Steering wheel mistaken touch prevention and hand release detection method and system based on fusion of capacitance and heart rate

Abstract

The present application relates to the field of automobile electronic control technology, specifically to a steering wheel anti-mis-touch hand-off detection method and system based on capacitance and heart rate fusion, the system comprising a steering wheel body, a multiplex electrode sensor, a segmented auxiliary capacitance sensor, a controller, a power management chip and a clock module; the method comprising: real-time acquisition of capacitance value and determination of potential effective contact, initiation of ECG differential acquisition and identification of QRS complex, determination of effective holding when the capacitance signal is effective, the ECG electrocardiogram signal is effective and the homologous condition is met, switching to a degraded mode for hand-off determination through dynamic capacitance analysis when the ECG is invalid; the present application can eliminate hand-off sensing mis-touch or fraudulent behavior, significantly improve the anti-mis-touch capability, greatly improve the overall detection accuracy and robustness, support the degraded mode after the main mode fails, and meet the functional safety level requirements.

Description

Technical Field

[0001] This invention relates to the field of automotive electronic control technology, and in particular to a method and system for detecting accidental hand-off steering wheel touches based on the fusion of capacitance and heart rate. Background Technology

[0002] Currently, Level 2 autonomous driving systems generally rely on hands-off detection (HOD) technology to determine whether the driver has effectively taken over the vehicle. The mainstream solutions mainly include torque detection, capacitance detection and simple multimodal fusion, but all of them have obvious defects.

[0003] The first approach is the torque detection method, which uses EPS steering torque to determine the grip status. However, under conditions such as bumpy roads and continuous steering, road excitation and vehicle vibration can cause significant torque interference, resulting in a false alarm rate as high as 30%. At the same time, it cannot recognize static grip behaviors such as lightly touching the steering wheel, which can easily lead to false alarms where the hands are on the steering wheel but the system is judged to be off the wheel.

[0004] The second approach is capacitive HOD detection, which determines whether a person has taken over the steering wheel by detecting changes in capacitance on the surface. While it can identify static grip, it relies solely on a fixed capacitance threshold and cannot distinguish between a human body and inanimate objects such as pork, metal blocks, or wet towels, resulting in poor anti-spoofing capabilities. Some patents incorporate temperature sensors to assist in identification, but these are easily affected by ambient temperature, sunlight, and hand sweat, leading to insufficient stability.

[0005] The third approach is to integrate features such as those from cameras to comprehensively determine whether a person has taken over the steering wheel. However, cameras also have certain blind spots, and it is not possible to accurately determine whether a person has taken over the steering wheel in certain locations. Furthermore, they lack dynamic collaborative verification and fault degradation mechanisms, and are prone to failure or misjudgment when the camera's field of vision is obstructed.

[0006] In summary, existing technologies cannot simultaneously meet the requirements of preventing accidental touches / deception and high robustness, posing certain driving safety hazards. Summary of the Invention

[0007] To address the aforementioned technical problems, this invention proposes a steering wheel anti-accidental touch detection method and system based on the fusion of capacitance and heart rate. By strongly coupling capacitive sensing and electrocardiogram detection, high-precision off-hand detection is achieved while simultaneously preventing accidental touches.

[0008] On one hand, embodiments of the present invention provide a steering wheel anti-accidental touch hands-off detection system based on capacitance and heart rate fusion, comprising: Steering wheel body; A multiplexed electrode sensor is arranged under the leather in the grip area of ​​the steering wheel body. The multiplexed electrode sensor is used as both a capacitance detection electrode and an ECG electrocardiogram acquisition electrode. The multiplexed electrode sensor acquires capacitance signals and ECG electrocardiogram signals. A segmented auxiliary capacitance sensor is arranged under the leather in the non-grip area of ​​the steering wheel body, and the segmented auxiliary capacitance sensor collects capacitance signals. The controller includes a capacitance detection chip, an ECG acquisition chip, and a main chip. The capacitance signal acquired by the multiplexed electrode sensor is transmitted to the capacitance detection chip, the ECG signal acquired by the multiplexed electrode sensor is transmitted to the ECG acquisition chip, the capacitance signal acquired by the segmented auxiliary capacitance sensor is transmitted to the capacitance detection chip, and the signal processed by the capacitance detection chip and the ECG acquisition chip is sent to the main chip. A power management chip that converts the vehicle power supply voltage to power the main chip, the multiplexed electrode sensor, the segmented auxiliary capacitor sensor, the capacitance detection chip, and the ECG acquisition chip. A clock module provides a synchronization clock for the main chip, the capacitance detection chip, and the ECG acquisition chip.

[0009] Optionally, the multiplexed electrode sensor is arranged in the 3 o'clock and 9 o'clock regions of the steering wheel body; the segmented auxiliary capacitance sensor includes two sets, which are respectively arranged in the 10 o'clock-2 o'clock region and the 4 o'clock-8 o'clock region of the steering wheel body.

[0010] Optionally, the surface of the multiplexed electrode sensor is provided with an insulating layer, and the material of the multiplexed electrode sensor is copper wire plated with silver; the multiplexed electrode sensor corresponds to two sets of differential ECG acquisition channels, which respectively acquire ECG signals of the driver's left and right hands; the capacitance detection and the ECG detection share the same set of electrodes and the same clock source.

[0011] On the other hand, embodiments of the present invention provide a steering wheel anti-accidental touch hands-off detection method based on capacitance and heart rate fusion, applied to the above-mentioned system, the method comprising the following steps: The capacitance values ​​of all capacitive sensors on the steering wheel body are collected in real time. When the capacitance value of any group of capacitive sensors continuously exceeds the effective capacitance detection threshold and remains so for a preset time, it is determined to be a potential effective contact and the ECG electrocardiogram detection module is activated. After capacitor triggering, ECG differential acquisition is started to acquire the electrocardiogram signal of the driver's hand. The QRS complex in the electrocardiogram signal is identified by the signal processing algorithm. When a preset number of stable QRS waveforms are continuously detected, it is determined to be a valid human electrocardiogram signal. When it is determined that the capacitance signal is valid, the ECG signal is valid, and the capacitance signal and ECG signal come from the same set of electrodes, it is considered a valid grip; When the ECG detection in the main mode fails, it automatically switches to the degraded mode, which uses dynamic capacitance analysis to determine if the device is off-hand.

[0012] Optionally, the capacitance values ​​of all capacitive sensors on the steering wheel body are collected in real time, including: Capacitance values ​​are simultaneously acquired using a multiplexed electrode sensor and a segmented auxiliary capacitor sensor. Set an effective capacitance detection threshold, which is adapted to the coupling capacitance range between the human hand and the electrode; When the capacitance value of any set of capacitance sensors continuously exceeds the effective capacitance detection threshold and remains so for a preset time, it is determined as a potential effective contact and the ECG electrocardiogram detection module is activated.

[0013] Optionally, starting ECG differential acquisition after capacitor triggering includes: After capacitor triggering, ECG differential acquisition is initiated to acquire the electrocardiogram signal of the driver's hand; When the detected vibration frequency exceeds the preset frequency, the ECG acquisition chip enables power frequency notch filtering and adaptive filtering algorithms. When hand sweating or fluctuations in skin impedance are detected that cause ECG signal attenuation, the ECG acquisition gain and bias voltage are automatically adjusted.

[0014] Optionally, in S400, the automatic switch to degraded mode when the ECG detection in the main mode fails includes: The downgrade mode is triggered when any of the following situations occur: the ECG test fails to detect a valid QRS complex for a preset number of consecutive preset number of times; the detected vibration frequency exceeds the preset frequency and lasts for a preset time; or the electrode is contaminated or has poor contact and lasts for a preset time. After switching to degraded mode, all capacitance signals are collected at a high-frequency sampling rate. The collected capacitance signals are processed using a sliding window, and the variance of the capacitance values ​​within the window and the proportion of spectral energy in the preset frequency band are calculated. The steering wheel angular velocity is obtained, the ratio of the steering wheel speed to the speed reference value is calculated, and the product of the first constant, the second constant and the ratio is added to obtain the dynamic threshold. The dynamic threshold increases as the steering wheel speed increases. When the variance of the capacitance signal is greater than or equal to the dynamic threshold, and the spectral energy proportion of the preset frequency band is greater than or equal to the preset proportion threshold, it is determined to be a valid grip; otherwise, it is determined to be a release.

[0015] Optionally, the variance threshold is adjusted in real time based on the steering wheel angular velocity, including: Get the steering wheel speed; Calculate the ratio of steering wheel rotation speed to the reference rotation speed value; The dynamic threshold is obtained by adding the product of the first constant, the second constant, and the ratio. The dynamic threshold increases as the steering wheel rotation speed increases.

[0016] Optionally, in S400, after automatically switching to downgrade mode, the method further includes: The switching delay between the primary mode and the degraded mode is less than a preset delay time; During mode switching, maintain the previous valid judgment state; If the driver fails to return to the main mode after the preset recovery time in downgrade mode, a fault alarm will be activated to alert the driver, while the downgrade mode will continue to operate.

[0017] On the other hand, embodiments of the present invention provide a computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to perform the above-described method.

[0018] The embodiments of the present invention have the following beneficial effects: This invention achieves strong coupling between capacitive sensing and ECG detection by employing a design that reuses the capacitive electrode and the ECG electrode in the same body and with strong spatiotemporal coupling. The capacitive detection electrode and the ECG acquisition electrode are reused as the same electrode with 100% spatial overlap. Furthermore, a shared clock source ensures that the sampling time difference is less than a preset value, guaranteeing that the ECG signal comes from the actual hand holding the steering wheel. This fundamentally eliminates the problem of inanimate objects deceiving the signal and the signal source being inconsistent.

[0019] This invention employs a dual-layer discrimination architecture of capacitive triggering and ECG liveness verification. It uses capacitive signals to quickly trigger detection and ECG electrocardiogram signals to verify human liveness, which ensures both detection response speed and recognition reliability.

[0020] In the degradation mode of this invention, the variance threshold is coupled with the steering wheel speed in real time. By dynamically adjusting the threshold to adapt to different steering conditions, the robustness under complex scenarios such as vibration and bumps is significantly improved, solving the problem of poor adaptability of traditional static thresholds.

[0021] This invention features a well-designed mode switching mechanism and fault degradation strategy, supporting redundancy determination in scenarios such as ECG module failure and poor electrode contact, meeting functional safety level requirements, and improving system functional safety. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of a steering wheel anti-accidental touch hands-off detection system based on the fusion of capacitance and heart rate provided in an embodiment of the present invention; Figure 2 This is a circuit connection diagram of the controller provided in an embodiment of the present invention; Figure 3 This is a flowchart illustrating the steps of a steering wheel anti-accidental touch hands-off detection method based on capacitance and heart rate fusion provided in an embodiment of the present invention. Figure 4 This is a system workflow diagram provided in an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0025] It should be noted that although the device diagram shows a modular division and the flowchart illustrates a logical order, in some cases, the steps shown or described may be performed in a different order than the modular division in the device or the order shown in the flowchart. The terms "first," "second," etc., used in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0027] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a full understanding of embodiments of the invention. However, those skilled in the art will recognize that the technical solutions of the invention can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of the invention.

[0028] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0029] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0030] To address the aforementioned technical issues, this invention proposes a steering wheel anti-accidental touch hands-off detection method and system based on capacitance and heart rate fusion. By strongly coupling capacitance sensing and ECG detection, employing a design that reuses capacitor electrodes and ECG electrodes in the same body with strong spatiotemporal coupling, and combining a dual-layer discrimination architecture of capacitance triggering and ECG liveness verification with a dynamic capacitance degradation algorithm that adapts to steering wheel rotation speed, this method achieves high-precision hands-off detection while preventing accidental touches and meeting functional safety requirements.

[0031] See Figure 1 This invention provides a steering wheel anti-accidental touch hands-off detection system based on capacitance and heart rate fusion, comprising: Steering wheel body 6; The multiplexed electrode sensor 2 is arranged under the leather in the grip area of ​​the steering wheel body 6. The multiplexed electrode sensor 2 is used as both a capacitance detection electrode and an ECG electrocardiogram acquisition electrode. The multiplexed electrode sensor 2 acquires capacitance signals and ECG electrocardiogram signals. Segmented auxiliary capacitance sensor 1, the segmented auxiliary capacitance sensor 1 is arranged under the leather in the non-grip area of ​​the steering wheel body 6, the segmented auxiliary capacitance sensor 1 collects capacitance signals; The controller 3 includes a capacitance detection chip, an ECG acquisition chip, and a main chip. The capacitance signal collected by the multiplexed electrode sensor 2 is transmitted to the capacitance detection chip, the ECG signal collected by the multiplexed electrode sensor 2 is transmitted to the ECG acquisition chip, the capacitance signal collected by the segmented auxiliary capacitance sensor 1 is transmitted to the capacitance detection chip, and the signal processed by the capacitance detection chip and the ECG acquisition chip is sent to the main chip. The power management chip converts the voltage of the vehicle power supply 4 to power the main chip, the multiplexed electrode sensor 2, the segmented auxiliary capacitor sensor 1, the capacitor detection chip and the ECG acquisition chip. A clock module provides a synchronization clock for the main chip, the capacitance detection chip, and the ECG acquisition chip.

[0032] The following is a detailed description of the steering wheel anti-accidental touch and hands-off detection method based on the fusion of capacitance and heart rate proposed in this invention: In this embodiment, the hardware structure is first arranged by placing a multiplexed electrode sensor 2 and a segmented auxiliary capacitance sensor 1 under the leather of the grip area and non-grip area of ​​the steering wheel body 6, respectively. The capacitance detection chip, ECG acquisition chip and main chip in the controller 3 work together to achieve spatiotemporal synchronization of capacitance detection and ECG acquisition. It defaults to the main mode and uses a two-layer discrimination architecture that combines capacitance triggering and ECG liveness verification for off-hand detection. When the ECG detection in the main mode fails, it automatically switches to the degraded mode and realizes off-hand determination through dynamic capacitance analysis to ensure continuous operation.

[0033] refer to Figure 1 and Figure 2 The hardware structure provided in this embodiment of the invention is arranged as follows: A multiplexed electrode sensor 2 is arranged under the leather in the 3 o'clock and 9 o'clock areas (the areas where the driver typically grips the steering wheel) of the steering wheel body 6. The surface of this multiplexed electrode sensor 2 is reused as an ECG detection electrode, achieving dual-purpose functionality. The sensor material is silver-plated copper wire, balancing capacitive coupling and ECG bioelectric signal acquisition efficiency. An insulating layer with a thickness of 0.2mm or less is provided on the surface to ensure safety for human contact without affecting capacitive coupling and ECG signal transmission. Capacitive detection and ECG detection share the same set of electrodes with 100% spatial overlap. They also share the same clock source with a sampling time deviation of less than 1ms, ensuring the timing consistency of the two signals. Each hand corresponds to a differential ECG acquisition channel, with a total of two ECG channels set up to acquire ECG signals from the driver's left and right hands respectively, improving recognition reliability. The data fusion period is set to 100ms, balancing detection response speed and data processing efficiency. Two sets of segmented auxiliary capacitive sensors 1 are arranged under the leather in the 10 o'clock-2 o'clock and 4 o'clock-8 o'clock areas of the steering wheel body 6 to avoid missed detections caused by the grip position deviating from the 3 o'clock and 9 o'clock areas; the two sets of auxiliary capacitive sensors 1 are symmetrically arranged and have complementary coverage, which can completely cover the entire circumference area outside the 3 o'clock and 9 o'clock multiplexed electrodes.

[0034] refer to Figure 2The controller 3 includes a capacitance detection chip, an ECG acquisition chip, a main chip (MCU), a power management chip, and a clock module. Multiplexed electrode sensor 2 collects capacitance and ECG signals, transmitting them to the capacitance detection chip and ECG acquisition chip respectively. After processing, the signals are sent to the main chip (MCU). Segmented auxiliary capacitance sensor 1 collects capacitance signals and transmits them to the capacitance detection chip, which converts them into digital signals before sending them to the MCU (main chip). The power management chip converts the voltage of the vehicle power supply 4 from 12V to 3.5V and 5V, supplying power to the main chip (MCU), all sensors, and the acquisition chip, ensuring the normal operation of all components. The clock module (16MHz crystal oscillator) provides a synchronous clock for the main chip (MCU), capacitance detection chip, and ECG acquisition chip, ensuring that the sampling timing deviation is less than 1ms. In the specific circuit diagram, red lines represent power lines (grounding lines are omitted), and black lines represent signal lines.

[0035] like Figure 3 As shown, Figure 3 A method for preventing accidental hand-off detection of a steering wheel based on capacitance and heart rate fusion is provided in this embodiment of the invention. The method includes the following steps: S100: Real-time acquisition of capacitance values ​​of all capacitive sensors on the steering wheel body 6. When the capacitance value of any group of capacitive sensors continuously exceeds the effective capacitance detection threshold and remains at that threshold for a preset time, it is determined to be a potential effective contact and the ECG electrocardiogram detection module is activated. S200, after capacitor triggering, starts ECG differential acquisition, acquires the electrocardiogram signal of the driver's hand, identifies the QRS complex in the electrocardiogram signal through signal processing algorithm, and determines it as a valid human electrocardiogram signal when a preset number of stable QRS waveforms are continuously detected. S300: When it is determined that the capacitance signal is valid, the ECG signal is valid, and the capacitance signal and the ECG signal come from the same set of electrodes, it is considered a valid grip. When the ECG detection in the main mode fails, the S400 automatically switches to the degraded mode and uses dynamic capacitance analysis to determine if the device is off-hand.

[0036] This invention proposes a steering wheel anti-accidental touch hand-off detection method and system based on the fusion of capacitance and heart rate, which forms a complete hand-off detection link by strongly coupling capacitive sensing and electrocardiogram detection. Among them, the reused electrode sensor 2 realizes the reuse of the capacitance detection electrode and the ECG acquisition electrode in the same body, with 100% spatial overlap, and the shared clock source achieves a sampling time difference of less than 1ms, ensuring that the ECG signal comes from the actual hand holding the steering wheel, eliminating the problem of inanimate objects deceiving and signal source inconsistency from the root. The main mode adopts a two-layer discrimination architecture of capacitance trigger and ECG liveness verification. It quickly triggers detection through capacitance signal and then realizes human liveness verification through ECG signal, which not only ensures detection response speed, but also improves recognition reliability. The degradation mode adopts a dynamic capacitance analysis algorithm that adapts to the steering wheel speed. The variance threshold is coupled with the steering wheel speed in real time. By dynamically adjusting the threshold to adapt to different steering conditions, it significantly improves the robustness under complex scenarios such as vibration and bumps, and solves the problem of poor adaptability of traditional static thresholds. The perfect mode switching mechanism and fault degradation strategy support redundant judgment in scenarios such as ECG module failure and poor electrode contact, meet functional safety level requirements, and improve system functional safety.

[0037] In some embodiments, S100 involves real-time acquisition of the capacitance values ​​of all capacitance sensors on the steering wheel body 6, including: S111, the capacitance value is synchronously acquired by multiplexed electrode sensor 2 and segmented auxiliary capacitor sensor 1; S112, Set an effective capacitance detection threshold, wherein the effective capacitance detection threshold is adapted to the coupling capacitance range between the human hand and the electrode. S113, when the capacitance value of any group of capacitance sensors continuously exceeds the effective capacitance detection threshold and remains so for a preset time, it is determined as a potential effective contact and the ECG electrocardiogram detection module is activated.

[0038] In this embodiment, by combining the multiplexed electrode sensor 2 with the segmented auxiliary capacitor sensor 1, all possible gripping areas of the steering wheel can be covered, avoiding missed detections when the driver's gripping position deviates from the conventional 3 o'clock and 9 o'clock areas, thus improving the comprehensiveness of the detection range. At the same time, the preset time setting can filter out interference caused by brief accidental touches, reduce unnecessary ECG module activation, and lower system power consumption.

[0039] In some embodiments, S200, starting ECG differential acquisition after capacitor triggering includes: S211, after capacitor triggering, starts ECG differential acquisition to acquire the electrocardiogram signal of the driver's hand; S212, when the vibration frequency is detected to exceed the preset frequency, the ECG acquisition chip enables the power frequency notch filter and adaptive filtering algorithm to filter out vibration interference and power frequency interference, ensuring clear ECG signal; S213: When hand sweating or skin impedance fluctuations are detected, causing ECG signal attenuation, the ECG acquisition gain and bias voltage are automatically adjusted to ensure effective acquisition of ECG signals. S214, the QRS complex in the electrocardiogram signal is identified by the signal processing algorithm, and the heart rate range is detected. When a preset number of stable QRS waveforms are continuously detected, it is determined to be a valid human electrocardiogram signal.

[0040] In this embodiment, adaptive filtering and gain adjustment can be used to adapt to the ECG signal acquisition needs of different skin types and environments, reduce the interference of vibration and skin condition changes on signal acquisition under driving conditions, improve the accuracy of QRS group recognition, and ensure the reliability of liveness verification.

[0041] In some embodiments, S400, the automatic switching to a degraded mode when the ECG detection in the main mode fails includes: S411, when any of the following situations occur, the ECG electrocardiogram test fails to detect a valid QRS complex for a preset number of consecutive preset numbers, the detected vibration frequency exceeds the preset frequency and lasts for a preset time, or the electrode is contaminated or has poor contact and lasts for a preset time, the downgrade mode is triggered. S412, after switching to degraded mode, acquires all capacitor signals at a high-frequency sampling rate and processes the acquired capacitor signals using a sliding window. S413, Calculate the variance of the capacitance value within the sliding window; S414, calculate the spectral energy percentage of the capacitor signal within the preset frequency band; S415, obtain the steering wheel angular velocity, calculate the ratio of the steering wheel speed to the speed reference value, add the product of the first constant and the second constant and the ratio to obtain the dynamic threshold, the dynamic threshold increases as the steering wheel speed increases; S416, when the variance of the capacitor signal is greater than or equal to the dynamic threshold and the spectral energy ratio of the preset frequency band is greater than or equal to the preset ratio threshold, it is determined to be a valid grip; otherwise, it is determined to be a release.

[0042] In this embodiment, by adjusting the dynamic threshold in real time, it can adapt to steering conditions at different speeds: when the steering wheel speed is high, the vehicle itself is in the process of steering operation, and the overall vibration amplitude of the steering wheel is greater. At this time, raising the variance threshold can avoid misjudgment caused by vibration; when the steering wheel speed is low, lowering the variance threshold can effectively identify the driver's light grip action and avoid missed judgment. Combined with the spectrum energy ratio analysis, it further distinguishes the capacitance fluctuation generated by the actual grip and the capacitance fluctuation caused by environmental interference, which greatly improves the accuracy of off-hand detection under complex conditions and ensures that the system can still work reliably after ECG failure.

[0043] Specifically, the main mode is the system's default operating mode, employing a dual-layer discrimination architecture of capacitive triggering and ECG verification, balancing response speed and recognition reliability. During the capacitive triggering phase, the capacitance values ​​of all capacitive sensors on the steering wheel (2 sets of multiplexed electrodes + 2 sets of auxiliary capacitors) are collected in real time, with the effective capacitance detection threshold set to C1 (adapting to the coupling capacitance range between the human hand and the electrodes). When the capacitance value of any set of capacitive sensors continuously exceeds the threshold and remains above it for more than 5 seconds, it is determined to be a potentially valid contact, activating the ECG detection module. During the ECG verification phase, differential ECG acquisition is initiated within 100ms after capacitive triggering, acquiring the driver's hand's ECG signal. A signal processing algorithm identifies the QRS complex (the core waveform characteristic of human ECG) in the ECG signal and detects the heart rate range (ensuring coverage of normal human heart rate range and abnormal heart rate scenarios). When three stable QRS waveforms are detected consecutively, it is determined to be a valid human ECG signal. During the judgment rule phase, a valid grip is determined when all three of the following conditions are met: the capacitance signal is valid (the capacitance value is within the threshold range and remains stable); the ECG signal is valid (a stable QRS complex is detected and the heart rate is within the valid range); and the capacitance signal and the ECG signal come from the same set of electrodes (ensuring that the ECG signal comes from the actual gripping hand).

[0044] The degradation mode uses dynamic capacitance analysis to determine when the device is removed from the hand, ensuring continuous system operation. Triggering conditions include: three consecutive ECG tests failing to detect a valid QRS complex (indicating ECG acquisition failure); detecting a vibration frequency greater than 15Hz for more than 10 seconds (in extreme turbulence scenarios, ECG signal interference is too great, and the frequency and time can be adjusted according to the specific situation); and electrode contamination or poor contact lasting for more than 5 seconds (e.g., oil or water stains on the hands causing abnormal contact). The degradation process includes: after switching the system to degradation mode, acquiring all capacitance signals (2 sets of multiplexed electrodes + 2 sets of auxiliary capacitors) at a high-frequency sampling rate of ≥200Hz to improve the temporal resolution of the signals; processing the acquired capacitance signals using a 0.1s sliding window, calculating the variance σ² of the capacitance values ​​within the window (reflecting the fluctuation characteristics of the capacitance signal, with larger fluctuations when held by a human and minimal fluctuations when there is no living object in contact) and the spectral energy proportion of the 1-10Hz frequency band (capacitance fluctuations caused by slight movements of the human hand are mainly concentrated in this frequency band); in the dynamic threshold calculation stage, adjusting the variance threshold in real time according to the steering wheel angular velocity, the dynamic threshold formula is as follows: ; The steering wheel rotation speed is measured in ° / s, and the dynamic threshold increases with the rotation speed to accommodate the capacitance fluctuation characteristics under steering conditions. The determination criteria are: when the variance σ² of the capacitance signal is greater than or equal to the dynamic threshold, and the spectral energy proportion of the 1-10Hz frequency band is greater than or equal to 70%, it is determined to be a valid grip; otherwise, it is determined to be a release from the hands.

[0045] The mode switching protection mechanism includes: a switching delay of less than 500ms between the main mode and the downgraded mode to ensure timely system response and prevent detection gaps; during mode switching, the system maintains the previous valid judgment state (valid grip or release) to prevent judgment jumps or data frame drops, ensuring continuous detection; if the downgraded mode continues for 10 minutes without returning to the main mode (indicating a continuous ECG module failure or severe electrode abnormality), the system will activate a fault alarm and alert the driver, while maintaining continuous operation in the downgraded mode to prevent system failure.

[0046] The flowchart of the system operation of this invention is shown below. Figure 4 As shown.

[0047] Example 1: Normal multimodal hand-off determination; Scenario: The driver has his hands on the steering wheel at the 3 o'clock position, and the vehicle is moving steadily in a straight line.

[0048] 1. The system collects the capacitance value at the 3 o'clock position in real time. It detects that the capacitance value is stable within the threshold range and remains stable for 5 seconds, which meets the capacitance triggering condition. 2. The system started ECG acquisition within 100ms after capacitor triggering, successfully detected a stable QRS complex, and calculated the heart rate to be 72 beats / min, which is within the effective heart rate range; 3. Three stable QRS waveforms were continuously detected, and the capacitance signal and ECG signal came from the same set of ring electrodes, meeting the requirement of being of the same origin; 4. The system determines that the grip is valid and does not trigger the hands-off alarm; the autopilot system is working normally.

[0049] Example 2: ECG failure leads to degradation mode; Scenario: The driver's hands are at the 9 o'clock position on the steering wheel. Dry hands cause excessive skin resistance, resulting in poor contact of ECG signals.

[0050] 1. The capacitance detection is normal and the capacitance value is stable within the threshold range, but the ECG acquisition module fails to detect a valid QRS complex for 3 consecutive times, triggering the degradation mode; 2. The system completes the switch from primary mode to degraded mode within 200ms (calibrable), maintaining "valid grip" during the switch without any jumps; 3. In degraded mode, the capacitor signal is sampled at a high frequency of 200Hz (2 sets of multiplexed electrodes + 2 sets of auxiliary capacitors), and the variance σ²=0.8 of the 0.1s sliding window is calculated. At this time, the steering wheel speed is 20° / s. 4. Calculate according to the dynamic threshold formula: ; 5. The variance σ² of the detected capacitor signal is greater than or equal to 0.7, and the energy proportion of the 1-10Hz spectrum is greater than or equal to 75%, which meets the degradation mode judgment condition. 6. The system determines that the grip is valid and continues normal operation. Once the hand contact condition improves, it will automatically switch back to the main mode.

[0051] Example 3: Anti-accidental touch / spoofing test; Scenario: Simulate accidental touch / deception scenario, cover and suspend 500g of pork (simulating contact with inanimate objects) at the 10 o'clock-2 o'clock position of the steering wheel (auxiliary capacitor area).

[0052] 1. When pork comes into contact with the auxiliary capacitor, the capacitance detection value is within the threshold range, within the valid range and lasts for 5 seconds, thus meeting the capacitor triggering condition; 2. The system started ECG acquisition, but pork does not have human ECG signals, and QRS complexes could not be detected. 3. According to the judgment rules, the system rejected the valid grip because the ECG signal was invalid, with a false judgment rate of 0%, successfully resisting the deception of inanimate objects.

[0053] Example 4: Robustness test on bumpy roads; Scenario: Simulating a bumpy road surface, the vehicle is continuously vibrating at 15Hz, and the driver's hands are on the steering wheel at the 4 o'clock-8 o'clock position (auxiliary capacitor area).

[0054] 1. Traditional torque-based off-hand detection is susceptible to vibration interference in this scenario, with a false judgment rate as high as 30%. 2. In the main mode of this invention, the ECG module uses 50Hz power frequency notch filtering + adaptive filtering to effectively filter out vibration interference and reduce the false detection rate of off-hand to below 1%. If the ECG module fails due to vibration interference, the system switches to degraded mode. Through dynamic capacitance analysis (collecting signals from 2 sets of multiplexed electrodes + 2 sets of auxiliary capacitors), it can still maintain an off-hand detection accuracy of over 97% and avoid system failure.

[0055] Furthermore, embodiments of the present invention also disclose a computer program product or computer program stored in a computer-readable storage medium. A processor of a computer device can read the computer program from the computer-readable storage medium, and the processor executes the computer program, causing the computer device to perform the described method. Similarly, the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0056] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0057] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0058] The terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0059] It should be understood that in this invention, "at least one (item)" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0060] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0061] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0062] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0063] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0064] The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and spirit of the present invention should be within the scope of the claims of the present invention.

Claims

1. A steering wheel anti-accidental touch hands-off detection system based on capacitance and heart rate fusion, characterized in that, include: Steering wheel body; A multiplexed electrode sensor is arranged under the leather in the grip area of ​​the steering wheel body. The multiplexed electrode sensor is used as both a capacitance detection electrode and an ECG electrocardiogram acquisition electrode. The multiplexed electrode sensor acquires capacitance signals and ECG electrocardiogram signals. A segmented auxiliary capacitance sensor is arranged under the leather in the non-grip area of ​​the steering wheel body, and the segmented auxiliary capacitance sensor collects capacitance signals. The controller includes a capacitance detection chip, an ECG acquisition chip, and a main chip. The capacitance signal acquired by the multiplexed electrode sensor is transmitted to the capacitance detection chip, the ECG signal acquired by the multiplexed electrode sensor is transmitted to the ECG acquisition chip, the capacitance signal acquired by the segmented auxiliary capacitance sensor is transmitted to the capacitance detection chip, and the signal processed by the capacitance detection chip and the ECG acquisition chip is sent to the main chip. A power management chip that converts the vehicle power supply voltage to power the main chip, the multiplexed electrode sensor, the segmented auxiliary capacitor sensor, the capacitance detection chip, and the ECG acquisition chip. A clock module provides a synchronization clock for the main chip, the capacitance detection chip, and the ECG acquisition chip.

2. The system according to claim 1, characterized in that, The multiplexed electrode sensor is arranged in the 3 o'clock and 9 o'clock areas of the steering wheel body; the segmented auxiliary capacitance sensor includes two sets, which are respectively arranged in the 10 o'clock-2 o'clock area and the 4 o'clock-8 o'clock area of ​​the steering wheel body.

3. The system according to claim 1, characterized in that, The multiplexed electrode sensor has an insulating layer on its surface and is made of silver-plated copper wire. The multiplexed electrode sensor corresponds to two sets of differential ECG acquisition channels, which respectively acquire ECG signals from the driver's left and right hands. The capacitance detection and the ECG detection share the same set of electrodes and the same clock source.

4. A steering wheel anti-accidental touch and hands-off detection method based on capacitance and heart rate fusion, applied to the system described in any one of claims 1 to 3, characterized in that, The method includes the following steps: The capacitance values ​​of all capacitive sensors on the steering wheel body are collected in real time. When the capacitance value of any group of capacitive sensors continuously exceeds the effective capacitance detection threshold and remains so for a preset time, it is determined to be a potential effective contact and the ECG electrocardiogram detection module is activated. After capacitor triggering, ECG differential acquisition is started to acquire the electrocardiogram signal of the driver's hand. The QRS complex in the electrocardiogram signal is identified by the signal processing algorithm. When a preset number of stable QRS waveforms are continuously detected, it is determined to be a valid human electrocardiogram signal. When it is determined that the capacitance signal is valid, the ECG signal is valid, and the capacitance signal and ECG signal come from the same set of electrodes, it is considered a valid grip; When the ECG detection in the main mode fails, it automatically switches to the degraded mode, which uses dynamic capacitance analysis to determine if the device is off-hand.

5. The method according to claim 4, characterized in that, Real-time acquisition of capacitance values ​​from all capacitive sensors on the steering wheel body, including: Capacitance values ​​are simultaneously acquired using a multiplexed electrode sensor and a segmented auxiliary capacitor sensor. Set an effective capacitance detection threshold, which is adapted to the coupling capacitance range between the human hand and the electrode; When the capacitance value of any set of capacitance sensors continuously exceeds the effective capacitance detection threshold and remains so for a preset time, it is determined as a potential effective contact and the ECG electrocardiogram detection module is activated.

6. The method according to claim 4, characterized in that, The step of initiating ECG differential acquisition after capacitor triggering includes: After capacitor triggering, ECG differential acquisition is initiated to acquire the electrocardiogram signal of the driver's hand; When the detected vibration frequency exceeds the preset frequency, the ECG acquisition chip enables power frequency notch filtering and adaptive filtering algorithms. When hand sweating or fluctuations in skin impedance are detected that cause ECG signal attenuation, the ECG acquisition gain and bias voltage are automatically adjusted.

7. The method according to claim 4, characterized in that, When the ECG monitoring in the main mode fails, the system automatically switches to a degraded mode, including: The downgrade mode is triggered when any of the following situations occur: the ECG test fails to detect a valid QRS complex for a preset number of consecutive preset number of times; the detected vibration frequency exceeds the preset frequency and lasts for a preset time; or the electrode is contaminated or has poor contact and lasts for a preset time. After switching to degraded mode, all capacitance signals are collected at a high-frequency sampling rate. The collected capacitance signals are processed using a sliding window, and the variance of the capacitance values ​​within the window and the proportion of spectral energy in the preset frequency band are calculated. The steering wheel angular velocity is obtained, the ratio of the steering wheel speed to the speed reference value is calculated, and the product of the first constant, the second constant and the ratio is added to obtain the dynamic threshold. The dynamic threshold increases as the steering wheel speed increases. When the variance of the capacitance signal is greater than or equal to the dynamic threshold, and the spectral energy proportion of the preset frequency band is greater than or equal to the preset proportion threshold, it is determined to be a valid grip; otherwise, it is determined to be a release.

8. The method according to claim 7, characterized in that, The variance of the capacitance value within the calculation window and the proportion of spectral energy in the preset frequency band are included: The acquired capacitance signals are processed using a sliding window. Calculate the variance of the capacitance value within the sliding window; Calculate the spectral energy percentage of the capacitor signal within the preset frequency band; The variance reflects the fluctuation characteristics of the capacitance signal, and the spectral energy ratio reflects the capacitance fluctuation characteristics caused by the micro-movement of the human hand.

9. The method according to claim 4, characterized in that, After automatically switching to downgrade mode, the method further includes: The switching delay between the primary mode and the degraded mode is less than a preset delay time; During mode switching, maintain the previous valid judgment state; If the driver fails to return to the main mode after the preset recovery time in downgrade mode, a fault alarm will be activated to alert the driver, while the downgrade mode will continue to operate.

10. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to perform the method as described in any one of claims 4 to 9.

Images