Method and device for estimating vehicle sideslip angle

Abstract

An embodiment of the present invention discloses a method and device for estimating a vehicle sideslip angle. The method includes: identifying whether a first yaw rate from a vehicle yaw rate sensor is valid; when the first yaw rate is valid, calculating a first sideslip angle according to the first yaw rate and a vehicle dynamics model; and when the first yaw rate is invalid, calculating a second sideslip angle of the vehicle based on a trained neural network model; wherein the input of the neural network model is a first signal and a vehicle speed, the output of the neural network model is the second sideslip angle, and the first signal includes at least one of a vehicle wheel speed, a vehicle acceleration, and a vehicle steering angle. In the embodiment of the present invention, when there is no valid yaw rate (provided by the yaw rate sensor), the situation where no sideslip angle is available can be avoided.

Description

Technical Field

[0001] The present invention relates to vehicle technologies, and in particular, to a method and device for estimating a sideslip angle of a vehicle. Background Art

[0002] The sideslip angle of a vehicle refers to the angle between the projection of the vehicle's x0 axis (moving coordinate system) on the road surface and the projection of the vehicle speed (at the center of mass) on the road surface. This parameter is generally used to evaluate the stability of the vehicle and is also the target control variable of most electronic stability systems.

[0003] However, the sideslip angle of a vehicle cannot be directly measured, so it is generally observed through other variables. For example, based on a vehicle kinematic model, the sideslip angle of the vehicle can be calculated using the yaw rate and vehicle speed of the vehicle, where the yaw rate can be directly measured by a yaw rate sensor.

[0004] The inventors of the present application found that: in a millimeter-wave radar of a vehicle, it is also necessary to calculate the sideslip angle of the vehicle based on the yaw rate collected by the yaw rate sensor. However, the millimeter-wave radar and the yaw rate sensor are in different domains. In some cases, the millimeter-wave radar may not be able to obtain the yaw rate or the obtained yaw rate is invalid, which may be caused by an error in the transmission of the signal in the in-vehicle network. Therefore, in this case, the millimeter-wave radar may face the problem of not being able to accurately obtain the sideslip angle of the vehicle. Summary of the Invention

[0005] In view of this, an embodiment of the present invention provides a method for estimating a sideslip angle of a vehicle, which can avoid the situation where no sideslip angle is available when the yaw rate provided by the yaw angle sensor is invalid.

[0006] A method for estimating a sideslip angle of a vehicle according to an embodiment of the present invention is used for a radar, and the method includes: identifying whether a first yaw rate from a vehicle yaw angle sensor is valid; when the first yaw rate is valid, calculating a first sideslip angle according to the first yaw rate and a vehicle dynamics model; and when the first yaw rate is invalid, estimating a second sideslip angle of the vehicle based on a trained neural network model; wherein, the input of the neural network model is a first signal and a vehicle speed, and the output is the second sideslip angle, and the first signal includes at least one of a wheel speed, an acceleration, and a steering angle.

[0007] Wherein, the method further includes: when the first yaw rate is valid, training the neural network model based on the first signal, the vehicle speed, and the first sideslip angle.

[0008] Wherein, the method further includes: when the first yaw rate is valid, calculating a third sideslip angle based on the neural network model; and fusing the first and third sideslip angles to generate a final sideslip angle.

[0009] Wherein, the method further includes: determining whether the error between the first and third sideslip angles is within an allowable range; if it is within the allowable range, performing the step of fusing the first and third sideslip angles; if it is not within the allowable range, using the first sideslip angle as the final sideslip angle, and retraining the neural network model based on the error value between the first and third sideslip angles.

[0010] Wherein, the step of calculating the first sideslip angle according to the first yaw rate and the vehicle dynamics model includes: calculating at least one second yaw rate based on the first signal; using a Kalman filter to fuse the first and at least one second yaw rates to obtain a third yaw rate; and calculating the first sideslip angle based on the third yaw rate and the vehicle dynamics model.

[0011] Wherein, the vehicle dynamics model is:

[0012]

[0013] Wherein, β is the sideslip angle, is the yaw rate, m is the vehicle mass, l is the vehicle wheelbase, lr is the product of the rear axle load ratio and the wheelbase, lf is the product of the front axle load ratio and the wheelbase, v is the vehicle speed, and Ch is a constant.

[0014] An estimation device for a vehicle sideslip angle according to an embodiment of the present invention includes: a signal processing module for identifying whether a first yaw rate from a vehicle yaw angle sensor is valid; a first sideslip angle estimation module for estimating a first sideslip angle based on the first yaw rate and the vehicle dynamics model; a second sideslip angle estimation module for estimating a second sideslip angle based on a trained neural network model, wherein the input of the neural network model is the first signal and the vehicle speed, and the output is the second sideslip angle, and the first signal includes at least one of wheel speed, acceleration, and steering angle; and a processing module for: when the signal processing module identifies that the first yaw rate is valid, at least enabling the first sideslip angle estimation module, and when the signal processing module identifies that the first yaw rate is invalid, enabling the second sideslip angle estimation module.

[0015] Wherein, the processing module is specifically configured to: when the signal processing module recognizes that the first yaw rate is valid, enable the first and second sideslip angle estimation modules; determine whether the error between the first and second sideslip angles is within the allowable range; if it is within the allowable range, fuse the first and second sideslip angles; if it is not within the allowable range, use the first sideslip angle as the final sideslip angle, and control the second sideslip angle estimation module to retrain the neural network model based on the error value between the first and second sideslip angles.

[0016] An electronic device according to an embodiment of the present invention includes: a processor; and a memory for storing executable instructions of the processor; wherein, the processor is configured to execute the executable instructions to implement the method according to an embodiment of the present invention.

[0017] A computer-readable storage medium according to an embodiment of the present invention stores a computer program thereon, and the computer program includes executable instructions, and when the executable instructions are executed by a processor, the method according to an embodiment of the present invention is implemented.

[0018] Advantages of the embodiments of the present invention:

[0019] When the yaw rate of the yaw angle sensor is invalid, the sideslip angle is estimated based on the neural network model, thereby avoiding the situation where no sideslip angle is available. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Other details and advantages of the present invention will become apparent from the detailed description provided below. It should be understood that the following drawings are merely illustrative and thus should not be considered as limiting the present invention. The following will be described in detail with reference to the drawings, where:

[0021] Figure 1A is a schematic flowchart of an embodiment of the method for estimating the sideslip angle of a vehicle according to the present invention;

[0022] Figure 1B is Figure 1A a schematic flowchart of an embodiment of step S12 in

[0023] Figure 2 is a schematic flowchart of another embodiment of the method for estimating the sideslip angle of a vehicle according to the present invention;

[0024] Figure 3 is a schematic flowchart of another embodiment of the method for estimating the sideslip angle of a vehicle according to the present invention;

[0025] Figure 4 is a schematic flowchart of another embodiment of the method for estimating the sideslip angle of a vehicle according to the present invention;

[0026] Figure 5It is a schematic structural diagram of the BP neural network according to an embodiment of the present invention;

[0027] Figure 6 It is a schematic structural diagram of an embodiment of the vehicle sideslip angle estimation device of the present invention;

[0028] Figure 7 It is a schematic structural diagram of an embodiment of the electronic device of the present invention. Detailed implementation manners

[0029] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0030] In the description of the present invention, it should be understood that the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. Moreover, the terms "first", "second", etc. are applicable to distinguish similar objects and do not have to be used to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0031] In the embodiment of the present invention, in the case where the yaw rate provided by the yaw rate sensor is invalid, a neural network model is used to estimate the sideslip angle of the vehicle, thereby preventing the situation where there is no available sideslip angle in products such as radars. The embodiments of the present invention will be specifically described below with reference to the drawings.

[0032] As Figure 1A shown, it is a schematic flowchart of an embodiment of the vehicle sideslip angle estimation method of the present invention. This method can be used in products such as radars, for example, millimeter-wave radars. In products such as radars, a vehicle dynamics module is provided for collecting and calculating various parameters of the vehicle, such as vehicle speed, yaw rate, and sideslip angle, etc., for use by ADAS (Advanced Driving Assistance System), etc. Specifically, Figure 1A The method includes the following steps:

[0033] Step S10: Identify whether the first yaw rate from the yaw angle sensor of the vehicle is valid.

[0034] Among them, the situation where the yaw rate is invalid can be, for example, that the yaw rate cannot be obtained, or the obtained yaw rate is not within the effective range.

[0035] Step S12: When the first yaw rate is valid, calculate the first sideslip angle according to the first yaw rate and the vehicle dynamics model.

[0036] Among them, the vehicle dynamics model can be:

[0037]

[0038] Among them, β is the sideslip angle, is the yaw rate, m is the vehicle mass, l is the vehicle wheelbase, lr is the product of the rear axle load ratio and the wheelbase, lf is the product of the front axle load ratio and the wheelbase, v is the vehicle speed, and Ch is a constant.

[0039] When the first yaw rate is valid, the first sideslip angle can be used as the final sideslip angle.

[0040] Step S14: When the first yaw rate is invalid, calculate the second sideslip angle of the vehicle based on the trained neural network model.

[0041] Among them, the trained neural network model means that the error value of the neural network model is within a predetermined range, that is, the accuracy can meet the requirements.

[0042] Among them, the input of the neural network model is the first signal and the vehicle speed, and the output is the second sideslip angle. Among them, the first signal includes at least one of wheel speed, acceleration, and steering angle. Among them, the wheel speed, acceleration, and steering angle can be obtained by corresponding sensors, and before use, it can be first determined whether the signal is valid, and only when it is valid, it is used.

[0043] Among them, the wheel speed, acceleration, and steering angle all have a conversion relationship with the yaw rate. Therefore, the neural network model can be trained based on the wheel speed, acceleration, and steering angle to achieve the purpose of estimating the sideslip angle using the neural network model.

[0044] When the first yaw rate is invalid, the second sideslip angle can be output as the final sideslip angle.

[0045] In this embodiment, when the first yaw rate of the yaw angle sensor is invalid, estimating the sideslip angle based on the neural network model can avoid the situation where there is no available sideslip angle. In addition, compared with the method of converting the wheel speed, acceleration, or steering angle into the yaw rate and then calculating the sideslip angle based on the yaw rate, the method using the neural network can directly estimate the sideslip angle based on the wheel speed, acceleration, or steering angle, and the accuracy is higher.

[0046] In step S12, the first yaw rate can be further corrected to make it more accurate.

[0047] As Figure 1B shown, it is a schematic flow diagram of an embodiment of step S12, which includes:

[0048] Step S121: Calculate at least one second yaw rate based on the first signal.

[0049] In step S121, based on at least one of the wheel speed, acceleration, or steering angle, the corresponding yaw rate can be calculated respectively by using the corresponding dynamic model.

[0050] Specifically, the formula for calculating the yaw rate based on the wheel speed is as follows:

[0051]

[0052] In the formula, is the yaw rate estimated from the front wheel speed, whspdfr is the right front axle wheel speed, whspdfl is the left front axle wheel speed, and L is the vehicle wheelbase.

[0053]

[0054] In the formula, is the yaw rate estimated from the rear wheel speed, whspdfr is the right rear axle wheel speed, whspdfl is the left rear axle wheel speed, and L is the vehicle wheelbase.

[0055] Among them, the formula for estimating the yaw rate based on the steering angle is as follows:

[0056]

[0057] In the formula, is the yaw rate estimated from the steering angle, Br and Bf are the distances from the vehicle center of mass to the rear axle and the front axle respectively, and θ is the vehicle steering angle.

[0058] Among them, the formula for estimating the yaw rate based on the acceleration is as follows:

[0059]

[0060] In the formula, is the yaw rate estimated from the acceleration, a y is the vehicle lateral acceleration, and V x is the vehicle longitudinal speed.

[0061] Step S122: Use the Kalman filter to fuse the first and at least one second yaw rates to obtain a third yaw rate.

[0062] Among them, in the Kalman filter, the yaw rate collected by the yaw angle sensor is used as the main quantity, and the yaw rate calculated based on the wheel speed, angular velocity, and steering angle is used as the auxiliary quantity to obtain a more accurate yaw rate.

[0063] Step S123: Calculate the first sideslip angle based on the third yaw rate and the vehicle dynamics model.

[0064] In this embodiment, using the second yaw rate calculated from the first signal to correct the first yaw rate can make the finally calculated first sideslip angle more accurate.

[0065] As Figure 2 shown, it is a schematic flowchart of an embodiment of the method for estimating the vehicle sideslip angle of the present invention. Among them Figure 2 it includes steps S20, S24, and S26 similar to those in FIG. 1, which will not be elaborated here. In Figure 2 it, it further includes: step S24, that is, when the first yaw rate of the yaw angle sensor is valid, the neural network model is trained using the first sideslip angle calculated based on the first yaw rate.

[0066] After the neural network model is deployed in the vehicle, the accuracy of the neural network model does not meet the requirements at the beginning. Therefore, during the normal driving of the vehicle, the neural network model can be continuously trained using the first signal, vehicle speed, and first sideslip angle to meet the accuracy requirements.

[0067] As Figure 5 shown, it is a schematic structural diagram of a BP (back propagation) neural network model. The BP neural network is a multi-layer feedforward neural network, with signals propagating forward and errors propagating backward.

[0068] In the BP neural network, it is mainly divided into two stages: the first stage is the forward propagation of signals, from the input layer through the hidden layer (there can be multiple hidden layers), and finally reaching the output layer. The second stage is the backward propagation of errors, from the output layer to the hidden layer, and finally to the input layer, sequentially adjusting the weights and biases from the hidden layer to the output layer, and the weights and biases from the input layer to the hidden layer.

[0069] In the structure in the figure, the number of nodes in the input layer is n, the number of nodes in the hidden layer is l, and the number of nodes in the output layer is m. The weight from the input layer to the hidden layer is Wij, the weight from the hidden layer to the output layer is Wjk, the bias from the input layer to the hidden layer is Aj, and the bias from the hidden layer to the output layer is Bk. The learning rate is η, and the activation function is g(x), where the activation function takes the sigmoid function, and the function formula is as follows:

[0070]

[0071] Among them, x i represents the input, that is, the first signal and the vehicle speed.

[0072] Similar to a three-layer BP neural network, the output of the hidden layer is:

[0073]

[0074] The output of the output layer:

[0075]

[0076] The error formula is:

[0077]

[0078] Among them, Yk is the expected output, and Yk - Ok = ek. Among them, Yk can be the above-mentioned first sideslip angle, and ek is the set error range.

[0079] The weight update formula is:

[0080]

[0081] The bias update formula is:

[0082]

[0083] In the solution, an area for separately storing the database will be designed. The database stores data such as the first signal, vehicle speed, and first sideslip angle generated in real time during vehicle driving, and then trains the above neural network model based on the data in the database until the sideslip angle estimated by the neural network model meets the accuracy requirements.

[0084] In this embodiment, the neural network model can be trained based on real vehicle data, so that the trained neural network model has a higher matching degree with the real vehicle and can obtain a more accurate sideslip angle.

[0085] Such as Figure 3 shown, is a schematic flowchart of an embodiment of the method for estimating the sideslip angle of a vehicle according to the present invention. Figure 3 It includes steps S30 and S32 similar to those in FIG. 1, which will not be elaborated here. Figure 3 The difference from FIG. 1 is that when the first yaw rate is valid, not only the first sideslip angle is calculated based on the vehicle dynamics model, but also the neural network model is used to calculate the second sideslip angle (step S34), and the first and second sideslip angles are fused to obtain the final sideslip angle (S36). Although this method will increase the computational complexity, it helps to improve the accuracy of the final sideslip angle. Among them, the fusion method of the first and second sideslip angles can adopt the method of taking the average value, or the method of taking the average value based on weights, etc.

[0086] In this embodiment, when the first yaw rate is valid, both the vehicle dynamics model and the neural network model are enabled to improve the accuracy of the finally obtained sideslip angle.

[0087] As Figure 4 shown, it is a schematic flowchart of an embodiment of the method for estimating the sideslip angle of a vehicle according to the present invention. Figure 4 It includes steps S40, S42, and S44 Figure 3 similar to those described above, which will not be elaborated here. Different from Figure 3 , before fusing the first and second sideslip angles, first determine whether the error between the first and second sideslip angles is within the allowable range (step S46). If it is within the allowable range, then fuse the first and second sideslip angles (step S48). Otherwise, use the first sideslip angle as the final sideslip angle (step S47), and retrain the neural network model based on the error value between the first and second sideslip angles (step S49).

[0088] In this embodiment, a step of verifying the second sideslip angle is added. When the error between the second sideslip angle and the first sideslip angle exceeds the range, an operation of retraining the neural network model is started, so that the neural network model can be maintained in an accurate state.

[0089] As Figure 6 shown, it is a schematic structural diagram of an embodiment of the device for estimating the sideslip angle of a vehicle according to the present invention, which includes: a signal processing module 60 for identifying whether the first yaw rate from the vehicle yaw rate sensor is valid; a first sideslip angle estimating module 62 for estimating the first sideslip angle based on the first yaw rate and the vehicle dynamics model; a second sideslip angle estimating module 64 for estimating the second sideslip angle based on the trained neural network model, where the input of the neural network model is the first signal and the vehicle speed, and the output is the second sideslip angle, and the first signal includes at least one of wheel speed, acceleration, and steering angle; and a processing module 66 for: when the signal processing module identifies that the first yaw rate is valid, enabling at least the first sideslip angle estimating module, and when the signal processing module identifies that the first yaw rate is invalid, enabling the second sideslip angle estimating module.

[0090] Further, the processing module 66 is specifically configured to: when the signal processing module identifies that the first yaw rate is valid, enable the first and second sideslip angle estimating modules; determine whether the error between the first and second sideslip angles is within the allowable range; if it is within the allowable range, then fuse the first and second sideslip angles; if it is not within the allowable range, then use the first sideslip angle as the final sideslip angle, and control the second sideslip angle estimating module to retrain the neural network model based on the error value between the first and second sideslip angles.

[0091] As Figure 7As shown, it is a schematic structural diagram of an embodiment of the electronic device 7 of the present invention. The electronic device 7 is, for example, a radar, and it includes: a processor 70; and a memory 72 for storing executable instructions of the processor. Wherein, the processor is configured to execute the executable instructions to implement the method of the present invention.

[0092] In addition, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. The computer program includes executable instructions, and when the executable instructions are executed by a processor, the method of the embodiment of the present invention is implemented.

[0093] The descriptions of the above storage medium and device embodiments are similar to the descriptions of the above method embodiments, and have beneficial effects similar to those of the method embodiments. For the technical details not disclosed in the storage medium and device embodiments of the present application, please refer to the descriptions of the method embodiments of the present application for understanding.

[0094] The above processor may be at least one of an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, a microprocessor, etc. It can be understood that the electronic device implementing the above processor function may also be others, and the embodiments of the present application do not make specific limitations.

[0095] The above computer storage medium / memory can be a read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM), etc.; it can also be various terminals including one or any combination of the above memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0096] It should be noted that the above description is only an example and not a limitation of the present invention. In other embodiments of the present invention, the method may have more, fewer, or different steps, and the relationships such as the order, inclusion, and function between the steps may be different from those described and illustrated. For example, usually multiple steps can be combined into a single step, and a single step can also be split into multiple steps. For those of ordinary skill in the art, without creative efforts, the sequence changes of the steps are also within the protection scope of the present invention.

[0097] The technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.), or a processor, or a microcontroller to execute all or part of the steps of the methods described in various embodiments of the present invention.

[0098] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments.

[0099] Although the present invention has been disclosed above in its preferred embodiments, the present invention is not limited thereto. Any person skilled in the art, without departing from the spirit and scope of the present invention, makes various changes and modifications, which should be included within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the scope defined by the claims.

Claims

1. A method for estimating the sideslip angle of a vehicle, which is used for a radar, characterized in that, The method includes: Identifying whether the first yaw rate from the vehicle yaw angle sensor is valid; When the first yaw rate is valid, calculating a first sideslip angle according to the first yaw rate and the vehicle dynamics model; and When the first yaw rate is invalid, estimating a second sideslip angle of the vehicle based on the trained neural network model; Wherein, the input of the neural network model is a first signal and the vehicle speed, and the output is the second sideslip angle. The first signal includes at least one of wheel speed, acceleration, and steering angle. Wherein, the neural network method can directly estimate the sideslip angle based on the wheel speed, acceleration, or steering angle, without converting the wheel speed, acceleration, or steering angle into a yaw rate and then calculating the sideslip angle based on the yaw rate; The method further includes: When the first yaw rate is valid, calculating a third sideslip angle based on the neural network model; Judging whether the error between the first and third sideslip angles is within the allowable range; If it is within the allowable range, fusing the first and third sideslip angles to generate a final sideslip angle; If it is not within the allowable range, using the first sideslip angle as the final sideslip angle, and retraining the neural network model based on the error value between the first and third sideslip angles.

2. The vehicle sideslip angle estimation method according to claim 1, characterized in that, Training the neural network model includes: training the neural network model based on the first signal, the vehicle speed, and the first sideslip angle.

3. The vehicle sideslip angle estimation method according to claim 1, wherein The step of calculating the first sideslip angle according to the first yaw rate and the vehicle dynamics model includes: Calculating at least one second yaw rate based on the first signal; Using a Kalman filter to fuse the first and at least one second yaw rates to obtain a third yaw rate; and Calculating the first sideslip angle based on the third yaw rate and the vehicle dynamics model.

4. The vehicle sideslip angle estimation method according to claim 1, characterized in that The vehicle dynamics model is: where β is the side slip angle, is the yaw rate, m is the vehicle mass, l is the wheelbase of the vehicle, lr is the product of the rear axle load ratio and the wheelbase, lf is the product of the front axle load ratio and the wheelbase, v is the vehicle speed, and Ch is a constant.

5. The vehicle sideslip angle estimation method according to claim 1, wherein The situation where the yaw rate is invalid includes: unable to obtain the yaw rate, or the obtained yaw rate is not within the valid range.

6. A vehicle sideslip angle estimation device for use in a radar, characterized in that, Including: A signal processing module for identifying whether the first yaw rate from the vehicle yaw angle sensor is valid; A first sideslip angle estimation module for estimating the first sideslip angle based on the first yaw rate and the vehicle dynamics model; A second sideslip angle estimation module for estimating the second sideslip angle based on the trained neural network model. Wherein, the input of the neural network model is a first signal and the vehicle speed, and the output is the second sideslip angle. The first signal includes at least one of wheel speed, acceleration, and steering angle. Wherein, the neural network method can directly estimate the sideslip angle based on the wheel speed, acceleration, or steering angle, without converting the wheel speed, acceleration, or steering angle into a yaw rate and then calculating the sideslip angle based on the yaw rate; and A processing module for enabling the second sideslip angle estimation module when the signal processing module identifies that the first yaw rate is invalid, and for: Enabling the first and second sideslip angle estimation modules when the signal processing module identifies that the first yaw rate is valid; Judging whether the error between the first and second sideslip angles is within the allowable range; If it is within the allowable range, fusing the first and second sideslip angles; If it is not within the allowed range, the first sideslip angle is used as the final sideslip angle, and the second sideslip angle estimation module is controlled to retrain the neural network model based on the error value between the first and second sideslip angles.

7. An electronic device, characterized in that, Comprising: A processor; And A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the executable instructions to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, on which a computer program is stored, the computer program comprising executable instructions, which when executed by a processor, implement the method according to any one of claims 1 to 5.

Images