Hand release detection method and device for vehicle steering wheel, vehicle and storage medium

Abstract

The invention relates to the technical field of aided driving, in particular to a hand release detection method and device for a vehicle steering wheel, a vehicle and a storage medium. The method comprises the steps that under the condition that the vehicle is in a target aided driving working condition, a steering wheel torque signal of the vehicle is obtained; matching a state detection interval in which the torque value of the torque signal of the steering wheel is located; determining a current steering wheel prediction state of the vehicle according to the state detection interval, and obtaining a hand release detection result of the steering wheel according to the current steering wheel prediction state. According to the embodiment of the invention, the method can confirm the detection mode of the hand release of the steering wheel based on the state detection interval of the torque signal of the steering wheel, carries out the comprehensive analysis of the torque signal through combining with multiple signal features, obtains a final hand release detection result, achieves the comprehensive coverage of a subdivided driving scene, and improves the detection accuracy of the hand release state.

Description

Technical Field

[0001] The present application relates to the field of assisted driving technology, and in particular to a method, device, vehicle and storage medium for detecting hands-off of a vehicle steering wheel. Background Art

[0002] When the vehicle's advanced driver assistance system ADAS (Advanced Driver Assistance System) is running, the driver's status needs to be monitored. The hands-off detection method can be used to continuously monitor whether the driver is performing the corresponding dynamic driving tasks.

[0003] In the related art, the hands-off state of the steering wheel can be confirmed by detecting the steering wheel torque and duration, or by integrating information from multiple sensors. The state of the steering wheel can also be determined by pre-training a neural network algorithm.

[0004] However, in the related art, the detection strategy of judging whether the driver has taken the hands off the steering wheel through steering wheel torque is difficult to cover specific driving scenarios, resulting in an increased probability of misjudgment of hands off the steering wheel. The method of integrating information from multiple sensors or detecting through pre-trained neural algorithms increases the cost of steering wheel status detection, which cannot meet the comprehensiveness and economy requirements of hands off detection, affecting the safety of the vehicle and needs to be urgently resolved. Summary of the invention

[0005] The present application provides a vehicle steering wheel hands-off detection method, device, vehicle and storage medium to solve the problems in the related art that the detection strategy of judging whether the driver has taken the hands off the steering wheel by steering wheel torque is difficult to achieve coverage for segmented driving scenarios, resulting in an increased probability of misjudgment of steering wheel hands-off, and the method of integrating information from multiple sensors or detecting through pre-trained neural algorithms increases the cost of steering wheel status detection, cannot meet the comprehensiveness and economy requirements of hands-off detection, and affects the safety of the vehicle.

[0006] The first aspect of the present application provides a method for detecting a hands-off state of a vehicle steering wheel, comprising the following steps: when the vehicle is in a target assisted driving condition, obtaining a steering wheel torque signal of the vehicle; matching a state detection interval in which the torque value of the steering wheel torque signal is located; confirming a current predicted steering wheel state of the vehicle based on the state detection interval, and obtaining a hands-off state detection result of the steering wheel based on the current predicted steering wheel state.

[0007] Optionally, in one embodiment of the present application, before confirming the current steering wheel predicted state of the vehicle according to the state detection interval, it also includes: calculating the standard deviation and DC component of the steering wheel torque signal, and detecting whether the standard deviation and / or the DC component satisfies a first preset filtering condition; when the standard deviation and / or the DC component satisfies the first preset filtering condition, outputting the current steering wheel predicted state as a hands-off state.

[0008] Optionally, in one embodiment of the present application, confirming the current steering wheel predicted state of the vehicle based on the state detection interval includes: determining whether the state detection interval satisfies a preset second filtering condition; if the state detection interval satisfies the preset second filtering condition, generating the current steering wheel predicted state based on the state detection interval, otherwise confirming the current steering wheel predicted state based on the frequency signal characteristics of the steering wheel torque signal.

[0009] Optionally, in one embodiment of the present application, confirming the current steering wheel predicted state based on the frequency signal characteristics of the steering wheel torque signal includes: detecting whether the gain value and the frequency domain amplitude of the frequency signal characteristics meet a preset third filtering condition; if the gain value and the frequency domain amplitude meet the preset third filtering condition, confirming that the current steering wheel predicted state is a hand-holding state, otherwise, confirming that the current steering wheel predicted state is a hands-off state.

[0010] Optionally, in one embodiment of the present application, the steering wheel hands-off detection result obtained based on the current steering wheel predicted state includes: when the current steering wheel predicted state satisfies a preset state locking condition, determining whether the locking time of the vehicle satisfies a preset update condition; when the locking time satisfies the preset update condition, using the current steering wheel predicted state that satisfies the preset state locking condition as the hands-off detection result, and updating the historical locking state of the vehicle based on the hands-off detection result; otherwise, obtaining the hands-off detection result from the historical locking state.

[0011] Optionally, in one embodiment of the present application, before determining whether the locking time of the vehicle satisfies the preset update condition, it also includes: confirming the time window maintenance state based on the current steering wheel prediction state and the historical steering wheel prediction state at the previous moment; when the time window maintenance state reaches a preset period length, determining that the current steering wheel prediction state satisfies the preset state locking condition.

[0012] The second aspect of the present application provides a device for detecting a hands-off steering wheel of a vehicle, comprising: an acquisition module for acquiring a steering wheel torque signal of the vehicle when the vehicle is in a target assisted driving condition; a matching module for matching a state detection interval in which the torque value of the steering wheel torque signal is located; and a detection module for confirming a current predicted steering wheel state of the vehicle based on the state detection interval, and obtaining a hands-off steering wheel detection result based on the current predicted steering wheel state.

[0013] Optionally, in one embodiment of the present application, the detection module includes: a detection unit, used to calculate the standard deviation and DC component of the steering wheel torque signal before confirming the current steering wheel predicted state of the vehicle according to the state detection interval, and detect whether the standard deviation and / or the DC component meet a first preset filtering condition; an output unit, used to output the current steering wheel predicted state as a hands-off state when the standard deviation and / or the DC component meet the first preset filtering condition.

[0014] Optionally, in one embodiment of the present application, the detection module includes: a first judgment unit, used to judge whether the state detection interval satisfies a preset second filtering condition; a generation unit, used to generate the current steering wheel predicted state according to the state detection interval when the state detection interval satisfies the preset second filtering condition, otherwise confirming the current steering wheel predicted state according to the frequency signal characteristics of the steering wheel torque signal.

[0015] Optionally, in one embodiment of the present application, the generating unit is specifically used to: detect whether the gain value and the frequency domain amplitude of the frequency signal characteristic meet a preset third filtering condition; if the gain value and the frequency domain amplitude meet the preset third filtering condition, confirm that the current steering wheel predicted state is a hand-holding state; otherwise, confirm that the current steering wheel predicted state is a hands-off state.

[0016] Optionally, in one embodiment of the present application, the detection module includes: a second judgment unit, used to judge whether the locking time of the vehicle meets the preset update condition when the current steering wheel prediction state meets the preset state locking condition; an update unit, used to take the current steering wheel prediction state that meets the preset state locking condition as the hands-off detection result when the locking time meets the preset update condition, and update the historical locking state of the vehicle based on the hands-off detection result; otherwise, the hands-off detection result is obtained from the historical locking state.

[0017] Optionally, in one embodiment of the present application, the detection module also includes: a confirmation unit, used to confirm the time window maintenance state according to the current steering wheel prediction state and the historical steering wheel prediction state at the previous moment before determining whether the locking time of the vehicle meets the preset update condition; a determination unit, used to determine that the current steering wheel prediction state meets the preset state locking condition when the time window maintenance state reaches a preset period length.

[0018] A third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle steering wheel hands-off detection method as described in the above embodiment.

[0019] A fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the above-mentioned vehicle steering wheel hands-off detection method.

[0020] A fifth aspect of the present application provides a computer program, which, when executed, implements the above-mentioned method for detecting hands-off of the vehicle steering wheel.

[0021] The embodiment of the present application can confirm the detection method of the hands-off steering wheel based on the detection interval of the steering wheel torque signal state, and conduct a comprehensive analysis of the torque signal in combination with various signal characteristics to obtain the final hands-off detection result, thereby achieving comprehensive coverage for segmented driving scenarios and improving the accuracy of hands-off state detection. Thus, it solves the problem that the detection strategy of judging whether the driver has taken the hands off the steering wheel through the steering wheel torque in the related technology is difficult to achieve coverage for segmented driving scenarios, resulting in an increase in the probability of misjudgment of the hands-off steering wheel, and the method of integrating multiple sensor information or detecting through pre-trained neural algorithms increases the cost of steering wheel state detection, which cannot meet the comprehensiveness and economy requirements of hands-off detection, affecting the safety of the vehicle, and other problems.

[0022] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 A flowchart of a method for detecting a hands-off state of a vehicle steering wheel provided according to an embodiment of the present application;

[0025] Figure 2A schematic diagram of obtaining a standard deviation and a DC component of a steering wheel torque signal according to an embodiment of the present application;

[0026] Figure 3 A schematic diagram of frequency domain analysis of a steering wheel torque signal according to an embodiment of the present application;

[0027] Figure 4 A schematic diagram of obtaining a frequency domain gain of a steering wheel torque signal according to an embodiment of the present application;

[0028] Figure 5 A schematic diagram of a section determination process of a steering wheel torque signal according to an embodiment of the present application;

[0029] Figure 6 A schematic diagram of a state latch determination process for hands-off steering wheel detection according to an embodiment of the present application;

[0030] Figure 7 A schematic diagram of a time window determination process for hands-off steering detection according to an embodiment of the present application;

[0031] Figure 8 Schematic diagram of the structure of a hands-off detection device for a vehicle steering wheel according to an embodiment of the present application;

[0032] Fig. 9 It is a schematic diagram of the structure of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0034] The following describes the vehicle steering wheel hands-off detection method, device, vehicle and storage medium of the embodiment of the present application with reference to the accompanying drawings. In view of the related technologies mentioned in the above background technology, the detection strategy of judging whether the driver has taken the hands off the steering wheel by the steering wheel torque is difficult to achieve coverage for segmented driving scenarios, resulting in an increase in the probability of misjudgment of the steering wheel hands-off, and the method of integrating multiple sensor information or detecting by pre-trained neural algorithms increases the cost of steering wheel state detection, which cannot meet the comprehensiveness and economy requirements of hands-off detection, affecting the safety of the vehicle. The present application provides a vehicle steering wheel hands-off detection method, in which the detection method of steering wheel hands-off can be confirmed based on the steering wheel torque signal state detection interval, and the torque signal is comprehensively analyzed in combination with various signal characteristics to obtain the final hands-off detection result, thereby achieving comprehensive coverage for segmented driving scenarios and improving the accuracy of hands-off state detection. Thereby, a problem is solved in the related technology that the detection strategy of judging whether the driver has taken the hands off the steering wheel by steering wheel torque is difficult to cover specific driving scenarios, resulting in an increased probability of misjudgment of hands off the steering wheel, while the method of integrating information from multiple sensors or detecting through pre-trained neural algorithms increases the cost of steering wheel status detection, cannot meet the comprehensiveness and economy requirements of hands off detection, and affects the safety of the vehicle.

[0035] Specifically, Figure 1 A schematic flow chart of a method for detecting hands-off steering wheel movement in a vehicle provided in an embodiment of the present application.

[0036] like Figure 1 As shown, the vehicle steering wheel hands-off detection method comprises the following steps:

[0037] In step S101 , when the vehicle is in a target assisted driving condition, a steering wheel torque signal of the vehicle is obtained.

[0038] It is understandable that in the embodiments of the present application, the target assisted driving condition may be the corresponding condition when the ADAS advanced driving assistance system function of the vehicle is activated. At this time, the vehicle in the target assisted driving condition needs to use the hands-off detection method to continuously detect whether the driver is performing the corresponding dynamic driving task and whether there is a situation where the steering wheel is out of hand. The steering wheel torque signal can be obtained by installing a torque sensor on the vehicle steering wheel, and the sensor measures the torque applied by the driver to the steering wheel. The torque sensor can be contact type, such as a potentiometer or a differential transformer, or non-contact type, such as a magnetic induction sensor.

[0039] In step S102, the state detection interval of the torque value of the steering wheel torque signal is matched.

[0040] It can be understood that in the embodiments of the present application, the size interval corresponding to the torque value is matched by using the signal characteristics based on the torque value of the steering wheel torque signal, wherein the division of the state detection interval can be achieved by considering the steering system characteristics of the vehicle and distinguishing the torque signal under different states, thereby speeding up the process of the steering wheel hands-off detection function and ensuring the accuracy of the detection results.

[0041] In step S103, the current predicted state of the steering wheel of the vehicle is confirmed according to the state detection interval, and a hands-off detection result of the steering wheel is obtained according to the current predicted state of the steering wheel.

[0042] It is understood that in the embodiments of the present application, the confirmation method of the hands-off steering wheel can be determined according to different state detection intervals. For example, the time state of the steering wheel can be directly confirmed when it is less than a set maximum or minimum threshold. After obtaining the current predicted state of the steering wheel, the applicability of the prediction result can be further confirmed according to the program setting of the hands-off detection.

[0043] Optionally, in one embodiment of the present application, before confirming the current predicted steering wheel state of the vehicle according to the state detection interval, it also includes: calculating the standard deviation and DC component of the steering wheel torque signal, and detecting whether the standard deviation and / or DC component meet the first preset filtering condition; when the standard deviation and / or DC component meet the first preset filtering condition, outputting the current predicted steering wheel state as a hands-off state.

[0044] It should be noted that the first preset filtering condition can be set by those skilled in the art according to actual conditions and is not specifically limited here.

[0045] In the actual implementation process, the first preset filtering condition can be set to determine that the steering wheel is in a hands-off state when the standard deviation and / or DC component of the steering wheel torque signal is less than a certain set threshold. The standard deviation and DC component of the steering wheel torque signal can be calculated by obtaining the time domain characteristics of the data signal of the unfiltered torque signal, and analyzing the time domain characteristics of different time periods to obtain the change trend of the signal, so as to confirm the current state of the user holding the steering wheel when driving.

[0046] Specifically, Figure 2A schematic diagram of obtaining the standard deviation and DC component of a steering wheel torque signal according to an embodiment of the present application is provided. The unfiltered torque signal is received and input into a buffer of size 500. Window calculation is performed on the parameters in the buffer. The standard deviation of the torque signal in the time domain buffer is calculated to obtain the standard deviation within 0.4s. All parameters are averaged to obtain the DC component of the torque signal. The DC component is compared with the threshold value. For a DC component that is too small, the current state is judged as hands-off. The threshold value can be set to 0.11Nm to filter out external impact signals and avoid misidentification of the state due to impact signals.

[0047] Optionally, in one embodiment of the present application, the current steering wheel predicted state of the vehicle is confirmed according to the state detection interval, including: determining whether the state detection interval satisfies a preset second filtering condition; if the state detection interval satisfies the preset second filtering condition, generating the current steering wheel predicted state according to the state detection interval, otherwise confirming the current steering wheel predicted state according to the frequency signal characteristics of the steering wheel torque signal.

[0048] It should be noted that the preset second filtering condition can be set by those skilled in the art according to actual conditions and is not specifically limited here.

[0049] In the actual implementation process, the preset second filtering condition can be that the state detection interval can directly confirm the predicted state of the steering wheel according to the torque value. For example, the state detection interval is divided into three sections. The first section is that the absolute value of the torque is greater than 0.25Nm, and the output steering wheel state is the hand-held state. The second section is that the absolute value of the torque is less than 0.1Nm, and the output steering wheel state is the hands-off state. For the case of the intermediate torque interval between 0.1Nm and 0.25Nm, the current steering wheel predicted state is further confirmed based on the frequency signal characteristics of the steering wheel torque signal.

[0050] Optionally, in one embodiment of the present application, the current predicted steering wheel state is confirmed based on the frequency signal characteristics of the steering wheel torque signal, including: detecting whether the gain value and the frequency domain amplitude of the frequency signal characteristics meet a preset third filtering condition; when the gain value and the frequency domain amplitude meet the preset third filtering condition, confirming that the current predicted steering wheel state is a hand-holding state, otherwise, confirming that the current predicted steering wheel state is a hands-off state.

[0051] It should be noted that the preset third filtering condition can be set by those skilled in the art according to actual conditions and is not specifically limited here.

[0052] In the actual implementation process, the preset third filtering condition can be that when the frequency domain signal feature of the steering wheel torque signal is greater than the set threshold, it is determined that the current steering wheel predicted state is the hand-held state. The frequency domain signal feature can be obtained by multiplying the frequency gain value and the frequency domain amplitude.

[0053] Specifically, Figure 3 As shown, it is a schematic diagram of the frequency domain analysis of the steering wheel torque signal of an embodiment of the present application, the torque signal is low-pass filtered to filter out signals above 10 Hz, and the frequency domain amplitudes of the signals of 1 Hz, 4 Hz, 5 Hz, 6 Hz, and 7 Hz are respectively obtained to realize the analysis of the frequency domain, and the shown components are selected to determine whether the hands are out of the car. Figure 4 This is a schematic diagram of obtaining the frequency domain gain of a steering wheel torque signal according to an embodiment of the present application, wherein an unfiltered torque signal is received and input into a buffer, the size of the buffer is 50, and the torque change trend within 100ms can be obtained by subtracting the values ​​at intervals of 25 cycles. The difference after subtraction is used as an input quantity, and the gain value of the frequency is matched through the one-dimensional calibration table corresponding to Table 1. The larger the difference, the greater the gain, thereby utilizing the frequency domain signal characteristics to speed up the detection speed and reduce the delay time of getting started.

[0054] Table 1

[0055] Output 1 1 2 2 2 2.5 3 3 enter 0 0.01 0.1 0.2 0.3 0.4 0.5 0.51

[0056] For example, Figure 5 FIG. 1 is a schematic diagram of a section determination process of a steering wheel torque signal according to an embodiment of the present application, wherein:

[0057] Step S501: input a steering wheel torque signal.

[0058] Among them, the absolute value of the torque corresponding to the steering wheel torque signal is obtained.

[0059] Step S502: Determine whether it is less than 0.1Nm?

[0060] Here, it is determined whether the absolute value of the torque is less than 0.1 Nm. If so, the process proceeds to step S503 , otherwise, the process proceeds to step S504 .

[0061] Step S503: Output the hands-off status.

[0062] Among them, it is confirmed that the steering wheel prediction result is a hands-off state.

[0063] Step S504: Determine whether it is greater than 0.25 Nm?

[0064] Here, it is determined whether the absolute value of the torque is greater than 0.25 Nm. If so, the process proceeds to step S505 , otherwise, the process proceeds to step S506 .

[0065] Step S505: Output the hand-holding status.

[0066] Among them, confirm that the steering wheel prediction result is in the hand-held state.

[0067] Step S506: Determine whether the frequency domain signal feature reaches a threshold.

[0068] If the frequency domain signal feature reaches the threshold, the process proceeds to step S507 , otherwise, the process proceeds to step S508 .

[0069] Step S507: Output the hand-holding status.

[0070] Among them, confirm that the steering wheel prediction result is in the hand-held state.

[0071] Step S508: Output the hands-off status.

[0072] Among them, it is confirmed that the steering wheel prediction result is a hands-off state.

[0073] Step S509: Output the predicted status.

[0074] Among them, the steering wheel prediction result is confirmed.

[0075] Optionally, in one embodiment of the present application, a hands-off detection result of the steering wheel is obtained based on the current predicted steering wheel state, including: when the current predicted steering wheel state satisfies a preset state locking condition, determining whether the locking time of the vehicle satisfies a preset update condition; when the locking time satisfies the preset update condition, using the current predicted steering wheel state that satisfies the preset state locking condition as the hands-off detection result, and updating the historical locking state of the vehicle based on the hands-off detection result; otherwise, obtaining the hands-off detection result from the historical locking state.

[0076] It should be noted that the preset state latching condition and the preset update condition can be set by those skilled in the art according to actual conditions and are not specifically limited here.

[0077] During the actual execution process, after confirming that the current steering wheel predicted state meets the preset state latching conditions, it can be determined whether the vehicle's latching duration meets the preset update conditions, that is, whether the duration of the steering wheel hands-off detection result output by the vehicle in the previous cycle exceeds the preset duration. By judging whether the current vehicle has a state latch, the latched state will be maintained when there is a state latch. If there is no state latch or the state latch can be updated, the state will be latched and maintained for 0.1s.

[0078] Specifically, Figure 6 FIG. 1 is a schematic diagram of a state latch judgment process for hands-off detection of a steering wheel according to an embodiment of the present application, wherein:

[0079] Step S601: Latest prediction of the user's hand-holding steering wheel status.

[0080] Among them, the latest output steering wheel state prediction result is obtained.

[0081] Step S602: Is there any status latch?

[0082] It is determined whether the vehicle has a status lock, if so, the process proceeds to step S603, otherwise, the process proceeds to step S604.

[0083] Step S603: Output the original state.

[0084] Among them, the historical locking status of the vehicle is maintained.

[0085] Step S604: Output the new state and latch it.

[0086] Among them, the vehicle's steering wheel hands-off detection results are updated according to the steering wheel state prediction results.

[0087] Optionally, in one embodiment of the present application, before determining whether the vehicle's lock time meets the preset update conditions, it also includes: confirming the time window maintenance state based on the current steering wheel prediction state and the historical steering wheel prediction state at the previous moment; when the time window maintenance state reaches a preset cycle length, determining that the current steering wheel prediction state meets the preset state lock conditions.

[0088] It should be noted that the preset update condition can be set by those skilled in the art according to actual conditions and is not specifically limited here.

[0089] During the actual execution process, the preset state latching condition can be the length of time that the current steering wheel prediction result can be maintained within the preset cycle length. Some state switches with too short a time are filtered out to ensure state continuity and avoid continuous resetting of the hands-off warning time due to repeated switching of states.

[0090] Specifically, Figure 7 FIG. 1 is a schematic diagram of a time window judgment process for hands-off steering wheel detection according to an embodiment of the present application, wherein:

[0091] Step S701: Input the latest predicted user's hand-holding steering wheel status.

[0092] Among them, the prediction result of the steering wheel state is obtained.

[0093] Step S702: Determine whether the state is the same as the previous state.

[0094] Here, it is determined whether the current cycle detection state is the same as the historical cycle detection state. If so, the process proceeds to step S703; otherwise, the process proceeds to step S704.

[0095] Step S703: The counter is incremented by 1.

[0096] Among them, the counter is increased by 1.

[0097] Step S704: The counter is reset to 0.

[0098] Among them, the counter returns to 0.

[0099] Step S705: Determine whether the counter is greater than a threshold.

[0100] If the counter is greater than the threshold, the process proceeds to step S706 , otherwise, the process proceeds to step S707 .

[0101] Step S706: Output the new state.

[0102] Among them, the steering wheel state prediction result of the current cycle is output.

[0103] Step S707: Output the original state.

[0104] Among them, the historical detection results of the steering wheel are output.

[0105] Step S708: state preprocessing output.

[0106] Among them, the output state preprocessing result.

[0107] Based on the above embodiments, the torque signal characteristic difference of the steering system when the steering wheel is out of hand and in the hand-held state can be used to eliminate the torque fluctuation caused by external impact from the signal characteristics, and the current state can be jointly judged by the frequency domain signal and the time domain signal. Combined with the real-time updated reference signal, the reference signal can be corrected to overcome the steering wheel bias problem caused by short-term impact or installation defects. Through the analysis of different frequency signals and the comprehensive judgment of time domain signals, irregular external interference can be filtered out, such as external interference in driving scenarios such as seams, manhole covers, brick roads, and long-term bumps, and the current state of the steering wheel out of hand can be effectively judged, expanding the applicable scenarios of hands-off detection, thereby reducing the safety risks of users.

[0108] In particular, the above-mentioned embodiment can realize the update of the reference signal during driving according to the self-learning strategy, thereby overcoming the torque zero drift caused by the loss of sensors, etc., ensuring that the user has the intention to operate the steering wheel when on the steering wheel, and the current state can be judged, and the user's input can be distinguished from the external interference input for testing.

[0109] According to the vehicle steering wheel hands-off detection method proposed in the embodiment of the present application, the detection method of steering wheel hands-off can be confirmed based on the steering wheel torque signal state detection interval, and the torque signal can be comprehensively analyzed in combination with various signal characteristics to obtain the final hands-off detection result, thereby achieving comprehensive coverage for segmented driving scenarios and improving the accuracy of hands-off state detection. Thus, the problem that the detection strategy of judging whether the driver has taken the hands off by steering wheel torque in the related technology is difficult to achieve coverage for segmented driving scenarios, resulting in an increased probability of misjudgment of steering wheel hands-off, and the method of integrating multiple sensor information or detecting by pre-trained neural algorithms increases the cost of steering wheel state detection, cannot meet the comprehensiveness and economy requirements of hands-off detection, and affects the safety of the vehicle is solved.

[0110] Next, a hands-off detection device for a vehicle steering wheel proposed in an embodiment of the present application will be described with reference to the accompanying drawings.

[0111] Figure 8 It is a structural schematic diagram of a vehicle steering wheel hands-off detection device according to an embodiment of the present application.

[0112] like Figure 8 As shown, the vehicle steering wheel hands-off detection device 10 includes: an acquisition module 100 , a matching module 200 and a detection module 300 .

[0113] The acquisition module 100 is used to acquire the steering wheel torque signal of the vehicle when the vehicle is in a target assisted driving condition.

[0114] The matching module 200 is used to match the state detection interval of the torque value of the steering wheel torque signal.

[0115] The detection module 300 is used to confirm the current predicted state of the steering wheel of the vehicle according to the state detection interval, and obtain a hands-off detection result of the steering wheel according to the current predicted state of the steering wheel.

[0116] Optionally, in one embodiment of the present application, the detection module 300 includes: a detection unit and an output unit.

[0117] Among them, the detection unit is used to calculate the standard deviation and DC component of the steering wheel torque signal before confirming the current steering wheel predicted state of the vehicle according to the state detection interval, and detect whether the standard deviation and / or DC component meets the first preset filtering condition.

[0118] The output unit is used to output the current steering wheel predicted state as a hands-off state when the standard deviation and / or the DC component meet the first preset filtering condition.

[0119] Optionally, in one embodiment of the present application, the detection module 300 includes: a first judgment unit and a generation unit.

[0120] The first judgment unit is used to judge whether the state detection interval meets the preset second filtering condition.

[0121] The generating unit is used to generate the current steering wheel predicted state according to the state detection interval when the state detection interval meets the preset second filtering condition, otherwise confirm the current steering wheel predicted state according to the frequency signal characteristics of the steering wheel torque signal.

[0122] Optionally, in one embodiment of the present application, the generation unit is specifically used to: detect whether the gain value and the frequency domain amplitude of the frequency signal characteristics meet the preset third filtering condition; when the gain value and the frequency domain amplitude meet the preset third filtering condition, confirm that the current steering wheel predicted state is a hand-holding state, otherwise, confirm that the current steering wheel predicted state is a hands-off state.

[0123] Optionally, in one embodiment of the present application, the detection module 300 includes: a second judgment unit and an updating unit.

[0124] Among them, the second judgment unit is used to judge whether the vehicle's locking time meets the preset update condition when the current steering wheel prediction state meets the preset state locking condition.

[0125] The update unit is used to use the current steering wheel predicted state that meets the preset state locking condition as the hands-off detection result when the locking duration meets the preset update condition, and to update the vehicle's historical locking state based on the hands-off detection result; otherwise, the hands-off detection result is obtained from the historical locking state.

[0126] Optionally, in one embodiment of the present application, the detection module 300 further includes: a confirmation unit and a determination unit.

[0127] The confirmation unit is used to confirm the time window maintenance state according to the current steering wheel prediction state and the historical steering wheel prediction state at the previous moment before determining whether the vehicle lock duration meets the preset update condition;

[0128] The determination unit is used to determine that the current steering wheel prediction state meets the preset state latching condition when the time window maintenance state reaches a preset period length.

[0129] It should be noted that the aforementioned explanation of the embodiment of the method for detecting hands-off of the vehicle steering wheel is also applicable to the device for detecting hands-off of the vehicle steering wheel of this embodiment, and will not be repeated here.

[0130] According to the vehicle steering wheel hands-off detection device proposed in the embodiment of the present application, the detection method of steering wheel hands-off can be confirmed based on the steering wheel torque signal state detection interval, and the torque signal can be comprehensively analyzed in combination with various signal characteristics to obtain the final hands-off detection result, thereby achieving comprehensive coverage for segmented driving scenarios and improving the accuracy of hands-off state detection. As a result, the problem that the detection strategy of judging whether the driver has taken the hands off by steering wheel torque in the related technology is difficult to achieve coverage for segmented driving scenarios, resulting in an increased probability of misjudgment of steering wheel hands-off, and the method of integrating multiple sensor information or detecting by pre-trained neural algorithms increases the cost of steering wheel state detection, cannot meet the comprehensiveness and economy requirements of hands-off detection, and affects the safety of the vehicle is solved.

[0131] Fig. 9 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0132] A memory 901 , a processor 902 , and a computer program stored in the memory 901 and executable on the processor 902 .

[0133] When the processor 902 executes the program, the vehicle steering wheel hands-off detection method provided in the above embodiment is implemented.

[0134] Furthermore, the vehicle also includes:

[0135] The communication interface 903 is used for communication between the memory 901 and the processor 902 .

[0136] The memory 901 is used to store computer programs that can be executed on the processor 902 .

[0137] The memory 901 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0138] If the memory 901, the processor 902 and the communication interface 903 are implemented independently, the communication interface 903, the memory 901 and the processor 902 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0139] Optionally, in a specific implementation, if the memory 901, the processor 902 and the communication interface 903 are integrated on a chip, the memory 901, the processor 902 and the communication interface 903 can communicate with each other through an internal interface.

[0140] The processor 902 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0141] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned vehicle steering wheel hands-off detection method is implemented.

[0142] This embodiment also provides a computer program, which implements the above-mentioned vehicle steering wheel hands-off detection method when executed.

[0143] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0144] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0145] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0146] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0147] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0148] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0149] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0150] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for detecting a vehicle steering wheel being taken off the steering wheel, characterized in that: The following steps are involved: When the vehicle is in a target assisted driving condition, obtaining a steering wheel torque signal of the vehicle; Matching the state detection interval of the torque value of the steering wheel torque signal; The current predicted state of the steering wheel of the vehicle is confirmed according to the state detection interval, and a hands-off detection result of the steering wheel is obtained according to the current predicted state of the steering wheel.

2. The method according to claim 1, characterized in that: Before confirming the predicted current steering wheel state of the vehicle according to the state detection interval, the method further includes: Calculating a standard deviation and a DC component of the steering wheel torque signal, and detecting whether the standard deviation and / or the DC component meets a first preset filtering condition; When the standard deviation and / or the DC component satisfies the first preset filtering condition, the current steering wheel predicted state is output as a hands-off state.

3. The method according to claim 1, characterized in that The step of confirming the predicted current steering wheel state of the vehicle according to the state detection interval includes: Determining whether the state detection interval satisfies a preset second filtering condition; If the state detection interval satisfies the preset second filtering condition, the current steering wheel predicted state is generated according to the state detection interval; otherwise, the current steering wheel predicted state is confirmed according to the frequency signal characteristics of the steering wheel torque signal.

4. The method according to claim 3, characterized in that The confirming the current steering wheel predicted state according to the frequency signal characteristics of the steering wheel torque signal includes: Detecting whether the gain value and the frequency domain amplitude of the frequency signal characteristic meet a preset third filtering condition; When the gain value and the frequency domain amplitude satisfy the preset third filtering condition, the current predicted state of the steering wheel is confirmed to be a hands-on state; otherwise, the current predicted state of the steering wheel is confirmed to be a hands-off state.

5. The method according to claim 1, characterized in that The obtaining a hands-off steering wheel detection result according to the current steering wheel prediction state includes: In the case where the current predicted steering wheel state meets the preset state locking condition, determining whether the locking time of the vehicle meets the preset update condition; When the latching duration satisfies the preset update condition, the current predicted steering wheel state that satisfies the preset state latching condition is used as the hands-off detection result, and the historical latching state of the vehicle is updated based on the hands-off detection result; otherwise, the hands-off detection result is obtained from the historical latching state.

6. The method according to claim 5, characterized in that Before determining whether the locking time of the vehicle meets the preset update condition, the method further includes: Confirming the time window maintenance state according to the current steering wheel prediction state and the historical steering wheel prediction state at the previous moment; When the time window maintenance state reaches a preset period length, it is determined that the current steering wheel prediction state satisfies the preset state latching condition.

7. A vehicle steering wheel hands-off detection device, characterized in that: include: An acquisition module, used for acquiring a steering wheel torque signal of the vehicle when the vehicle is in a target assisted driving condition; A matching module, used for matching the state detection interval of the torque value of the steering wheel torque signal; The detection module is used to confirm the current predicted state of the steering wheel of the vehicle according to the state detection interval, and obtain a hands-off detection result of the steering wheel according to the current predicted state of the steering wheel.

8. The device according to claim 7, characterized in that The detection module comprises: a detection unit, configured to calculate a standard deviation and a DC component of the steering wheel torque signal before confirming the current steering wheel predicted state of the vehicle according to the state detection interval, and detect whether the standard deviation and / or the DC component satisfies a first preset filtering condition; An output unit is used to output the current steering wheel predicted state as a hands-off state when the standard deviation and / or the DC component meets the first preset filtering condition.

9. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle steering wheel hands-off detection method as described in any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement a vehicle steering wheel hands-off detection method as described in any one of claims 1-6.

Images