KR102287546B1 - System and Method for Vehicle future trajectory prediction using E-Kalman Filter with IMM in the Soft-Defined Internet of Vehicles - Google Patents

Abstract

According to an embodiment of the present invention, the function of selecting the correct network slice instance that appropriately meets the request of the user terminal is implemented in the 5G architecture (23.501 3GGP technical specification), and in particular, the current state of the network is known by communicating with the VNF orchestration platform. To provide a network slice selection function for identifying and selecting a network slice instance for interaction with a Mobility Management Entity (MME)/Access Mobility Function (AMF).

Description

A vehicle trajectory prediction system using an extended Kalman filter in vehicle software-defined networking, a method for the same, and a computer-readable recording medium in which a program performing the method is recorded the Soft-Defined Internet of Vehicles}

The present invention relates to a technology capable of providing stabilization to future vehicle networking by calculating the positions of vehicles on a road in a certain area in an edge cloud.

Vehicle group driving consists of a top-level vehicle driven directly by the driver and a number of sub-vehicles that follow. In this case, the subordinate vehicles may autonomously drive without driver intervention. Such vehicle group driving is an intermediate step towards fully autonomous driving, and technology development is in progress in developed countries such as Europe.

The SARTRE (Safe Road Trains for the Environment) project was researched as part of EC FP7 and developed a system for safely and conveniently performing vehicle platoon or vehicle group driving in general public highways.

The system provides a safe group driving service while interoperating with other traffic on the highway. In particular, the system provides autonomous driving for subordinate vehicles, with the exception of top-level vehicles driven by individual drivers.

Software Defined Networking (SDN) is a new network structure or paradigm, and separates the network into a control plane and a transmission plane. One of the technologies that implemented this is OpenFlow. The Open Networking Foundation (ONF), which develops OpenFlow-related standards, was the most influential until recently, but recently, the European Telecommunications Standards Institute (ETSI), Internet Engineering Task Force (IETF), etc. . Recently, network function virtualization technology is bringing about a new change in the overall network architecture, which used to be hardware-oriented. Network Function Virtualization (NFV), that is, NFV, separates hardware and software, which are components of a network, and virtualizes the functions of physical network facilities, such as a VM (Virtual Machine) server, hardware equipped with a general-purpose processor, and cloud. Ding is a concept that runs on a computer. According to this, various network devices such as routers, load balancers, firewalls, intrusion prevention, and virtual private networks can be implemented as software in general servers, thereby freeing from vendor dependence in network configuration. This is because expensive dedicated equipment can be replaced with general-purpose hardware and dedicated software. Furthermore, it has the advantage of being able to quickly respond to changes in traffic as well as reducing equipment operating costs.

On the other hand, Software Defined Networking (SDN), that is, SDN technology, is characterized by separating the functions of a complex control plane from the data plane. According to this, the complex functions of the control plane are processed by software, and the data plane performs only simple functions instructed by the control plane, such as forwarding, ignoring, and changing network packets. By applying these technologies, new network functions can be developed in software without complex hardware restrictions, and at the same time, various attempts that were not possible in the previous network structure can be made.

Although the NFV and SDN are separate technologies, they can complement each other. This is because various network functions implemented in software by NFV can be efficiently controlled using SDN.

SDN is based on two basic principles.

First, SDN must do Software Defined Forwarding. Software-defined forwarding means that the data forwarding function handled by hardware in the switch/router must be controlled through an open interface and software.

Second, SDN aims to be a Global Management Abstraction. SDN enables more advanced network management through abstraction.

For example, this abstraction could include the ability to control network elements and react in response to events (such as topology changes or new flow inputs) based on the state of the entire network.

As interest in autonomous vehicles increases, interest in vehicle communication is also growing naturally. Stability is also a big concern in vehicle networks where various types of data must be transmitted, but the connection of vehicles on the road is due to its mobility, and although research on inter-vehicle communication has been conducted for a long time, the communication stability needs to be further improved. .

Predicting the trajectory of a vehicle is not deterministic because the movement of the vehicle depends entirely on the habits and judgment of the vehicle driver.

Furthermore, in many cases, vehicle trajectory prediction has been limited to models that predict well when the vehicle is traveling at a constant speed and constant acceleration. As a result, V2V (V2V, Vehicle to Vehicle, communication between vehicles) and V2I (V2I, Vehicle to Infrastructure, communication between vehicle and roadside base station) were rarely considered as a problem that resulted in communication failure.

Korean Patent Registration No. 10-1472090 Korean Patent Publication No. 10-2018-0021650

The present invention has been devised to solve the above problem, and in an embodiment of the present invention, an Extended Kalman Filter (EKF; Extended Kalman Filter) that integrates Interacting Multiple Model (IMM) is used to It is possible to provide a method of predicting the vehicle position, and through this, Edge Cloud can provide a system that can provide stability to the networking of vehicles in the future by calculating the positions of vehicles on the road in a certain area.

In addition, in the present invention, since the navigation map has most of the information on the road, information on the number of lanes on the road can be known, so it is possible to correlate the vehicle speed with the vehicle speed, thereby suggesting a vehicle turn model.

In order to solve the above problems, in an embodiment of the present invention, in a system for tracking the location of a vehicle having a device capable of SDN (Software Defined Networking) under an edge crowd, the tracking of the location of the vehicle SDN control device installed in a vehicle that applies edge crowd to a specific target area; an edge controller that receives driving information including vehicle speed, position, and acceleration generated in the vehicle from the SDN control device; The edge controller, based on the driving information provided from the driving means, calculates and accumulates a probability density function by an IMM (Interacting Multiple Model; Interacting Multiple Model Program) unit to calculate the expected position of the vehicle by Extended Kalman. It is possible to provide a vehicle trajectory prediction system using an extended Kalman filter in vehicle software-defined networking including a filter (Extended Kalman Filter; EKF) module.

According to an embodiment of the present invention, it is possible to provide a method for predicting the location of a vehicle on a road using an Extended Kalman Filter (EKF; Extended Kalman Filter) that integrates Interacting Multiple Model (IMM; Interacting Multiple Model Program), Through this, the edge cloud calculates the positions of vehicles on the road in a certain area, thereby providing stabilization to future vehicle networking.

In addition, in the present invention, since the navigation map has most of the information on the road, information on the number of lanes on the road can be known, so the turn model can be proposed by correlating it with the vehicle speed.

The most unstable part of vehicle communication is due to the situation in which the communication link between vehicles needs to be changed frequently due to the mobility of the vehicle. It will be possible.

1 is a block diagram illustrating a vehicle trajectory prediction system using an extended Kalman filter in vehicle software-defined networking implemented according to an embodiment of the present invention, and FIG. 2 is a configuration centered on an edge controller among the components of FIG. It is a conceptual diagram showing together.
3 is an applied conceptual diagram of implementing a vehicle trajectory prediction system using an extended Kalman filter in vehicle software defined networking in an embodiment of the present invention.

Advantages and features of the present invention, and methods for achieving them, will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various different forms.

In the present specification, the present embodiment is provided to complete the disclosure of the present invention, and to fully inform those of ordinary skill in the art to which the present invention pertains to the scope of the present invention. And the invention is only defined by the scope of the claims. Accordingly, in some embodiments, well-known components, well-known operations, and well-known techniques have not been specifically described to avoid obscuring the present invention.

The configuration provided in the embodiment of the present invention proposes a method of predicting a vehicle position on a road using an Extended Kalman Filter (EKF; Extended Kalman Filter) that integrates Interacting Multiple Model (IMM; Interacting Multiple Model Program), By calculating the location of vehicles on the road in a certain area in the edge cloud, it is a gist to implement a method that can provide stability to the networking of vehicles in the future.

FIG. 1 is a block diagram illustrating a vehicle trajectory prediction system (hereinafter, referred to as 'the present invention') using an extended Kalman filter in vehicle software-defined networking implemented according to an embodiment of the present invention, and FIG. 2 is FIG. It is a conceptual diagram showing the configuration centered on the edge controller among the components of .

3 is an applied conceptual diagram of implementing a vehicle trajectory prediction system using an extended Kalman filter in vehicle software defined networking in an embodiment of the present invention.

1 to 3 , the present invention provides a system for tracking the location of a vehicle having a device capable of SDN (Software Defined Networking) under an edge crowd, the tracking target of the location of the vehicle The SDN control device 110, 120, 130 installed in a vehicle that applies the edge crowd to a specific area, and operation information including vehicle speed, position, and acceleration generated in the vehicle is transmitted from the SDN control device. It may be configured to include an edge controller (EC).

In this case, the edge controller EC calculates a probability density function by the IMM (Interacting Multiple Model) unit 210 based on the driving information provided from the SDN control device of the vehicle. and an extended Kalman filter (EKF) module 200 that accumulates and calculates an expected position of the vehicle.

Therefore, in the embodiment in which the present invention is implemented, SDN networking technology is implemented in vehicle communication, and it is premised that communication is possible through this, and since one SDN controller cannot control the entire network, edge cloud for each region When is applied, it is premised on an environment in which information transmission and calculation on roads in the area are possible.

Therefore, it is assumed that if the computing resource in the edge cloud, not the computing resource of the vehicle itself, can continuously calculate the location of the vehicle using the Kalman filter, the SDN controller can perform much more stable communication control.

The least stable part of vehicle communication is due to a situation in which the communication link between vehicles needs to be changed frequently due to the mobility of the vehicle. Beyond that, it becomes controllable so that traffic loss does not occur.

In order to implement this function, as shown in Fig. 2, the edge controller (EC) of the present invention, based on the operation information provided from the operation means, an IMM (Interacting Multiple Model; Interacting Multiple Model program) unit It includes an extended Kalman filter (EKF) module 210 that calculates and accumulates the probability density function by 210 to calculate the expected position of the vehicle, and also provides a predictive model for expected dynamic information. It is configured to include a predictive model providing unit 220 .

In particular, in the predictive model providing unit, five KF (Kalman filter) models are derived and provided in consideration of all possible situations of vehicle movement.

Each of these models is set to fit a specific set of scenarios in which a vehicle can be found: a constant jerk model, a constant acceleration model, a constant speed model, a fixed position model, and a vehicle turning model.

The predictive model provided by the predictive model providing unit 220 may be provided as a total of five models according to the following {Equation 1} to {Equation 5}. (Vehicle position (Xv), vehicle speed (Vv) and distance from the nearest intersection in the direction of vehicle movement (Dv))

{Equation 1: Constant location model (CL)}

(The constant position model (CL) describes the scenario where the vehicle is not moving or the speed is '0'.)

{Equation 2: Constant velocity model (CV)}

(Constant speed model (CV) _{represents the situation of a vehicle when a vehicle with a current position Xv t of the vehicle and a distance DvI t} at the nearest intersection in the vehicle moving direction moves at a constant speed Vvt. ω is the processing noise covariance ( process noise covariance), which is a constant.)

{Equation 3: Constant acceleration model (CA)}

(Constant acceleration model (CA) represents the state of the vehicle when the vehicle moves with a constant acceleration (a). In this equation, the state of the vehicle is considered to be in a moving state in a fluid position, and Δt is the previous period. Therefore, the variable of (t - 1) means the statistics of the previous period, ω is the process noise covariance, which is a constant.)

{Equation 4: Constant Jerk model (constant jerk model; CJ)}

(Constant jerk model (CJ) shows the situation when a vehicle moves with a change in acceleration for a certain period of time at a constant acceleration.)

{Equation 5: Constant vehicle turn model (Vehicle turning model; VT)}

(The vehicle's turning model (VT) tells the vehicle's SDN control whether the vehicle is constantly turning, or two parameters: junction/intersection and lane number (rightmost, left or middle). used to express that you will go straight on the same road.)

That is, if the vehicle is in the largest right lane and the DvIt value is close to '0', the vehicle will turn to the right.

Alternatively, if the vehicle is placed in the left lane and the DvIt value is close to '0', the vehicle will drive to the left. However, vehicles in the middle lane follow a straight path.

The Kalman filter of the present invention operates in a feedback approach, first processing the data at time T, and receiving feedback from the vehicle's SDN controller in terms of GPS measurements including vehicle speed, position and acceleration. A state vector is formed using these parameters, which are decomposed into x and y components, respectively.

In the present invention, to define the state vector for the above-mentioned model, the vehicle position (Xv), the vehicle speed (Vv) and the vehicle position from the nearest intersection in the direction of vehicle movement based on the Global Positioning System (GPS) as shown in Equation 1. Distance (Dv) Three parameters were considered.

{Equation 1}

The three parameters are then decomposed into x and y components, respectively. Therefore, for every Xv in the equation, it is denoted as Xxv and Xyv, respectively.

In the above equation, every parameter has two components, x and y, i.e. position in x and y coordinates, and normal and tangential acceleration. Also, the correction and prediction formula for vehicle position using KF is as follows.

[Vehicle Position Correction Prediction Formula]

H is the Jacobian of the parametric model, P is the prediction error covariance, R is the noise covariance of the model, and K is the Kalman gain. x represents the prediction of the vehicle's state at time k-1, k represents the current time, and A represents the Jacobian's system model for the current state.

In general, since the vehicle has a GIS system such as a navigation map on its own, it is possible to reduce the accuracy of location prediction by recognizing such a road on a curved road, but in an embodiment of the present invention, a formula is presented in consideration of only a straight road. . For the Kalman filter, the predicted covariance P (covariance P) is

(in this case, the vehicle position (Xv), the vehicle speed (Vv), and the distance (Dv) from the nearest intersection in the direction of vehicle movement. The matrix 'P' represents the estimated error covariance, and then ) with 'K' (covariance for estimating the value of Kalman gain) and 'H' (Jacobian matrix). The matrix 'PP is a data set that describes the association in the observation error between all pairs at the vertical level. In our case, the error covariance for all proposed models is estimated by mapping the filter to itself).

After obtaining all possible scenarios of the vehicle, the probability density function (pdf) is computed and the most probable model is selected to predict the vehicle's future location. This is performed by the IMM algorithm that accumulates the probability of occurrence for each model using the Markov model, and the final transition metric is defined as all probabilities.

Through the five prediction models (Kalman model), the IMM unit predicts the next point through the following feedback processor.

[Feedback Processor]

The above process can be provided as a solution driven in the following manner through the system of the present invention.

First, in the method of tracking the location of a vehicle having a device capable of SDN (Software Defined Networking) under the edge cloud, the vehicle's location, speed, Step 1 of transmitting the driving information including the acceleration can be performed.

In this case, in the Extended Kalman Filter (EKF) module 200 in the edge controller, based on the operation information, the probability density is generated by the Interacting Multiple Model (IMM) unit 210. Step 2 of calculating and accumulating the function to calculate the expected position of the vehicle may be performed.

In particular, in the second step, the IMM (Interacting Multiple Model; Interacting Multiple Model Program) unit 210 calculates the probability of occurrence for a predictive model modeling the motion of the vehicle, and applies the calculated probability to the corresponding model. The step of identifying the dominance of vehicle position prediction through

When the IMM unit 210 identifies the dominant model (from among the models according to Equations 1 to 5) through the feedback process, the IMM unit 210 continues to recalculate the probability for each iteration in the entire driving of the vehicle and calculates from the previous iteration. This is performed by weighting a new probability value with respect to the new probability value, and based on the calculated information, the probability of each model is calculated through the state transition matrix according to Equation 7 below. The IMM unit 210 calculates a probability density function (pdf) using a Markov chain model in this process, and then calculates a cumulative probability for each model.

{expression 7}

(CL: constant position model, CV: constant speed model, CA: constant acceleration model, CJ: constant jerk model, VT: vehicle turning model)

For example, the current vehicle location is estimated using a constant location model (CL), and then the CL model is applied again to find a future vehicle location or the probability of applying another model is calculated.

To this end, the IMM unit calculates the probability density function (pdf) using the Markov chain model and then calculates the probability. The most probable model is selected for vehicle position prediction.

3 is a conceptual diagram illustrating the application of the system ( FIGS. 1 and 2 ) according to the present invention.

Referring to FIG. 3, the working state of the present invention is summarized as follows.

In the Soft Definition Internet (SD-IoV) of vehicles moving in a specific area, vehicles on the road explore cellular networks to dynamically transmit information, and RSU (Road Side Unit) and RSU (Road Side Unit) for data communication between vehicles unit) is explored.

In this case, the extended Kalman filter module in the present invention is used for vehicle prediction in the edge controller (EC).

In general, a Kalman filter (KF) provides an efficient recursive method to predict the future state of a vehicle using a set of mathematical equations. A Kalman filter (KF) with a multi-model approach avoids a single model but complex model. The reason why the scenarios are divided into sub-scenarios according to each KF model is because more accurate results are obtained than scenarios with high complexity. Scenarios for such a vehicle are a non-motorized vehicle, a constant acceleration vehicle, a constant speed vehicle, and a variable acceleration vehicle (five models proposed in the present invention). In the case of the extended Kalman filter module in the present invention, based on driving information through five models, the probability density function is calculated and accumulated by the IMM (Interacting Multiple Model) unit to determine the expected location of the vehicle. Calculated is done.

That is, the vehicle position at time T can be predicted by deriving a complete series of equations by combining scenarios such as movement, acceleration, position, variableness, and turn of the vehicle. This prediction process is performed by the edge controller (EC). After fully predicting the vehicle's future location, flow rules are installed in each RSU (Road Side Unit) to efficiently forward data packets along the predicted path. If flow rules are installed in the Road Side Unit (RSU) and adjacent vehicles, the source vehicle can immediately find a new route without repeatedly sending route requests to the SDN controller as shown in FIG. 3 .

That is, the present invention introduces a new technique to the soft definition Internet of a vehicle for estimating the location of the vehicle so that a new route can be secured in advance when the vehicle enters a new road section with another neighboring vehicle. The five position prediction models proposed in the present invention can predict the vehicle position not only on a straight path but also on a random and curved path.

As interest in autonomous vehicles increases, vehicle communication, the basis of which is essential, is essential. Since V2V, that is, inter-vehicle communication, is the least stable field among vehicle communication, it is essential to supplement it.

In the case of communication necessary for autonomous driving through LTE network, a huge amount of data must be exchanged. Since this is only considering V2I, which is a direct communication method, communication through RSU (Road Side Unit) through V2V is indispensable. .

Therefore, since the present invention can provide a model for predicting the location of a vehicle essential for stabilizing communication between vehicles, if the SDN controller is combined with a direct stabilization model of vehicle communication in the future, it is considered to have great competitiveness.

The system and method according to the present invention is intended to bring about stabilization of vehicle communication by predicting the location of the vehicle, and can be performed in the edge cloud.

Therefore, it can be used by communication network operators as well as ITS centers that require communication stabilization of the corresponding vehicle by using the communication infrastructure of the backbone network, and can be applied to companies providing vehicle communication services.

The vehicle position prediction implementation solution function performed through each model implemented through the extended Kalman filter module provided in the present invention can be programmed and provided. The medium may be executed using a computer or a mobile communication terminal (eg, a smart phone, a tablet PC). In this case, such an application program may be installed on the hard disk of the computer, installed on a CD-ROM or DVD-ROM, or installed on a USB memory and executed. In addition, it may be installed and executed in various playback devices.

In addition, the communication network to which the system of the present invention is applied is a network capable of wired and wireless communication, and a mobile communication network installed and operated by a telecommunication company (including 3G network, 4G network, 5G network, WiBro network, LTE network), Internet network / It may include a Public Switched Telephone Network (PSTN) network.

The configuration and execution of the Kalman filter module implemented in the edge controller applied to the present invention may be represented by functional block configurations and various processing steps. These functional blocks may be implemented in any number of hardware and/or software configurations that perform specific functions. For example, the present invention provides integrated circuit configurations, such as memory, processing, logic, look-up table, etc., capable of executing various functions by means of the control of one or more microprocessors or other control devices. can be hired

Similar to how components of the present invention may be implemented as software programming or software elements, the present invention includes various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, including C, C++ , Java, assembler, etc. may be implemented in a programming or scripting language. Functional aspects may be implemented in an algorithm running on one or more processors. Further, the present invention may employ prior art techniques for electronic configuration, signal processing, and/or data processing, and the like. Terms such as “mechanism”, “element”, “means” and “configuration” may be used broadly and are not limited to mechanical and physical configurations. The term may include the meaning of a series of routines of software in association with a processor or the like.

As described above, the technical idea of the present invention has been specifically described in the preferred embodiment, but the preferred embodiment is for the purpose of explanation and not for limitation. As such, those of ordinary skill in the art will be able to understand that various embodiments are possible through combination of embodiments of the present invention within the scope of the technical spirit of the present invention.

10: Network with SDN
EC: Edge Controller
110, 120, 130: SDN control device
115, 125, 135: vehicle operation information sensing module
200: extended Kalman filter module
210: IMM part
220: predictive model providing unit

Claims (14)

A system for tracking the location of a vehicle having a device capable of Software Defined Networking (SDN) under an edge crowd, the system comprising:
SDN control device installed in the vehicle that applies the edge crowd to a specific area to be tracked of the vehicle location;
an edge controller that receives driving information including vehicle speed, position, and acceleration generated in the vehicle from the SDN control device;
The edge controller is
an Extended Kalman Filter that calculates and accumulates a probability density function by an Interacting Multiple Model (IMM) unit based on the driving information provided by the vehicle to calculate an expected position of the vehicle; EKF) module;
The extended Kalman filter module,
It includes; a prediction model providing unit that provides a prediction model for the predicted dynamic information of the vehicle;
The predictive model provided by the predictive model providing unit is,
a constant position model CL indicating a situation in which the vehicle does not move or the speed is '0';
a constant speed model (CV) representing the situation of the vehicle when the vehicle having a distance from the current location of the vehicle and the nearest intersection in the vehicle moving direction moves at a constant speed;
a constant acceleration model (CA) representing the situation of the vehicle when the vehicle moves with a constant acceleration (a);
a constant jerk model (CJ) representing a situation when the vehicle moves with an acceleration change for a predetermined time at a constant acceleration;
Indicates to the vehicle's SDN controller that the vehicle is continuously turning or going straight on the same road using the parameters of junction, intersection and rightmost, left or middle lane number. Turning model (VT) of the vehicle to include;
The IMM unit of the extended Kalman filter module,
The update process is performed using the predictive model provided by the predictive model providing unit, and the feedback process of correcting the prediction error is repeated,
Calculating the probability of occurrence according to each of the constant position model (CL), constant velocity model (CV), constant acceleration model (CA), constant jerk model (CJ) and turning model (VT) of the vehicle included in the predictive model, , use the calculated probabilities to identify which model will dominate the vehicle's position prediction;
When a dominant model is identified through the feedback process,
It is performed by continuously recalculating the probability for each iteration over the entire run of the vehicle, weighting the new probability value to the probability value calculated in the previous iteration,
Based on the information calculated through this, the probability of each model is calculated,
Vehicle trajectory prediction system using extended Kalman filter in vehicle software-defined networking.
delete delete delete According to claim 1,
The IMM unit,
To calculate the probability of each model through the state transition matrix according to Equation 7 below,
Vehicle trajectory prediction system using extended Kalman filter in vehicle software-defined networking.
{expression 7}

(CL: constant position model, CV: constant speed model, CA: constant acceleration model, CJ: constant jerk model, VT: vehicle turning model)
6. The method of claim 5,
The IMM unit,
Calculate the probability density function (pdf) using the Markov chain model and then compute the cumulative probability for each model.
Vehicle trajectory prediction system using extended Kalman filter in vehicle software-defined networking.
A method for tracking the location of a vehicle equipped with a device capable of SDN (Software Defined Networking) under an edge crowd by applying the system according to claim 1, the method comprising:
Step 1 of transmitting driving information including the position, speed, and acceleration of the vehicle to the edge controller of the edge cloud through the SDN device of the vehicle;
In the Extended Kalman Filter (EKF) module in the edge controller, based on the driving information, the probability density function is calculated and accumulated by the IMM (Interacting Multiple Model) unit to predict the vehicle Step 2 of calculating the location; includes,
The second step is
In the IMM (Interacting Multiple Model; Interacting Multiple Model Program) part,
The update process is performed using the predictive model provided by the predictive model providing unit, and the feedback process of correcting the prediction error is repeated,
Calculating the probability of occurrence according to each of the constant position model (CL), constant velocity model (CV), constant acceleration model (CA), constant jerk model (CJ) and turning model (VT) of the vehicle included in the predictive model, , use the calculated probabilities to identify which model will dominate the vehicle's position prediction;
When a dominant model is identified through the feedback process,
It is performed by continuously recalculating the probability for each iteration over the entire run of the vehicle, weighting the new probability value to the probability value calculated in the previous iteration,
Based on the information calculated through this, the probability of each model is calculated,
A vehicle trajectory prediction method using an extended Kalman filter in vehicle software-defined networking.
delete delete delete delete delete 8. The method of claim 7,
The second step is
To calculate the probability of each model through the state transition matrix according to the following {Equation 7},
A vehicle trajectory prediction method using an extended Kalman filter in vehicle software-defined networking.
{expression 7}

(CL: constant position model, CV: constant speed model, CA: constant acceleration model, CJ: constant jerk model, VT: vehicle turning model)
A computer-readable recording medium in which a program for performing a vehicle trajectory prediction method using an extended Kalman filter in vehicle software defined networking according to claim 13 is recorded.

Images