Multi-scene vehicle-mounted control method and system

Abstract

The invention belongs to the technical field of vehicle-mounted man-machine interaction, and provides a multi-scene vehicle-mounted control method and system, which perform touch control operation based on a touch control sensing array on a steering wheel, establish unified gesture interaction logic and realize blind operation of a touch control area of the steering wheel, so that vehicle control operation can be completed without shifting sight of a user, and the user experience is improved. The operation risk in the driving process is reduced from the interaction source; track processing and feature extraction and recognition are integrated, and gesture intentions are accurately recognized; meanwhile, the current scene is intelligently recognized in combination with a foreground focus window, and situational self-adaption is achieved; a standard control instruction is matched according to the gesture recognition result and the target control scene, so that compatibility and precise control of multiple scenes are realized; and finally, control, visual feedback and multi-dimensional interaction feedback are synchronously executed, so that the interaction immersion and security are enhanced.

Description

Technical Field

[0001] This invention belongs to the field of vehicle-mounted human-machine interaction technology, specifically relating to a multi-scenario vehicle control method and system. Background Technology

[0002] As the level of automotive intelligence continues to improve and in-vehicle interaction scenarios become increasingly diverse, users are placing higher demands on the convenience, safety, and consistency of operation while driving. Current mainstream in-vehicle control methods suffer from the following problems: Existing vehicle controls are mostly distributed across various methods such as the central control screen, physical buttons, and voice wake-up. Operating the central control screen requires the user to shift their gaze, physical buttons have limited functions and are scattered in layout, and voice wake-up is easily interfered with by driving noise. None of these can meet the safe operation requirements of zero gaze shift during driving.

[0003] Although some models have touch buttons on the steering wheel, they only support single function switching and lack gesture logic designed for blind operation. Users need to memorize the positions of different buttons, and the operation is prone to misoperation due to unclear tactile feedback. Furthermore, they cannot cover the control needs of multiple scenarios.

[0004] In-vehicle control scenarios cover multiple dimensions such as entertainment, windows, sunroof, and navigation. Existing systems require switching between scenarios through multiple menus or different operation entry points, resulting in a lengthy interaction process that does not conform to the operating habits of quick response during driving.

[0005] Current touch operation feedback is mostly limited to single vibration or indicator light prompts, without combining with in-vehicle PHUD / ARHUD and other display devices to form multi-dimensional collaborative feedback of vision, touch and hearing. This makes it difficult for users to quickly confirm the validity of the operation, further increasing the probability of misoperation. Summary of the Invention

[0006] The purpose of this invention is to disclose a multi-scenario vehicle control method and system, which solves the technical problems.

[0007] To achieve the above objectives, the present invention discloses a multi-scenario vehicle control method, comprising: Data is collected based on the touch sensor array on the steering wheel to obtain touch data and process it to obtain the touch operation trajectory; Feature extraction is performed on the touch operation trajectory to perform gesture recognition and output a valid gesture recognition result; Identify the current foreground focus window and determine the target control scene based on the gesture recognition results; Based on preset mapping rules, standardized control commands are matched according to the gesture recognition results and the target control scenario. The system generates drive signals based on the standardized control commands to perform vehicle control and status monitoring feedback; it also generates corresponding visual display content based on the standardized control commands for synchronous display and performs multi-dimensional feedback interaction.

[0008] This basic solution utilizes a touch sensor array on the steering wheel for touch operation, establishing a unified gesture interaction logic to enable blind operation of the steering wheel touch area. This allows users to control the vehicle without shifting their gaze, reducing operational risks during driving from the source of interaction. It integrates trajectory processing and feature extraction and recognition to accurately identify gesture intentions. Simultaneously, it intelligently identifies the current scene by combining the foreground focus window, achieving contextual self-adaptation. Furthermore, it matches standardized control commands based on gesture recognition results and target control scenarios, achieving compatibility and precise control across multiple scenarios. Finally, it simultaneously executes control, provides visual feedback, and offers multi-dimensional interactive feedback, enhancing the interactive immersion and safety.

[0009] As an optional implementation, data is collected based on the touch sensor array on the steering wheel to obtain touch data, and the touch operation trajectory is processed, including: The sensor signals output by the touch sensor array on the steering wheel are acquired in real time to obtain the touch data input by the user; the touch data includes at least one of pressure value, contact position coordinates and continuous motion trajectory; The touch data is preprocessed to output standardized data; Based on the standardized data, a discrete sequence of trajectory points is obtained, and the trajectory breakpoints are filled in using a linear interpolation algorithm to output a smooth touch operation trajectory.

[0010] This solution converts touch data into standardized data with a uniform range through signal preprocessing, effectively avoiding recognition errors caused by signal fluctuations. At the same time, it uses a linear interpolation algorithm to fill in trajectory breakpoints, outputting continuous and smooth operation trajectory data, effectively eliminating touch gaps and providing a solid foundation for subsequent accurate gesture recognition.

[0011] As an optional implementation, feature extraction is performed on the touch operation trajectory to perform gesture recognition and output a valid gesture recognition result, including: The touch operation trajectory is subjected to feature extraction to obtain at least one feature parameter; The feature parameters of the touch operation trajectory are compared with the features of the preset standard gesture, the comprehensive similarity is calculated, and the preset standard gesture with the highest comprehensive similarity is determined. Action verification is performed based on the comprehensive similarity of the preset standard gestures. If the verification is successful, a valid gesture recognition result is output.

[0012] This solution compares at least one feature parameter of the touch operation trajectory with the features of a preset standard gesture, and determines the preset standard gesture with the highest comprehensive similarity as the gesture recognition result. By comparing multiple feature parameters and calculating comprehensive similarity, it can effectively improve the fault tolerance of non-standard gestures in complex environments.

[0013] As an optional implementation, the action verification based on the comprehensive similarity of the preset standard gestures includes: Validity verification involves obtaining the comprehensive similarity of the preset standard gestures and determining whether it is less than the similarity threshold. If it is, the gesture matching is initially determined to be invalid; otherwise, the gesture matching is initially determined to be valid and proceeds to the next step of integrity verification. Integrity verification involves acquiring key feature points of the preset standard gesture, matching the touch operation trajectory with the key feature points, and determining whether there is complete coverage. If yes, the verification is successful; otherwise, the verification fails.

[0014] This solution introduces an action verification mechanism, employing a dual mechanism of comprehensive similarity calculation and operation integrity verification. Combined with signal preprocessing, it effectively filters out accidental touches and environmental interference, ensuring the accuracy of gesture recognition and guaranteeing the safety and efficiency of in-vehicle interaction.

[0015] As an optional implementation, identifying the current foreground focus window and determining the target control scene based on the gesture recognition result includes: Identify the current user interface and its corresponding application scenario; Determine whether the gesture recognition result triggers window switching. If not, determine the current application scenario as the target control scenario. If so, determine the candidate scenario as the target control scenario based on the scenario switching order and the current application scenario. The system obtains the frequency of user scene switching, adjusts frequently switched scenes to the top of the switching order, and dynamically adjusts the scene switching order.

[0016] This solution utilizes a scene decision-making mechanism based on focus window recognition, prioritizing responses to the operational needs of the current foreground application. Combined with user-initiated switching functionality, it fully adheres to user intent, avoiding scene misjudgments caused by algorithmic speculation, thus improving interaction accuracy and user control. Furthermore, based on focus window recognition and user-initiated switching, it enables precise switching between multiple scenes without requiring multi-level menus. It integrates controls for disparate scenarios such as entertainment, windows, sunroof, and navigation into a single touch area, simplifying the interaction process and enhancing operational convenience and accuracy.

[0017] As an optional implementation, based on preset mapping rules, standardized control commands are matched according to the gesture recognition results and the target control scenario, including: Match the corresponding target control scenario instruction set according to the target control scenario; The preset mapping rule matches the initial control command corresponding to the gesture recognition result from the target control scene command set; the preset mapping rule includes a one-to-one mapping relationship between the gesture recognition result and the target control scene command set. Based on vehicle driving parameters and user operating habits, the initial control commands generated by mapping are optimized and adjusted to output standardized control commands.

[0018] This solution supports custom mapping rules to adapt to the operating habits of different users. At the same time, it optimizes and adjusts the initial control commands generated by mapping based on vehicle driving parameters and user operating habits, outputting standardized control commands, reducing the difficulty of information reading, and improving the system's personalized adaptation capabilities.

[0019] As an optional implementation method, generating corresponding visual display content for synchronized display includes: Generate visual display content based on standardized control commands and target control scenarios; Based on vehicle driving parameters and driving environment, the interface display parameters are adaptively adjusted and updated synchronously.

[0020] This solution synchronizes touch operation with PHUD / ARHUD display, providing concise and intuitive content and adaptive parameter adjustment. It helps users confirm the operation status without interfering with driving attention, forming a closed-loop interaction of operation-display-feedback, further improving the reliability of blind operation.

[0021] As an optional implementation, the multi-dimensional feedback interaction includes: The system acquires vehicle driving parameters and user operation frequency to dynamically adjust the feedback intensity. Tactile feedback is performed based on the feedback intensity, and vibration feedback with different vibration frequencies is output according to different gesture recognition results and / or command execution results; Auditory feedback is performed based on the feedback intensity, and corresponding prompt sounds are output according to the gesture recognition result and / or command execution result.

[0022] This solution uses an adaptive formula to dynamically match feedback intensity with driving speed and operation frequency. By combining multi-dimensional tactile and auditory feedback, it ensures the effectiveness of operation confirmation while avoiding interference caused by excessive feedback, thus improving the user experience.

[0023] The present invention also provides a multi-scenario vehicle control system for implementing the multi-scenario vehicle control method described above, comprising: The touch sensing module is used to collect the user's touch data and obtain the touch operation trajectory; The gesture recognition module extracts features from the touch operation trajectory to perform gesture recognition and outputs a valid gesture recognition result. The scene decision module is used to identify the current foreground focus window and determine the target control scene based on the gesture recognition results; The control mapping module is used to match standardized control commands based on the gesture recognition results and the target control scenario according to preset mapping rules. The HUD collaborative display module is used to generate and synchronously display visual content based on standardized control commands and target control scenarios. The feedback interaction module is used to perform multi-dimensional feedback interactions based on vehicle driving parameters and user operation frequency; The execution control module generates drive signals based on the standardized control instructions to execute vehicle control, and synchronously monitors the execution status and provides feedback.

[0024] As an optional implementation, the touch sensing module includes touch sensors, and the touch sensing array composed of the touch sensors is evenly distributed in a ring in the steering wheel control button area.

[0025] This design features a circular, evenly distributed touch sensor array around the steering wheel control button area, ensuring that the touch surface covers the area accessible to the user's thumb when naturally holding the steering wheel. The spacing between sensor units is adapted to the steering wheel size, ensuring no blind spots during thumb movement, thereby reducing the difficulty of touch operation and improving touch accuracy. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying 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.

[0027] Figure 1 This is a flowchart illustrating the process of a multi-scenario vehicle control method provided in an embodiment of the present invention; Figure 2 This is a system framework diagram of a multi-scenario vehicle control system provided by an embodiment of the present invention; Figure 3 This is a specific system framework diagram of a multi-scenario vehicle control provided by an embodiment of the present invention. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] In this invention, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing the invention and its embodiments, and are not intended to limit the indicated devices, elements, or components to having a specific orientation, or to be constructed and operated in a specific orientation.

[0030] Furthermore, in addition to indicating direction or positional relationship, some of the aforementioned terms may also have other meanings. For example, the term "above" may also be used in certain situations to indicate a dependency or connection. Those skilled in the art can understand the specific meaning of these terms in this invention based on the specific circumstances.

[0031] Furthermore, the terms "installation," "setup," "equipped with," "connection," and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral structure; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium, or an internal connection between two devices, components, or parts. Those skilled in the art can understand the specific meaning of these terms in this invention based on the specific circumstances.

[0032] Furthermore, the terms "first," "second," etc., are primarily used to distinguish different devices, components, or parts (which may be the same or different in specific type and construction), and are not intended to indicate or imply the relative importance or quantity of the indicated devices, components, or parts. Unless otherwise stated, "a plurality of" means two or more.

[0033] The technical solution of the present invention will be further described below with reference to the embodiments and accompanying drawings.

[0034] Example 1 Please see Figure 1 As shown, this application provides a multi-scenario vehicle control method and system, including the following steps: S1. Data acquisition is performed based on the touch sensor array on the steering wheel to obtain touch data, and the touch operation trajectory is processed, including: The sensor signals output by the touch sensor array on the steering wheel are acquired in real time to obtain the touch data input by the user; the touch data includes at least one of pressure value, contact position coordinates and continuous motion trajectory; The touch data is preprocessed to output standardized data; Based on the standardized data, a discrete sequence of trajectory points is obtained, and the trajectory breakpoints are filled in using a linear interpolation algorithm to output a smooth touch operation trajectory.

[0035] The signal preprocessing includes filtering, noise reduction, and normalization. Specifically, the mean filtering algorithm is used to remove environmental interference noise from the original signal (i.e., touch data), and the pressure signal and position coordinate signal are converted into standardized data with a unified range through normalization transformation to avoid recognition errors caused by signal fluctuations.

[0036] This embodiment converts touch data into standardized data with a uniform range through signal preprocessing, effectively avoiding recognition errors caused by signal fluctuations; at the same time, it completes trajectory breakpoints through linear interpolation algorithm, outputting continuous and smooth operation trajectory data, effectively eliminating touch gaps and providing a solid foundation for subsequent accurate gesture recognition.

[0037] S2. Extract features from the touch operation trajectory to perform gesture recognition and output valid gesture recognition results, including: S21. Extract features from the touch operation trajectory to obtain at least one feature parameter; Specifically, the feature parameters include trajectory direction ( The trajectory can be one or more of the following: trajectory length (L), number of operations (N), dwell time (T), and trajectory shape characteristics (S). Among them, trajectory shape characteristics include straight lines, broken lines, circles (clockwise and counterclockwise), etc.

[0038] S22. Compare the feature parameters of the touch operation trajectory with the features of the preset standard gesture, calculate the comprehensive similarity, and determine the preset standard gesture with the highest comprehensive similarity. For example, standard gesture features are pre-stored in the pre-stored gesture library. The standard gesture features include six standard gestures: swiping up and down, swiping left and right, double-tapping, long-pressing, drawing circles clockwise, and drawing circles counterclockwise.

[0039] Specifically, the formula for calculating the overall similarity is as follows:

[0040] in, Indicates overall similarity; Indicates the number of feature parameters involved in the comparison; For the first The weight coefficients of each feature parameter, and ; Indicates the gesture to be recognized. The standardized values ​​of the feature parameters are in the range of [0,1]. Indicates the pre-stored standard gesture number The standardized values ​​of the feature parameters, with a value range of [0,1].

[0041] S23. Perform action verification based on the comprehensive similarity of the preset standard gestures. If the verification is successful, output a valid gesture recognition result.

[0042] The action verification includes: Validity verification involves obtaining the comprehensive similarity of the preset standard gestures and determining whether it is less than the similarity threshold. If it is, the gesture matching is initially determined to be invalid; otherwise, the gesture matching is initially determined to be valid and proceeds to the next step of integrity verification. Integrity verification involves acquiring key feature points of the preset standard gesture, matching the touch operation trajectory with the key feature points, and determining whether there is complete coverage. If yes, the verification is successful; otherwise, the verification fails.

[0043] For example, when When the similarity threshold is ≥, the gesture matching is initially determined to be valid; further verification of the completeness of the gesture operation is performed by judging whether the trajectory point sequence covers the key feature points of the standard gesture, eliminating invalid matches caused by incomplete operations or accidental touches, and finally outputting a clear gesture recognition result.

[0044] This embodiment introduces an action verification mechanism, which adopts a dual mechanism of comprehensive similarity calculation and operation integrity verification. Combined with signal preprocessing, it effectively filters out accidental touches and environmental interference, ensuring the accuracy of gesture recognition and guaranteeing the safety and efficiency of in-vehicle interaction.

[0045] This embodiment compares at least one feature parameter of the touch operation trajectory with the features of a preset standard gesture, and determines the preset standard gesture with the highest comprehensive similarity as the gesture recognition result. By comparing multiple feature parameters and calculating comprehensive similarity, the tolerance for non-standard gestures in complex environments can be effectively improved.

[0046] S3. Identify the current foreground focus window and determine the target control scene based on the gesture recognition result, including: Identify the current user interface and its corresponding application scenario; Determine whether the gesture recognition result triggers window switching. If not, determine the current application scenario as the target control scenario. If so, determine the candidate scenario as the target control scenario based on the scenario switching order and the current application scenario. The system obtains the frequency of user scene switching, adjusts frequently switched scenes to the top of the switching order, and dynamically adjusts the scene switching order.

[0047] This embodiment uses a scene decision-making mechanism based on focus window recognition to prioritize responding to the operational needs of the current foreground program. Combined with user-initiated switching functionality, it fully adheres to user intent, avoiding scene misjudgments caused by algorithmic speculation, thus improving the accuracy of interaction and user control. Simultaneously, based on focus window recognition and user-initiated switching, it enables precise switching between multiple scenes without the need for multi-level menu operations. It integrates the control of scattered scenes such as entertainment, windows, sunroof, and navigation into a single touch area, simplifying the interaction process and improving operational convenience and accuracy.

[0048] S4. Based on preset mapping rules, match standardized control commands according to the gesture recognition results and the target control scenario, including: S41. Match the corresponding target control scenario instruction set according to the target control scenario; S42, The preset mapping rule matches the initial control command corresponding to the gesture recognition result from the target control scene command set; the preset mapping rule includes a one-to-one mapping relationship between the gesture recognition result and the target control scene command set. The preset mapping rules include fixed mapping rules and custom mapping rules: The fixed mapping rules are the default configuration. For example, swiping up and down corresponds to volume up and down, swiping left and right corresponds to previous and next tracks, double-tapping corresponds to pause / play, long-press corresponds to scene switching, drawing a circle clockwise corresponds to function enhancement, and drawing a circle counterclockwise corresponds to function deprecation. Custom mapping rules allow users to modify the correspondence between gestures and commands within a preset range according to their usage habits. The modified mapping rules are stored in the user's personalized configuration library.

[0049] S43. Based on vehicle driving parameters and user operating habits, optimize and adjust the initial control commands generated by mapping, and output standardized control commands.

[0050] For example, the sensitivity of command execution can be dynamically adjusted based on driving speed (i.e., vehicle driving parameters) (reducing the volume adjustment step size when driving at high speed), and the initial parameters of command execution can be optimized based on user history operation records (i.e. user operation habits) (matching the user's commonly used volume and window opening range) to output standardized control commands.

[0051] This embodiment supports custom mapping rules to adapt to the operating habits of different users. At the same time, it optimizes and adjusts the initial control commands generated by mapping based on vehicle driving parameters and user operating habits, outputting standardized control commands, reducing the difficulty of information reading, and improving the system's personalized adaptation capability.

[0052] S5. Generate drive signals according to the standardized control instructions to perform vehicle control and status monitoring feedback; simultaneously generate corresponding visual display content according to the standardized control instructions for synchronous display, and perform multi-dimensional feedback interaction.

[0053] In this embodiment, the standardized control command generates drive signals to execute vehicle control and status monitoring feedback, including: The standardized control commands are converted into corresponding drive signals according to the communication protocols of each on-board actuator, and timing coordination is performed. The system collects real-time vehicle operating status data, compares it with target parameters, and judges the execution status of instructions. If the execution is normal, it returns to standby status. If a deviation or fault occurs, it triggers warning feedback and records fault information (for subsequent troubleshooting).

[0054] The drive signals include, but are not limited to, audio control signals for the audio system, motor drive signals for the window controller, motor drive signals for the sunroof controller, and interactive control signals for the navigation system, ensuring that commands can be recognized by each executing component. The vehicle operating status data includes, but is not limited to, motor speed, switch position, and functional operating parameters.

[0055] In this embodiment, corresponding visual display content is generated and displayed synchronously according to the standardized control instructions, and multi-dimensional feedback interaction is performed, specifically including: 1. Generate visual display content based on standardized control instructions and target control scenarios; The visual display includes operation function icons (such as volume, window, and sunroof icons), operation status prompts (such as adjustment progress bars and on / off status), and scene switching prompts (such as the name of the currently active scene). The display uses a simple and clear combination of icons and text to further avoid distracting users with complex information.

[0056] Second, based on vehicle driving parameters and driving environment, the interface display parameters are adaptively adjusted and updated synchronously.

[0057] Specifically, the vehicle driving parameters include vehicle speed, the driving environment includes ambient light intensity, and the interface display parameters include at least one of display brightness, contrast, and font size.

[0058] For example, the display brightness, contrast, and font size of the PHUD / ARHUD can be adaptively adjusted according to the vehicle speed and ambient light intensity to ensure that users can quickly identify the displayed content under different driving conditions, while avoiding interference with the driver's line of sight due to the display light.

[0059] Specifically, the synchronized update display establishes a synchronization mechanism between the displayed content and the operation process. When the user performs a gesture operation, the displayed content is updated synchronously. After the operation is completed, the displayed content is automatically hidden after a preset time, ensuring that the display prompts are consistent with the operation rhythm and do not occupy the user's visual resources.

[0060] This embodiment synchronizes touch operation with PHUD / ARHUD display, displaying concise and intuitive content with adaptive parameter adjustment. This not only helps users confirm the operation status but also does not interfere with driving attention, forming a closed-loop interaction of operation-display-feedback, further improving the reliability of blind operation.

[0061] III. Implement multi-dimensional feedback interactions, including: The system acquires vehicle driving parameters and user operation frequency to dynamically adjust the feedback intensity. Tactile feedback is performed based on the feedback intensity, and vibration feedback with different vibration frequencies is output according to different gesture recognition results and / or command execution results; Auditory feedback is performed based on the feedback intensity, and corresponding prompt sounds are output according to the gesture recognition result and / or command execution result.

[0062] Specifically: The feedback intensity is dynamically adjusted based on vehicle speed and user operation frequency. The adaptive formula for feedback intensity is:

[0063] In the formula, Indicates the intensity of feedback; , These represent the speed influence coefficient and the operating frequency influence coefficient, respectively. The normalized value representing the vehicle's current speed; This represents the normalized value of the frequency of user operations per unit of time.

[0064] This embodiment uses an adaptive feedback strength formula to enhance feedback strength during high-speed driving or high-frequency operation, and weaken feedback strength during low-speed driving or low-frequency operation, thus balancing feedback effectiveness and operational comfort.

[0065] Different gestures correspond to different vibration frequencies, such as a single click for a short vibration, a long press for a continuous vibration, and scene switching for a double vibration, helping users to confirm the validity of the operation through touch.

[0066] The prompts include a success prompt, a scene switching prompt, and a misoperation warning. The prompts are designed with low volume and short duration to avoid interfering with the driving environment and user communication.

[0067] This embodiment achieves dynamic matching between feedback intensity and driving speed and operation frequency through an adaptive formula for feedback intensity. By combining multi-dimensional tactile and auditory feedback, it ensures the effectiveness of operation confirmation while avoiding interference caused by excessive feedback, thus improving the user's operating experience.

[0068] Taking the entertainment control scenario during driving as an example, the working principle of this embodiment is as follows: Operational objective: While the vehicle is in motion, the user should be able to control music playback blindly using the steering wheel touch area without having to take their eyes off the road. Hardware configuration: Touch sensing layer: The steering wheel control button area integrates a ring-shaped flexible capacitive touch sensor array with a sensor unit spacing of 5mm, covering the range of motion of the thumb when naturally gripping the steering wheel, and supporting the acquisition of pressure, position and trajectory signals; Computing processing layer: Equipped with an onboard MCU processor, responsible for signal processing, gesture recognition, scene decision-making, and instruction optimization; Display feedback layer: Equipped with a PHUD display device, the steering wheel touch area integrates 4 micro vibration motors, which work in conjunction with the car audio system to provide auditory feedback; Execution layer: Execution components such as the vehicle audio system, window controller, sunroof controller, and navigation host communicate with the control module via the CAN bus.

[0069] Implementation process: (1) After the system starts, the initial configuration is completed.

[0070] The touch sensor array calibration is complete, and the gesture library has been loaded with 6 standard gestures, including swiping up and down, swiping left and right, double-tap, long press, drawing a circle clockwise, and drawing a circle counterclockwise. The default mapping rules have been loaded, including swiping up and down for volume up and down, swiping left and right for previous / next track, double-tap for pause / play, long press for scene switching, drawing a circle clockwise for rapid volume increase, and drawing a circle counterclockwise for rapid volume decrease. The PHUD display parameters have been initialized, the feedback intensity baseline value has been set to level 3, and the system has entered standby mode.

[0071] (2) When the user drives the vehicle, the thumb slides upward on the steering wheel touch area, and the touch sensor array collects continuous position coordinate signals and pressure signals, and outputs touch data; (3) Perform data preprocessing and output standardized data; Mean filtering is used to remove signal noise caused by road bumps, and the pressure signal is normalized to the range of [0,1]. Position coordinates are collected at preset time intervals (e.g., 10ms interval) to form an upward trajectory point sequence. Linear interpolation is used to fill in the breaks caused by slight thumb shaking, and standardized upward sliding trajectory data is output to obtain standardized data.

[0072] (4) Extract feature parameters from trajectory data: Trajectory direction =90° (upward), trajectory length L=3cm, number of operations N=1, dwell time T=0.5s, trajectory shape S=straight line; substituting these values ​​into the comprehensive similarity calculation formula and comparing it with the pre-stored standard "upward swipe" gesture features, the calculated result is... =0.92 (similarity threshold set to 0.8); confirm that the trajectory covers the key feature points of "swipe up", determine that the gesture is valid, and output the "swipe up" recognition result.

[0073] (5) If the current foreground focus window is identified as the music player, the corresponding target control scene is the entertainment control scene. Since no user long press switch command is received, the entertainment control scene is locked as the final target control scene.

[0074] (6) Call the default mapping rule. "Slide up" corresponds to the "volume up" command in the entertainment control scenario. The initial command execution parameter is to increase the volume by 1 bar. However, based on the current driving speed of 60km / h, the volume adjustment step size is optimized to 0.5 bars, and a standardized "volume up 0.5 bars" control command is output.

[0075] (7) Visual display: Generate a volume adjustment progress bar and a "volume+" icon; adjust the display brightness to 600 cd / m2 according to the current ambient light intensity; and update the display content synchronously. At the same time, it outputs short vibrations and a low-volume "beep" sound through the car audio system.

[0076] Based on the adaptive formula for feedback strength =60km / h, normalized to 0.6, user operation frequency =1 time / minute, normalized to 0.1, =3、 =2, calculated to =Level 2, output feedback signal at Level 2 intensity.

[0077] Step 7: Execute vehicle control, convert the "volume up 0.5 increments" command into a drive signal of the CAN bus communication protocol, and send it to the vehicle audio system; after confirming that there are no other conflicting commands, allow the audio system to execute the operation; at the same time, collect the audio system volume parameters, confirm that the increase from 30% to 32.5% is complete, and the system returns to standby state.

[0078] Example 2 The reference numerals in the accompanying drawings of the embodiments of the present invention include: a touch sensing module 1, a touch sensor array 11, a signal processing unit 12, and a trajectory acquisition unit 13; a gesture recognition module 2, a feature extraction unit 21, a gesture matching unit 22, and an action verification unit 23; a scene decision module 3, a window detection unit 31, a switching receiving unit 32, and a scene determination unit 33; a control mapping module 4, an instruction storage unit 41, a mapping unit 42, and an instruction optimization unit 43; a HUD collaborative display module 5, a content generation unit 51, a parameter adaptation unit 52, and a synchronization control unit 53; a feedback interaction module 6, a tactile feedback unit 61, an auditory feedback unit 62, and a feedback adjustment unit 63; and an execution control module 7, an instruction conversion unit 71, a collaboration unit 72, and a status monitoring unit 73.

[0079] This invention also provides a multi-scenario vehicle control system, see [link / reference]. Figure 2 , Figure 3 The method is used to implement a multi-scenario vehicle control method as described in Embodiment 1 above, including: Touch sensing module 1 is used to collect the user's touch data and obtain the touch operation trajectory; The gesture recognition module 2 extracts features from the touch operation trajectory to perform gesture recognition and outputs a valid gesture recognition result; Scene decision module 3 is used to identify the current foreground focus window and determine the target control scene based on the gesture recognition result; Control mapping module 4 is used to match standardized control commands based on the gesture recognition results and the target control scenario according to preset mapping rules; HUD collaborative display module 5 is used to generate visual display content and display it synchronously based on standardized control commands and target control scenarios; Feedback interaction module 6 is used to perform multi-dimensional feedback interaction based on vehicle driving parameters and user operation frequency; The execution control module 7 generates drive signals according to the standardized control instructions to execute vehicle control, and synchronously monitors the execution status and provides feedback.

[0080] This embodiment features a touch sensor array that is evenly distributed in a ring around the steering wheel control button area. This ensures that the touch surface covers the area that the user's thumb can reach when naturally holding the steering wheel. The spacing between the sensor units is adapted to the size of the steering wheel to ensure that there are no blind spots during thumb movement, thereby reducing the difficulty of touch operation and improving touch accuracy.

[0081] In this embodiment, the touch sensing module 1 includes: a touch sensing array 11, a signal processing unit 12, and a trajectory acquisition unit 13; The touch sensor array 11 is used to collect touch data. It consists of touch sensors that are evenly distributed in a ring in the steering wheel control button area. The unit spacing between the touch sensors is adapted to the steering wheel size to ensure that there are no touch blind spots during thumb movement.

[0082] The signal processing unit 12 is used to preprocess the touch data and output standardized data; The trajectory acquisition unit 13 is used to acquire the standardized data (e.g., the continuous position coordinates of the user's thumb) at fixed time intervals, form a discrete trajectory point sequence, and fill in the trajectory breakpoints through a linear interpolation algorithm to output a smooth touch operation trajectory.

[0083] In this embodiment, the gesture recognition module 2 includes a feature extraction unit 21, a gesture matching unit 22, and an action verification unit 23; Feature extraction unit 21 is used to extract features from the touch operation trajectory and obtain at least one feature parameter; The gesture matching unit 22 is used to compare the feature parameters of the touch operation trajectory with the features of the preset standard gesture, calculate the comprehensive similarity, and determine the preset standard gesture with the highest comprehensive similarity. The action verification unit 23 is used to perform action verification based on the comprehensive similarity of the preset standard gestures. If the verification is successful, a valid gesture recognition result is output.

[0084] In this embodiment, the scene decision module 3 includes a window detection unit 31, a switching receiving unit 32, and a scene determination unit 33; The window detection unit 31 is used to communicate with the vehicle system operating system in real time, monitor the currently active application interface (i.e., the focus window), identify the control scene type corresponding to the focus window (e.g., if the focus window is a music player, it corresponds to the entertainment control scene; if the focus window is a navigation APP, it corresponds to the navigation control scene), and ensure that the target control scene is consistent with the program currently operated by the user. The switching receiving unit 32 is used to determine whether to trigger window switching based on the gesture recognition result. If not, the current application scenario is determined as the target control scenario. If so, a candidate scenario is determined as the target control scenario based on the scenario switching order and the current application scenario. For example, when a user "long-presses" the recognition result, it is determined that the user has triggered a scene switch, and the candidate scenes are cycled through in a preset scene order. The default order is: Entertainment → Navigation → Windows → Sunroof, and users can customize the order in the vehicle settings.

[0085] Scene determination unit 33 is used to determine the target control scene based on the foreground focus window and the gesture recognition result; For example, in the initial state, the scene corresponding to the foreground focus window is directly used as the target control scene to ensure that the user's gesture operation directly affects the current foreground program; when a window switching is detected, the program switches to the next candidate scene in a preset order, and at the same time sends a focus window switching command to the vehicle system to set the program corresponding to the current target control scene as the foreground focus window; the frequency of user scene switching is recorded in sync, and high-frequency switching scenes are adjusted to the front of the switching order to optimize operation efficiency.

[0086] In this embodiment, the control mapping module 4 includes an instruction storage unit 41, a mapping unit 42, and an instruction optimization unit 43; The instruction storage unit 41 is used to pre-store the instruction sets for each control scenario; Specifically: Entertainment control scenarios include commands such as volume up, volume down, previous track, next track, pause, and play; Window control scenarios include commands such as raising the left front window, lowering the left front window, raising the right front window, lowering the right front window, raising all four windows simultaneously, and lowering all four windows simultaneously. Sunroof control scenarios include commands such as sunroof opening, sunroof closing, and sunroof tilting. Navigation control scenarios include commands such as zooming in / out, voice navigation activation, and route switching. Each instruction corresponds to a specific range of execution parameters.

[0087] Mapping unit 42 is used to generate fixed mapping rules and custom mapping rules based on the mapping relationship between gesture recognition results and target control scene instruction set; The instruction optimization unit 43 is used to optimize and adjust the initial control instructions generated by mapping according to the vehicle driving parameters and user operating habits, and output standardized control instructions.

[0088] In this embodiment, the HUD collaborative display module 5 includes a content generation unit 51, a parameter adaptation unit 52, and a synchronization control unit 53; Content generation unit 51 is used to generate corresponding visual display content based on standardized control instructions and target control scenarios. The parameter adaptation unit 52 is used to adaptively adjust the interface display parameters according to the vehicle driving parameters and driving environment; The synchronization control unit 53 is used to establish a synchronization mechanism between the displayed content and the operation process, and to perform synchronous update of the display.

[0089] In this embodiment, the feedback interaction module 6 includes a tactile feedback unit 61, an auditory feedback unit 62, and a feedback adjustment unit 63; The haptic feedback unit 61 is integrated below the steering wheel touch sensor array and uses a micro vibration motor; it is used to perform haptic feedback based on the feedback intensity and output corresponding vibration feedback when the gesture recognition is effective or the command is executed. The auditory feedback unit 62 is linked with the vehicle audio system to perform auditory feedback based on the feedback intensity. The feedback adjustment unit 63 is used to acquire vehicle driving parameters and user operation frequency to dynamically adjust the feedback intensity.

[0090] In this embodiment, the execution control module 7 includes an instruction conversion unit 71, a coordination unit 72, and a status monitoring unit 73; The instruction conversion unit 71 is used to convert standardized control instructions into corresponding drive signals according to the communication protocols of the various on-board execution components; The coordination unit 72 is used to coordinate the execution timing of each component; Specifically, when control commands involve multiple execution components (such as simultaneous control of four windows or coordinated control of entertainment and navigation), the execution sequence of each component is coordinated to avoid conflicts between components and ensure a smooth and orderly control process.

[0091] Status monitoring unit 73; used to perform status monitoring feedback.

[0092] The working process of this embodiment is as follows: (I) System Initialization and Parameter Configuration Upon starting the vehicle control system, the touch sensing module 1 initializes the touch sensor array and calibrates the signal acquisition accuracy; the gesture recognition module 2 loads the pre-stored gesture library and similarity threshold; the scene decision module 3 loads the candidate scene list; the control mapping module 4 loads the default mapping rules and custom mapping rules (e.g., obtained from the user's personalized configuration library); the HUD collaborative display module initializes the display parameters; the feedback interaction module 6 initializes the feedback intensity benchmark value; and the execution control module 7 establishes communication connections with each vehicle execution component. After the system completes initialization, it enters a standby state.

[0093] (II) Touch operation signal acquisition and preprocessing When a user holds the steering wheel and performs operations on the touch area with their thumb, the touch sensing array of the touch sensing module 1 collects pressure signals, position coordinate signals, and motion trajectory signals in real time; the signal processing unit filters, reduces noise, and normalizes the raw signals to remove environmental interference and signal noise; the trajectory acquisition unit collects continuous position coordinates at fixed time intervals, completes trajectory breakpoints through linear interpolation, and outputs standardized operation trajectory data.

[0094] (III) Gesture Recognition and Validity Verification The feature extraction unit of gesture recognition module 2 extracts core feature parameters such as trajectory direction, length, number of operations, dwell time, and trajectory shape from the operation trajectory data; the gesture matching unit compares the extracted feature parameters with pre-stored standard gesture features based on the comprehensive similarity calculation formula to calculate the comprehensive similarity. The action verification unit determines the validity of the gesture operation based on the similarity threshold and the integrity of the gesture, and outputs a clear gesture recognition result.

[0095] (iv) Decision-making in target control scenarios The window detection unit of the scene decision module 3 monitors the vehicle system in real time, identifies the currently active focus window (e.g., if the user is currently opening a music player, the focus window corresponds to the entertainment control scene), and determines the scene as the initial target control scene; if the gesture recognition result is "long press", the switching receiving unit determines that the user has triggered an active switch, switches to the next candidate scene according to the preset scene order (e.g., switch from entertainment to navigation), and updates the focus window of the foreground to the navigation APP. The scene determination unit locks the scene after the switch, that is, determines the navigation control scene as the target control scene.

[0096] (v) Control command mapping and optimization The mapping unit of the control mapping module 4 calls the corresponding mapping rules to generate initial control commands based on the gesture recognition results and the target control scenario. The command optimization unit optimizes and adjusts the initial commands in terms of sensitivity, execution parameters, etc., by combining vehicle driving parameters and user operating habits, and outputs standardized control commands.

[0097] (vi) HUD collaborative display and multi-dimensional feedback The content generation unit of the HUD collaborative display module generates visual display content based on standardized control commands and target control scenarios; the parameter adaptation unit adaptively adjusts display parameters such as brightness and contrast; the synchronous control unit performs synchronous updates of the operation process and display content; the tactile feedback unit and auditory feedback unit of the feedback interaction module 6 output corresponding feedback signals; and the feedback adjustment unit dynamically adjusts the feedback intensity based on the feedback intensity adaptive formula to assist users in confirming the effectiveness of the operation.

[0098] (vii) Control command execution and status monitoring The instruction conversion unit of the execution control module 7 converts standardized control instructions into drive signals for each execution component and sends them to the corresponding on-board execution component; the coordination unit coordinates the execution timing of multiple components to avoid action conflicts; the status monitoring unit collects the operating status data of the execution components in real time, compares it with the target parameters, and judges the instruction execution status; if the execution is normal, the system returns to the standby state; if a deviation or fault occurs, an alarm feedback is triggered and the fault information is recorded.

[0099] This invention utilizes a touch sensor array on the steering wheel for touch operation, establishing a unified gesture interaction logic to enable blind operation of the steering wheel touch area. This allows users to control the vehicle without shifting their gaze, reducing operational risks during driving from the source of interaction. It integrates trajectory processing, feature extraction, and recognition to accurately identify gesture intentions. Simultaneously, it intelligently identifies the current scene using the foreground focus window, achieving contextualized self-adaptation. Furthermore, it matches standardized control commands based on gesture recognition results and target control scenarios, achieving multi-scenario compatibility and precise control. Finally, it synchronously executes control, provides visual feedback, and offers multi-dimensional interactive feedback, enhancing the immersive experience and safety of the interaction.

[0100] The technical means disclosed in this invention are not limited to those disclosed in the above embodiments, but also include technical solutions composed of any combination of the above technical features. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this invention, and these improvements and modifications are also considered within the scope of protection of this invention.

Claims

1. A multi-scenario vehicle control method, characterized in that, include: Data is collected based on the touch sensor array on the steering wheel to obtain touch data and process it to obtain the touch operation trajectory; Feature extraction is performed on the touch operation trajectory to perform gesture recognition and output a valid gesture recognition result; Identify the current foreground focus window and determine the target control scene based on the gesture recognition results; Based on preset mapping rules, standardized control commands are matched according to the gesture recognition results and the target control scenario. The system generates drive signals based on the standardized control commands to perform vehicle control and status monitoring feedback; it also generates corresponding visual display content based on the standardized control commands for synchronous display and performs multi-dimensional feedback interaction.

2. The multi-scenario vehicle control method as described in claim 1, characterized in that, Data is collected based on the touch sensor array on the steering wheel to acquire touch data, and the touch operation trajectory is obtained through processing, including: The sensor signals output by the touch sensor array on the steering wheel are acquired in real time to obtain the touch data input by the user; the touch data includes at least one of pressure value, contact position coordinates and continuous motion trajectory; The touch data is preprocessed to output standardized data; Based on the standardized data, a discrete sequence of trajectory points is obtained, and the trajectory breakpoints are filled in using a linear interpolation algorithm to output a smooth touch operation trajectory.

3. The multi-scenario vehicle control method as described in claim 1, characterized in that, Feature extraction is performed on the touch operation trajectory to perform gesture recognition and output a valid gesture recognition result, including: The touch operation trajectory is subjected to feature extraction to obtain at least one feature parameter; The feature parameters of the touch operation trajectory are compared with the features of the preset standard gesture, the comprehensive similarity is calculated, and the preset standard gesture with the highest comprehensive similarity is determined. Action verification is performed based on the comprehensive similarity of the preset standard gestures. If the verification is successful, a valid gesture recognition result is output.

4. The multi-scenario vehicle control method as described in claim 3, characterized in that, The step of verifying the action based on the comprehensive similarity of the preset standard gestures includes: Validity verification involves obtaining the comprehensive similarity of the preset standard gestures and determining whether it is less than the similarity threshold. If it is, the gesture matching is initially determined to be invalid; otherwise, the gesture matching is initially determined to be valid and proceeds to the next step of integrity verification. Integrity verification involves acquiring key feature points of the preset standard gesture, matching the touch operation trajectory with the key feature points, and determining whether there is complete coverage. If yes, the verification is successful; otherwise, the verification fails.

5. The multi-scenario vehicle control method as described in claim 1, characterized in that, Identify the current foreground focus window and determine the target control scene based on the gesture recognition result, including: Identify the current user interface and its corresponding application scenario; Determine whether the gesture recognition result triggers window switching. If not, determine the current application scenario as the target control scenario. If so, determine the candidate scenario as the target control scenario based on the scenario switching order and the current application scenario. The system obtains the frequency of user scene switching, adjusts frequently switched scenes to the top of the switching order, and dynamically adjusts the scene switching order.

6. The multi-scenario vehicle control method as described in claim 1, characterized in that, Based on preset mapping rules, standardized control commands are matched according to the gesture recognition results and the target control scenario, including: Match the corresponding target control scenario instruction set according to the target control scenario; The preset mapping rule matches the initial control command corresponding to the gesture recognition result from the target control scene command set; the preset mapping rule includes a one-to-one mapping relationship between the gesture recognition result and the target control scene command set. Based on vehicle driving parameters and user operating habits, the initial control commands generated by mapping are optimized and adjusted to output standardized control commands.

7. The multi-scenario vehicle control method as described in claim 1, characterized in that, Generate corresponding visual content for synchronized display, including: Generate visual display content based on standardized control commands and target control scenarios; Based on vehicle driving parameters and driving environment, the interface display parameters are adaptively adjusted and updated synchronously.

8. The multi-scenario vehicle control method as described in claim 1, characterized in that, The multi-dimensional feedback interaction includes: The system acquires vehicle driving parameters and user operation frequency to dynamically adjust the feedback intensity. Tactile feedback is performed based on the feedback intensity, and vibration feedback with different vibration frequencies is output according to different gesture recognition results and / or command execution results; Auditory feedback is performed based on the feedback intensity, and corresponding prompt sounds are output according to the gesture recognition result and / or command execution result.

9. A multi-scenario vehicle control system, used to implement the multi-scenario vehicle control method as described in any one of claims 1 to 8, characterized in that, include: The touch sensing module is used to collect the user's touch data and obtain the touch operation trajectory; The gesture recognition module extracts features from the touch operation trajectory to perform gesture recognition and outputs a valid gesture recognition result. The scene decision module is used to identify the current foreground focus window and determine the target control scene based on the gesture recognition results; The control mapping module is used to match standardized control commands based on the gesture recognition results and the target control scenario according to preset mapping rules. The HUD collaborative display module is used to generate and synchronously display visual content based on standardized control commands and target control scenarios. The feedback interaction module is used to perform multi-dimensional feedback interactions based on vehicle driving parameters and user operation frequency; The execution control module generates drive signals based on the standardized control instructions to execute vehicle control, and synchronously monitors the execution status and provides feedback.

10. A multi-scenario vehicle control system as described in claim 9, characterized in that: The touch sensing module includes touch sensors, and the touch sensing array composed of the touch sensors is evenly distributed in a ring in the steering wheel control button area.

Images