Steering wheel multi-area hand separation detection device and method based on high-order intelligent driving

Abstract

The invention discloses a steering wheel multi-area hand separation detection device and method based on high-order intelligent driving, and relates to the technical field of intelligent driving safety. The apparatus includes a steering wheel assembly, a flexible sensor pad, and an electronic control unit (ECU). The annular holding part of the steering wheel is divided into at least three physical and signal independent sensing areas, and all the areas are arranged in a crossed mode to achieve non-blind area coverage. The flexible sensor pad is integrated between a steering wheel framework and a skin layer, and a sensor layer of the flexible sensor pad is composed of conductive fabric, metal wires or metal foils and used for detecting capacitance changes. The ECU is used for collecting signals of all the induction areas and judging the hand state of a driver through software integrating temperature compensation, signal filtering and a multi-source information fusion algorithm. According to the method, high-precision hand-leaving detection is realized based on the device. The method solves the problems of high false alarm rate and poor environmental adaptability in the prior art, and has the advantages of high detection precision, good reliability, strong process compatibility and OTA upgrade support.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving and active safety technology for automobiles, specifically to a steering wheel hands-off detection device and its detection method for advanced intelligent driving systems. Background Technology

[0002] With the continuous improvement of automotive intelligence, Level 2 / Level 3 Advanced Driver Assistance Systems (ADAS) have gradually become widespread. In these systems, while the driver does not need to operate the vehicle continuously, they must maintain constant awareness of the driving environment and be prepared to take over vehicle control at any time in response to system requests or emergencies. Therefore, domestic and international regulations and industry standards clearly require that vehicles with autonomous driving capabilities must be equipped with effective hands-off detection (HOD) functionality to prevent the driver from taking their hands off the steering wheel while in assisted driving mode, thereby ensuring driving safety.

[0003] Currently, mainstream hands-off detection technologies mainly include torque-based detection and vision / image recognition detection. Torque-based detection relies on the torque sensor in the vehicle's electric power steering system to determine whether the driver's hands are on the steering wheel by detecting the steering torque applied by the driver. However, this technology has a significant drawback: when the driver lightly grips the steering wheel, the resulting torque change is very slight and easily masked by system noise and mechanical friction, leading to insufficient detection sensitivity. Vision / image recognition detection uses a camera installed inside the vehicle to directly identify whether the driver's hands are on the steering wheel using computer vision algorithms. While intuitive, its performance is greatly affected by environmental factors. For example, in poor lighting conditions such as at night, in strong backlight, or in tunnels, image quality deteriorates, and recognition accuracy drops sharply. Furthermore, the driver's hands, clothing, or other objects may obstruct the camera's view, causing false positives.

[0004] Publication No. (CN114852092A) discloses a method and apparatus for detecting steering wheel hands-off issues. This scheme integrates data from a capacitive sensor and a torque sensor to construct redundant detection logic. The method includes: periodically acquiring the capacitance value collected by the steering wheel capacitive sensor and simultaneously acquiring the torque value collected by the torque sensor; calculating the change in capacitance value; when the change in capacitance value is less than a preset threshold, and the working state of the capacitive sensor itself is determined to be "invalid," the final hands-off detection result is then determined by comprehensively considering the working state of the capacitive sensor and the backup torque value.

[0005] This patent aims to improve the overall robustness of the system in special scenarios where a single sensor fails or is interfered with, by using heterogeneous sensors—that is, the fusion of capacitance and torque and redundant backup—to ensure continuous provision of hands-off detection information. However, the optimization focus of this solution is mainly on improving the reliability of "whether the system can continuously output a binary judgment of hands-off / hands-on," rather than fundamentally improving the accuracy and precision of the perception of the driver's grip status itself.

[0006] In summary, existing technologies all have shortcomings in terms of reliability, adaptability, or economy, making it difficult to meet the stringent requirements of high-level intelligent driving systems for high precision, high robustness, and low cost of hands-off detection functions. Summary of the Invention

[0007] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a device and method for multi-zone hand-off detection of the steering wheel based on advanced intelligent driving. This device, through a multi-zone capacitive sensing design combined with a flexible sensor pad and intelligent algorithms, can achieve high-precision, high-reliability, and low-false-alarm-rate hand status detection.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: A device for multi-zone hands-off detection of a steering wheel based on advanced intelligent driving includes: a steering wheel assembly, a flexible sensor pad, and an electronic control unit (ECU); the annular grip portion of the steering wheel assembly is divided into at least three physically independent and signal-distinguishable sensing zones; the flexible sensor pad includes a flexible base fabric and a sensor layer attached thereto; the ECU is connected to the flexible sensor pad.

[0009] Furthermore, at least three sensing zones include: a first zone covering the lower half of the steering wheel, a second zone covering the left side of the upper half of the steering wheel, and a third zone covering the right side of the upper half of the steering wheel. The first zone is further divided into left and right sub-zones in the lower half of the steering wheel. The sensing zones are arranged in a cross pattern in space to achieve blind spot-free coverage.

[0010] Furthermore, the steering wheel assembly also includes, from the inside out, the following components arranged sequentially: a steering wheel frame 1, a foam body 2, a flexible sensor 3, and a skin layer 4; the foam body 2 is fixed to the outside of the steering wheel frame 1 by a first adhesive layer; the flexible sensor 3 pad is fixed to the outside of the foam body 2 by a second adhesive layer; and the skin layer 4 covers the outside of the flexible sensor pad 3.

[0011] Furthermore, the sensor layer of the flexible sensor pad is composed of at least one of conductive fabric, metal wire, or metal foil; the first adhesive layer and the second adhesive layer are double-sided adhesive layers or other adhesive materials.

[0012] Furthermore, the Electronic Control Unit (ECU) includes: a signal acquisition and processing module, a main control logic module, a vehicle communication module, and a power management and safety monitoring module; the signal acquisition and processing module performs analog-to-digital conversion and preprocessing on the raw capacitance signals of each sensing area; the main control logic module runs the hand state determination algorithm; the vehicle communication module performs data interaction with the advanced intelligent driving system and reports hand state information; the power management and safety monitoring module ensures stable power supply to the system and performs functional safety monitoring.

[0013] Furthermore, this device also features a steering wheel heating function, with the flexible sensor layer and heating element arranged in layers in space or sharing some structures, and the electronic control unit (ECU) used to control the heating logic.

[0014] This invention also provides a detection method based on a multi-zone hands-off detection device for steering wheels in advanced intelligent driving systems, comprising the following steps: S1: After the electronic control unit (ECU) is powered on, it performs self-test and initialization, controls the flexible sensor pads of each sensing area to start working, and collects signals within the preset learning period to establish the dynamic capacitance signal baseline value of each sensing area. S2: The signal acquisition and processing module synchronously acquires the original capacitance signal of each of the sensing areas at a fixed frequency; S3: The acquired raw capacitance signal is sequentially processed by baseline subtraction, digital filtering and temperature adaptive compensation to obtain the preprocessed signal value of each sensing area reflecting the state of hand approach or contact. S4: The main control logic module compares the preprocessed signal values ​​of each sensing area with the dynamic threshold, and combines them with at least one of the steering wheel torque signal and visual perception signal from the vehicle for fusion judgment. The driver's hand state is identified through the hand state determination algorithm. The hand state includes single-hand operation, two-hand operation, specific grip area recognition, and off-hand state. S5: The vehicle communication module reports the determined hand status information to the advanced intelligent driving system; when it is determined to be a hands-off state and the duration exceeds the preset warning time, a graded warning signal is triggered.

[0015] Furthermore, in step S4, the hand state determination algorithm is as follows: when only one sensing area detects a valid capacitance signal, it is determined to be a single-handed operation; when at least two sensing areas detect a valid capacitance signal, it is determined to be a two-handed operation; when none of the sensing areas detect a continuous valid capacitance signal, it is determined to be a hands-free state.

[0016] Furthermore, in step S4, the electronic control unit (ECU) also receives at least one of the temperature signal, steering wheel torque signal, and visual perception signal from the vehicle, and fuses the signal with the capacitance change signal to dynamically optimize the threshold for the hand-off determination.

[0017] Furthermore, the method also includes a step of processing the capacitance change signal, the processing of which includes at least a signal compensation algorithm based on temperature change and a signal filtering algorithm for noise suppression.

[0018] Compared with the prior art, the apparatus and method provided by the present invention have the following significant advantages: (1) The multi-zone design adopted in this invention can not only detect whether the hand is off, but also accurately distinguish whether it is held with one hand or two hands, and can identify the specific area where the hand is located, providing a more refined data dimension for assessing the driver's readiness to take over, and adapting to complex and ever-changing real driving postures.

[0019] (2) This invention adopts the principle of capacitive sensing, which can sensitively respond to slight contact or even proximity of the hand, and is not affected by the mechanical friction of the steering system. The flexible sensor pad and layered structure design ensure signal stability and anti-electromagnetic interference capability. Combined with intelligent algorithms for multi-source data fusion, the possibility of false alarms caused by misjudgment by a single sensor is further reduced.

[0020] (3) The flexible sensor pad is made of textile or bonding process, and the modular design makes it easy to integrate with steering wheels of different shapes. The layered fixing structure is simple and reliable, suitable for large-scale automated production of automotive parts, and conducive to cost control.

[0021] (4) The design of this invention fully considers the compatibility with other functions of the steering wheel, such as heating, touch control, decorative lights, etc. Functional integration can be achieved through layered or reused design, adapting to the future trend of diversified and integrated intelligent steering wheels. Attached Figure Description

[0022] This manual includes the following figures, which illustrate the following: Figure 1 This is a logic structure block diagram of a multi-zone hands-off detection device for steering wheels based on advanced intelligent driving according to the present invention; Figure 2 This is a schematic diagram of the sensor area division of the steering wheel assembly of the present invention; Figure 3 This is a model diagram of the steering wheel of the present invention; Figure 4 This is a schematic diagram of the layered structure of the steering wheel cross-section of the present invention; Figure 5 This is a schematic diagram of the software functional module architecture of the electronic control unit (ECU) of the device of the present invention; The components include: 1. Steering wheel frame; 2. Foam body; 3. Flexible sensor pad; 4. Skin layer. Detailed Implementation

[0023] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings, in order to help those skilled in the art to have a more complete, accurate and in-depth understanding of the inventive concept and technical solution of the present invention, and to facilitate its implementation.

[0024] This embodiment details a multi-zone hands-off detection device for steering wheels based on advanced intelligent driving, constructed according to the present invention. The device mainly consists of three parts: a steering wheel assembly, a flexible sensor pad, and an electronic control unit (ECU).

[0025] The steering wheel assembly is based on a modified traditional automotive steering wheel frame structure. This invention features precise sensor zoning of the annular area where the driver grips the steering wheel.

[0026] like Figure 2 , Figure 3 The diagram shows a schematic and model of the steering wheel assembly's sensing area division. In this embodiment, the steering wheel rim is divided into three physically isolated, electrically independent sensing areas, each capable of individually acquiring signals: a first sensing area, a second sensing area, and a third sensing area.

[0027] The first sensing area covers the lower half of the steering wheel and is further subdivided circumferentially into a first left sensing area and a first right sensing area, corresponding to the left and right sides of the lower half of the wheel, respectively. The second sensing area covers the left side of the upper half of the steering wheel. The third sensing area covers the right side of the upper half of the steering wheel. These sensing areas are not clearly separated by boundaries in three-dimensional space, but rather arranged in an overlapping, cross-hatching pattern to achieve blind-spot-free hand detection coverage. Specifically, the detection electrodes of the first sensing area are not only located on the front of the lower half of the wheel rim, but their electrode patterns or wiring also extend upwards along the side of the wheel rim, partially covering the back and inner rim areas. Similarly, the electrodes of the second and third sensing areas, while covering the main front area of ​​the upper half of the wheel rim, also extend downwards to part of the side edges and may extend to part of the back area of ​​the lower half of the wheel rim, thus forming a spatially staggered coverage.

[0028] The flexible sensor pad mainly comprises, from bottom to top: a flexible base fabric, a sensor layer, and a surface insulating layer. The flexible base fabric is typically made of polyester fiber cloth, non-woven fabric, or similar flexible insulating materials, possessing good bending resistance and dimensional stability. The sensor layer is attached to the flexible base fabric through weaving, printing, etching, or bonding processes. In this embodiment, the sensor layer uses silver fiber conductive fabric cut or woven into specific electrode patterns. These patterns correspond to the three sensing areas mentioned above, and the electrodes in each area are separated by insulating gaps. The electrodes are led out from the edge of the base fabric through extremely fine insulated wires, forming independent signal channels Channel1, Channel2, and Channel3. Besides conductive fabric, depending on cost and performance requirements, the sensor layer can also be constructed using etched copper foil, printed silver paste, or arranged micro-metal wires. A surface insulating protective layer covers the surface of the sensor layer to prevent electrode oxidation and physical damage.

[0029] like Figure 4 The diagram shows a multi-layered structure of the steering wheel cross-section. It is a multi-layered composite structure integrated with the steering wheel frame through a specific layering process. From the inside out, the layers are: steering wheel frame 1, first adhesive layer, foam 2, flexible sensor pad 3, second adhesive layer, and skin layer 4.

[0030] The steering wheel frame 1, made of metal or high-strength engineering plastic, provides the main support. A first adhesive layer, using high-adhesion double-sided tape coated or adhered to the frame surface, firmly bonds the foam 2 to the frame at predetermined positions, forming the internal cushioning and filling base of the steering wheel. On the outer surface of the foam 2, a thin aluminum foil or conductive cloth can be optionally laid as an electromagnetic shielding layer and grounded to suppress electromagnetic interference from the steering column motor, high-power in-vehicle equipment, etc. A flexible sensor pad 3 is fixed to the shielding layer via a second adhesive layer. Its sensor layer, composed of conductive fabric, metal wires, or metal foil, is responsible for sensing capacitance changes caused by hand proximity or contact. Because the sensor layer is located outside the foam 2 and closer to the outer surface of the steering wheel, the dielectric layer thickness between it and the driver's hand is reduced, thereby improving the sensitivity and response speed of capacitance detection. On the outside of the flexible sensor pad 3, a skin layer 4, made of genuine leather, artificial leather, or other finishing materials, is covered. This layer is bonded to the sensor pad with an adhesive to form the final steering wheel appearance and provides a good tactile feel and durability.

[0031] like Figure 1 The diagram shown is a logical structure block diagram of the device of the present invention. The electronic control unit (ECU) includes a microcontroller (MCU), a capacitor detection front-end circuit, a power management module, a communication interface, and a watchdog circuit.

[0032] The microcontroller (MCU) is responsible for all signal processing, algorithm execution, and logic control. It needs to possess a multi-channel high-precision ADC, sufficient computing power, and automotive-grade reliability. Each sensing area of ​​the steering wheel assembly corresponds to a capacitance detection circuit. This solution uses a chip based on a capacitance-to-digital converter (CDC) or an analog front-end (AFE) to convert minute capacitance changes on the electrodes into digital or analog voltage signals. The circuit integrates a shielding driver to drive the shielding layer, eliminating the influence of parasitic capacitance and improving detection accuracy. The power management module converts the vehicle battery voltage to the stable low voltage required by the system and has overvoltage, overcurrent, reverse connection protection, and power consumption management functions. The communication interface includes a LIN transceiver for communication with the vehicle network. A watchdog circuit monitors the MCU's operating status and forces a system reset in case of program crashes, meeting functional safety requirements.

[0033] This device also integrates a steering wheel heating function, and the electronic control unit (ECU) includes power devices such as MOSFETs to control the on / off state of the heating element and PWM power adjustment.

[0034] like Figure 5 The diagram shows the software functional module architecture of the Electronic Control Unit (ECU), which includes: a signal acquisition and processing module, a main control logic module (CPU), a safety monitoring module, a power management module, and a vehicle communication module.

[0035] The main control logic module's CPU is responsible for running the core algorithms for hand state determination, temperature adaptive compensation, and multi-source information fusion. The signal acquisition and processing module continuously acquires raw signals from the capacitive sensor and performs preprocessing tasks such as analog-to-digital conversion, digital filtering, and dynamic baseline calibration, sending the cleaned and effective signal features to the main control logic for in-depth analysis. Simultaneously, the multi-source information fusion algorithm receives auxiliary signals from the vehicle network in real time, including steering wheel torque, steering angle, and visual perception, and performs cross-validation and intelligent fusion with the capacitive features. This dynamically optimizes the judgment threshold in complex driving scenarios, improving detection accuracy.

[0036] The safety monitoring module includes an independent watchdog timer, program flow monitoring, end-to-end communication protection, and fault diagnosis and handling units, continuously safeguarding system functional safety. The vehicle communication module, an advanced intelligent driving domain controller, provides stable and efficient real-time data interaction, promptly reporting hand status and system health information, and receiving control commands. Furthermore, the power management module provides a clean and stable power supply to all units and performs real-time diagnostics, while the peripheral control interface integrates the drive logic for extended functions such as steering wheel heating. The entire software architecture is designed with excellent configurability and scalability, and supports secure remote firmware updates via the OTA upgrade module.

[0037] The following describes in detail the method for hands-off detection using the multi-zone hands-off detection device for steering wheels based on advanced intelligent driving as described in this invention. This method is a closed-loop control process that runs continuously within the electronic control unit (ECU).

[0038] S1: After the vehicle is powered on, the Electronic Control Unit (ECU) starts. First, a hardware self-test is performed, checking sensor connections, communication links, etc., and then each software module is initialized. The sensors begin working, and the system enters a short learning period. During this period, the system assumes the driver is not touching the steering wheel, thereby acquiring and establishing the initial dynamic baseline values ​​of the capacitance signals in each sensing area.

[0039] Step S2: After initialization, the system enters the main loop. The signal acquisition and processing module synchronously samples the capacitance values ​​of Channel1, Channel2, and Channel3 at a frequency of 100Hz. At each moment, the system obtains a set of independent raw data points [C1, C2, C3].

[0040] S3: The raw data points obtained by the system are preprocessed by subtracting the corresponding real-time dynamic baseline value from the raw value of each channel to obtain the capacitance change ΔC reflected by hand proximity. For example, ΔC1 = C1 - Baseline1; ΔC2 = C2 - Baseline2; ΔC3 = C3 - Baseline3. Then, the ΔC signal is digitally low-pass filtered to remove noise higher than the hand movement frequency, resulting in smooth signal strength values ​​S1, S2, and S3. The temperature adaptive compensation algorithm module makes small-amplitude gain or offset adjustments to S1, S2, and S3 according to the current temperature, and outputs the compensated final signal values ​​V1, V2, and V3. This step ensures that the sensor sensitivity remains consistent in extremely cold or hot environments.

[0041] S4: The main control logic module receives the preprocessed signals V1, V2, and V3 and executes the following judgment logic: comparing each V value with a dynamic threshold Th. The initial value of Th is set during calibration and can be fine-tuned based on the output of the multi-source information fusion algorithm. For example, if the in-cabin camera confirms that the driver's gaze has left the front and their hands are suspected of not being on the steering wheel, the system can temporarily and slightly lower the threshold Th to improve the sensitivity of detecting hands-off states. Conversely, when the vehicle is cornering aggressively, to prevent signal fluctuations caused by hand slippage from being mistakenly judged as hands-off, the threshold Th can be temporarily and slightly increased.

[0042] If V > Th, the sensing area corresponding to that channel is determined to be in an active state; if V ≤ Th, it is in an inactive state. A two-handed grip is determined if and only if the signals V2 and V3 of Channel2 and Channel3 simultaneously exceed the threshold Th and remain stable for more than a certain period of time.

[0043] If V2 > Th and V3 ≤ Th, and this condition persists for a certain period of time, it is determined to be a left-handed grip. If only V3 > Th and V2 ≤ Th, and this condition persists for a certain period of time, it is determined to be a right-handed grip. If only V1 > Th and both V2 and V3 are lower than Th, and this condition persists for a certain period of time, it is determined to be a top-handed grip.

[0044] When the V1, V2, and V3 signals of all channels are below the threshold Th, and this state is maintained continuously for a set safety warning time, the system will not alarm upon the instantaneous disappearance of the signal, but will instead employ time hysteresis to avoid unnecessary interference. For situations that do not meet the above explicit rules, the system may classify them as an uncertain state or maintain the previous definite state, while simultaneously increasing the monitoring frequency or requesting visual assistance from the DMS camera via the vehicle communication module, to prevent alarms from being triggered even after a brief change of hands.

[0045] Based on the above determination based on capacitance signals, the algorithm processes auxiliary information from the bus in parallel: if the vehicle is actively steer, but the HOD system is about to determine that the hands are off, this contradiction will be identified.

[0046] S5: Based on the final determination result of step S4, the Electronic Control Unit (ECU) executes corresponding actions, periodically sending standard messages containing information such as "hands-off status code," "signal strength of each channel," and "system health status" to the ADAS domain controller via the LIN bus. When a hands-off state is determined to have lasted for more than a preset time, the ECU not only reports the status but also sends a high-level warning trigger signal via the communication module. Upon receiving this signal, the ADAS controller will take tiered warning measures according to a preset strategy: for example, firstly, a visual warning will be displayed on the instrument panel and an audible alarm will sound; if the driver continues not to take over, the warning will escalate to a rapid audible warning accompanied by steering wheel vibration; finally, if there is still no response, the system will implement a risk minimization strategy, such as activating hazard lights, slowing down gradually, and stopping in a safe area.

[0047] This embodiment provides a multi-zone steering wheel hands-off detection device and method based on advanced intelligent driving. By dividing the steering wheel grip area into at least three spatially intersecting independent sensing zones, and employing an integrated flexible sensor pad module with the sensor layer placed on the outside of a foam body, a blind-spot-free, highly sensitive capacitive sensing hardware foundation is constructed. Combined with an intelligent electronic control unit (ECU) and software algorithms possessing multi-source information fusion capabilities, the system can accurately and reliably identify single-hand / double-hand grip, the specific grip area, and the hands-off state.

[0048] Compared with existing technologies, this embodiment effectively overcomes the inherent defects of torque detection methods, such as insufficient sensitivity and high false alarm rate, as well as visual detection methods, which are greatly affected by ambient light and are costly. Its beneficial effects are significant: First, through multi-zone collaboration and data fusion, it achieves high-precision, fine-grained monitoring of the driver's hand position, meeting the stringent requirements of advanced intelligent driving systems for assessing driver readiness to take over. Second, the modular design combining capacitive sensing with an internal foam not only improves the reliability and environmental adaptability of the detection but also simplifies the production and assembly process, facilitating mass production and cost control. Third, the overall solution possesses excellent functional compatibility and scalability, seamlessly integrating functions such as steering wheel heating and touch control, and supports continuous software upgrades via OTA, providing solid technical support for the future evolution of intelligent driving safety systems.

[0049] The present invention has been described above by way of example with reference to the accompanying drawings. Obviously, the specific implementation of the present invention is not limited to the above-described manner. Any non-substantial improvements made using the inventive concept and technical solution; or the direct application of the inventive concept and technical solution to other situations without modification, are all within the protection scope of the present invention.

Claims

1. A device for multi-zone hands-off detection of the steering wheel based on advanced intelligent driving, characterized in that, include: The steering wheel assembly includes a flexible sensor pad and an electronic control unit (ECU). The annular grip portion of the steering wheel assembly is divided into at least three physically independent and signal-distinguishable sensing zones. The flexible sensor pad includes a flexible base fabric and a sensor layer attached thereto. The electronic control unit (ECU) is connected to the flexible sensor pad.

2. The device for multi-zone hand-off detection of the steering wheel based on advanced intelligent driving as described in claim 1, characterized in that, The at least three sensing zones include: a first zone covering the lower half of the steering wheel, a second zone covering the left side of the upper half of the steering wheel, and a third zone covering the right side of the upper half of the steering wheel. The first zone is further divided into left and right sub-zones in the lower half of the steering wheel. The sensing zones are arranged in a cross pattern in space to achieve blind spot-free coverage.

3. A device for multi-zone hand-off detection of the steering wheel based on advanced intelligent driving as described in claim 1 or 2, characterized in that, The steering wheel assembly includes, from the inside out, the following components arranged sequentially: a steering wheel frame (1), a foam body (2), a flexible sensor pad (3), and a skin layer (4); the foam body (2) is fixed to the outside of the steering wheel frame (1) by a first adhesive layer; the flexible sensor pad (3) is fixed to the outside of the foam body (2) by a second adhesive layer; and the skin layer (4) covers the outside of the flexible sensor pad (3).

4. The device for multi-zone hand-off detection of the steering wheel based on advanced intelligent driving as described in claim 3, characterized in that, The sensor layer of the flexible sensor pad is composed of at least one of conductive fabric, metal wire, or metal foil; the first adhesive layer and the second adhesive layer are double-sided adhesive layers or other adhesive materials.

5. The device for multi-zone hand-off detection of the steering wheel based on advanced intelligent driving as described in claim 1, characterized in that, The electronic control unit (ECU) includes: a signal acquisition and processing module, a main control logic module, a vehicle communication module, and a power management and safety monitoring module. The signal acquisition and processing module performs analog-to-digital conversion and preprocessing on the raw capacitance signals of each sensing area. The main control logic module runs the hand state determination algorithm. The vehicle communication module interacts with the advanced intelligent driving system and reports hand state information. The power management and safety monitoring module ensures stable power supply to the system and performs functional safety monitoring.

6. The device for multi-zone hand-off detection of the steering wheel based on advanced intelligent driving as described in claim 1, characterized in that, The device also has a steering wheel heating function, the flexible sensor layer and the heating element are arranged in layers in space or reuse some structures, and the electronic control unit (ECU) is used to control the heating logic.

7. A detection method based on the multi-zone hands-off detection device for advanced intelligent driving according to any one of claims 1-6, characterized in that, Includes the following steps: S1: After the electronic control unit (ECU) is powered on, it performs self-test and initialization, controls the flexible sensor pads of each sensing area to start working, and collects signals within a preset learning period to establish the dynamic capacitance signal baseline value of each sensing area. S2: The signal acquisition and processing module synchronously acquires the original capacitance signal of each of the sensing areas at a fixed frequency; S3: The acquired raw capacitance signal is sequentially processed by baseline subtraction, digital filtering and temperature adaptive compensation to obtain the preprocessed signal value of each sensing area reflecting the state of hand approach or contact. S4: The main control logic module compares the preprocessed signal values ​​of each sensing area with the dynamic threshold, and combines them with at least one of the steering wheel torque signal and visual perception signal from the vehicle for fusion judgment. The driver's hand state is identified through the hand state determination algorithm. The hand state includes single-hand operation, two-hand operation, specific grip area recognition, and off-hand state. S5: The vehicle communication module reports the determined hand status information to the advanced intelligent driving system; when it is determined to be a hands-off state and the duration exceeds the preset warning time, a graded warning signal is triggered.

8. The method for multi-zone hand-off detection of the steering wheel based on advanced intelligent driving as described in claim 7, characterized in that, In step S4, the hand state determination algorithm is as follows: when only one sensing area's preprocessed signal value exceeds the dynamic threshold, it is determined to be a single-handed operation; when at least two sensing areas' preprocessed signal values ​​exceed the dynamic threshold simultaneously, it is determined to be a two-handed operation; when all sensing areas' preprocessed signal values ​​do not exceed the dynamic threshold and remain so for a preset time, it is determined to be a hands-free state.

9. The method for multi-zone hand-off detection of the steering wheel based on advanced intelligent driving as described in claim 7, characterized in that, In step S4, the dynamic threshold can be dynamically optimized and adjusted based on at least one of the steering wheel torque signal and the visual perception signal.

10. The method for multi-zone hand-off detection of the steering wheel based on advanced intelligent driving according to claim 7, characterized in that, In step S3, the signal preprocessing includes at least a signal compensation algorithm based on temperature changes and a signal filtering algorithm for noise suppression.

Images