Data acquisition system and method, safety constraint model training method and device, vehicle safety control method and device, vehicle and electronic equipment

Abstract

The invention relates to a data acquisition system and method, a safety constraint model training method and device, a vehicle safety control method and device, a vehicle and electronic equipment. The system comprises a motion platform, a vehicle cabin, a driving simulation device and an acquisition device. The motion platform is used for simulating the motion posture of the vehicle cabin and sending the motion posture to the driving simulation device; the vehicle cabin is used for responding to a driving operation instruction of a passenger and sending the driving operation instruction to the driving simulation device; the driving simulation device is used for generating dynamic data based on the driving operation instruction and the motion posture; determining whether the driving condition is a target condition based on the dynamic data; under the condition that the driving working condition is the target working condition, the dynamic data are sent to a vehicle cabin; the vehicle cabin is also used for generating a safety control signal based on the dynamic data; and the acquisition device is used for acquiring the dynamic data, the safety control signal, the electromyographic signal of the passenger in the moving posture and the physical sign data of the passenger.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, specifically to a data acquisition system and method, a training method and apparatus for a safety constraint model, a vehicle safety control method and apparatus, and vehicles and electronic equipment. Background Technology

[0002] The development and application of active restraint systems have effectively reduced the risk of injury in traffic accidents. During a vehicle collision, occupants' self-protective instincts cause varying degrees of muscle tension, and this difference in tension affects the performance of the active restraint system. Currently, the crash test dummies used in collision safety development are static human models constructed from a biomedical perspective. These models cannot accurately represent the physical state of muscle contraction and tension before and during a collision.

[0003] One related technology discloses a method of constructing an electromyographic (EMG) signal neural network model using data from inertial sensors and EMG signals. Another related technology discloses a method of observing the occupant's sitting posture before a collision using relevant equipment, and then using an external electrical stimulation device to stimulate the occupant in a predetermined manner to put them in a more advantageous sitting posture, thereby ensuring that the restraint system can provide maximum protection when a collision occurs. It can be seen that most of the related technologies construct models based on data from inertial sensors and EMG signals to reflect the human muscle condition or control the occupant's sitting posture through external intervention. Among them, constructing models based solely on data from inertial sensors and EMG signals has problems such as insufficient accuracy in predicting muscle responses under complex vehicle conditions and limited model adaptability. On the other hand, controlling the occupant's sitting posture through external intervention is only designed for the specific scenario of a collision because its core is to adjust the occupant's posture through electrical stimulation before a collision. It lacks effective response capability for complex dynamic scenarios (such as emergency avoidance, sudden braking, etc.) where there is a potential danger but no collision has occurred, and its applicable scenarios are obviously limited, thus failing to fully guarantee the occupant's driving safety. Summary of the Invention

[0004] This invention provides a data acquisition system and method, a training method and apparatus for a safety constraint model, a vehicle safety control method and apparatus, a vehicle, and electronic equipment. By acquiring a training dataset through the data acquisition system and training a safety constraint model, the driving safety of occupants can be significantly improved.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, this application provides a data acquisition system, comprising: a motion platform, a vehicle cockpit, a driving simulation device, and an acquisition device; the vehicle cockpit is physically connected to the motion platform; the driving simulation device is communicatively connected to the motion platform, the acquisition device, and the vehicle cockpit; the acquisition device is communicatively connected to the vehicle cockpit; the motion platform is used to simulate the motion posture of the vehicle cockpit and send the motion posture to the driving simulation device; the vehicle cockpit is used to respond to the occupant's driving operation commands and send the driving operation commands to the driving simulation device; the driving simulation device is used to generate dynamic data based on the driving operation commands and motion posture; determine whether the driving condition is a target condition based on the dynamic data; if the driving condition is the target condition, send the dynamic data to the vehicle cockpit; the target condition is a condition with a risk of driving collision; the vehicle cockpit is also used to generate a safety control signal based on the dynamic data; the safety control signal is used to control the safety control device in the vehicle cockpit to restrain the occupant; the acquisition device is used to acquire the dynamic data, the safety control signal, the occupant's electromyographic signals in the motion posture, and the occupant's vital signs data.

[0007] Based on the aforementioned technical means, a motion platform simulates the motion posture of the vehicle cabin, while the vehicle cabin receives occupant operation commands. The motion platform and vehicle cabin are physically connected, accurately replicating the dynamic posture changes of the vehicle under different road conditions, creating a highly realistic driving environment for occupants. Furthermore, the driving simulation device generates dynamic data through driving operation commands and motion postures, enabling the dynamic data to reflect the vehicle's motion state and force conditions in real time. This dynamic data is then used to determine whether the current driving condition is a target condition, achieving rapid identification of potentially dangerous driving scenarios. When the target condition is determined, the vehicle cabin generates safety control signals based on the dynamic data, triggering corresponding safety protection mechanisms in a timely manner, providing effective safety assurance for occupants. During the simulation, a data acquisition device collects dynamic data, safety control signals, occupant electromyography signals under motion postures, and occupant vital sign data. This provides comprehensive and accurate data support for subsequent analysis of the training of safety constraint models and the effectiveness of vehicle safety control, significantly improving occupant driving safety.

[0008] In one possible implementation, the vehicle cockpit further includes: a first controller and a second controller; the first controller is used to send driving operation commands to a driving simulation device in response to driving operation commands; the second controller is used to generate safety control signals based on dynamic data and use the safety control signals to control safety control devices to achieve safety restraint of occupants.

[0009] Based on the aforementioned technical means, the first controller ensures the accurate transmission of driving operation commands, providing reliable input for the simulation process, while the second controller outputs safety control signals to promptly ensure occupant safety. Through the coordinated operation of the first and second controllers, the smooth progress of the driving simulation is guaranteed, and occupant safety is effectively protected during dynamic processes, thus improving the overall performance and reliability of the vehicle cabin in terms of driving simulation and safety assurance.

[0010] In one possible implementation, the acquisition device is also used to acquire the displacement amount of the occupant in motion posture; if the displacement amount is not less than a preset displacement amount threshold, the dynamic data, safety control signals, electromyographic signals of the occupant in motion posture, and vital sign data of the occupant are discarded.

[0011] Based on the above technical means, by setting a preset displacement threshold, invalid data when the displacement state is abnormal can be accurately removed, avoiding such data from interfering with the analysis results, thereby improving the reliability and accuracy of the data.

[0012] In one possible implementation, the acquisition device is further configured to discard kinetic data, safety control signals, occupant's electromyographic signals in motion posture, and occupant's vital signs data when the electromyographic signal is less than the maximum voluntary contraction electromyographic signal; the maximum voluntary contraction electromyographic signal is the occupant's maximum electromyographic signal in a static state.

[0013] Based on the above technical means, by comparing electromyographic signals with the maximum voluntary contraction electromyographic signals, invalid or ineffective data can be accurately filtered out, reducing redundant information interference and significantly improving the effectiveness and relevance of the data.

[0014] In one possible implementation, the driving simulation device is specifically used to determine the driving condition as the target condition when the difference between the dynamic data and the target dynamic data under the target condition is less than a preset difference.

[0015] Based on the aforementioned technical means, this driving simulation device accurately identifies driving conditions by comparing dynamic data with target dynamic data under target conditions. This provides a reliable basis for judging driving conditions in scenarios such as driving simulation training and vehicle performance testing, improving the accuracy and effectiveness of simulation and helping related research and applications to better meet actual needs.

[0016] Secondly, this application provides a data acquisition method applied to a data acquisition system. The data acquisition system includes: a motion platform, a vehicle cockpit, a driving simulation device, and an acquisition device. The vehicle cockpit is physically connected to the motion platform. The driving simulation device is communicatively connected to the motion platform, the acquisition device, and the vehicle cockpit. The acquisition device is communicatively connected to the vehicle cockpit. The method includes: the motion platform simulating the motion posture of the vehicle cockpit and sending the motion posture to the driving simulation device; the vehicle cockpit responding to the occupant's driving operation command and sending the driving operation command to the driving simulation device; the driving simulation device generating dynamic data based on the driving operation command and the motion posture; determining whether the driving condition is a target condition based on the dynamic data; if the driving condition is the target condition, sending the dynamic data to the vehicle cockpit; the target condition is a condition with a risk of driving collision; the vehicle cockpit generating a safety control signal based on the dynamic data; the safety control signal being used to control the safety control device in the vehicle cockpit to restrain the occupant; and the acquisition device acquiring the dynamic data, the safety control signal, the occupant's electromyographic signals in the motion posture, and the occupant's vital signs data.

[0017] Based on the aforementioned technical means, a motion platform simulates the motion posture of the vehicle cabin, while the vehicle cabin receives occupant operation commands. The motion platform and vehicle cabin are physically connected, accurately replicating the dynamic posture changes of the vehicle under different road conditions, creating a highly realistic driving environment for occupants. Furthermore, the driving simulation device generates dynamic data through driving operation commands and motion postures, enabling the dynamic data to reflect the vehicle's motion state and force conditions in real time. This dynamic data is then used to determine whether the current driving condition is a target condition, achieving rapid identification of potentially dangerous driving scenarios. When the target condition is determined, the vehicle cabin generates safety control signals based on the dynamic data, triggering corresponding safety protection mechanisms in a timely manner, providing effective safety assurance for occupants. During the simulation, a data acquisition device collects dynamic data, safety control signals, occupant electromyography signals under motion postures, and occupant vital sign data. This provides comprehensive and accurate data support for subsequent analysis of the training of safety constraint models and the effectiveness of vehicle safety control, significantly improving occupant driving safety.

[0018] Thirdly, this application provides a training method for a safety constraint model, comprising: using the dynamic data collected by the acquisition device in the first aspect above, the electromyographic signals of the occupant in motion posture and the vital signs data of the occupant as training inputs, and the safety control signal as training outputs, to construct a training dataset; and using the training dataset to train the safety constraint model.

[0019] Based on the aforementioned technical means, a training dataset covering multiple groups and multiple dimensions of data, which has undergone standardized preprocessing, is obtained through a data acquisition system. This dataset is then used to train a safety constraint model, which can improve the model's adaptability and prediction accuracy for different occupants under hazardous conditions, enhance its generalization ability, provide reliable support for vehicle safety control, and effectively ensure occupant safety.

[0020] Fourthly, this application provides a vehicle safety control method, comprising: acquiring vehicle dynamics data, occupant electromyography signals, and occupant vital signs data; generating a vehicle safety control signal based on the vehicle dynamics data, occupant electromyography signals, and occupant vital signs data and the safety constraint model in the third aspect above; and controlling the vehicle's safety control device to perform safety constraints on the occupant based on the vehicle safety control signal.

[0021] Based on the aforementioned technical means, by collecting multi-dimensional data of vehicles and occupants in real time and combining it with an optimized and trained safety constraint model to generate highly adaptable safety control signals, the safety control device can provide timely and accurate safety constraints to occupants during actual vehicle operation, effectively improving occupant safety during driving.

[0022] Fifthly, this application provides a training device for a safety constraint model, comprising: a construction module and a training module; the construction module is used to construct a training dataset by taking the dynamic data, electromyographic signals of the occupant in motion posture, and occupant vital sign data collected by the acquisition device in the first aspect as training inputs and the safety control signal as training output; the training module is used to train the safety constraint model using the training dataset.

[0023] Sixthly, this application provides a vehicle safety control device, comprising: a communication module, a generation module, and a control module; the communication module is used to acquire vehicle dynamics data, occupant electromyography signals, and occupant vital sign data; the generation module is used to generate a vehicle safety control signal based on the vehicle dynamics data, occupant electromyography signals, and occupant vital sign data and the safety constraint model in the third aspect above; the control module is used to control the vehicle's safety control device to perform safety constraints on the occupant based on the vehicle safety control signal.

[0024] In a seventh aspect, this application provides a vehicle that includes the vehicle safety control device described in the sixth aspect above.

[0025] Eighthly, this application provides an electronic device comprising: a processor and a memory; the memory storing processor-executable instructions. When the processor is configured to execute the instructions, the electronic device implements the methods of the third or fourth aspect described above.

[0026] It should be noted that the technical effects of any of the implementation methods in aspects five to six can be found in the technical effects of the corresponding implementation methods in aspects one to four, and will not be repeated here.

[0027] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0028] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.

[0029] Figure 1 A structural block diagram of a data acquisition system provided by the present invention;

[0030] Figure 2 An architectural diagram of a motion platform provided by the present invention;

[0031] Figure 3 This invention provides an architectural block diagram of an electromyography signal acquisition device;

[0032] Figure 4 A control flowchart of a safety control device provided by the present invention;

[0033] Figure 5 A distribution diagram of crew member muscles provided for this invention;

[0034] Figure 6 A flowchart of a data acquisition method provided by the present invention;

[0035] Figure 7 A flowchart illustrating a training method for a safety constraint model provided by this invention;

[0036] Figure 8 A flowchart illustrating a training method for another safety constraint model provided by the present invention;

[0037] Figure 9 A flowchart of a vehicle safety control method provided by the present invention;

[0038] Figure 10 A structural diagram of a training device for a safety constraint model provided by the present invention;

[0039] Figure 11 A structural diagram of a vehicle safety control device provided by the present invention;

[0040] Figure 12 A block diagram of an electronic device provided by the present invention. Detailed Implementation

[0041] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0042] In embodiments of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, article, or apparatus that includes that element.

[0043] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0044] The data acquisition system provided in this application will be described in detail below.

[0045] In some embodiments, such as Figure 1 As shown, the data acquisition system includes: a motion platform 110, a vehicle cockpit 120, a driving simulation device 130, and a data acquisition device 140.

[0046] The vehicle cockpit 120 is physically connected to the motion platform 110, and the driving simulation device 130 is communicatively connected to the motion platform 110, the data acquisition device 140, and the vehicle cockpit 120 respectively; the data acquisition device 140 is communicatively connected to the vehicle cockpit 120.

[0047] It should be understood that the vehicle cabin 120 can be bolted to the motion platform 110.

[0048] As a feasible implementation method, the motion platform 110 is used to simulate the motion posture of the vehicle cockpit 120 and send the motion posture to the driving simulation device 130.

[0049] As a feasible implementation method, the motion platform 110 can be an eight-degree-of-freedom motion platform, such as... Figure 2 As shown, the eight-degree-of-freedom motion platform includes, but is not limited to: an upper mounting platform 111, an upper hinge 112, a servo electric cylinder system 113, a lower hinge 114, a mounting base 115, a platform slider 116, and a track 117.

[0050] For example, the upper mounting platform 111 is made of profiles and steel plates welded together, possessing sufficient structural strength. The supports on its surface are key components connecting the vehicle cabin 120, which can stably support the cabin and accurately transmit the various movements of the motion platform 110 to the vehicle cabin 120, ensuring that the vehicle cabin 120 moves synchronously with the motion platform 110. The lower part of the upper mounting platform 111 is fixed with three sets of upper hinge seats 112 distributed at 120° to each other by bolts. Each set of upper hinge seats 112 has two hinge shafts, which are connected to the servo electric cylinder system 113 by bolts. This distribution and connection structure provides stable support for the upper mounting platform and also creates conditions for the servo electric cylinder system to drive the platform to move in multiple directions. The design of the hinge shafts ensures flexible rotation of the connection parts, allowing the platform to smoothly achieve tilting, pitching, and other movements.

[0051] The servo electric cylinder system 113 is the power core of the motion platform 110. One end is bolted to the upper hinge seat 112, and the other end is bolted to the lower hinge seat 114. The servo electric cylinder system 113 can precisely extend and retract according to the instructions of the driving simulation device 130. By changing its own length, it pushes the upper mounting platform 111 to move in the up-down, forward-backward, left-right, and rotational directions, thereby simulating the dynamic changes of a vehicle during driving, such as acceleration, deceleration, turning, and bumping. The lower hinge seat 114 is fixed to the mounting base 115 with bolts, serving to connect the servo electric cylinder system 113 and the mounting base 115, providing a stable support foundation for the movement of the servo electric cylinder system 113, ensuring that it will not shift its position during driving and ensuring the accuracy of power transmission.

[0052] The mounting base 115 is bolted to the platform slider 116. The mounting base 115 integrates the upper mounting platform 111, upper hinge 112, servo electric cylinder system 113, lower hinge 114, and other components into a single unit, facilitating the movement of these components along with the platform slider 116. The platform slider 116 is mounted on the track 117 and can slide linearly along the track 117. This design increases the degree of freedom of the motion platform 110, enabling the simulation of a vehicle's forward and backward movement in a straight line, such as the jerking motion during vehicle start-up and braking. The track 117 is connected to and leveled to the foundation, providing smooth and precise guidance for the sliding of the platform slider 116, ensuring the linearity and stability of the slide's movement. Simultaneously, the leveling process ensures that the entire motion platform 110 is mounted on a level reference, preventing uneven foundations from affecting simulation accuracy.

[0053] Specifically, the extension and retraction of the servo electric cylinder system 113 drives the upper mounting platform 111 to perform movements such as up and down, pitch, and tilt, simulating the vehicle's up-and-down bumps, climbing, and tilting during turns; the sliding of the platform slider 116 along the track 117 realizes the forward and backward movement, simulating the vehicle's acceleration, deceleration, and reversing linear movements. Therefore, the eight-degree-of-freedom motion platform can reproduce the vehicle's driving under target conditions through eight degrees of freedom of motion.

[0054] The target operating conditions are those with a risk of driving collision, i.e., dangerous operating conditions. Target operating conditions include, but are not limited to: high-speed emergency lane change, high-speed emergency braking, oversteer, and understeer.

[0055] As a feasible implementation method, the vehicle cockpit 120 is used to respond to the occupant's driving operation commands by sending the driving operation commands to the driving simulation device 130.

[0056] As a feasible implementation method, the vehicle cockpit 120 can highly replicate the driving and riding environment inside a real vehicle cockpit. From the feel of the seats and the display of the instrument panel to the feedback of the control devices, every detail is close to that of a real vehicle, creating an immersive driving atmosphere for the occupants. Once the occupants enter the cockpit, it can receive various driving operation commands issued by them in real time, such as steering, accelerator, and braking commands, ensuring timely response to the occupants' driving intentions.

[0057] As a feasible implementation method, the vehicle cabin 120 includes: a body cabin, safety control devices, an instrument panel, a steering control device, and a power control pedal. The safety control devices, instrument panel, steering control device, and power control pedal are installed in the body cabin, referencing the interior of a real vehicle.

[0058] For example, the safety control device includes an active safety control device and a conventional safety control device. The active safety control device is used to restrain the occupants in advance in the event of a potential collision; the conventional safety control device is used to provide rigid restraint and buffering for the occupants through a predetermined mechanical structure and triggering mechanism.

[0059] For example, the power control pedal may include an accelerator pedal and a brake pedal. The steering control device may be a steering wheel.

[0060] As a feasible implementation method, the driving simulation device 130 is used to generate dynamic data based on driving operation commands and motion posture; determine whether the driving condition is the target condition based on the dynamic data; and send the dynamic data to the vehicle cockpit 120 when the driving condition is the target condition.

[0061] As a feasible implementation method, the driving simulation device 130 includes a dynamic model and a road scene corresponding to the target working condition. The dynamic model simulates the target working condition scene in the preset road scene, and at the same time, combined with the input driving operation commands and motion postures, it generates corresponding dynamic data through model calculations, thereby completing the complete process from command input to working condition judgment and data output.

[0062] For example, a dynamic model is a mathematical model that describes the relationship between a vehicle's motion state (such as position, velocity, acceleration, attitude, etc.) and external inputs (such as driving operation commands, road resistance, air resistance, etc.). Based on physical laws (such as Newton's laws of motion, the law of conservation of momentum, etc.), it quantifies the forces and motion responses of the vehicle through formulas or systems of equations, thereby generating dynamic data (such as longitudinal acceleration, lateral acceleration, sideslip angle, wheel speed, etc.) that reflect the actual dynamic behavior of the vehicle.

[0063] For example, the dynamic model can be a single-track model, taking the steering wheel (steering control device) angle and acceleration / braking commands (power control pedal) as inputs, and combining parameters such as vehicle mass and wheelbase. The longitudinal (driving force and resistance balance), lateral (resultant force of front and rear wheel side deviation), and yaw (torque difference between front and rear wheels) motion equations are established through Newton's laws. The Runge-Kutta method is used to iterate every 0.01 seconds, gradually updating the initial state (such as stationary) to continuous dynamic data including longitudinal / lateral acceleration, yaw rate, center of mass position, etc. The final output is a time-series data sequence reflecting the real-time dynamics of the vehicle.

[0064] As a feasible implementation method, dynamic data includes, but is not limited to: longitudinal acceleration time curves of the vehicle body, lateral acceleration time curves, brake pedal pressure gradient time curves, steering angle acceleration time curves, and active seat belt pull-back force time curves.

[0065] As a feasible approach, it is possible to determine whether a driving condition is the target condition using dynamic data and preset dynamic data. For example, if the dynamic data is greater than the preset dynamic data, the driving condition is considered the target condition.

[0066] The preset dynamic data can be the minimum dynamic data under the target working condition calibrated empirically, or the preset dynamic data can be the minimum dynamic data calibrated through a large number of experiments.

[0067] As a feasible implementation method, the vehicle cockpit 120 is also used to generate safety control signals based on dynamic data.

[0068] Among them, the safety control signal is used to control the safety control device in the vehicle cabin 120 to restrain the occupants.

[0069] For example, the vehicle cabin 120 receives dynamic data output by the dynamic model in real time, and judges dangerous scenarios by preset thresholds (such as the critical value of acceleration during rapid acceleration / braking and collision). When the data exceeds the threshold, a safety control signal is immediately generated to trigger safety control devices such as seat belt pretensioners and airbags in the cabin, so as to quickly complete the restraint and protection of the occupants, thereby reducing the risk of injury to the occupants in an accident.

[0070] As a feasible implementation method, the acquisition device 140 is used to acquire dynamic data, safety control signals, electromyographic signals of occupants in motion postures, and vital sign data of occupants.

[0071] As a feasible implementation method, the acquisition device 140 includes: an electromyography signal acquisition device, an image acquisition device, and a control signal acquisition device.

[0072] Among them, the electromyography (EMG) signal acquisition device is used to acquire EMG signals; EMG signals are used to represent the electrical signals generated when capturing the occupant's muscles.

[0073] For example, such as Figure 3 As shown, the electromyography (EMG) signal acquisition device includes: an EMG signal sensor, a signal amplifier, a filter, a digital-to-electrical converter, a power supply, a data interface, and a safety protector.

[0074] It should be understood that the electromyography (EMG) signal sensor is responsible for capturing the electrical signals generated by the occupant's muscle activity; the signal amplifier amplifies the weak EMG signals to a level suitable for subsequent processing; the filter purifies the amplified signal, removing interference noise; the digital-to-digital converter converts the noise-reduced analog EMG signals into digital signals for computer analysis and processing; the power module provides stable power support for other components of the EMG signal acquisition device; the data interface handles the transmission of digital signals to the computer; and the safety protector enhances the safety performance and operational reliability of the EMG signal acquisition device.

[0075] The image acquisition device is used to acquire images of the vehicle cabin interior and extract occupant vital signs data based on these images to classify the occupants. These vital signs data include, but are not limited to: gender, age, height, weight, and occupant's posture.

[0076] The control signal acquisition device is used to acquire safety control signals to facilitate subsequent data analysis and testing evaluation.

[0077] In some embodiments, the vehicle cabin 120 further includes: a first controller and a second controller;

[0078] The first controller is used to respond to driving operation commands and send driving operation commands to the driving simulation device 130.

[0079] As a feasible implementation method, the first controller may include: an instruction receiving module for acquiring the steering, accelerator, brake and other operation instructions input by the driver; a signal processing module for converting the received driving operation instructions into formats and verifying their validity; and a communication module for stably transmitting the processed driving operation instructions to the driving simulation device 130 through a preset protocol to ensure the accuracy and real-time performance of the driving operation instructions.

[0080] The second controller is used to generate safety control signals based on dynamic data, and to use the safety control signals to control the safety control device in order to achieve safety restraint of the occupants.

[0081] As a feasible implementation method, the second controller can be an active constraint controller; the safety control device can be an active constraint device; the active constraint device includes: an active constraint device control unit and an active constraint device actuator.

[0082] As a feasible implementation method, an active constraint controller refers to a control unit that can actively determine and trigger constraint actions based on real-time dynamic data. An active constraint device refers to a device that can actively adjust the constraint force and timing based on control signals, as opposed to traditional passively triggered devices.

[0083] For example, such as Figure 4 As shown, after receiving dynamic data, the active restraint controller performs calculations and results judgments using a preset algorithm (such as a risk level determination algorithm based on a collision warning model) to generate a safety control signal containing parameters such as restraint timing and force (active restraint force). The signal is then sent to the active restraint device control unit. After parsing the signal, the active restraint device control unit drives the active restraint device actuator to act in a timely manner (such as quickly pre-tensioning the seat belt or accurately triggering the airbag), thereby providing effective protection for the occupants.

[0084] It should be understood that the preset algorithm can be set according to the type of vehicle, and the embodiments of this application do not limit this.

[0085] In some embodiments, the acquisition device 140 is also used to acquire the displacement amount of the occupant in motion posture; if the displacement amount is not less than a preset displacement amount threshold, the dynamic data, safety control signals, electromyographic signals of the occupant in motion posture, and vital sign data of the occupant are discarded.

[0086] The displacement amount represents the occupant's positional deviation during vehicle testing. The preset displacement threshold represents the maximum permissible positional deviation of the occupant.

[0087] As a feasible approach, the image acquisition device can also determine the occupant's displacement based on images of the vehicle's interior.

[0088] For example, the image acquisition device captures dynamic images of the occupant in real time, extracts the coordinate information of key parts of the occupant such as the head and torso through image recognition algorithms (such as positioning algorithms based on skeletal key point detection), compares and calculates the coordinates of these parts with preset standard position coordinates (such as the occupant position parameters in a normal sitting posture), and determines the positional offset value of each part. The overall displacement of the occupant is determined by combining these offset values. If the calculated displacement reaches or exceeds the preset displacement threshold, the dynamic data, safety control signals, electromyographic signals of the occupant in motion posture, and vital sign data of the occupant are automatically discarded, and the preset algorithm in the second controller is triggered for correction. After the preset algorithm correction, the test is repeated.

[0089] It should be understood that if the displacement amount is greater than or equal to the preset displacement threshold, it indicates that there is a problem with the accuracy of the preset algorithm in the second controller, which needs to be corrected. Therefore, the dynamic data, safety control signals, electromyographic signals of the occupants in motion posture and the vital signs data of the occupants in this test can be discarded, and the above data can be re-acquired after the preset algorithm is corrected.

[0090] As a feasible implementation method, the acquisition device 140 is also used to discard dynamic data, safety control signals, occupant's electromyographic signals in motion posture and occupant's vital signs data when the electromyographic signal is less than the maximum voluntary contraction electromyographic signal.

[0091] Among them, the maximum voluntary contraction electromyographic signal is the maximum electromyographic signal of the occupant under static conditions.

[0092] As a feasible approach, the acquisition of maximal voluntary contraction electromyographic (EMG) signals can be achieved as follows: First, the occupant's skin is pre-treated, typically involving cleaning the skin surface to remove dirt, oil, and dead skin cells, thereby reducing skin impedance and ensuring more stable acquisition of EMG signals. Next, an EMG signal sensor module is attached to the corresponding area of ​​the target muscle, ensuring close contact and accurate positioning of the sensor. Then, the occupant sits on a rigid testing fixture module, which provides stable support and reduces interference from body swaying. Finally, the EMG signal acquisition device is activated, and under its control, the EMG signals generated during the occupant's maximal voluntary muscle contraction are acquired, thus obtaining the required maximal voluntary contraction EMG signal.

[0093] For example, such as Figure 5 As shown, the target muscle is divided into anterior and posterior parts.

[0094] The anterior muscle includes: sternocleidomastoid (SCM), masseter (MS), anterior deltoid (ADELT), pectoralis major (PM), biceps brachii (BIC), serratus anterior (SERAN), rectus abdominis (RA), external oblique (EXOB), lower limb muscles (Ref), rectus femoris (RF), and vastus medialis (VM).

[0095] The posterior includes: the cervical posterior vertebral muscle (CPVM), the upper trapezius (UTRP), the posterior deltoid (PDELT), the lower trapezius (LTRP), the triceps brachii (TRIC), the latissimus dorsi (LD), the longissimus pars vertebrarum (LPVM), the gluteus maximus (GMAX), and the semitendinosus (SEMI).

[0096] As a feasible implementation method, after the acquisition device 140 acquires the occupant's electromyography (EMG) signal, it first normalizes the signal and then compares the processed signal with the maximum voluntary contraction EMG signal (i.e., the maximum EMG signal acquired in the static state). Since the occupant's EMG signal will necessarily be greater than the maximum voluntary contraction EMG signal when in a dangerous working condition (target working condition), when the detected EMG signal is less than this benchmark value, the acquired data is automatically discarded, the preset algorithm in the second controller is re-optimized, and the test is conducted again.

[0097] In some embodiments, the driving simulation device 130 is specifically used to determine the driving condition as the target condition when the difference between the dynamic data and the target dynamic data under the target condition is less than a preset difference.

[0098] As a feasible approach, the process of acquiring target dynamics data can be as follows: extract time curve data such as longitudinal / lateral acceleration of the vehicle body and brake pedal pressure gradient from actual traffic accident records; and collect time curve data such as steering angle acceleration and active seat belt pull-back force by simulating hazardous conditions (such as emergency braking and high-speed avoidance) at the test track.

[0099] For example, the target dynamics data under the target operating condition is pre-stored in the driving simulation device 130, and a preset difference threshold is set (such as the maximum deviation value or mean square error range of each data curve); the dynamics model generates the current dynamics data in real time based on the input driving operation command and motion posture; the data comparison module is called to compare the real-time generated dynamics data with the target dynamics data point by point along the time axis, and the difference value between the two is calculated (such as using the root mean square error formula to calculate the overall deviation); if the calculated difference value is less than the preset difference threshold, the current driving condition is determined to be the target operating condition.

[0100] In some embodiments, the data acquisition system may further include a measurement and control device.

[0101] As a feasible implementation method, the measurement and control device is used for synchronous signal processing between the motion platform 110, vehicle cockpit 120, driving simulation device 130, and data acquisition device 140. It performs signal analysis, data processing, and forwarding for the motion platform 110, vehicle cockpit 120, driving simulation device 130, and data acquisition device 140, enabling communication between the various devices.

[0102] As a feasible implementation method, the measurement and control device includes, but is not limited to, a host computer and a slave computer. The host computer is used to deploy the environmental model and sensor model; the slave computer is used to deploy the vehicle dynamics model.

[0103] For example, the instrument panel, steering control device, and power control pedal in the vehicle cabin 120 can send driving operation commands to the measurement and control device via User Datagram Protocol (UDP). After receiving the commands, the measurement and control device forwards them to the driving simulation device 130. The driving simulation device 130 generates dynamic signals based on the received driving operation commands and transmits them to the measurement and control device via a Local Area Network (LAN) line. The measurement and control device parses and processes the dynamic signals, converts them into a recognizable form, and then sends them to the second controller for algorithm calculation.

[0104] The data collection method provided in this application will be described in detail below.

[0105] In some embodiments, the data acquisition method provided in this application can be applied to Figure 1 The data acquisition system shown is as follows: Figure 6 As shown, the data acquisition method specifically includes the following steps:

[0106] S601, the motion platform simulates the motion posture of the vehicle cockpit and sends the motion posture to the driving simulation device.

[0107] As a feasible implementation method, the motion platform can be an eight-degree-of-freedom (DOF) motion platform. An eight-DOF motion platform can reproduce the vehicle's movement under target conditions through eight degrees of freedom of motion.

[0108] S602, the vehicle cockpit responds to the occupant's driving operation commands and sends the driving operation commands to the driving simulation device.

[0109] As a feasible approach, the vehicle cockpit can highly replicate the driving and riding environment of a real vehicle. From the feel of the seats and the display of the instrument panel to the feedback of the control devices, every detail closely resembles that of a real vehicle, creating an immersive driving atmosphere for the occupants. Once the occupants enter the cockpit, it can receive various driving operation commands issued by them in real time, such as steering, accelerator, and braking commands, ensuring timely response to the occupants' driving intentions.

[0110] S603, the driving simulation device generates dynamic data based on driving operation commands and motion posture; determines whether the driving condition is the target condition based on the dynamic data; and sends the dynamic data to the vehicle cockpit if the driving condition is the target condition.

[0111] As a feasible implementation method, the driving simulation device includes a dynamic model and a road scene corresponding to the target working condition. The dynamic model simulates the target working condition in a preset road scene, and at the same time, combined with the input driving operation commands and motion postures, it generates corresponding dynamic data through model calculations, thereby completing the entire process from command input to working condition judgment and data output.

[0112] S604: The vehicle cabin generates safety control signals based on dynamic data.

[0113] Among them, the safety control signal is used to control the safety control devices in the vehicle cabin to restrain the occupants.

[0114] S605, the data acquisition device acquires dynamic data, safety control signals, electromyographic signals of occupants in motion postures, and vital signs data of occupants.

[0115] In some embodiments, after acquiring dynamic data, safety control signals, electromyographic signals of occupants in motion postures, and occupant vital signs data through the acquisition device, the safety constraint model can be trained using these data.

[0116] As a feasible implementation method, such as Figure 7 As shown, the training method for the safety constraint model can be implemented in the following steps:

[0117] S701. A training dataset is constructed using dynamic data, electromyographic signals of occupants in motion postures, and occupant vital signs data as training inputs, and safety control signals as training outputs.

[0118] As a feasible approach, people of different ages, heights, weights, and genders are selected as occupants. Electromyography (EMG) sensor modules are attached to various muscle sites of the occupants. Using a data acquisition system, the EMG signals and vital signs of the occupants, as well as the dynamic data generated by the driving simulation device, are collected simultaneously under target conditions (such as emergency braking and high-speed avoidance) simulated by the driving simulation device. At the same time, the safety control signals (such as seat belt pretension force and airbag triggering timing commands) generated by the second controller under the target conditions are recorded.

[0119] As a feasible approach, the collected training dataset (including electromyography signals, vital sign data, dynamic data, and safety control signals) is subjected to feature normalization processing, mapping features of different magnitudes to a unified range.

[0120] For example, normalization can satisfy the following formula:

[0121]

[0122] in, Used to represent data after normalization, x (n) The original data used to represent a certain feature, where n represents the amount of data for that feature.

[0123] S702. Train the safety constraint model using the training dataset.

[0124] As a feasible implementation method, the training process of the safety constraint model includes: constructing an initial model based on the design of the basic model and hyperparameter optimization; performing ensemble training based on the initial model and the training sample set to obtain the safety constraint model; and verifying and optimizing the safety constraint model.

[0125] For example, the basic model design includes: selecting a gated recurrent unit (GRU) network as the basic model, because the GRU network can effectively process time-series data (such as electromyographic signals and acceleration curves that change over time); selecting a computationally efficient nonlinear activation function, and at the same time limiting the model complexity through regularization to avoid overfitting.

[0126] Hyperparameter optimization includes: based on the tested combinations of hyperparameters (learning rate, batch size, number of neurons, number of network layers, etc.), using Bayesian optimization to iteratively predict the optimal combination, and using the prediction accuracy of the validation set as the objective function to determine the best parameter configuration of the model.

[0127] The ensemble training includes training multiple GRU sub-models with different hyperparameters or initial weights, and fusing the outputs of each sub-model through voting or weighted averaging to further improve the model's predictive stability and generalization ability for safety control signals.

[0128] Validation and optimization include: dividing the dataset into a training set (70%), a validation set (15%), and a test set (15%); using the test set to evaluate the model's prediction error (such as root mean square error); if the performance does not meet expectations, returning to the hyperparameter optimization or data preprocessing stage for adjustment until the model meets the requirements of actual applications.

[0129] By acquiring training datasets that cover multiple groups of people and multiple dimensions and have undergone standardized preprocessing through a data acquisition system, the safety constraint model can be trained. This can improve the model's adaptability and prediction accuracy for different occupants under hazardous conditions, enhance its generalization ability, provide reliable support for vehicle safety control, and effectively protect occupant safety.

[0130] In some embodiments, such as Figure 8 As shown, the training method for the safety constraint model can be specifically implemented as follows:

[0131] S801. Obtain the training dataset.

[0132] S802. Normalize the training dataset.

[0133] S803, Basic Model Design.

[0134] S804. Hyperparameter optimization yields the initial model.

[0135] S805, ensemble training based on the initial model and training sample set.

[0136] S806, Verification and Optimization.

[0137] In some embodiments, after the safety constraint model is trained, it can be deployed on the vehicle to help with vehicle safety control.

[0138] As a feasible implementation method, such as Figure 9 As shown, the vehicle safety control method can be implemented in the following steps:

[0139] S901: Acquire vehicle dynamics data, occupant electromyography signals, and occupant vital signs data.

[0140] For example, vehicle dynamics data includes data such as longitudinal / lateral acceleration and steering angle acceleration of the vehicle body collected during actual vehicle operation; occupant electromyography signals are electromyography signals of various muscle parts of the occupant collected in real time during actual vehicle operation; and occupant vital signs data include data such as height, weight, and age of the current occupants inside the vehicle.

[0141] S902. Based on vehicle dynamics data, occupant electromyography signals, occupant vital signs data, and safety constraint models, generate vehicle safety control signals.

[0142] For example, based on vehicle dynamics data, occupant electromyography signals and occupant vital signs data, combined with a pre-trained safety constraint model (constructed using a gated recurrent unit network and a multi-model integration strategy), vehicle safety control signals (such as seat belt pretension force, airbag triggering timing, etc.) adapted to the current working conditions can be generated.

[0143] S903, A safety control device that controls a vehicle based on a vehicle safety control signal to restrain occupants.

[0144] By collecting multi-dimensional data on vehicles and occupants in real time and combining it with an optimized and trained safety constraint model to generate highly adaptable safety control signals, the safety control device can provide timely and accurate safety constraints to occupants during actual vehicle operation, effectively improving occupant safety during driving.

[0145] The foregoing has described the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the training device for the safety constraint model and the vehicle safety control device include hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Experts may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0146] like Figure 10 As shown, the training device 1000 for the safety constraint model includes: a construction module 1001 and a training module 1002; the construction module 1001 is used to construct a training dataset by taking the dynamic data, electromyographic signals of the occupant in motion posture and the occupant's vital signs data collected by the acquisition device in the first aspect as training input and the safety control signal as training output; the training module 1002 is used to train the safety constraint model using the training dataset.

[0147] like Figure 11As shown, the vehicle safety control device 1100 includes: a communication module 1101, a generation module 1102, and a control module 1103; the communication module 1101 is used to acquire vehicle dynamics data, occupant electromyography signals, and occupant vital signs data; the generation module 1102 is used to generate vehicle safety control signals based on the vehicle dynamics data, occupant electromyography signals, and occupant vital signs data, and the safety constraint model in the third aspect mentioned above; the control module 1103 is used to control the vehicle's safety control device to perform safety constraints on the occupants based on the vehicle safety control signals.

[0148] like Figure 12 As shown, the electronic device 1200 includes, but is not limited to, a processor 1201 and a memory 1202.

[0149] The memory 1202 described above is used to store the executable instructions of the processor 1201. It is understood that the processor 1201 is configured to execute instructions to implement the driving planning method in the above embodiments.

[0150] It should be noted that those skilled in the art will understand that Figure 12 The structure of the electronic device 1200 shown does not constitute a limitation on the electronic device 1200; the electronic device 1200 may include, but is not limited to, other electronic devices. Figure 12 This may indicate more or fewer components, or combinations of certain components, or different component arrangements.

[0151] Processor 1201 is the control center of electronic device 1200. It connects various parts of electronic device 1200 via various interfaces and lines. By running or executing software programs and / or modules stored in memory 1202, and by calling data stored in memory 1202, it performs various functions and processes data of electronic device 1200, thereby providing overall monitoring of electronic device 1200. Processor 1201 may include one or more processing units. Optionally, processor 1201 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into processor 1201.

[0152] The memory 1202 can be used to store software programs and various data. The memory 1202 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required by at least one functional module (such as a determination unit, processing unit, etc.), etc. Furthermore, the memory 1202 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0153] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 1202 including instructions, which can be executed by a processor 1201 of an electronic device 1200 to implement the training method of the safety constraint model or the vehicle safety control method in the above embodiments.

[0154] In actual implementation, Figure 10 The building module 1001 and training module 1002 in the middle, Figure 11 The functions of the communication module 1101, generation module 1102, and control module 1103 can all be provided by... Figure 12 The processor 1201 calls the computer program stored in the memory 1202 to implement the process. The specific execution process can be found in the method section of the previous embodiment, and will not be repeated here.

[0155] Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0156] In an exemplary embodiment, this application also provides a computer program product including one or more instructions, which can be executed by the processor 1201 of the electronic device 1200 to complete the training method of the safety constraint model or the vehicle safety control method in the above embodiments.

[0157] It should be noted that when one or more instructions in the computer-readable storage medium or computer program product are executed by the processor of an electronic device, they implement the various processes of the above method embodiments and achieve the same technical effect as the above method. To avoid repetition, they will not be described again here.

[0158] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0159] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0160] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the classified units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0161] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0162] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, essentially, or the part that contributes to the prior art, or a complete or partial classification of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0163] The above embodiments are merely preferred embodiments provided to fully illustrate the present invention, and the scope of protection of the present invention is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on the present invention are all within the scope of protection of the present invention.

Claims

1. A data acquisition system, characterized by, The system comprises a motion platform, a vehicle cabin, a driving simulation device and a collection device; the vehicle cabin is physically connected to the motion platform; the driving simulation device is communicatively connected to the motion platform, the collection device and the vehicle cabin respectively; and the collection device is communicatively connected to the vehicle cabin; The motion platform is configured to simulate a motion posture of the vehicle cabin and send the motion posture to the driving simulation device; The vehicle cabin is configured to send a driving operation instruction of an occupant to the driving simulation device in response to the driving operation instruction; The driving simulation device is configured to generate dynamics data based on the driving operation instruction and the motion posture, determine whether a driving working condition is a target working condition based on the dynamics data, and send the dynamics data to the vehicle cabin when the driving working condition is the target working condition; the target working condition is a working condition in which a driving collision risk exists; The vehicle cabin is further configured to generate a safety control signal based on the dynamics data; the safety control signal is used to control a safety control device in the vehicle cabin to safely restrain the occupant; The collection device is configured to collect the dynamics data, the safety control signal, an electromyography signal of the occupant in the motion posture and physical data of the occupant.

2. The data acquisition system of claim 1, wherein, The vehicle cabin further comprises a first controller and a second controller; The first controller is configured to send the driving operation instruction to the driving simulation device in response to the driving operation instruction; The second controller is configured to generate a safety control signal based on the dynamics data and control the safety control device by using the safety control signal to safely restrain the occupant.

3. The data acquisition system of claim 1, wherein, The collection device is further configured to collect an off-site amount of the occupant in the motion posture; and discard the dynamics data, the safety control signal, the electromyography signal of the occupant in the motion posture and the physical data of the occupant when the off-site amount is not less than a preset off-site amount threshold.

4. The data acquisition system of claim 1, wherein, The collection device is further configured to discard the dynamics data, the safety control signal, the electromyography signal of the occupant in the motion posture and the physical data of the occupant when the electromyography signal is less than a maximum autonomous contraction electromyography signal; the maximum autonomous contraction electromyography signal is a maximum electromyography signal of the occupant in a static state.

5. The data acquisition system of claim 1, wherein, The driving simulation device is specifically configured to determine that the driving working condition is the target working condition when a difference between the dynamics data and target dynamics data in the target working condition is less than a preset difference.

6. A data acquisition method characterized by, The application is applied to a data collection system; The data collection system comprises a motion platform, a vehicle cabin, a driving simulation device and a collection device; the vehicle cabin is physically connected to the motion platform; the driving simulation device is communicatively connected to the motion platform, the collection device and the vehicle cabin respectively; and the collection device is communicatively connected to the vehicle cabin; and the method comprises: The motion platform simulates a motion posture of the vehicle cabin and sends the motion posture to the driving simulation device; The vehicle cabin sends a driving operation instruction of a passenger to the driving simulation device in response to the driving operation instruction; The driving simulation device generates dynamics data based on the driving operation instruction and the motion posture, determines whether a driving working condition is a target working condition based on the dynamics data, and sends the dynamics data to the vehicle cabin in a case where the driving working condition is the target working condition; the target working condition is a working condition in which a driving collision risk exists; The vehicle cabin generates a safety control signal based on the dynamics data; the safety control signal is used to control a safety control device in the vehicle cabin to perform safety restraint on the passenger; The collection device collects the dynamics data, the safety control signal, an electromyography signal of the passenger in the motion posture, and a physical data of the passenger. 7.A method for training a safety constraint model, the method comprising: The method comprises: The dynamics data, the electromyography signal of the passenger in the motion posture, and the physical data of the passenger collected by the collection device of any one of claims 1-5 are used as training input, and the safety control signal is used as training output to construct a training data set; The safety restraint model is trained by using the training data set.

8. A vehicle safety control method characterized by The method comprises: Obtaining vehicle dynamics data, a passenger electromyography signal, and a passenger physical data; Generating a vehicle safety control signal based on the vehicle dynamics data, the passenger electromyography signal, the passenger physical data, and the safety restraint model of claim 7; Controlling a safety control device of a vehicle to perform safety restraint on a passenger based on the vehicle safety control signal. 9.A training apparatus of a safety constraint model, characterized by, The device comprises a construction module and a training module; The construction module is configured to use the dynamics data, the electromyography signal of the passenger in the motion posture, and the physical data of the passenger collected by the collection device of any one of claims 1-5 as training input, and use the safety control signal as training output to construct a training data set; The training module is configured to train the safety restraint model by using the training data set.

10. A vehicle safety control device characterized by comprising: The device comprises a communication module, a generation module, and a control module; The communication module is configured to obtain vehicle dynamics data, a passenger electromyography signal, and a passenger physical data; The generation module is configured to generate a vehicle safety control signal based on the vehicle dynamics data, the passenger electromyography signal, the passenger physical data, and the safety restraint model of claim 7; The control module is configured to control a safety control device of a vehicle to perform safety restraint on a passenger based on the vehicle safety control signal.

11. A vehicle characterized by comprising: The vehicle safety control device comprises the vehicle safety control device of claim 10.

12. An electronic device, comprising: Comprise: A processor and a memory; The memory stores instructions executable by the processor; The processor is configured to execute the instructions, so that the electronic device implements the method of any one of claims 7-8.

Images