KR102307076B1 - Vehicle Sideslip Angle Estimation Method and Apparatus Using an Integrated Deep Ensemble-Kalman Filter - Google Patents

Abstract

A method and apparatus for estimating a vehicle side slip angle in an integrated deep ensemble and Kalman filter are presented. An apparatus for estimating a side slip angle of a vehicle according to an embodiment includes: a sensor information acquisition unit configured to acquire sensor information from a vehicle; a deep ensemble-based artificial neural network for estimating a predicted value by receiving the sensor information obtained from the sensor information acquisition unit; and a model-based observer that considers the predicted value estimated in the deep ensemble-based artificial neural network as sensor information obtained from a virtual sensor, receives the predicted value and estimates a sideslip angle value. can

Description

Vehicle Sideslip Angle Estimation Method and Apparatus Using an Integrated Deep Ensemble-Kalman Filter

The following embodiments relate to a vehicle side slip angle estimation technique, and more particularly, to a vehicle side slip angle estimation method and apparatus in which a deep ensemble and a Kalman filter are integrated.

With the development of the automobile industry, various active safety systems are being developed as vehicle technology develops. At this time, it is very important to know the sideslip angle to keep the vehicle's stability.

As existing technologies, there are many methods of estimating the side slip angle using a Kalman filter based mainly on a vehicle model. In this case, extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) methods are often used to consider the nonlinearity of the system.

Recently, there have been many studies using artificial neural networks. There are various approaches to solving this problem through various networks, each showing the result of estimating the side slip angle with some degree of success.

1A is a diagram illustrating a vehicle model used in an existing model-based observer.

As shown in FIG. 1A , in the case of a model-based observer in the prior art, there is a problem in that it is sensitive to the uncertainty of the model used. First, in order to consider the nonlinearity of the system, the performance is improved by using a nonlinear Kalman filter rather than a linear Kalman filter, but when model-related values such as tire cornering stiffness become uncertain, the prediction performance deteriorates.

1B is a diagram illustrating an existing artificial neural network-based network model.

As shown in FIG. 1B , there are a number of techniques using artificial neural networks, but such a machine learning-based method has a problem in that it is difficult to generalize the problem. For example, if the training dataset used to train the artificial neural network and the test dataset used to validate the trained model are not similar, there is a problem in that it is difficult to obtain good estimation results.

Korea Patent Registration No. 10-1208369 relates to such a vehicle path prediction and a method thereof, by detecting the speed, steering angle, and side slip angle of a vehicle while the vehicle is driving, and comparing the detected side slip angle with a preset reference angle of the vehicle. Describes a technique for a device for predicting a path.

Korean Patent No. 10-1208369

The embodiments describe a method and apparatus for estimating a vehicle side slip angle using a deep ensemble and a Kalman filter integrated, and not only estimating a predicted value using a deep ensemble-based artificial neural network, but also estimating an uncertainty value of the predicted value It is to provide a vehicle side slip angle estimation method and apparatus that integrates a deep ensemble and a Kalman filter that can check how reliable the predicted value is.

In addition, in the embodiments, the predicted value and uncertainty value resulting from the deep ensemble-based artificial neural network are regarded as values obtained from a new virtual sensor and input to the model-based observer, so that the value is calculated according to the degree of uncertainty of the prediction value at every instant. It is to provide a vehicle side slip angle estimation method and apparatus that integrates deep ensemble and Kalman filter that can automatically determine how reliable and how much to use in a model-based observer.

An apparatus for estimating a side slip angle of a vehicle according to an embodiment includes: a sensor information acquisition unit configured to acquire sensor information from a vehicle; a deep ensemble-based artificial neural network for estimating a predicted value by receiving the sensor information obtained from the sensor information acquisition unit; and a model-based observer that considers the predicted value estimated in the deep ensemble-based artificial neural network as sensor information obtained from a virtual sensor, receives the predicted value and estimates a sideslip angle value. can

According to another embodiment, the apparatus may further include an artificial neural network learning unit configured to learn a deep ensemble-based artificial neural network through the acquired sensor information.

According to another embodiment, the deep ensemble-based neural network estimates the predicted value by inputting the sensor information into the learned deep ensemble-based neural network, estimates the uncertainty value of the predicted value, and the model-based observer considers the predicted value and the uncertainty value as sensor information acquired from a virtual sensor, and inputs the predicted value, the uncertainty value, and the sensor information acquired from the sensor information acquisition unit to a model-based observer to side-slip Angle values can be estimated.

According to another embodiment, the model-based observer may automatically determine how to trust and use the prediction value according to the uncertainty value of the prediction value.

According to another embodiment, the model-based observer may estimate the side slip angle using the model-based observer using a vehicle model-based Kalman filter method.

According to another embodiment, the model-based observer may be a model-based observer of an Extended Kalman Filter (EKF) or an Unscented Kalman Filter (UKF) type.

According to another embodiment, the active safety system may further include an active safety system using the finally estimated side slip angle value in a vehicle active safety system.

A vehicle side slip angle estimation method according to an embodiment includes: acquiring sensor information from a vehicle; estimating a predicted value by inputting the acquired sensor information into a trained deep ensemble-based artificial neural network; and considering the predicted value as sensor information obtained from a virtual sensor, and estimating a sideslip angle value by inputting the predicted value into a model-based observer.

According to another embodiment, the method may further include learning the deep ensemble-based artificial neural network through the acquired sensor information.

According to another embodiment, the step of estimating the predicted value by inputting the sensor information into the learned deep ensemble-based artificial neural network includes inputting the sensor information into the learned deep ensemble-based artificial neural network to estimate the predicted value, In the step of estimating the uncertainty value of the predicted value, and the step of estimating the side slip angle value by inputting the predicted value into a model-based observer, the predicted value and the uncertainty value are regarded as sensor information obtained from a virtual sensor and estimating a side slip angle value by inputting the prediction value and the uncertainty value into a model-based observer.

According to another embodiment, the step of estimating the side slip angle value by inputting the predicted value to a model-based observer includes the sensor information obtained from the vehicle, the predicted value output from the deep ensemble-based artificial neural network, and the The value of the side slip angle may be estimated by receiving the uncertainty value from the model-based observer.

According to another embodiment, the step of estimating the side slip angle value by inputting the predicted value into a model-based observer may include determining, by the model-based observer, how much to trust and use the predicted value according to the uncertainty value of the predicted value. can be determined automatically.

According to another embodiment, the step of estimating the side slip angle value by inputting the predicted value to a model-based observer may include: using the model-based observer of a vehicle model-based Kalman filter method can be estimated.

According to another embodiment, the step of estimating the side slip angle value by inputting the predicted value to a model-based observer may include, in the model-based observer, an Extended Kalman Filter (EKF) or an Unscented Kalman Filter (Unscented Kalman Filter). Filter, UKF) method may be a model-based observer.

According to another embodiment, the method may further include using the finally estimated side slip angle value in a vehicle active safety system.

According to embodiments, a deep ensemble and a Kalman filter that can check how reliable a predicted value is by not only estimating the predicted value using the deep ensemble-based artificial neural network but also estimating the uncertainty value of the predicted value It is possible to provide a method and apparatus for estimating a vehicle side slip angle in an integrated manner.

In addition, according to embodiments, the prediction value and uncertainty value resulting from the deep ensemble-based artificial neural network are regarded as values obtained from a new virtual sensor and input to the model-based observer, It is possible to provide a vehicle side slip angle estimation method and apparatus that integrates a deep ensemble and Kalman filter that can automatically determine how much to trust and use a value in a model-based observer.

1A is a diagram illustrating a vehicle model used in an existing model-based observer.
1B is a diagram illustrating an existing artificial neural network-based network model.
2 is a flowchart illustrating a vehicle side slip angle estimation method according to an exemplary embodiment.
3 is a diagram schematically illustrating an apparatus for estimating a vehicle side slip angle according to an exemplary embodiment.
4 is a diagram for explaining the structure of a deep ensemble-based artificial neural network according to an embodiment.
5 is a diagram illustrating a vehicle side slip angle estimation result using a deep ensemble-based artificial neural network according to an embodiment.
6 is a diagram illustrating a vehicle side slip angle estimation result using a deep ensemble-based artificial neural network and a model-based observer according to an embodiment.

Hereinafter, embodiments will be described with reference to the accompanying drawings. However, the described embodiments may be modified in various other forms, and the scope of the present invention is not limited by the embodiments described below. In addition, various embodiments are provided in order to more completely explain the present invention to those of ordinary skill in the art. The shapes and sizes of elements in the drawings may be exaggerated for clearer description.

The following embodiments relate to techniques for estimating state variables that are important for an active safety system, and provide techniques for estimating a vehicle side slip angle using a deep ensemble and a Kalman filter integrated method and apparatus. We propose a system for estimating in an integrated way by introducing a deep ensemble method to compensate for the shortcomings of the existing model-based Kalman filter-based prediction and simple artificial neural network-based estimation methods, and to take advantage of each advantage.

The present embodiments may be used in various vehicle active safety systems. It is essential to maintain lateral stability for the safe driving of a vehicle, and the side slip angle becomes an important criterion in this case. Therefore, it is very important to estimate this value well.

2 is a flowchart illustrating a vehicle side slip angle estimation method according to an exemplary embodiment.

Referring to FIG. 2 , in the method for estimating a vehicle side slip angle according to an embodiment, the step of acquiring sensor information from a vehicle 210 , and inputting the acquired sensor information into a learned deep ensemble-based artificial neural network to estimate a predicted value estimating a sideslip angle value by considering the predicted value as sensor information obtained from a virtual sensor (230), and inputting the predicted value into a model-based observer (240). have.

In addition, the method may further include the step 220 of learning the deep ensemble-based artificial neural network through the acquired sensor information.

The method may further include using the finally estimated side slip angle value in the vehicle active safety system.

Embodiments can utilize all advantages of each by mixing the artificial neural network technique, which has recently become a hot topic, and the existing model-based observer method. First, when learning through an artificial neural network is performed, not only the predicted value is obtained using the deep ensemble method, but also the uncertainty value of the value can be obtained. This method is different from the prior art in which only predicted values are estimated using artificial neural networks, and it is possible to know how reliable the predicted values are.

In addition, the predicted value and uncertainty value resulting from the deep ensemble-based artificial neural network can be considered as values obtained from a new virtual sensor. A new approach can be proposed that utilizes this value in the existing model-based observer. In this case, the uncertainty of the predicted value from the artificial neural network can be used for the measurement covariance matrix of the model-based observer (nonlinear Kalman filter). In this way, the model-based observer can automatically determine how much to trust and use the predicted value at every instant according to the degree of uncertainty.

Hereinafter, a method for estimating a vehicle side slip angle according to an exemplary embodiment will be described in more detail.

The vehicle side slip angle estimation method according to the embodiment may be described in more detail by taking the vehicle side slip angle estimation apparatus according to the embodiment.

3 is a diagram schematically illustrating an apparatus for estimating a vehicle side slip angle according to an exemplary embodiment.

3, the vehicle side slip angle estimation apparatus 300 according to an embodiment may include a sensor information acquisition unit 310, a deep ensemble-based artificial neural network 320, and a model-based observer 330. , may be made to further include an artificial neural network learning unit and an active safety system according to an embodiment. The vehicle side slip angle estimation apparatus 300 according to this embodiment is made in a way that integrates a deep ensemble and a Kalman filter, and when sensor data passes through the learned deep ensemble-based artificial neural network 320, the prediction value and the uncertainty value can be printed together. The output prediction value and uncertainty value may be regarded as information obtained from the virtual sensor and used in the model-based observer 330 . Through this, the model-based observer 330 at each moment may finally estimate the side slip angle value in consideration of the uncertainty value transmitted from the artificial neural network.

In step 210 , the sensor information acquisition unit 310 may acquire sensor information from the vehicle. For example, the sensor information acquisition unit 310 may obtain a velocity, yawrate, longitudinal acceleration, lateral acceleration value, etc. from sensors such as velocity, yawrate, longitudinal acceleration, and lateral acceleration configured in the vehicle.

The deep ensemble-based artificial neural network 320 is a deep learning model, and may receive sensor information obtained from the sensor information acquisition unit 310 and estimate a predicted value. In particular, the deep ensemble-based neural network 320 may input sensor information into the learned deep ensemble-based neural network 320 to estimate a predicted value and at the same time estimate an uncertainty value of the predicted value. In this way, by estimating the uncertainty value of the prediction value together, it is possible to know how reliable the estimated prediction value is.

The deep ensemble-based artificial neural network 320 may estimate a prediction value and an uncertainty value using a deep ensemble method when learning through the artificial neural network is performed.

On the other hand, according to an embodiment, the deep ensemble-based artificial neural network 320 through the acquired sensor information may further include an artificial neural network learning unit for learning. The artificial neural network learning unit may be included in the deep ensemble-based artificial neural network 320 .

The model-based observer 330 may regard the predicted value estimated in the deep ensemble-based artificial neural network as sensor information obtained from a virtual sensor, and receive the predicted value to estimate a sideslip angle value. In particular, the model-based observer 330 regards not only the predicted value but also the uncertainty value as sensor information obtained from a virtual sensor, and uses the predicted value and the uncertainty value and the sensor information obtained from the sensor information acquisition unit 310 as the model-based observer. By inputting in 330, the side slip angle value can be estimated. The model-based observer 330 may automatically determine how much to trust and use the prediction value according to the uncertainty value of the prediction value.

The model-based observer 330 may estimate the side slip angle using the model-based observer 330 of the Kalman filter method based on the vehicle model. In particular, the model-based observer 330 may be a model-based observer 330 of an Extended Kalman Filter (EKF) or an Unscented Kalman Filter (UKF) type.

Hereinafter, the model-based observer (EKF, UKF) 330 will be described in more detail with one example.

과

로 나타낼 수 있다. 그리고 이 값들을 새로운 가상의 센서로부터 얻은 측정(measurement)으로 간주하여 칼만필터에 이용할 수 있다. A new side-slip angle estimation algorithm can be proposed by integrating the method using the model-based observer (EKF, UKF) 330, which is commonly used in estimating the side slip angle, and the information obtained from the deep ensemble-based artificial neural network 320. have. The prediction value and uncertainty value obtained from the deep ensemble-based artificial neural network 320 are

class

can be expressed as And these values can be regarded as measurements obtained from a new virtual sensor and used in the Kalman filter.

이 추가되어 측정 벡터(measurement vector)

를

로 표현할 수 있다. Here, as the measurement of the Kalman filter, the predicted value, which is a new measurement, is the sensor information that can be easily obtained from the current commercial vehicle: speed, yawrate, longitudinal acceleration, and lateral acceleration.

is added to the measurement vector

cast

can be expressed as

는

로 표현되어, 가상의 센서로부터 얻은 불확실도 값

에 따라 적응적으로(adaptive) 변하는 행렬(matrix)이 될 수 있다. In addition, the predicted value is a covariance matrix (measurement noise covariance matrix)

Is

expressed as , the uncertainty value obtained from the virtual sensor

It may be a matrix that changes adaptively according to

이 작을 때는 딥러닝 모델로부터 구한 예측 값

를 많이 신뢰하고, 불확실도 값

이 커질 때는 예측 값

을 덜 신뢰하고 다른 센서 측정(measurement)을 더 믿는 방식으로 최종 사이드슬립 앵글 값을 추정할 수 있다.Therefore, the uncertainty value

When this is small, the predicted value obtained from the deep learning model

trust a lot, and the uncertainty value

When this increases, the predicted value

We can estimate the final sideslip angle value in a way that is less reliable and more reliable in other sensor measurements.

An active safety system that uses the finally estimated side slip angle value in the vehicle active safety system may be further included.

According to embodiments, it is possible to design a side slip angle estimation method and apparatus using the deep ensemble-based artificial neural network 320 and the model-based observer 330 by mixing advantages of existing methods. Through this, it can be usefully used for active safety systems by estimating important state variables related to lateral safety.

4 is a diagram for explaining the structure of a deep ensemble-based artificial neural network according to an embodiment.

Referring to FIG. 4 , the structure of the deep ensemble-based artificial neural network 400 of the vehicle side slip angle estimation apparatus according to the embodiment described with reference to FIG. 3 is shown.

만을 도출하는 것을 발전시켜, 딥 앙상블 기반 인공신경망(400)은 결과 값

뿐만 아니라 그 결과 값에 대한 불확실도 값을

의 형태로 함께 도출할 수 있다. 따라서 딥 앙상블 기반 인공신경망(400)의 현재 딥러닝 모델이 출력한

라는 값이 얼마나 믿을만한지를 함께 알려주는 것이다. 하나의 예를 들어 보다 상세히 설명한다. 여기서 사용되는 데이터셋(401)은 샘플링을 통해 샘플된 데이터셋(410)을 각 네트워크 모델(420)에 입력하여 학습 및 테스트할 수 있다. Conventionally, when solving deep learning-based regression and classification problems, one result value

By developing the derivation of only the deep ensemble-based artificial neural network 400

as well as the uncertainty value for the resulting value.

can be derived together in the form of Therefore, the current deep learning model of the deep ensemble-based artificial neural network 400 outputs

It also shows how reliable the value is. One example will be described in more detail. The dataset 401 used here can be trained and tested by inputting the sampled dataset 410 to each network model 420 through sampling.

과 불확실도 값

을 출력할 수 있다.It is assumed that a total of five network models 420 are used when designing and learning the deep ensemble-based artificial neural network (network) 400 . At this time, when training is finished with a training dataset and the network model 420 is verified with a test dataset, a total of 5 network models 420 are predicted values as follows, respectively.

and uncertainty values

can be printed out.

,

Network model 1:

,

,

Network model 2:

,

,

Network model 3:

,

,

Network model 4:

,

,

Network model 5:

,

The predicted values and uncertainty values 402 of the entire deep ensemble-based artificial neural network 400 may be finally obtained by mixing the predicted values and the uncertainty values of each of the network models 420 derived in this way. In this case, the predicted value and the uncertainty value 402 of the entire deep ensemble-based artificial neural network 400 may be calculated using the following equation.

[Equation 1]

[Equation 2]

과 root를 씌운

이 최종적으로 구해지는 예측 값과 표준편차 형태의 불확실도 값이 된다.calculated like this

and rooted

This finally becomes the predicted value and the uncertainty value in the form of standard deviation.

In this way, learning of the deep ensemble-based artificial neural network 400 is performed through sensor information that can be easily obtained from commercialized vehicles, and prediction values and uncertainty values are estimated from the deep ensemble-based artificial neural network 400 together, The side slip angle value can be obtained by assuming a sensor of Finally, the estimated side slip angle value can be used in the vehicle's active safety system.

MATLAB/Simulink and Carsim were used for verification of this example. Using Carsim, datasets necessary for artificial neural network learning were collected, and deep ensemble-based artificial neural network network design and learning was carried out using python. In MATLAB/Simulink, the algorithm was designed to predict the final side slip angle by using this result as a model-based observer.

5 is a diagram illustrating a vehicle side slip angle estimation result using a deep ensemble-based artificial neural network according to an embodiment.

Referring to FIG. 5 , the results of the side slip angle values obtained using the vehicle side slip angle estimation method through the deep ensemble-based artificial neural network are shown, the dotted line (DNN) is the predicted value, and the solid line is the uncertainty value including the uncertainty. .

6 is a diagram illustrating a vehicle side slip angle estimation result using a deep ensemble-based artificial neural network and a model-based observer according to an embodiment.

Referring to FIG. 6 , the results of side slip angle values obtained through two existing model-based observers (EKF and UKF), an EKF-based model-based observer (a) and a UKF-based model-based observer (b), are shown.

In addition, the results obtained through the two existing model-based observers (EKF, UKF) and the method of mixing the vehicle side slip angle estimation method that integrates the deep ensemble and Kalman filter proposed in this example are shown together. Here, the real value represents a real value obtained from Carsim.

[Table 1]

Table 1 shows a comparison of the root mean square error (RMSE) and the mean absolute error (MAE) to verify the results. As the experimental scenario, it is assumed that the vehicle speed is accelerated from 70kph to 120kph in the middle with sine wave steering in two friction coefficient situations consisting of dry asphalt and slippery road.

Looking at the results, it can be seen that the performance is improved through the method according to the present embodiment in all situations. That is, in the case of EKF + DNN and UKF + DNN, it can be seen that the performance is improved compared to the existing EKF and UKF methods.

The embodiments may be applied to a vehicle active safety system. In order to apply the system, vehicle driving information is required, and lateral acceleration sensors and yawrate sensors, which are currently generally installed in commercial vehicles, can be used.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. may be embodied in The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible from the above description by those skilled in the art. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (15)

a sensor information acquisition unit for acquiring sensor information from a vehicle;
a deep ensemble-based artificial neural network for estimating a predicted value by receiving the sensor information obtained from the sensor information acquisition unit; and
A model-based observer that considers the predicted value estimated in the deep ensemble-based artificial neural network as sensor information acquired from a virtual sensor, and receives the predicted value as input to estimate a sideslip angle value
including,
The deep ensemble-based artificial neural network,
input the sensor information into a trained deep ensemble-based artificial neural network to estimate the predicted value, estimate the uncertainty value of the predicted value,
The model-based observer,
The predicted value and the uncertainty value are regarded as sensor information obtained from a virtual sensor, and the predicted value, the uncertainty value, and the sensor information obtained from the sensor information acquisition unit are input to a model-based observer to obtain a side slip angle value. to estimate
A vehicle side slip angle estimation device, characterized in that. According to claim 1,
An artificial neural network learning unit that conducts learning of a deep ensemble-based artificial neural network through the acquired sensor information
Further comprising a vehicle side slip angle estimation device. delete According to claim 1,
The model-based observer,
automatically determining how much to trust and use the prediction value according to the uncertainty value of the prediction value.
A vehicle side slip angle estimation device, characterized in that. According to claim 1,
The model-based observer,
Estimating the side slip angle using the model-based observer of a vehicle model-based Kalman filter method
A vehicle side slip angle estimation device, characterized in that. 6. The method of claim 5,
The model-based observer,
A model-based observer of the Extended Kalman Filter (EKF) or Unscented Kalman Filter (UKF) method.
A vehicle side slip angle estimation device, characterized in that. According to claim 1,
An active safety system that uses the finally estimated side slip angle value in a vehicle active safety system
Further comprising a vehicle side slip angle estimation device. obtaining sensor information from the vehicle;
estimating a predicted value by inputting the acquired sensor information into a trained deep ensemble-based artificial neural network; and
estimating a sideslip angle value by considering the predicted value as sensor information obtained from a virtual sensor, and inputting the predicted value into a model-based observer
including,
The step of estimating the predicted value by inputting the sensor information into the learned deep ensemble-based artificial neural network,
estimating the predicted value by inputting the sensor information into a learned deep ensemble-based artificial neural network, and estimating the uncertainty value of the predicted value,
The step of estimating the side slip angle value by inputting the predicted value into a model-based observer,
estimating a side slip angle value by considering the predicted value and the uncertainty value as sensor information obtained from a virtual sensor, and inputting the predicted value and the uncertainty value into a model-based observer
A method for estimating a vehicle side slip angle. 9. The method of claim 8,
Learning of the deep ensemble-based artificial neural network through the acquired sensor information
A method for estimating a vehicle side slip angle further comprising: delete 9. The method of claim 8,
The step of estimating the side slip angle value by inputting the predicted value into a model-based observer,
estimating the side slip angle value by receiving the sensor information acquired from the vehicle, the predicted value output from the deep ensemble-based artificial neural network, and the uncertainty value from the model-based observer
A method for estimating a vehicle side slip angle. 9. The method of claim 8,
The step of estimating the side slip angle value by inputting the predicted value into a model-based observer,
and the model-based observer automatically determines how much to trust and use the predicted value according to the uncertainty value of the predicted value.
A method for estimating a vehicle side slip angle. 9. The method of claim 8,
The step of estimating the side slip angle value by inputting the predicted value into a model-based observer,
Estimating the side slip angle using the model-based observer of a vehicle model-based Kalman filter method
A method for estimating a vehicle side slip angle. 14. The method of claim 13,
The step of estimating the side slip angle value by inputting the predicted value into a model-based observer,
The model-based observer is a model-based observer of an Extended Kalman Filter (EKF) or Unscented Kalman Filter (UKF) method.
A method for estimating a vehicle side slip angle. 9. The method of claim 8,
using the finally estimated side slip angle value in a vehicle active safety system
A method for estimating a vehicle side slip angle further comprising:

Images