequence is the torque signal of the steering wheel when the driver takes his hands off the wheel, and the second sample torque sequence is the torque signal of the steering wheel when the driver does not take his hands off the wheel.

7. The method for detecting hand loss according to claim 6, characterized in that, The method further includes: The first sample torque sequence is subjected to mean-reduction processing to obtain the third sample torque sequence; The second sample torque sequence is subjected to mean-reduction processing to obtain the fourth sample torque sequence; The power spectral density threshold is calibrated based on the third sample torque sequence and the fourth sample torque sequence.

8. The method for detecting hand removal according to any one of claims 1 to 7, characterized in that, The method further includes: The standard deviation threshold is calibrated based on the first sample torque sequence and the fifth sample torque sequence, wherein the first sample torque sequence is the torque signal of the steering wheel when the driver has his hands off the wheel, and the fifth sample torque sequence is the torque signal of the steering wheel when the driver has his hands on the wheel and there is no hand force output.

9. A hand-removal detection device, characterized in that, include: The sequence acquisition module is used to acquire the first torque sequence; The first torque sequence includes the torque signal of the steering wheel within a preset time period; The feature extraction module is used to extract sequence feature parameters based on the first torque sequence, wherein the sequence feature parameters include the power spectral density estimation result of the first torque sequence; The detection module is used to perform hand removal detection based on the sequence feature parameters.

10. An electronic device, characterized in that, It includes a memory and a computer program stored in the memory and executable on a processor, wherein the processor, when executing the computer program, implements the off-hand detection method as described in any one of claims 1-8.

11. A computer program product, characterized in that, When the computer program product is run on the electronic device, the electronic device performs the hands-free detection method as described in any one of claims 1-8.

Images