Vehicle control method and device and vehicle

Abstract

The embodiment of the invention provides a vehicle control method and device and a vehicle, and relates to the technical field of motor control technologies and auxiliary driving, and the method comprises the steps that driving state data and driving operation data of the vehicle are acquired; performing tire burst state detection on the vehicle by using the driving state data to obtain a detection result; determining target threshold data by using the driving state data, the driving operation data and the detection result; and a target reverse yaw moment is determined based on a multiple control mode, the driving state data, the driving operation data and the target threshold data, the multiple control mode is constructed based on a self-adaptive feedforward control rule and a feedback control rule, and the target reverse yaw moment is used for controlling a driving moment or a braking moment of an execution assembly in the vehicle. The technical problems of high delay and poor accuracy of a vehicle control method in the prior art are solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical fields of motor control technology and assisted driving technology, and in particular, to a vehicle control method, device and vehicle. Background Art

[0002] In the case of a flat tire failure of a vehicle, due to damage to the tire, the handling performance of the vehicle will be severely degraded. How to maintain the stable driving of the vehicle in this case has become an urgent problem in the related technical fields.

[0003] In the related art, usually, the driving motor torque of the flat tire wheel is directly adjusted to zero, and then the driving motor torque of the non-flat tire wheel is determined according to a certain parameter of the vehicle. However, on the one hand, this method has a high delay and cannot control the vehicle in time, resulting in poor stability of the vehicle; on the other hand, this method relies on a single parameter, resulting in poor accuracy of the determined motor torque, making it difficult for the vehicle to drive stably in the case of a flat tire failure.

[0004] In view of the above problems, no effective solution has been proposed yet. Summary of the Invention

[0005] The embodiments of the present application provide a model training method, a confidence inference method, a driving decision method, a model training device, a confidence inference device, a system, an electronic device and a computer-readable storage medium, aiming to improve the technical problems of high delay and poor accuracy in the vehicle control method in the related art.

[0006] According to one aspect of the embodiments of the present application, a vehicle control method is provided, including: obtaining the driving state data and driving operation data of the vehicle; using the driving state data to detect the flat tire state of the vehicle to obtain a detection result; using the driving state data, driving operation data and detection result to determine target threshold data; based on multiple control modes, driving state data, driving operation data and target threshold data, determining a target reverse yaw moment, where the multiple control modes are constructed based on an adaptive feedforward control rule and a feedback control rule, and the target reverse yaw moment is used to control the driving torque or braking torque of an execution component in the vehicle.

[0007] The above vehicle control method provided by the embodiments of the present application achieves the following technical effects: By obtaining the driving state data and driving operation data of the vehicle, the current driving state and driving operation conditions of the vehicle can be determined in real time, enhancing the timeliness of the data and contributing to more accurate subsequent detection of the flat tire state of the vehicle; furthermore, using the driving state data to detect the flat tire state of the vehicle and obtaining the detection result can timely determine whether the vehicle has a flat tire fault and enhance the accuracy of the detection result; further, using the driving state data, driving operation data and detection result to determine the target threshold data, by comprehensively considering the driving state data, driving operation data and detection result, it is judged whether there is a driver's misoperation, and then the target threshold data is determined to limit the driver's wrong operation, reducing the impact of the driver's misoperation, and determining the target threshold data that can ensure the stable driving of the vehicle; finally, the adaptive feedforward control can predict the unstable state that the vehicle will appear according to the current driving state and driving operation conditions of the vehicle, so as to apply a control torque in advance to control the vehicle in time, improving the response speed of the vehicle control method, while the feedback control can make an immediate correction according to the actual motion deviation of the vehicle. The multiple control methods constructed by using the adaptive feedforward control rule and the feedback control rule can combine the advantages of the adaptive feedforward control and the feedback control. Based on this multiple control method, driving state data, driving operation data and target threshold data, the target reverse yaw moment can be obtained more quickly, and the accuracy of the determined target reverse yaw moment is also higher, thus ensuring that the vehicle can drive stably in the case of a flat tire fault and improving the safety of the vehicle. Therefore, the embodiments of the present application achieve the purpose of efficiently and accurately determining the target reverse yaw moment by combining the driving state data and driving operation data and using the multiple control methods of adaptive feedforward control and feedback control, realizing the technical effect of improving the accuracy and response speed of the target reverse yaw moment, overcoming the defect of poor stability of the vehicle in the case of a flat tire fault, and further solving the technical problems of high latency and poor accuracy in the vehicle control method in the related art.

[0008] Optionally, the driving state data includes: tire pressure perception data, wheel speed data, vibration perception data and acoustic perception data, and the detection result includes flat tire flag data. Using the driving state data to detect the flat tire state of the vehicle, the obtained detection result includes: determining the first flag data according to the tire pressure perception data, preset detection period and tire pressure change threshold; determining the second flag data according to the wheel speed data and wheel speed difference threshold; determining the third flag data according to the vibration perception data and vibration anomaly threshold; determining the fourth flag data according to the acoustic perception data and acoustic anomaly threshold; based on the first flag data, second flag data, third flag data and fourth flag data, determining the flat tire flag data, where the flat tire flag data is used to represent whether the vehicle is in a flat tire state.

[0009] The above optional embodiments of the present application can achieve the following technical effects: By comprehensively analyzing tire pressure perception, wheel speed changes, vehicle body vibration, and acoustic signals, the tire burst state of the vehicle is judged from multiple dimensions, and more accurate tire burst flag data can be obtained. It overcomes the problem of low accuracy in detecting the tire burst state of the vehicle relying on a single sensor, improves the accuracy of tire burst detection, and further ensures the effective implementation of subsequent control strategies to maintain the stable driving of the vehicle.

[0010] Optionally, the detection result further includes missed detection flag data and false detection flag data, and the above vehicle control method further includes: in response to the first flag data, the second flag data, the third flag data, and the fourth flag data satisfying the missed detection condition, determining the missed detection flag data, where the missed detection condition includes: determining that the tire pressure perception data does not include a tire burst anomaly according to the first flag data, determining that the wheel speed data includes a tire burst anomaly according to the second flag data, determining that the vibration perception data includes a tire burst anomaly according to the third flag data, and determining that the acoustic perception data includes a tire burst anomaly according to the fourth flag data; in response to the first flag data, the second flag data, the third flag data, and the fourth flag data satisfying the false detection condition, determining the false detection flag data, where the false detection condition includes: determining that the tire pressure perception data includes a tire burst anomaly according to the first flag data, determining that the wheel speed data does not include a tire burst anomaly according to the second flag data, determining that the vibration perception data does not include a tire burst anomaly according to the third flag data, and determining that the acoustic perception data does not include a tire burst anomaly according to the fourth flag data; generating an enable signal for the execution component according to the missed detection flag data and the false detection flag data.

[0011] The above optional embodiments of the present application can achieve the following technical effects: By comprehensively judging the first flag data, the second flag data, the third flag data, and the fourth flag data, it is possible to accurately judge whether there is a missed detection or a false detection, and respectively determine the missed detection flag data and the false detection flag data. An enable signal for the execution component is generated according to the missed detection flag data and the false detection flag data. Using this enable signal can ensure that the execution component of the vehicle performs tire burst stability control only when it is determined that the tire burst state of the vehicle is accurately identified, avoiding unnecessary control triggered by missed detection or false detection and interfering with the normal driving of the vehicle, and further enhancing the accuracy of the vehicle control method.

[0012] Optionally, the driving operation data includes: steering wheel signal, brake pedal signal, and radar perception signal. The target threshold data includes a target yaw threshold. Determining the target threshold data by using the driving state data, driving operation data, and detection result includes: in response to determining that the vehicle is in a flat tire state according to the detection result, determining the obstacle distance information corresponding to the vehicle based on the radar perception signal, and performing driving intention recognition by using the obstacle distance information, steering wheel signal, and brake pedal signal to determine the recognition result, where the recognition result is used to represent whether the corresponding driving operation of the vehicle belongs to a misoperation; determining the target yaw threshold by using the driving state data, driving operation data, and recognition result.

[0013] The above optional embodiment of the present application can achieve the following technical effects: By performing driving intention recognition by using the obstacle distance information, steering wheel signal, and brake pedal signal to determine the recognition result, it is possible to determine the operation intention of the driver in the event of a flat tire, and avoid the problem of vehicle out of control caused by the driver's improper operation or excessive operation (for example, suddenly turning the steering wheel, suddenly stepping on the brake, turning the steering wheel in the opposite direction, etc.) when the vehicle has a flat tire failure. Further, by using the driving state data, driving operation data, and recognition result, and combining with the threshold calculation method, the target yaw threshold is determined, so as to timely adjust the subsequent vehicle stability control strategy to ensure the accuracy of the control decision.

[0014] Optionally, the driving state data includes vehicle speed data and wheel speed data. Determining the target yaw threshold by using the driving state data, driving operation data, and recognition result includes: determining the basic yaw data by using the vehicle speed data, wheel speed data, steering wheel signal, wheelbase corresponding to the vehicle, and preset characteristic vehicle speed; in response to determining that the driving operation belongs to a misoperation according to the recognition result, correcting and updating the basic yaw data according to the vehicle speed data; determining the basic yaw threshold by using the basic yaw data and the yaw threshold sensitivity calibration coefficient corresponding to the vehicle; generating the target yaw threshold based on the basic yaw threshold and the lateral acceleration threshold corresponding to the vehicle.

[0015] The above optional embodiment of the present application can achieve the following technical effects: By comprehensively considering the influence of the driving operation data and correcting the basic yaw data, the basic yaw threshold for preventing vehicle out of control can be determined more accurately. Further, determining the target yaw threshold based on the basic yaw threshold and the lateral acceleration threshold takes into account more comprehensive information, improves the accuracy of the target yaw threshold, adapts to complex driving environments, and improves the stability and safety of the vehicle after a flat tire.

[0016] Optionally, the multiple control rules include an adaptive feedforward control rule and a feedback control rule. Determining the target reverse yaw moment based on the multiple control mode, driving state data, driving operation data, and target threshold data includes: calculating a feedforward yaw moment using the adaptive feedforward control rule, driving state data, and driving operation data; calculating a feedback yaw moment using the feedback control rule, driving state data, and target threshold data; and performing weighted calculation on the feedforward yaw moment and the feedback yaw moment to determine the target reverse yaw moment.

[0017] The above optional embodiments of the present application can achieve the following technical effects: In the case of a flat tire failure of the vehicle, the adaptive feedforward control rule can predict the future unstable state of the vehicle according to the driving state data and driving operation data of the vehicle, calculate the feedforward yaw moment in advance to control the vehicle, and improve the response speed of vehicle control; furthermore, the feedback control rule is used to dynamically adjust the deviation between the actual yaw and the target yaw to obtain a target reverse yaw moment with higher accuracy. By combining the two control methods of the adaptive feedforward control rule and the feedback control rule, the response speed of vehicle control can be improved while the accuracy of vehicle control is enhanced.

[0018] Optionally, the driving state data includes vehicle speed data, and the driving operation data includes steering wheel signal, brake pedal signal, and accelerator pedal signal. Calculating the feedforward yaw moment using the adaptive feedforward control rule, driving state data, and driving operation data includes: determining a feedforward yaw moment model and an adaptive correction model based on the adaptive feedforward control rule; calculating the feedforward yaw moment using the feedforward yaw moment model, vehicle speed data, steering wheel signal, brake pedal signal, accelerator pedal signal, and flat tire deflation rate; and adaptively correcting the feedforward yaw moment using the adaptive correction model and the road adhesion parameter and vehicle load corresponding to the vehicle to update the feedforward yaw moment.

[0019] The above optional embodiments of the present application can achieve the following technical effects: Based on the adaptive feedforward control rule, a feedforward yaw moment model and an adaptive correction model are determined. Using the feedforward yaw moment model, the control system of the vehicle can instantaneously generate a feedforward yaw moment according to real-time driving state data and driving operation data, improving the response speed of vehicle control. And using the adaptive correction model, considering the influence of the actual driving conditions of the vehicle on vehicle control, the feedforward yaw moment is dynamically adjusted, enhancing the robustness of the vehicle control system and ensuring the accuracy of the feedforward yaw moment.

[0020] Optionally, the target threshold data includes a target yaw threshold. In step S402 above, using the feedback control rule and the driving state data, the calculated feedback yaw moment includes: based on the feedback control rule, determining the feedback moment algorithm, the steering correction parameter, and the delay correction parameter; based on the driving state data, determining the vehicle's real-time yaw moment and the deviation of the center of mass sideslip angle; using the feedback moment algorithm, the threshold deviation between the real-time yaw moment and the target yaw threshold, and the deviation of the center of mass sideslip angle to calculate the basic feedback moment; using the steering correction parameter and the delay correction parameter to correct the basic feedback moment to obtain the feedback yaw moment.

[0021] The above optional embodiment of the present application can achieve the following technical effects: By using the feedback control rule, the feedback moment algorithm, the steering and delay correction parameters are determined, providing a calculation basis for the feedback control. Furthermore, based on the vehicle's real-time driving state data, the vehicle's real-time yaw moment and the deviation of the center of mass sideslip angle are determined, improving the timeliness of the data and providing an accurate data basis for the feedback control. Further, using the feedback moment algorithm, the threshold deviation between the real-time yaw moment and the target yaw threshold, and the deviation of the center of mass sideslip angle to calculate the basic feedback moment, and using the steering correction parameter and the delay correction parameter to correct the basic feedback moment, more comprehensively considering the changes in the vehicle's steering characteristics after a tire blowout failure and the time delay between the generation and execution of the control command, improving the accuracy of the feedback yaw moment. Using this feedback yaw moment can dynamically adjust the target reverse yaw moment, enhancing the accuracy of the vehicle control method, thereby improving the vehicle's ability to maintain stability after a tire blowout and enhancing the stability and safety of the vehicle.

[0022] Optionally, the above vehicle control method further includes: in response to determining that the vehicle is in a tire blowout state according to the detection result, determining the non-blowout wheels of the vehicle; based on the target reverse yaw moment, performing torque distribution on the non-blowout wheels to obtain a distribution result; sending a torque control command to the execution component according to the distribution result, where the torque control command is used to control the execution component to perform a driving action or a braking action so that the vehicle maintains vehicle body stability after a tire blowout.

[0023] The above optional embodiment of the present application can achieve the following technical effects: In the case of a vehicle tire blowout failure, the vehicle control system is used to identify the non-blowout wheels, and then according to the target reverse yaw moment, torque distribution is performed on these tires, which can make full use of the control ability of the vehicle's non-blowout wheels to compensate for the imbalance caused by the blown-out tire, enabling the vehicle to still drive stably after a tire blowout, avoiding serious traffic accidents, and enhancing the stability and safety of the vehicle.

[0024] According to another aspect of the embodiments of the present application, a vehicle control device is further provided, including: an acquisition module configured to acquire the driving state data and driving operation data of the vehicle; a detection module configured to detect the flat tire state of the vehicle by using the driving state data to obtain a detection result; a determination module configured to determine target threshold data by using the driving state data, driving operation data and the detection result; and a control module configured to determine a target reverse yaw moment based on a multiple control mode, driving state data, driving operation data and the target threshold data, wherein the multiple control mode is constructed based on an adaptive feedforward control rule and a feedback control rule, and the target reverse yaw moment is used to control the driving torque or braking torque of an execution component in the vehicle.

[0025] The vehicle control device provided by the embodiments of the present application achieves the following technical effects: By using the acquisition module to acquire the driving state data and driving operation data of the vehicle, the current driving state and driving operation situation of the vehicle can be determined in real time, enhancing the timeliness of the data and contributing to more accurate subsequent detection of the flat tire state of the vehicle; furthermore, by using the detection module to detect the flat tire state of the vehicle by using the driving state data to obtain a detection result, it is possible to timely determine whether the vehicle has a flat tire fault and enhance the accuracy of the detection result; further, by using the determination module to determine the target threshold data by using the driving state data, driving operation data and the detection result, by comprehensively considering the driving state data, driving operation data and the detection result, it is possible to judge whether there is a driver's misoperation situation, and then determine the target threshold data to limit the driver's wrong operation, reduce the impact of the driver's misoperation, and determine the target threshold data that can ensure the stable driving of the vehicle; finally, by using the control module, the multiple control mode constructed by using the adaptive feedforward control rule and the feedback control rule can combine the advantages of the adaptive feedforward control and the feedback control rule. Based on this multiple control mode, driving state data, driving operation data and the target threshold data, the target reverse yaw moment can be obtained more quickly, and the accuracy of the determined target reverse yaw moment is also higher, enabling the vehicle control device to efficiently and accurately determine the target reverse yaw moment and improving the performance of the vehicle control device.

[0026] According to another aspect of the embodiments of the present application, a vehicle is further provided, including a processor and a memory, wherein the memory is configured to store a computer program; and the processor is configured to execute the program stored on the memory to implement the vehicle control method according to any one of the above.

[0027] The vehicle provided by the embodiment of the present application achieves the following technical effects: By acquiring the driving state data and driving operation data of the vehicle, the current driving state and driving operation situation of the vehicle can be determined in real time, enhancing the timeliness of the data and contributing to more accurate subsequent detection of the flat tire state of the vehicle; furthermore, using the driving state data to detect the flat tire state of the vehicle and obtaining the detection result can timely determine whether the vehicle has a flat tire fault and enhance the accuracy of the detection result; further, by comprehensively considering the driving state data, driving operation data, and detection result, it is judged whether there is a driver's misoperation situation, and then the target threshold data is determined to limit the driver's wrong operation, reducing the impact of the driver's misoperation, and determining the target threshold data that can ensure the stable driving of the vehicle; finally, the multiple control method constructed by using the adaptive feedforward control rule and the feedback control rule can combine the advantages of the adaptive feedforward control and the feedback control rule. Based on this multiple control method, driving state data, driving operation data, and target threshold data, the target reverse yaw moment can be obtained more quickly, and the accuracy of the determined target reverse yaw moment is also higher, thereby ensuring that the vehicle can drive stably in the case of a flat tire fault and improving the safety of the vehicle. Description of the Drawings

[0028] Figure 1 is a flowchart of a vehicle control method provided by an embodiment of the present application;

[0029] Figure 2 is a schematic diagram of an optional vehicle control method provided by an embodiment of the present application;

[0030] Figure 3 is a schematic diagram of another optional vehicle control method provided by an embodiment of the present application;

[0031] Figure 4 is a structural block diagram of a vehicle control device provided by an embodiment of the present application;

[0032] Figure 5 is a structural block diagram of a vehicle provided by an embodiment of the present application;

[0033] Figure 6 is a hardware structural block diagram of a computing terminal provided by an embodiment of the present application;

[0034] Figure 7 is a structural block diagram of an electronic device provided by an embodiment of the present application. Detailed Embodiments

[0035] In order to make the technical problems, technical solutions, and beneficial effects solved by the present application more clear, the present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0036] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that such data used can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0037] Embodiment 1

[0038] The embodiment of this application provides a model training method. Please refer to Figure 1 , which includes the following steps:

[0039] S10: Obtain the driving state data and driving operation data of the vehicle;

[0040] S20: Use the driving state data to detect the flat tire state of the vehicle to obtain a detection result;

[0041] S30: Use the driving state data, driving operation data and detection result to determine the target threshold data;

[0042] S40: Based on multiple control modes, driving state data, driving operation data and target threshold data, determine the target reverse yaw moment, where the multiple control modes are constructed based on the adaptive feedforward control rule and the feedback control rule, and the target reverse yaw moment is used to control the driving torque or braking torque of the execution components in the vehicle.

[0043] The above-mentioned driving state data can be used to characterize the current operating state of the vehicle, and the driving state data may include, but is not limited to: sensor data, environmental data around the vehicle. The above-mentioned sensor data can be collected by on-vehicle sensors. The above-mentioned on-vehicle sensors may include, but are not limited to: vision sensors (such as cameras), radar sensors, laser sensors, inertial detection sensors, rotation sensors (such as Hall effect sensors), speed sensors, acceleration sensors, angular velocity detection sensors, temperature sensors, humidity sensors, tire pressure detection sensors, wheel speed sensors, vibration sensors, acoustic sensors.

[0044] The above sensor data may include, but are not limited to: vehicle gear information, pulse signals corresponding to the four wheels respectively, wheel speed signals corresponding to the four wheels respectively, inertial measurement unit information, driving torques corresponding to the four tires respectively, vehicle body vibration information, and noise information corresponding to the four tires respectively. The above inertial measurement unit information may include: triaxial (i.e., X-axis, Y-axis, and Z-axis) acceleration information in the vehicle body coordinate system, and triaxial angular velocity information in the vehicle body coordinate system. The environmental data around the vehicle may include, but are not limited to: data of surrounding vehicles (such as the vehicle speed of surrounding vehicles, the acceleration of surrounding vehicles, the distance from surrounding vehicles, etc.), and climate information data (such as temperature, humidity, light intensity, etc.). The above driving operation data can be used to characterize the operation behavior of the driver. The driving operation data may include, but are not limited to: angular information of the steering wheel angle, degree information of the accelerator pedal, vehicle braking information, and visual image information.

[0045] It is easy to understand that in the embodiments of the present application, by acquiring the driving state data and driving operation data of the vehicle, the current driving state of the vehicle and the operation situation of the driver on the vehicle can be determined in real time, enhancing the timeliness of the data, which is helpful for more accurately detecting the flat tire state of the vehicle and determining the target threshold data subsequently.

[0046] The above detection result can be used to determine flat tire information. The detection result may include, but are not limited to: the position of the tire with a flat tire fault (such as front left, front right, rear left, rear right), flat tire degree information, the time point when the flat tire fault occurs, and flat tire flag data. The above flat tire degree information may be flat tire degree level information (such as mild air leakage, severe air leakage, complete flat tire), and the flat tire degree information may also be a flat tire degree evaluation value. The detection result can be obtained by using a flat tire detection method. The above flat tire detection method may include, but are not limited to: a flat tire detection method based on image recognition, a flat tire detection method based on accelerometer analysis, a flat tire detection method based on temperature monitoring, and a flat tire detection method based on a deep model.

[0047] The above flat tire detection method based on image recognition may be: using an in-vehicle camera to capture images of the tire contact part with the ground in real time, and through image processing and analysis, identifying the changes in the tire shape and contact surface to determine whether a flat tire fault occurs. The above flat tire detection method based on accelerometer analysis may be: monitoring the changes in lateral and longitudinal accelerations through an accelerometer built in the vehicle, and combining the dynamic characteristics of the vehicle when a flat tire fault occurs to identify the flat tire fault state. The above flat tire detection method based on temperature monitoring may be: using a temperature sensor installed inside or outside the tire to monitor the temperature change of the tire, and using the abnormal change of the tire temperature to determine whether a flat tire fault occurs.

[0048] It should be noted that the above tire blowout detection methods can be used alone or in combination with each other. Through multi-sensor fusion and data analysis, the accuracy of tire blowout detection results can be improved.

[0049] The above target threshold data may include, but is not limited to: yaw rate threshold data, yaw acceleration threshold data, lateral acceleration threshold data, vehicle speed threshold data, and braking threshold data. This target threshold data can be used to characterize the boundary conditions for the stable driving of the vehicle. The above yaw acceleration threshold data can be used to determine the maximum allowable yaw rate change rate under stable vehicle driving. The above lateral acceleration threshold can be used to determine the maximum allowable speed change rate of lateral movement under stable vehicle driving.

[0050] It is easy to understand that by using the driving state data, driving operation data, and detection results, not only can the target threshold data allowed under stable vehicle driving be determined to ensure stable vehicle driving, but also in combination with the driving operation data, it can be judged whether there is a driver's misoperation, and then the target threshold data can be determined to limit the driver's wrong operation and reduce the impact of the driver's misoperation.

[0051] The above adaptive feedforward control rule can be a predictive control strategy. This adaptive feedforward control rule can include a feedforward control rule and an adaptive rule. The above feedforward control rule can be used to predict the driving torque or braking torque required by the execution component in the event of a tire blowout failure of the vehicle. The above adaptive rule can be used to dynamically adjust the parameters of the feedforward model (such as, friction coefficient estimation parameters, mass estimation parameters, etc.). The above feedback control rule can be used to measure the deviation between the actual driving state data of the vehicle and the target state. This feedback control rule can include, but is not limited to: deviation calculation, control methods (such as, proportional algorithm, integral algorithm, differential algorithm, etc.), and state observer. This feedback control rule can be used to characterize the real-time adjustment requirements for the stable driving of the vehicle.

[0052] The above execution component can be a system or component in the vehicle responsible for implementing control instructions. This execution component can include, but is not limited to: an electric drive system, a braking system, a steering system, and an electronically controlled suspension system. The above driving torque can be the torque exerted by the vehicle's drive motor or engine on the wheels to accelerate or maintain the speed of the vehicle. The above braking torque can refer to the torque exerted by the braking system on the wheels, which is used to decelerate or control the dynamic stability of the vehicle. The driving torque and braking torque directly affect the driving dynamics and stability of the vehicle. In the event of a tire blowout failure of the vehicle, by adjusting the driving torque and braking torque, it is possible to assist in restoring the yaw stability of the vehicle and avoid losing control.

[0053] Based on the control method corresponding to the adaptive feedforward control rule, input the real-time driving state data, driving operation data, and target threshold data of the vehicle into the feedforward control model for predictive calculation to determine the predicted reverse yaw moment required by the execution component. Use this predicted reverse yaw moment to control the vehicle in advance, seize the control window period of the vehicle in the event of a flat tire failure, ensure the response speed of the vehicle control method, and at the same time dynamically correct the parameters of the feedforward model using the real-time driving state data, driving operation data, and target threshold data to improve the robustness of the control method; furthermore, use the control method corresponding to the feedback control rule to measure the deviation between the actual driving state data of the vehicle and the target state, calculate the deviation value, and use this deviation value to adjust the above-mentioned predicted reverse yaw moment to obtain a more accurate target reverse yaw moment; further, use this target reverse yaw moment to control the driving torque or braking torque of the execution component in the vehicle to ensure that the vehicle can drive stably in the event of a flat tire failure and enhance the safety of the vehicle.

[0054] The vehicle control method provided by the embodiment of the present application achieves the following technical effects: by obtaining the driving state data and driving operation data of the vehicle, the current driving state and driving operation conditions of the vehicle can be determined in real time, enhancing the timeliness of the data and contributing to more accurate detection of the tire blowout state of the vehicle subsequently; furthermore, using the driving state data to detect the tire blowout state of the vehicle and obtaining the detection result can timely determine whether the vehicle has a tire blowout fault, enhancing the accuracy of the detection result; further, using the driving state data, driving operation data and detection result to determine the target threshold data, by comprehensively considering the driving state data, driving operation data and detection result, to judge whether there is a situation of driver misoperation, and then determine the target threshold data to limit the wrong operation of the driver, reducing the impact of driver misoperation, and determining the target threshold data that can ensure the stable driving of the vehicle; finally, the adaptive feedforward control can predict the unstable state that the vehicle will appear according to the current driving state and driving operation conditions of the vehicle, so as to apply a control torque in advance to control the vehicle in time, improving the response speed of the vehicle control method, while the feedback control can make an immediate correction according to the actual motion deviation of the vehicle. The multiple control methods constructed by using the adaptive feedforward control rule and the feedback control rule can combine the advantages of the adaptive feedforward control and the feedback control. Based on this multiple control method, driving state data, driving operation data and target threshold data, the target reverse yaw moment can be obtained more quickly, and the accuracy of the determined target reverse yaw moment is also higher, so as to ensure that the vehicle can drive stably in the case of a tire blowout fault, improving the safety of the vehicle. Thus, the embodiment of the present application achieves the purpose of efficiently and accurately determining the target reverse yaw moment by combining the driving state data and driving operation data and using the multiple control methods of adaptive feedforward control and feedback control, realizes the technical effect of improving the accuracy and response speed of the target reverse yaw moment, overcomes the defect of poor stability of the vehicle in the case of a tire blowout fault, and further solves the technical problems of high latency and poor accuracy in the vehicle control method in the related art.

[0055] The vehicle control method provided by the embodiment of the present application combines the driving state data and driving operation data, uses the multiple control methods of adaptive feedforward control and feedback control, and efficiently and accurately determines the target reverse yaw moment, and can be widely applied to multiple application scenarios.

[0056] For example, in the application scenario of intelligent driving, by integrating the technical solution of the present application with the intelligent driving system, by optimizing the target yaw angular velocity and control logic, the vehicle can still maintain high driving safety and intelligent decision-making ability when a tire blows out.

[0057] For example, in the application scenario of platoon driving, when multiple vehicles closely follow each other, a flat tire of the leading vehicle may cause a chain reaction. By applying the technical solution of the present application in combination with driving state data and driving operation data, and using multiple control methods of adaptive feedforward control and feedback control, an accurate target reverse yaw moment is determined, enabling the leading vehicle to drive stably, avoiding rear-end collisions of the following vehicles, and maintaining the safety of the platoon.

[0058] For example, in the application scenario of robot transportation, the technical solution of the present application is integrated with the robot transportation system. By combining the driving state data of the robot and the operation data of the robot transportation system, and using multiple control methods of adaptive feedforward control and feedback control, the target reverse yaw moment is determined efficiently and accurately, ensuring stable driving even when a flat tire occurs on the driving wheel of the robot, avoiding damage to transported items, and enhancing the robot transportation service experience.

[0059] The vehicle control method provided by the embodiments of the present application can be, but is not limited to, applied to the above-listed application scenarios. With the continuous evolution of technology, the above method can also be applied to a wider range of scenarios, such as remotely driven vehicles, unmanned aerial vehicle driving, domestic robots, etc. By combining driving state data and driving operation data, and using multiple control methods of adaptive feedforward control and feedback control, the target reverse yaw moment is determined more accurately and quickly, supporting a variety of advanced functions and applications, and being able to improve the driving safety of the machine.

[0060] Optionally, the driving state data includes: tire pressure perception data, wheel speed data, vibration perception data, and acoustic perception data, and the detection result includes flat tire flag data. In the above step S20, the flat tire state of the vehicle is detected using the driving state data, and the steps for obtaining the detection result include:

[0061] S201: Determine the first flag data according to the tire pressure perception data, the preset detection period, and the tire pressure change threshold;

[0062] S202: Determine the second flag data according to the wheel speed data and the wheel speed difference threshold;

[0063] S203: Determine the third flag data according to the vibration perception data and the vibration anomaly threshold;

[0064] S204: Determine the fourth flag data according to the acoustic perception data and the acoustic anomaly threshold;

[0065] S205: Determine the flat tire flag data based on the first flag data, the second flag data, the third flag data, and the fourth flag data, where the flat tire flag data is used to represent whether the vehicle is in a flat tire state.

[0066] The above tire pressure perception data can be used to determine whether the tire pressure of the vehicle tires has changed. The tire pressure perception data can include tire pressure values and tire pressure change rates. The tire pressure perception data can be obtained through tire pressure detection sensors, and the above tire pressure detection sensors can include, but are not limited to: high-frequency direct tire pressure monitoring systems and low-frequency direct tire pressure sensors.

[0067] It should be noted that each of the four tires of the vehicle can be detected to obtain the tire pressure perception data, wheel speed data, vibration perception data, and acoustic perception data corresponding to the tire.

[0068] The above preset detection period can be used to characterize the period of tire pressure detection for the vehicle tires. The preset monitoring period can be set according to detection requirements. In particular, when the tire pressure of the vehicle tires has not changed, a longer detection period (e.g., 64 seconds) can be used to detect the tire pressure of the vehicle tires. When the tire pressure of the vehicle tires has changed, a shorter detection period (e.g., 20 milliseconds) can be used to detect the tire pressure of the vehicle tires. Compared with the traditional method of using a fixed detection period to detect tire pressure, the present application can save detection costs while improving the real-time performance of tire pressure perception data to meet the requirements of the flat tire control function for flat tire condition identification.

[0069] The above tire pressure change threshold can be used to characterize the maximum value of the allowable tire pressure change when the vehicle tires are in a non-flat tire state. The tire pressure change threshold can include a first tire pressure change threshold and a second tire pressure change threshold, where the first tire pressure change threshold is less than the second tire pressure change threshold. The above first flag data can be determined by the direct tire pressure monitoring method, and the first flag data can be used to characterize whether a flat tire failure has occurred in the vehicle tires. In particular, the tire pressure perception data can be detected multiple times, and the first flag data can be determined based on the tire pressure perception data detected multiple times.

[0070] The above wheel speed data can include the inner wheel speed corresponding to each of the four tires, the outer wheel speed corresponding to each of the four tires, and the wheel speed difference value between the four tires. The wheel speed data can be obtained using a wheel speed sensor. The above wheel speed difference threshold can be used to characterize the maximum value of the allowable wheel speed difference between the four tires when the vehicle tires are in a non-flat tire state. The wheel speed difference threshold can be determined by conducting a wheel speed difference experiment on the vehicle in the case of a tire flat failure (e.g., combining wheel speed calculation theory and actual vehicle tests). The above second flag data can be determined by the indirect tire pressure monitoring method.

[0071] The above vibration perception data can be used to characterize the vibration amplitude of the vehicle body. The vibration perception data can be obtained by using an in-vehicle vibration sensor. The above vibration anomaly threshold can be used to characterize the maximum value of the vibration amplitude allowed for the vehicle body when the vehicle's tires are in a non-burst state. The above acoustic perception data can be used to characterize the noise change of the vehicle tires. The acoustic perception data can be obtained by using an acoustic sensor mounted on the vehicle tires. The above acoustic anomaly threshold can be used to characterize the maximum decibel value of the noise allowed for the vehicle tires when the vehicle's tires are in a non-burst state.

[0072] The above second flag data, third flag data, and fourth flag data can all be used to assist in determining whether there is an error in the first flag data, for example, whether there is a missed detection or a false detection. The above first flag data, second flag data, third flag data, fourth flag data, and the above tire burst flag data can all be continuous (e.g., any number between 0 and 1) scoring values, or binary (e.g., 0 or 1) values. In particular, when the above tire burst flag data is a binary value, a tire burst flag bit of 0 indicates that the vehicle tire has not had a tire burst failure, and a tire burst flag bit of 1 indicates that the vehicle tire has had a tire burst failure.

[0073] In an exemplary application scenario, such as Figure 2As shown, driving state data and driving operation data are input into the central controller corresponding to the vehicle, and the tire burst recognition module in the central controller is used to detect the tire burst state of the vehicle. First, the tire pressure is recognized by the tire burst recognition module. Specifically, the high-frequency direct tire pressure monitoring system corresponding to each tire of the vehicle is used to detect the tire pressure of the tire in real time according to the preset detection period, and the tire pressure perception data is obtained. In particular, the initial tire pressure perception data corresponding to a certain tire of the vehicle is denoted as p0. If it is detected within the first time range (denoted as t1, for example, 100 milliseconds) that the first tire pressure perception data (denoted as p1) corresponding to the tire represents a tire pressure change (that is, the difference between p1 and p0) greater than the first tire pressure change threshold in the tire pressure change threshold (denoted as △p, for example, 40 kPa), then the tire is subjected to a secondary detection to obtain the second tire pressure perception data (denoted as p2) corresponding to the tire. If the second tire pressure perception data p2 represents a tire pressure change (that is, the difference between p2 and p0) greater than the second tire pressure change threshold in the tire pressure change threshold (denoted as △p’, for example, 60 kPa), then the first flag data can be set to 1. If the second tire pressure perception data p2 does not represent a tire pressure change greater than the second tire pressure change threshold in the tire pressure change threshold, then the secondary detection process of the target number of times (for example, 3 to 5 times) can be performed on the tire again. If the tire pressure perception data obtained by detecting the tire within the target number of times does not represent a tire pressure change greater than the second tire pressure change threshold in the tire pressure change threshold, then the first flag data can be set to 0 to ensure the accuracy of the secondary detection. The above first time range, first tire pressure change threshold, second tire pressure change threshold, and target number of times can all be set according to actual needs, and the specific values of the first time range, first tire pressure change threshold, second tire pressure change threshold, and target number of times are not limited in this application.

[0074] Still in the above application scenario, the wheel speed is detected by the tire burst recognition module. Specifically, the wheel speed sensors in the Electronic Stability Program (ESP) system of the vehicle are used to monitor the inner wheel speed and outer wheel speed corresponding to each tire of the vehicle in real time. Combining the Ackermann effect and tire state information (such as whether the tire slips and whether the tire locks), the inner wheel speed and outer wheel speed collected by the wheel speed sensors are compensated and corrected accordingly to determine the wheel speed corresponding to each tire. Using the wheel speed corresponding to each of the four tires, the wheel speed difference data between the four tires is determined, and this wheel speed difference data is used as the wheel speed data. The wheel speed data is compared and analyzed with the wheel speed difference threshold to determine whether the wheel speed data is greater than the wheel speed difference threshold. If the wheel speed data is greater than the wheel speed difference threshold, then the second flag data is set to 1. If the wheel speed data is not greater than the wheel speed difference threshold, then the second flag data is set to 0.

[0075] Still in the above application scenario, the tire burst recognition module is used for vibration recognition. Specifically, an in-vehicle vibration sensor is used to detect the vibration amplitude of the vehicle body, and the vibration amplitude is determined as vibration perception data. The vibration perception data is compared and analyzed with a vibration anomaly threshold to determine whether the vibration perception data is greater than the vibration anomaly threshold. If the vibration perception data is greater than the vibration anomaly threshold, the third flag data is set to 1; if the vibration perception data is not greater than the vibration anomaly threshold, the third flag data is set to 0. Further, the tire burst recognition module is used for acoustic recognition. Specifically, an acoustic sensor mounted on each of the four vehicle tires is used to detect the ambient noise of the tire (e.g., the irregular friction sound emitted by the tire when a tire burst fault occurs), and the acoustic perception data corresponding to the tire is obtained. The acoustic perception data is compared and analyzed with an acoustic anomaly threshold to determine whether the acoustic perception data is greater than the acoustic anomaly threshold. If the acoustic perception data is greater than the acoustic anomaly threshold, the fourth flag data is set to 1; if the acoustic perception data is not greater than the acoustic anomaly threshold, the fourth flag data is set to 0.

[0076] Still in the above application scenario, the first flag data, the second flag data, the third flag data, and the fourth flag data in the central controller of the vehicle control system are subjected to multi-sensor fusion processing. The vehicle control system comprehensively determines whether the vehicle is in a tire burst state based on the first flag data, the second flag data, the third flag data, and the fourth flag data, and determines the tire burst flag data, improving the accuracy of the tire burst flag data. In addition, it should be noted that the above first flag data, second flag data, third flag data, fourth flag data, and tire burst flag data are all set to 0 in the initial state.

[0077] The above optional embodiments of the present application can achieve the following technical effects: By comprehensively analyzing tire pressure perception, wheel speed change, vehicle body vibration, and acoustic signals, it is possible to judge whether the vehicle is in a tire burst state from multiple dimensions, and tire burst flag data with higher accuracy can be obtained. It overcomes the problem of low accuracy in detecting the tire burst state of the vehicle relying on a single sensor, improves the accuracy of tire burst detection, and further ensures the effective implementation of subsequent control strategies to maintain the stable driving of the vehicle.

[0078] Optionally, the detection result further includes a missed detection flag data and a false detection flag data, and the vehicle control method further includes the following steps:

[0079] S206: In response to the first flag data, the second flag data, the third flag data, and the fourth flag data satisfying the missed detection condition, determine the missed detection flag data, where the missed detection condition includes: determining that the tire pressure perception data does not include a flat tire abnormality according to the first flag data, determining that the wheel speed data includes a flat tire abnormality according to the second flag data, determining that the vibration perception data includes a flat tire abnormality according to the third flag data, and determining that the acoustic perception data includes a flat tire abnormality according to the fourth flag data;

[0080] S207: In response to the first flag data, the second flag data, the third flag data, and the fourth flag data satisfying the false detection condition, determine the false detection flag data, where the false detection condition includes: determining that the tire pressure perception data includes a flat tire abnormality according to the first flag data, determining that the wheel speed data does not include a flat tire abnormality according to the second flag data, determining that the vibration perception data does not include a flat tire abnormality according to the third flag data, and determining that the acoustic perception data does not include a flat tire abnormality according to the fourth flag data;

[0081] S208: Generate an enable signal for the execution component according to the missed detection flag data and the false detection flag data.

[0082] The above missed detection condition is used to determine whether a missed detection event occurs. The missed detection event may refer to a situation where, when the vehicle is actually in a flat tire state, the first flag data indicates that the vehicle is not in a flat tire state. The above false detection condition is used to determine whether a false detection event occurs. The false detection event may refer to a situation where, when the vehicle is actually not in a flat tire state, the first flag data indicates that the vehicle is in a flat tire state. The above missed detection flag data and false detection flag data can both be binary (e.g., 0 or 1) values.

[0083] The above enable signal is used to represent the operation authorization status of the control system for the execution component. The enable signal may include an activation signal and an inhibition signal. The above activation signal may instruct the execution component of the vehicle to perform flat tire stability control, and the above inhibition signal may prevent the execution component of the vehicle from performing flat tire stability control.

[0084] In an exemplary application scenario, within a period of time after the vehicle is powered on, the direct tire pressure monitoring system needs to perform periodic self-checks. During this period when the direct tire pressure monitoring system performs periodic self-checks, there will be a phenomenon of missed detections in the direct tire pressure monitoring system. At this time, if the vehicle is in a flat tire state, the first flag data is still set to 0, and this first flag data cannot represent that the vehicle is in a flat tire state. Therefore, by setting the missed detection condition, the first flag data, the second flag data, the third flag data, and the fourth flag data are respectively judged. If it is determined according to the first flag data that the tire pressure sensing data does not contain a flat tire anomaly, according to the second flag data that the wheel speed data contains a flat tire anomaly, according to the third flag data that the vibration sensing data contains a flat tire anomaly, and according to the fourth flag data that the acoustic sensing data contains a flat tire anomaly, then it is determined that the first flag data, the second flag data, the third flag data, and the fourth flag data meet the missed detection condition, it is determined that a missed detection event has occurred, and the missed detection flag data is set to 1.

[0085] Still in the above application scenario, in order to further enhance the accuracy of flat tire detection, by setting the false detection condition, the first flag data, the second flag data, the third flag data, and the fourth flag data are respectively judged. If it is determined according to the first flag data that the tire pressure sensing data contains a flat tire anomaly, according to the second flag data that the wheel speed data does not contain a flat tire anomaly, according to the third flag data that the vibration sensing data does not contain a flat tire anomaly, and according to the fourth flag data that the acoustic sensing data does not contain a flat tire anomaly, then it is determined that the first flag data, the second flag data, the third flag data, and the fourth flag data meet the false detection condition, it is determined that a false detection event has occurred, and the false detection flag data is set to 1. It should be noted that the above missed detection flag data and false detection flag data are both set to 0 in the initial state.

[0086] Still in the above application scenario, an enable signal for the execution component is generated based on the missed detection flag data and the false detection flag data. If it is recognized that the missed detection flag data is set to 1, an activation signal for the execution component is generated, instructing the execution component of the vehicle to perform flat tire stability control; if it is recognized that the false detection flag data is set to 1, an inhibition signal for the execution component is generated to prevent the execution component of the vehicle from performing flat tire stability control.

[0087] The above optional embodiments of the present application can achieve the following technical effects: By comprehensively judging the first flag data, the second flag data, the third flag data, and the fourth flag data, it is possible to accurately judge whether there is a missed detection or a false detection, and respectively determine the missed detection flag data and the false detection flag data. An enabling signal for the execution component is generated according to the missed detection flag data and the false detection flag data. Using this enabling signal can ensure that the execution component of the vehicle performs tire blowout stability control only when it is determined that the tire blowout state of the vehicle is accurately recognized, avoiding unnecessary control triggered by missed detection or false detection and interfering with the normal driving of the vehicle, and further enhancing the accuracy of the vehicle control method.

[0088] Optionally, the driving operation data includes: a steering wheel signal, a brake pedal signal, and a radar sensing signal. The target threshold data includes a target yaw threshold. In the above step S30, using the driving state data, the driving operation data, and the detection result to determine the target threshold data includes the following steps:

[0089] S301: In response to determining that the vehicle is in a tire blowout state according to the detection result, based on the radar sensing signal, determine the obstacle distance information corresponding to the vehicle, and use the obstacle distance information, the steering wheel signal, and the brake pedal signal to perform driving intention recognition to determine the recognition result, where the recognition result is used to characterize whether the corresponding driving operation of the vehicle is a misoperation;

[0090] S302: Use the driving state data, the driving operation data, and the recognition result to determine the target yaw threshold.

[0091] The above steering wheel signal is used to characterize the change data corresponding to the vehicle steering wheel. The steering wheel signal may include, but is not limited to: steering wheel angle, steering wheel rotation speed. The above brake pedal signal is used to characterize the braking data corresponding to the vehicle. The above radar sensing signal can be obtained by using a radar sensor. The radar sensing signal can be used to determine the distance between the vehicle and the obstacle. The above obstacles may include, but are not limited to: traffic signs, traffic lights, pedestrian guardrails, trees, street lights, pedestrians, surrounding vehicles (such as, the vehicle in front, the vehicle behind, the vehicle on the left, the vehicle on the right, etc.).

[0092] The above recognition result can be used to determine the driver's driving intention in the event of a tire blowout (such as, whether it is to avoid an obstacle, whether it is to avoid rear-ending the vehicle in front, whether it is to avoid surrounding vehicles, etc.). The above misoperations may include, but are not limited to: misoperation of the steering wheel, misoperation of the brake pedal.

[0093] It should be noted that in the process of determining the obstacle distance information corresponding to the vehicle, the visual sensor data can also be combined for comprehensive judgment to improve the accuracy of the obstacle distance information, thereby improving the accuracy of the recognition result.

[0094] The above-mentioned target yaw threshold can be determined by using a threshold calculation method. The above-mentioned threshold calculation method can include, but is not limited to: a threshold calculation method based on a machine learning model, a threshold calculation method based on adaptive fuzzy logic, a threshold calculation method fused with a Kalman filter, and a threshold calculation method based on a vehicle yaw feature model.

[0095] In an exemplary application scenario, still as Figure 2 shown, the driving intention recognition module in the central controller is used to judge the detection result. In response to the detection result indicating that the vehicle is in a flat tire state, the radar sensor is used to obtain the radar perception signal of the vehicle in real time. Based on the radar perception signal, the distance between the vehicle and the surrounding obstacles is determined to obtain the obstacle distance information corresponding to the vehicle. Furthermore, the driving intention is recognized by using the obstacle distance information, the steering wheel signal, and the brake pedal signal. When the steering wheel signal indicates that there is a large change in the steering wheel of the vehicle, the obstacle distance information is used to judge whether there is an obstacle in front of the vehicle. If there is no obstacle in front of the vehicle, it is determined that the driver's driving intention is not to avoid the obstacle, and it is determined that there is a misoperation of the steering wheel, and the first misoperation flag bit is set to 1; otherwise, the first misoperation flag bit is not set.

[0096] Still in the above application scenario, when the brake pedal signal indicates that there is a large change in the brake pedal of the vehicle, the obstacle distance information is used to determine the distance between the vehicle and the surrounding vehicles. If the distance between the vehicle and the vehicles in front and behind satisfies the safety distance threshold, and there are no vehicles on the left and right near the vehicle, it is determined that the driver's driving intention is not to avoid rear-ending the vehicle in front, or to avoid lane-changing by vehicles on the left and right, or there is a risk of being rear-ended by the vehicle behind, and it is determined that there is a misoperation of the brake pedal, and the second misoperation flag bit is set to 1; otherwise, the second misoperation flag bit is not set. Further, the target yaw threshold is determined by using the driving state data, the driving operation data, and the recognition result to ensure that the vehicle can be accurately controlled subsequently.

[0097] It should be noted that when the steering wheel input signal of the vehicle is greater than the steering wheel change threshold, it can be considered that there is a large change in the steering wheel. When the brake pedal input signal of the vehicle is greater than the brake pedal change threshold, it can be considered that there is a large change in the brake pedal. Additionally, it should be noted that the above-mentioned first misoperation flag bit and second misoperation flag bit are both set to 0 in the initial state.

[0098] The above optional embodiments of the present application can achieve the following technical effects: By using obstacle distance information, steering wheel signals, and brake pedal signals to identify driving intentions and determine the recognition results, it is possible to determine the driver's operation intentions in the event of a flat tire, and avoid the problem of vehicle out of control caused by the driver's improper operation or excessive operation (for example, violently turning the steering wheel, slamming on the brakes, turning the steering wheel in the opposite direction, etc.) when a flat tire failure occurs in the vehicle. Further, by using the driving state data, driving operation data, and recognition results, combined with the threshold calculation method, the target yaw threshold is determined, so as to timely adjust the subsequent vehicle stability control strategy to ensure the accuracy of the control decision.

[0099] Optionally, the driving state data includes vehicle speed data and wheel speed data. In step S302 above, using the driving state data, driving operation data, and recognition results to determine the target yaw threshold includes the following steps:

[0100] S321: Using the vehicle speed data, wheel speed data, steering wheel signal, as well as the wheelbase and preset characteristic vehicle speed corresponding to the vehicle, determine the basic yaw data;

[0101] S322: In response to determining that the driving operation belongs to a misoperation according to the recognition result, correct and update the basic yaw data according to the vehicle speed data;

[0102] S323: Using the basic yaw data and the yaw threshold sensitivity calibration coefficient corresponding to the vehicle, determine the basic yaw threshold;

[0103] S324: Generate the target yaw threshold based on the basic yaw threshold and the lateral acceleration threshold corresponding to the vehicle.

[0104] The above preset characteristic vehicle speed can be used to distinguish the critical speed value of the linear and non-linear response characteristics of the vehicle. The preset characteristic vehicle speed can be obtained through tests on the vehicle. In particular, the vehicle can be tested for handling stability on a closed-loop test track, and the dynamic responses such as yaw angular velocity and lateral acceleration of the vehicle at different vehicle speeds can be analyzed to determine the turning point vehicle speed at which the vehicle changes from linear response to non-linear response as the basis for the preset characteristic vehicle speed. The preset characteristic vehicle speed can include a low characteristic vehicle speed and a high characteristic vehicle speed. In the vehicle control system, by using the preset characteristic vehicle speed, the yaw control strategy can be adjusted to ensure that the vehicle can obtain the best stability control effect at both low and high speeds.

[0105] It should be noted that the above low characteristic vehicle speed and high characteristic vehicle speed can be set by considering the differences between the linear interval and non-linear interval of the vehicle speed. The low characteristic vehicle speed and high characteristic vehicle speed can be used to characterize the handling stability characteristics of the vehicle at different speeds.

[0106] The above basic yaw data can be calculated by a vehicle dynamics model (such as a two-degree-of-freedom model of the vehicle). The above yaw threshold sensitivity calibration coefficient can be used to adjust the sensitivity of the vehicle's yaw state to the stability control. The yaw threshold sensitivity calibration coefficient can be calibrated and optimized through actual vehicle testing, simulation analysis or driving simulation. The yaw threshold sensitivity calibration coefficient can be adjusted according to actual needs. If it is necessary to increase the sensitivity of the yaw to the stability control, the coefficient can be reduced; conversely, if it is necessary to reduce the sensitivity of the yaw to the stability control, the coefficient can be increased. The above lateral acceleration threshold can be the maximum value used to ensure that the vehicle maintains lateral stability.

[0107] The process of correcting and updating the basic yaw data based on vehicle speed data may include: conducting actual vehicle testing, determining a basic yaw data correction mapping table corresponding to different vehicle speeds, and correcting and updating the basic yaw data using this basic yaw data correction mapping table. The process of correcting and updating the basic yaw data based on vehicle speed data may also include: using a correction method based on a deep learning correction model, inputting vehicle speed data into the deep learning correction model, which outputs a basic yaw data correction coefficient, and correcting and updating the basic yaw data using this basic yaw data correction coefficient.

[0108] The target yaw thresholds may include an oversteering comprehensive threshold, an understeering comprehensive threshold, and a reverse steering comprehensive threshold. Specifically, the oversteering comprehensive threshold, the understeering comprehensive threshold, and the reverse steering comprehensive threshold represent the corresponding yaw thresholds for different vehicle instability states. The target yaw thresholds can be calculated using a conversion coefficient, which varies depending on the vehicle's instability state. The conversion coefficients can be obtained through experimental calibration. Using these conversion coefficients, multiple thresholds can be converted into a target yaw threshold.

[0109] In an exemplary application scenario, the basic yaw data is calculated using a two-degree-of-freedom model of the vehicle, and the preset characteristic speed includes a low characteristic speed (denoted as v chL ), high characteristic speed (denoted as v chH The front wheel steering angle (denoted as δ) of the vehicle is determined by using the wheel speed data and the steering wheel angle in the steering wheel signal, and the vehicle speed data (denoted as v), the front wheel steering angle δ, the vehicle's corresponding wheelbase (denoted as L) and the low characteristic vehicle speed v are used. chL , the target first yaw data (denoted as γL) is calculated according to the two-degree-of-freedom model of the vehicle, as shown in formula (1).

[0110]

[0111] Still in the above application scenario, using the vehicle speed data v, the front wheel steering angle δ, the wheelbase L corresponding to the vehicle, and the high characteristic vehicle speed v chH , the initial second yaw data (denoted as γH1) is calculated according to the two-degree-of-freedom model of the vehicle, as shown in Equation (2). When the vehicle speed data v is less than the low vehicle speed threshold (denoted as a), the initial second yaw data is corrected using the low vehicle speed high Ackerman target correction coefficient (denoted as b) to obtain the target second yaw data (denoted as γH), as shown in Equation (3). The above low vehicle speed threshold a and the low vehicle speed high Ackerman target correction coefficient b can be obtained through experimental calibration of the vehicle, and can also be set in combination with actual requirements and calibration results.

[0112]

[0113] γH = γH1(1 + b) Equation (3)

[0114] Still in the above application scenario, still as Figure 2 shown, the yaw detection is performed using the tire blowout identification module in the central controller. Specifically, the yaw weighting coefficient (denoted as ε) is obtained based on the lateral acceleration (denoted as ay) in the driving state data, and the yaw weighting coefficient ε is used to perform a weighted calculation on the target first yaw data γL and the target second yaw data γH to obtain the basic yaw data (denoted as γ), as shown in Equation (4).

[0115] γ = ε * γL + (1 - ε)γH Equation (4)

[0116] Still in the above application scenario, the above incorrect operations include incorrect steering wheel operations and incorrect brake pedal operations. The target threshold calculation module is used to judge the recognition result. In response to the recognition result indicating that the driving operation belongs to an incorrect steering wheel operation, the mapping relationship corresponding to the vehicle speed data (denoted as f(γ, v)) is determined using the basic yaw data correction mapping table, and the basic yaw data is corrected and updated using this mapping relationship, as shown in Equation (5). The corrected and updated basic yaw data is denoted as γe. In response to the recognition result indicating that the driving operation does not belong to an incorrect steering wheel operation, the basic yaw data does not need to be updated (i.e., γe takes the value of γ).

[0117] γe = f(γ, v) Equation (5)

[0118] Still in the above application scenario, the above basic yaw data can refer to the yaw angular velocity (denoted as ω). The target threshold calculation module is used to calculate the basic yaw threshold. Using the above basic yaw data, the yaw angular velocity change rate (i.e., the yaw angular acceleration ) can be determined, and using this yaw angular acceleration The yaw threshold sensitivity calibration coefficient corresponding to the vehicle (denoted as A) can be used to calculate the basic yaw threshold (denoted as ) through Equation (6).

[0119]

[0120] Still in the above application scenario, the lateral acceleration threshold corresponding to the vehicle can be calculated through Equation (7). Further, the target yaw threshold calculation module is used to calculate the target yaw threshold. Using the conversion coefficient (denoted as α1), based on the basic yaw threshold and the lateral acceleration threshold corresponding to the vehicle, the target yaw threshold (denoted as σ) is calculated through Equation (8).

[0121]

[0122] In Equation (7), represents the lateral acceleration threshold sensitivity calibration coefficient. This lateral acceleration threshold sensitivity calibration coefficient is related to the absolute value of the lateral acceleration. The greater the absolute value of the lateral acceleration, the smaller the value, the greater the stability control sensitivity, and it is easier for stability to intervene. represents a parameter related to the nominal lateral acceleration. C represents the conversion coefficient.

[0123]

[0124] Still in the above application scenario, the actual yaw data of the vehicle is determined using the driving state data and driving operation data. Using this actual yaw data and the basic yaw data, the yaw difference between the actual yaw data and the basic yaw data is determined. By comparing and analyzing the magnitude and direction relationship between the yaw difference and the target yaw threshold, the instability state of the vehicle (such as under-steer instability state, over-steer instability state, neutral instability state, etc.) is judged, and the stability factor of the vehicle (denoted as η) is calculated based on the yaw difference. In response to the recognition result indicating that the driving operation belongs to a brake pedal misoperation, using the set deceleration threshold, this deceleration threshold (denoted as a1) is used as the target braking deceleration. The above deceleration threshold can be set according to the vehicle dynamics characteristics. For example, a1 can be set to a braking intensity of 0.3g (where g represents the value of the gravitational acceleration) to make the vehicle with a flat tire failure stop slowly; in response to the recognition result indicating that the driving operation does not belong to a brake pedal misoperation, using the stability factor η of the vehicle and the brake pedal signal in the driving operation data, the initial braking deceleration a2 is calculated, and the initial braking deceleration a2 is used as the target braking deceleration.

[0125] The above optional embodiments of the present application can achieve the following technical effects: By comprehensively considering the influence of driving operation data and correcting the basic yaw data, the basic yaw threshold for preventing vehicle out-of-control can be determined more accurately. Further, based on the basic yaw threshold and the lateral acceleration threshold, the target yaw threshold is determined, considering more comprehensive information, improving the accuracy of the target yaw threshold to adapt to complex driving environments, and enhancing the stability and safety of the vehicle after a tire blowout.

[0126] Optionally, the multiple control rules include an adaptive feedforward control rule and a feedback control rule. In the above step S40, based on the multiple control mode, driving state data, driving operation data, and target threshold data, determining the target reverse yaw moment includes the following steps:

[0127] S401: Using the adaptive feedforward control rule, driving state data, and driving operation data, calculate the feedforward yaw moment.

[0128] S402: Using the feedback control rule, driving state data, and target threshold data, calculate the feedback yaw moment.

[0129] S403: Perform a weighted calculation on the feedforward yaw moment and the feedback yaw moment to determine the target reverse yaw moment.

[0130] The above feedforward yaw moment can be used to instantaneously compensate for the vehicle yaw trend in the event of a tire blowout failure. The feedforward yaw moment can be obtained by looking up a feedforward yaw moment mapping table or using a real-time feedforward calculation model. The above feedforward yaw moment mapping table can be obtained through simulation or on-road vehicle testing. Based on the driving state data and driving operation data, determine the expected change of the vehicle, and pre-calculate the feedforward yaw moment using the adaptive feedforward control rule. Using this feedforward yaw moment can achieve a rapid response and quickly stabilize the vehicle body attitude in the initial stage of a tire blowout failure (e.g., within 200 milliseconds), reducing the difficulties and risks of subsequent control.

[0131] The above feedback yaw moment can refer to a control moment calculated based on the deviation between the actual yaw state and the desired target state of the current vehicle. The feedback yaw moment can be calculated by using the feedback control rule, and the feedback control rule can include, but is not limited to: proportional integral derivative control algorithm, linear quadratic regulator control algorithm.

[0132] Specifically, the state deviation value between the current actual yaw state and the desired target state of the vehicle can be calculated using the driving state data and the target threshold data. This state deviation value is input into the feedback control algorithm corresponding to the feedback control rule. The magnitude and direction of the feedback yaw moment are determined based on the magnitude and change rate of the state deviation value. The feedback yaw moment can be used to dynamically correct the yaw of the vehicle in real time, obtaining a more accurate target reverse yaw moment, enabling the vehicle to gradually tend to a stable state in the event of a flat tire failure and enhancing the safety of the vehicle.

[0133] The above-mentioned target reverse yaw moment can be obtained by using mathematical operation methods or machine learning weighted calculation models. The above-mentioned mathematical operation methods can include, but are not limited to: direct addition operation method, arithmetic mean operation method, weighted average operation method, error normal operation method.

[0134] In an exemplary application scenario, after calculating the weighted sum of the feedforward yaw moment and the feedback yaw moment to determine the target reverse yaw moment (denoted as ΔM), the influence of the limiting conditions corresponding to the vehicle tire out-of-round on the target reverse yaw moment can also be comprehensively considered to adjust the target reverse yaw moment and update the target reverse yaw moment. Specifically, the out-of-round lateral acceleration threshold value (denoted as |ay| * ) and the maximum reverse yaw moment allowed for the vehicle when the tire is not out-of-round (denoted as ΔM1) can be set. As shown in Equation (9), the lateral acceleration ay in the driving state data is used to judge with the out-of-round lateral acceleration threshold value |ay| * . When the absolute value |ay| of the lateral acceleration is less than the out-of-round lateral acceleration threshold value |ay| * , there is no need to adjust the target reverse yaw moment; when the absolute value |ay| of the lateral acceleration is not less than the out-of-round lateral acceleration threshold value |ay| * , the maximum reverse yaw moment ΔM1 allowed for the vehicle when the tire is not out-of-round is determined as the target reverse yaw moment to update the target reverse yaw moment.

[0135]

[0136] The above optional embodiments of the present application can achieve the following technical effects: in the case of a flat tire failure of the vehicle, the adaptive feedforward control rule can predict the future unstable state of the vehicle according to the vehicle's driving state data and driving operation data, calculate in advance the feedforward yaw moment to control the vehicle, and improve the response speed of vehicle control; furthermore, the feedback control rule is used to dynamically adjust the deviation between the actual yaw and the target yaw to obtain a more accurate target reverse yaw moment. By combining these two control methods, namely the adaptive feedforward control rule and the feedback control rule, it is possible to improve the response speed of vehicle control while enhancing the accuracy of vehicle control.

[0137] Optionally, the driving state data includes vehicle speed data, and the driving operation data includes steering wheel signal, brake pedal signal, and accelerator pedal signal. In the above step S401, using the adaptive feedforward control rule, driving state data, and driving operation data to calculate the feedforward yaw moment includes the following steps:

[0138] S411: Based on the adaptive feedforward control rule, determine the feedforward yaw moment model and the adaptive correction model;

[0139] S412: Use the feedforward yaw moment model, vehicle speed data, steering wheel signal, brake pedal signal, accelerator pedal signal, and flat tire deflation rate to calculate to obtain the feedforward yaw moment;

[0140] S413: Use the adaptive correction model and the road adhesion parameter and vehicle load corresponding to the vehicle to adaptively correct the feedforward yaw moment to update the feedforward yaw moment.

[0141] The above feedforward yaw moment model can be obtained through simulation tests or real vehicle tests on the vehicle. The feedforward yaw moment model can be constructed based on a predictive control strategy. Using this feedforward yaw moment model, in the event of an emergency (especially a flat tire failure) of the vehicle, it is possible to improve the response speed of vehicle control, help stabilize the vehicle in the shortest time, and reduce the additional risks caused by the driver's excessive reaction.

[0142] The above adaptive correction model can be used to dynamically adjust the output parameters of the feedforward yaw moment model. Using this adaptive correction model can make the control system more flexible and intelligent. In the event of an emergency (especially a flat tire failure) of the vehicle, it can quickly adapt to the current state of the vehicle, further correct and limit the feedforward yaw moment model, provide more precise control, enhance the robustness of the vehicle control method, and thus effectively improve the stability and safety of the vehicle.

[0143] The above road surface adhesion parameter can be a physical quantity of the friction characteristics between the vehicle tires and the road surface. This road surface adhesion parameter can reflect the ratio of the maximum lateral or longitudinal force that the tire can generate on the road surface to the vertical load of the tire. The higher this road surface adhesion coefficient, the greater the frictional force between the tire and the road surface, and the better the stability and controllability of the vehicle during acceleration, braking, or steering. The above vehicle load can be the total weight borne by the vehicle in real time. The above tire burst air leakage rate can be obtained through a tire pressure detection sensor.

[0144] In an exemplary application scenario, still as Figure 2 shown, the control module in the central controller is used for feedforward control and adaptive correction. Specifically, based on the adaptive feedforward control rule, a feedforward yaw moment model is established, and an adaptive correction model is set for this feedforward yaw moment model; furthermore, the vehicle speed data v, the steering wheel signal (denoted as ), the brake pedal signal (denoted as α), the accelerator pedal signal (denoted as β), and the tire burst air leakage rate (denoted as δ) are input into the feedforward yaw moment model, and the feedforward yaw moment (denoted as ΔMfx) is calculated, as shown in Equation (10).

[0145]

[0146] Still in the above application scenario, the road surface adhesion parameter (denoted as μ) and the vehicle load (denoted as load) corresponding to the vehicle are input into the adaptive correction model to adaptively correct the above feedforward yaw moment to update the feedforward yaw moment, and the updated feedforward yaw moment is denoted as ΔMfx', as shown in Equation (11).

[0147] ΔMfx' = f(μ, load) * ΔMfx Equation (11)

[0148] It should be noted that in the above application scenario, a feedforward yaw moment model corresponding to each tire can be set for the four tires of the vehicle respectively. Thus, in the case of a tire burst failure of different tires, the feedforward yaw moment can be calculated for the specific tire, improving the accuracy of the feedforward yaw moment.

[0149] The above optional embodiments of the present application can achieve the following technical effects: Based on the adaptive feedforward control rule, the feedforward yaw moment model and the adaptive correction model are determined. Using the feedforward yaw moment model, the control system of the vehicle can instantaneously generate the feedforward yaw moment according to the real-time driving state data and driving operation data, improving the response speed of vehicle control, and using the adaptive correction model to consider the influence of the actual driving conditions of the vehicle on vehicle control, thereby dynamically adjusting the feedforward yaw moment, enhancing the robustness of the vehicle control system, and ensuring the accuracy of the feedforward yaw moment.

[0150] Optionally, the target threshold data includes a target yaw threshold. In step S402 above, using the feedback control rule and the driving state data, calculating the feedback yaw moment includes the following steps:

[0151] S421: Based on the feedback control rule, determine the feedback torque algorithm, the steering correction parameter, and the delay correction parameter;

[0152] S422: Based on the driving state data, determine the vehicle's real-time yaw moment and the deviation of the center of mass sideslip angle;

[0153] S423: Use the feedback torque algorithm, the threshold deviation between the real-time yaw moment and the target yaw threshold, and the deviation of the center of mass sideslip angle to calculate and obtain the basic feedback torque;

[0154] S424: Use the steering correction parameter and the delay correction parameter to correct the basic feedback torque to obtain the feedback yaw moment.

[0155] The above feedback torque algorithm may refer to the response strategy of the vehicle control system to the deviation between the actual state and the desired target state of the vehicle. The above steering correction parameter can be used to compensate for the change in steering characteristics caused by the vehicle being in a flat tire state. The steering correction parameter can characterize the actual steering efficiency of the vehicle in response to the steering wheel input. The steering correction parameter can be obtained through experimental calibration of the vehicle based on the change in tire side slip characteristics.

[0156] The above delay correction parameter can be used to compensate for the time delay between when the vehicle control system detects a flat tire fault in the vehicle and when it actually starts to execute the control instruction. The delay correction parameter can include the time delay amount and the corresponding correction coefficient. The delay correction parameter can reflect the influence degree of the response lag of the vehicle control system on the vehicle stability control. The delay correction parameter can be obtained through experimental calibration of the vehicle. Using the delay correction parameter can ensure that the control instruction can still effectively control the vehicle after considering the inherent delay of the vehicle control system, and improve the accuracy of vehicle control.

[0157] The above real-time yaw moment can reflect the immediate lateral stability state of the vehicle. The real-time yaw moment can refer to the rotational moment generated by the vehicle around the vertical axis of the vehicle body during driving. The real-time yaw moment can be obtained by using an inertial detection sensor. The above-mentioned center-of-gravity sideslip angle deviation can refer to the angular difference between the actual moving direction of the vehicle's center of gravity and the forward direction of the vehicle. Specifically, when the vehicle encounters an emergency (for example, a flat tire failure occurs to the vehicle), the grip of the tire on one side of the vehicle will decrease, and the center of gravity of the vehicle (i.e., the center of the vehicle's weight) will tend to shift to the side with the decreased grip. At this time, an angular deviation will occur between the actual driving direction of the vehicle and the direction intended to be controlled by the driver, and this angular deviation is the center-of-gravity sideslip angle deviation. The center-of-gravity sideslip angle deviation can be obtained by combining an inertial detection sensor and a wheel speed sensor.

[0158] In an exemplary application scenario, still as Figure 2 shown, the control module and the vehicle stability state judgment module in the central controller are used for feedback control. Specifically, based on the feedback control rule, the feedback torque algorithm, the steering correction parameter, and the delay correction parameter (denoted as k) are determined; furthermore, using the vehicle stability state judgment module, a deviation calculation is performed between the real-time yaw moment of the vehicle determined based on the real-time acquired driving state data and the target yaw threshold, obtaining a threshold deviation (denoted as Δγ). The center-of-gravity sideslip angle deviation (denoted as Δβ) determined based on the real-time acquired driving state data and the above-mentioned threshold deviation Δy are input into the feedback torque algorithm for calculation, obtaining a basic feedback torque (denoted as ΔMz); further, the basic feedback torque is preliminarily corrected using the steering correction parameter, and a certain reverse correction yaw torque is superimposed on the basic feedback torque to obtain a preliminarily corrected basic feedback torque (denoted as ΔMz c ), and the preliminarily corrected basic feedback torque ΔMz c is corrected using the delay correction parameter k to obtain a feedback yaw torque (denoted as ΔMz′), as shown in Equation (12).

[0159] ΔMz′ = k × ΔMz c Equation (12)

[0160] Still in the above application scenario, the above feedforward yaw torque and the above feedback yaw torque are weighted and calculated through Equation (13) to determine the target reverse yaw torque (denoted as ΔM).

[0161] ΔM = ΔMfx' + ΔMz′ Equation (13)

[0162] The above optional embodiments of the present application can achieve the following technical effects: By the feedback control rule, the feedback torque algorithm, the steering and delay correction parameters are determined, providing a calculation basis for feedback control. Furthermore, based on the real-time driving state data of the vehicle, the real-time yaw moment and the deviation of the center of mass side slip angle of the vehicle are determined, improving the timeliness of the data and providing an accurate data basis for feedback control. Further, the basic feedback torque is obtained by calculating using the feedback torque algorithm, the threshold deviation between the real-time yaw moment and the target yaw threshold, and the deviation of the center of mass side slip angle, and the basic feedback torque is corrected using the steering correction parameter and the delay correction parameter, more comprehensively considering the change of the vehicle steering characteristics after a tire blowout failure and the time delay between the generation and execution of the control command, improving the accuracy of the feedback yaw moment. Using this feedback yaw moment can dynamically adjust the target reverse yaw moment, enhancing the accuracy of the vehicle control method, thereby improving the ability of the vehicle to maintain stability after a tire blowout and enhancing the stability and safety of the vehicle.

[0163] Optionally, the above vehicle control method further includes the following steps:

[0164] S41: In response to determining that the vehicle is in a tire blowout state according to the detection result, determine the non-blowout wheels of the vehicle;

[0165] S42: Based on the target reverse yaw moment, perform torque distribution on the non-blowout wheels to obtain a distribution result;

[0166] S43: Send a torque control command to the execution component according to the distribution result, where the torque control command is used to control the execution component to perform a driving action or a braking action so that the vehicle maintains body stability after a tire blowout.

[0167] The above tire blowout state can be used to determine the tire corresponding to the tire blowout failure of the vehicle. The above distribution result can be determined by an actuator cooperative control strategy. The above execution component can include a power system, an electronic control suspension system, a steering system, and a braking system.

[0168] In an exemplary application scenario, as Figure 3 shown, the data obtained by the tire pressure detection sensor, the wheel speed sensor, the inertial detection sensor, the acoustic sensor, and the vibration sensor (i.e., the driving state data and the driving operation data) are input into the central controller, and the central controller calculates the driving state data and the driving operation data to obtain the target reverse yaw moment, and performs torque distribution on the non-blowout wheels based on the target reverse yaw moment to obtain a distribution result, and sends a torque control command to the execution component according to the distribution result. Specifically, reference can be made to Figure 2, send the torque control instruction corresponding to the driving torque to the power system, the torque control instruction corresponding to the deceleration request to the braking system, the torque control instruction corresponding to the steering torque to the steering system, and the torque control instruction corresponding to the target height to the electronic control suspension system according to the distribution result.

[0169] Still in the above application scenario, in response to determining that the vehicle is in a flat tire state according to the detection result, determine the tire corresponding to the flat tire failure of the vehicle, and determine the tires other than the tire corresponding to the flat tire failure as the non-flat tires; further, perform torque distribution on the non-flat tires based on the target reverse yaw moment to obtain the distribution result to compensate for the vehicle imbalance caused by the flat tire. For example, if the left rear tire of the vehicle has a flat tire, the vehicle control system will increase the driving torque of the right front wheel and at the same time reduce the braking torque of the left front wheel to maintain the lateral balance of the vehicle and prevent the vehicle from tilting or skidding to the left; furthermore, send the torque control instruction to the power system in the execution component according to the distribution result to control the power system to perform the driving action.

[0170] Still in the above application scenario, send the torque control instruction to the electronic control suspension system in the execution component according to the distribution result to control the electronic control suspension system to perform dynamic vehicle center of gravity management, lower the height of the vehicle to the target height, make the vertical load corresponding to the non-flat tires close to horizontal, and redistribute the vertical loads of the four tires to avoid excessive vertical load differences between the four tires, thereby improving the stability boundary and the available range of the four tires, reducing the risk of vehicle rollover, and controlling the electronic control suspension system to adjust the damping to the maximum to reduce the roll angle of the vehicle. Send the torque control instruction to the steering system in the execution component according to the distribution result to control the steering system to perform steering wheel angle control and maintain the steering wheel angle at a fixed angle (for example, or turn a small angle value on the side without a flat tire, and this angle value can be set according to vehicle calibration) to reduce the steering assist. In the case of triggering the vehicle body stability control of the braking system, send the torque control instruction to the braking system in the execution component according to the distribution result to control the braking system of the vehicle to perform the braking action (i.e., the deceleration request of the vehicle) to assist in controlling the vehicle to maintain stability.

[0171] The above optional embodiments of the present application can achieve the following technical effects: In the case of a flat tire failure of the vehicle, the vehicle control system is used to identify the non-flat tires, and then according to the target reverse yaw moment, torque distribution is performed on these tires, which can make full use of the handling ability of the non-flat tires of the vehicle, compensate for the imbalance caused by the flat tire, enable the vehicle to still drive stably after a flat tire, avoid causing serious traffic accidents, and improve the stability and safety of the vehicle.

[0172] Embodiment 2

[0173] An embodiment of the present application also provides a vehicle control device 400. Please refer to Figure 4 , including: an acquisition module 410 for acquiring the driving state data and driving operation data of the vehicle; a detection module 420 for detecting the flat tire state of the vehicle by using the driving state data to obtain a detection result; a determination module 430 for determining target threshold data by using the driving state data, driving operation data and detection result; and a control module 440 for determining a target reverse yaw moment based on a multiple control method, driving state data, driving operation data and target threshold data, wherein the multiple control method is constructed based on an adaptive feedforward control rule and a feedback control rule, and the target reverse yaw moment is used to control the driving torque or braking torque of an execution component in the vehicle.

[0174] The vehicle control device provided by the embodiment of the present application achieves the following technical effects: By using the acquisition module 410 to acquire the driving state data and driving operation data of the vehicle, the current driving state and driving operation situation of the vehicle can be determined in real time, enhancing the timeliness of the data and helping to more accurately detect the flat tire state of the vehicle subsequently; furthermore, by using the detection module 420 to detect the flat tire state of the vehicle by using the driving state data to obtain a detection result, it is possible to timely determine whether the vehicle has a flat tire fault and enhance the accuracy of the detection result; further, by using the determination module 430 to determine the target threshold data by using the driving state data, driving operation data and detection result, by comprehensively considering the driving state data, driving operation data and detection result, it is possible to determine whether there is a driver's misoperation situation, and then determine the target threshold data to limit the driver's wrong operation, reduce the influence of the driver's misoperation, and determine the target threshold data that can ensure the stable driving of the vehicle; finally, by using the control module 440, the multiple control method constructed by using the adaptive feedforward control rule and the feedback control rule can combine the advantages of the adaptive feedforward control and the feedback control rule. Based on this multiple control method, driving state data, driving operation data and target threshold data, the target reverse yaw moment can be obtained more quickly, and the accuracy of the determined target reverse yaw moment is also higher, enabling the vehicle control device to efficiently and accurately determine the target reverse yaw moment and improving the performance of the vehicle control device.

[0175] It should be noted that the optional implementation manners of this embodiment can refer to the relevant descriptions in Embodiment 1, and will not be elaborated here.

[0176] Embodiment 3

[0177] An embodiment of the present application also provides a vehicle 50. Please refer to Figure 5, including an in-vehicle memory 510 and an in-vehicle processor 520. Among them, the in-vehicle memory 510 is used to store computer programs; the in-vehicle processor 520 is used to execute the computer programs stored on the memory to implement the vehicle control method of any embodiment.

[0178] The vehicle provided by the embodiment of the present application achieves the following technical effects: By obtaining the driving state data and driving operation data of the vehicle, the current driving state and driving operation situation of the vehicle can be determined in real time, enhancing the timeliness of the data and contributing to more accurate subsequent detection of the flat tire state of the vehicle; furthermore, using the driving state data to detect the flat tire state of the vehicle and obtaining the detection result can timely determine whether the vehicle has a flat tire fault and enhance the accuracy of the detection result; further, by comprehensively considering the driving state data, driving operation data, and detection result, it is judged whether there is a driver's misoperation, and then the target threshold data is determined to limit the driver's wrong operation, reducing the impact of the driver's misoperation and determining the target threshold data that can ensure the stable driving of the vehicle; finally, using the multiple control methods constructed by the adaptive feedforward control rule and the feedback control rule can combine the advantages of the adaptive feedforward control and the feedback control rule. Based on this multiple control method, driving state data, driving operation data, and target threshold data, the target reverse yaw moment can be obtained more quickly, and the accuracy of the determined target reverse yaw moment is also higher, thereby ensuring that the vehicle can drive stably in the case of a flat tire fault and improving the safety of the vehicle.

[0179] Those of ordinary skill in the art can understand that, similarly, the above vehicle can also be a computing terminal. Figure 6 is the hardware structure block diagram of the computing terminal for implementing the vehicle control method in the embodiment of the present application. As Figure 6 shown, the computing terminal 60 (such as, a computer terminal, a mobile intelligent terminal, a vehicle terminal, or a cloud computing virtual terminal, etc.) can include: one or more processors 602 (such as, it can include processors 602a, 602b,..., 602n), a memory 604 for storing data, and a transmission device 606 for implementing communication functions. Among them, the processor 602 can include, but is not limited to, processing components such as a microcontroller unit (MCU) or a field programmable gate array (FPGA).

[0180] The above computing terminal 60 may further include: a display, an input / output interface, a Universal Serial Bus (USB) port (which may be one of the ports of the computer bus and is not shown in the figure), a network interface (not shown in the figure), a power supply (not shown in the figure), and a camera (not shown in the figure).

[0181] It should be noted that one or more processors 602 and / or other data processing circuits in the above computing terminal 60 may be embodied in software, hardware, firmware, or any combination thereof, in whole or in part. Additionally, the data processing circuit may be a single independent processing module, or may be incorporated, in whole or in part, into any one of the other elements in the computing terminal 60 (or mobile device).

[0182] The memory 604 may be used to store software programs and modules of application software, such as the program instructions and data storage devices corresponding to the path planning method in the embodiments of the present application. The processor 602 executes various functional applications and data processing by running the software programs and modules stored in the memory 604, thereby implementing the above path planning method. The memory 604 may include a high-speed random access memory, and may further include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory 604 may further include a memory remotely disposed relative to the processor 602, and these remote memories may be connected to the vehicle terminal 60 through a network. Examples of the above network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0183] The transmission device 606 is used to receive or send data via a network. Specific examples of the above network may include a wireless network provided by the communication provider of the vehicle terminal 60. In one instance, the transmission device 606 includes a Network Interface Controller (NIC) and a network interface, and the network adapter can be connected to other network devices through a base station to communicate with the Internet. The transmission device 606 may perform data communication in a wired and / or wireless network connection manner. In one instance, the transmission device 606 may be a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0184] The input / output interface may be connected to the input / output devices corresponding to the computing terminal 60 to implement input / output functions. The input / output devices may include, but are not limited to: a cursor control device, a keyboard, a display, etc. The above input / output devices may be built into the computing terminal 60, or may be external devices outside the computing terminal 60.

[0185] Those of ordinary skill in the art can understand that Figure 6 the structure of the computing terminal 60 shown is only illustrative and does not impose strict limitations on the structure of the above-mentioned computing terminal 60. For example, the computing terminal 60 may further include more or fewer components than those shown in Figure 6 or the computing terminal 60 may have different types of components from those shown in Figure 6 the illustration.

[0186] Embodiment 4

[0187] The embodiment of the present application further provides an electronic device 70. Please refer to Figure 7 , which includes a memory 710 and a processor 720. Among them, the memory 710 is used to store a computer program; the processor 720 is used to execute the program stored on the memory 710 to implement the vehicle control method introduced in any embodiment of the present application. <<

[0188] The above electronic device provided by the embodiment of the present application achieves the following technical effects: By obtaining the driving state data and driving operation data of the vehicle, the current driving state and driving operation situation of the vehicle can be determined in real time, enhancing the timeliness of the data and helping to more accurately detect the flat tire state of the vehicle subsequently; furthermore, using the driving state data to detect the flat tire state of the vehicle and obtaining the detection result can timely determine whether the vehicle has a flat tire fault and enhance the accuracy of the detection result; further, by comprehensively considering the driving state data, driving operation data, and detection result, it is judged whether there is a driver's misoperation situation, and then the target threshold data is determined to limit the driver's wrong operation, reducing the impact of the driver's misoperation, and determining the target threshold data that can ensure the stable driving of the vehicle; finally, using the multiple control methods constructed by the adaptive feedforward control rule and the feedback control rule can combine the advantages of the adaptive feedforward control and the feedback control rule. Based on this multiple control method, driving state data, driving operation data, and target threshold data, the target reverse yaw moment can be obtained more quickly, and the accuracy of the determined target reverse yaw moment is also higher, so that the electronic device can efficiently and accurately determine the target reverse yaw moment and improve the performance of the electronic device.

[0189] [[ID=z1]]Those of ordinary skill in the art can understand that Figure 7 the structure shown is only illustrative, and the electronic device can also be a terminal device such as a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, and a Mobile Internet Device (MID). Figure 7 It does not impose limitations on the structure of the above-mentioned electronic device. For example, the electronic device 70 may further include more or fewer components than those shown in Figure 7more or fewer components (such as, network interfaces, display devices, etc.) shown therein, or having a configuration different from that Figure 7 shown.

[0190] Embodiment 5

[0191] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the vehicle control method introduced in any embodiment of the present application is implemented.

[0192] Optionally, in this embodiment, the above storage medium may include but is not limited to: various media such as USB flash drives, read-only memories (ROM), random access memories (RAM), mobile hard disks, magnetic disks, or optical discs that can store computer programs.

[0193] The above computer-readable storage medium provided by the embodiment of the present application achieves the following technical effects: By acquiring the driving state data and driving operation data of the vehicle, the current driving state and driving operation situation of the vehicle can be determined in real time, enhancing the timeliness of the data, which helps to more accurately detect the flat tire state of the vehicle subsequently; further, using the driving state data to detect the flat tire state of the vehicle and obtaining a detection result can timely determine whether the vehicle has a flat tire fault, enhancing the accuracy of the detection result; further, by comprehensively considering the driving state data, driving operation data, and detection result, it is judged whether there is a driver's misoperation situation, and then the target threshold data is determined to limit the driver's wrong operation, reducing the impact of the driver's misoperation, and determining the target threshold data that can ensure the stable driving of the vehicle; finally, using the multiple control method constructed by the adaptive feedforward control rule and the feedback control rule can combine the advantages of the adaptive feedforward control and the feedback control rule. Based on this multiple control method, driving state data, driving operation data, and target threshold data, the target reverse yaw moment can be obtained more quickly, and the accuracy of the determined target reverse yaw moment is also higher.

[0194] The above serial numbers of the embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0195] In the above embodiments of the present application, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0196] In the present application, multiple means two or more.

[0197] In this application, unless otherwise clearly defined, the terms "installed", "connected", and "linked" shall be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0198] In this application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this application generally represents an "or" relationship between the associated objects before and after.

[0199] If there is no special instruction, all steps of this application can be carried out sequentially or randomly. For example, the method includes steps A and B, indicating that the method can include steps A and B carried out sequentially, or steps B and A carried out sequentially. For example, it is mentioned that the method may further include step C, indicating that step C can be added to the method in any order. For example, the method can include steps A, B, and C, or steps A, C, and B, or steps C, A, and B, etc.

[0200] The above are only the preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent replacements, and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims

1. A vehicle control method, characterized in that, Including: Obtaining the driving state data and driving operation data of the vehicle; Detecting the flat tire state of the vehicle by using the driving state data to obtain a detection result; Determining target threshold data by using the driving state data, the driving operation data and the detection result; Determining a target reverse yaw moment based on multiple control methods, the driving state data, the driving operation data and the target threshold data, wherein the multiple control methods are constructed based on an adaptive feedforward control rule and a feedback control rule, and the target reverse yaw moment is used to control the driving torque or braking torque of an execution component in the vehicle.

2. The vehicle control method according to claim 1, wherein The driving state data includes: tire pressure sensing data, wheel speed data, vibration sensing data and acoustic sensing data, and the detection result includes flat tire flag data. Detecting the flat tire state of the vehicle by using the driving state data to obtain the detection result includes: Determining first flag data according to the tire pressure sensing data, a preset detection period and a tire pressure change threshold; Determining second flag data according to the wheel speed data and a wheel speed difference threshold; Determining third flag data according to the vibration sensing data and a vibration anomaly threshold; Determining fourth flag data according to the acoustic sensing data and an acoustic anomaly threshold; Determining the flat tire flag data based on the first flag data, the second flag data, the third flag data and the fourth flag data, wherein the flat tire flag data is used to represent whether the vehicle is in a flat tire state.

3. The vehicle control method according to claim 2, characterized in that, The detection result further includes a missed detection flag data and a false detection flag data, and the vehicle control method further includes: In response to the first flag data, the second flag data, the third flag data and the fourth flag data satisfying the missed detection condition, determining the missed detection flag data, wherein the missed detection condition includes: determining that the tire pressure sensing data does not include a flat tire anomaly according to the first flag data, determining that the wheel speed data includes a flat tire anomaly according to the second flag data, determining that the vibration sensing data includes a flat tire anomaly according to the third flag data, and determining that the acoustic sensing data includes a flat tire anomaly according to the fourth flag data; In response to the first flag data, the second flag data, the third flag data and the fourth flag data satisfying the false detection condition, determining the false detection flag data, wherein the false detection condition includes: determining that the tire pressure sensing data includes a flat tire anomaly according to the first flag data, determining that the wheel speed data does not include a flat tire anomaly according to the second flag data, determining that the vibration sensing data does not include a flat tire anomaly according to the third flag data, and determining that the acoustic sensing data does not include a flat tire anomaly according to the fourth flag data; Generating an enable signal for the execution component according to the missed detection flag data and the false detection flag data.

4. The vehicle control method according to claim 1, wherein The driving operation data includes: a steering wheel signal, a brake pedal signal and a radar sensing signal, and the target threshold data includes a target yaw threshold. Determining the target threshold data by using the driving state data, the driving operation data and the detection result includes: In response to determining that the vehicle is in a flat tire state based on the detection result, based on the radar sensing signal, determine the obstacle distance information corresponding to the vehicle, and use the obstacle distance information, the steering wheel signal, and the brake pedal signal to perform driving intention recognition to determine the recognition result, where the recognition result is used to characterize whether the driving operation corresponding to the vehicle belongs to a misoperation; Use the driving state data, the driving operation data, and the recognition result to determine the target yaw threshold.

5. The vehicle control method according to claim 4, characterized in that The driving state data includes vehicle speed data and wheel speed data. Using the driving state data, the driving operation data, and the recognition result to determine the target yaw threshold includes: Use the vehicle speed data, the wheel speed data, the steering wheel signal, as well as the wheelbase and the preset characteristic vehicle speed corresponding to the vehicle to determine the basic yaw data; In response to determining that the driving operation belongs to the misoperation according to the recognition result, correct and update the basic yaw data according to the vehicle speed data; Use the basic yaw data and the yaw threshold sensitivity calibration coefficient corresponding to the vehicle to determine the basic yaw threshold; Generate the target yaw threshold based on the basic yaw threshold and the lateral acceleration threshold corresponding to the vehicle.

6. The vehicle control method according to claim 1, wherein The multiple control rules include an adaptive feedforward control rule and a feedback control rule. Based on the multiple control methods, the driving state data, the driving operation data, and the target threshold data, determining the target reverse yaw moment includes: Use the adaptive feedforward control rule, the driving state data, and the driving operation data to calculate the feedforward yaw moment; Use the feedback control rule, the driving state data, and the target threshold data to calculate the feedback yaw moment; Perform weighted calculation on the feedforward yaw moment and the feedback yaw moment to determine the target reverse yaw moment.

7. The vehicle control method according to claim 6, characterized in that, The driving state data includes vehicle speed data, and the driving operation data includes a steering wheel signal, a brake pedal signal, and an accelerator pedal signal. Using the adaptive feedforward control rule, the driving state data, and the driving operation data to calculate the feedforward yaw moment includes: Based on the adaptive feedforward control rule, determine the feedforward yaw moment model and the adaptive correction model; Use the feedforward yaw moment model, the vehicle speed data, the steering wheel signal, the brake pedal signal, the accelerator pedal signal, and the flat tire deflation rate to calculate the feedforward yaw moment; Use the adaptive correction model, as well as the road surface adhesion parameter and the vehicle load corresponding to the vehicle, to perform adaptive correction on the feedforward yaw moment to update the feedforward yaw moment.

8. The vehicle control method according to claim 6, characterized in that, The target threshold data includes the target yaw threshold. Using the feedback control rule and the driving state data to calculate the feedback yaw moment includes: Based on the feedback control rule, determine the feedback moment algorithm, the steering correction parameter, and the delay correction parameter; Based on the driving state data, determine the real-time yaw moment and the deviation of the center of mass sideslip angle of the vehicle; Calculation is performed using the feedback torque algorithm, the threshold deviation between the real-time yaw torque and the target yaw threshold, and the center of mass sideslip angle deviation to obtain the basic feedback torque; The basic feedback torque is corrected using the steering correction parameter and the delay correction parameter to obtain the feedback yaw torque.

9. The vehicle control method according to claim 1, wherein The vehicle control method further includes: In response to determining that the vehicle is in a flat tire state according to the detection result, determining the non-flat tires of the vehicle; Performing torque distribution on the non-flat tires based on the target reverse yaw torque to obtain a distribution result; Sending a torque control instruction to the execution component according to the distribution result, where the torque control instruction is used to control the execution component to perform a driving action or a braking action so that the vehicle maintains vehicle body stability after a flat tire.

10. A vehicle control device, characterized in that, including: An acquisition module for acquiring the driving state data and driving operation data of the vehicle; A detection module for detecting the flat tire state of the vehicle using the driving state data to obtain a detection result; A determination module for determining target threshold data using the driving state data, the driving operation data, and the detection result; A control module for determining a target reverse yaw torque based on multiple control methods, the driving state data, the driving operation data, and the target threshold data, where the multiple control methods are constructed based on an adaptive feedforward control rule and a feedback control rule, and the target reverse yaw torque is used to control the driving torque or braking torque of the execution component in the vehicle.

11. A vehicle, characterized in that, including a processor and a memory, where The memory is used to store a computer program; The processor is used to execute the program stored on the memory to implement the vehicle control method according to any one of claims 1 to 9.

Images