KR102057372B1 - Vehicle crash prediction method based on graphs including heterogeneous network and apparatus using the same - Google Patents

Abstract

A graphical vehicle collision prediction method and apparatus using the same are disclosed. The vehicle collision prediction method may include obtaining vehicle information including moving direction and speed of vehicles in a road network of a predetermined area, obtaining characteristic information including wireless network characteristics of vehicles, and based on vehicle information and specific information. Modeling a graph in the form of a topology.

Description

Graph-based Vehicle Collision Prediction Method in Heterogeneous Networks and Apparatus Using Them {VEHICLE CRASH PREDICTION METHOD BASED ON GRAPHS INCLUDING HETEROGENEOUS NETWORK AND APPARATUS USING THE SAME}

An embodiment of the present invention relates to a vehicle collision prediction method, and more particularly, to a graphical vehicle collision prediction method and apparatus using the same.

Existing collision prediction techniques perform collision prediction between the current vehicle and vehicles that can communicate in one hop through V2X.

The vehicle collision avoidance device of Korean Patent No. 10-1414571 (June 26, 2014), which is one of the prior arts, receives location information of an intersection from a communication device installed at an intersection, and indicates the position and direction of the other vehicle to be entered into the intersection. The time period for the own vehicle and the relative vehicles to reach the intersection based on the intersection position information and the vehicle entry information received by the wireless communication unit, and the vehicle communication information receiving the vehicle entry information including speed, deceleration, and braking information. The collision risk candidates are selected from the counterpart vehicles based on the calculated time difference between the intersection arrival time of the own vehicle and the intersection arrival time of the counterpart vehicles, and based on the acceleration and braking information of the counterpart vehicles of the selected collision risk candidates. Finally, among the collision risk candidates, the final collision risk candidates with the collision risk are selected, and the vehicle is selected. In response to a control signal of the electronic control yunitwa, an electronic control unit that controls to warn of danger of collision between the end-collision hazard candidates it is configured to include a warning alert to the risk of collision.

The above-described conventional technology predicts a collision risk based on various surrounding traffic information by a vehicle control device connected to a traffic control center or a central server, but quickly and accurately transmits the predicted collision risk to a driver, a passenger, or a manager of a traffic control center. There is a limit.

An object of the present invention for solving the problems of the prior art described above is to graph the inter-vehicle network by using the direction and speed of the vehicle in the road network and reflect the characteristics of heterogeneous networks, and not only 1 hop, but also 2 The present invention provides a vehicle collision prediction method capable of predicting collision between hops or more vehicles, thereby enabling more effective collision prevention between vehicles.

Another object of the present invention is to provide an apparatus using the above-described vehicle collision prediction method as a portable terminal such as a smartphone, a navigation device, an image display device, or the like.

Vehicle collision prediction method according to an aspect of the present invention for achieving the above technical problem, the vehicle information including the moving direction and the speed of the vehicle in the road network of a certain area; Obtaining characteristic information including wireless network characteristics of the vehicles; And modeling a vehicle network as a graph in a topology form based on the vehicle information and the specific information.

In an exemplary embodiment, the modeling may include modeling vehicles on a vehicle network to which heterogeneous communication networks are combined as a weighted graph having a direction in which weights of collisions between vehicles are weighted.

In one embodiment, each vehicle on the vehicle network shown in the graph is a vertex and may have edges between vehicles that are likely to collide with each other via the road network.

In one embodiment, the vehicle collision prediction method further includes, after the modeling, calculating, for each vehicle, a time required for collision with a neighboring vehicle capable of communicating in one or two hops in the vehicle network. It may include.

In one embodiment, the vehicle collision prediction method may further include generating or converting the trunk line into a trunk having a weight by applying the crash time to all neighboring vehicles after the calculating.

According to another aspect of the present invention, there is provided a vehicle collision prediction apparatus, including: a first obtaining unit obtaining vehicle information including a moving direction and a speed of vehicles in a road network of a predetermined area; A second acquiring unit acquiring characteristic information including wireless network characteristics of the vehicles; And a graphic modeling unit for modeling a network between vehicles based on the vehicle information and the specific information.

In one embodiment, the graphical modeling unit, models the vehicle on the vehicle network coupled with the heterogeneous communication network as a weighted graph with a direction to weight the probability of collision between vehicles, wherein each vehicle on the vehicle network is a vertex (vertex) And edges between vehicles that are likely to collide with each other through the road network.

In one embodiment, the vehicle collision prediction apparatus, after modeling the graphical modeling unit, the collision time for calculating the collision time with the neighboring vehicle that can communicate in one hop (hop) or two hops in the vehicle network for each vehicle A calculator; And an edge generation unit configured to generate or convert the edge into a trunk having a weight by applying the collision time to all neighboring vehicles after the calculation of the calculator.

In the case of using the vehicle collision prediction method and apparatus of the present invention as described above, it is possible to calculate the reliable vehicle collision possibility in consideration of the vehicle speed and direction and the characteristics of the vehicle communication network, and reflect the calculated vehicle collision probability. An inter-vehicle network can be provided in graphical form.

In addition, according to the present invention, it is possible to maximize user convenience through the possibility of collision with the inter-vehicle network provided in a graphic form in real time.

1 is a flowchart illustrating a vehicle collision prediction method according to an embodiment of the present invention.
FIG. 2 is a diagram for describing a vehicle network on a specific road for explaining the method of FIG. 1.
3 is an exemplary diagram for graphical modeling of the vehicle network of FIG. 2.
4 is an exemplary diagram for describing a trunk line having a weight in the vehicle network of FIG. 3.
5 is a schematic block diagram of a vehicle collision prediction apparatus according to another embodiment of the present invention.

As the invention allows for various changes and numerous embodiments, particular embodiments will be illustrated in the drawings and described in detail in the written description. However, this is not intended to limit the present invention to specific embodiments, it should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. In describing the drawings, similar reference numerals are used for similar elements.

Terms such as first, second, A, and B may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component. The term and / or includes a combination of a plurality of related items or any item of a plurality of related items.

When a component is said to be "connected" or "connected" to another component, it may be directly connected to or connected to that other component, but it may be understood that another component may be present in the middle. Should be. On the other hand, when a component is said to be "directly connected" or "directly connected" to another component, it should be understood that there is no other component in between.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. As used herein, the terms “comprise,” “having,” and the like are intended to indicate that there is a feature, number, step, action, component, part, or combination thereof described in the specification, and one or more other features. It is to be understood that the present invention does not exclude the possibility of the presence or the addition of numbers, steps, operations, components, components, or a combination thereof.

Unless otherwise defined herein, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in the commonly used dictionaries are to be interpreted in a meaning consistent with the contextual meaning of the related art, and are not to be construed in ideal or excessively formal meanings unless expressly defined herein.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a flowchart illustrating a vehicle collision prediction method according to an embodiment of the present invention.

Referring to FIG. 1, a vehicle collision prediction method according to an embodiment of the present disclosure obtains a moving direction and speed of vehicles (S11), obtains wireless network characteristics of vehicles (S12), and calculates movement and wireless network characteristics of a vehicle. Graphically model the vehicle network based on (S13), calculate the collision time with neighboring vehicles that can be communicated in one-hop communication in the vehicle network for each vehicle (S14), and weight the edges between the vehicles in the graphic modeling based on the collision time. Generate or convert to an edge having a (S15).

The graphical modeling information is displayed on a vehicle network including a trunk having a weighted trunk having a device using a vehicle collision prediction method, for example, a vehicle navigation device, a smartphone or mobile terminal equipped with a navigation application as a user terminal, and other screen display devices. Can be output from a device capable of displaying on it.

In graphical modeling, vehicles on a vehicle network with heterogeneous communication networks may be modeled as weighted graphs with a direction that weights the likelihood of collisions between vehicles. Each vehicle on the vehicle network displayed in the graph becomes a vertex, and vehicles that may collide with each other in the road network or the vehicle network on the road network may have edges between the vehicles.

In calculating the collision time, in this embodiment, considering the situation where heterogeneous communication networks are combined to form an inter-vehicle network, when the collision time is the weight of the trunk, different delay times of the communication networks are determined. Consider.

In the present embodiment, when modeling a network between vehicles as a graph, vertices and edges which are components of the graph may be set as follows.

Vertex Vehicle ID Edge Weighted time to colliaion

As shown in Table 1 above, a vertex of graphic modeling of each vehicle is set, and a vehicle ID may be assigned to each vertex. In addition, the line segments connecting the vertices have a weight or probability of collision (WT) corresponding to the difference of the network deley (Dn) previously determined according to the network characteristics of the vehicle in the time to collision (Tc). Can be. This possibility of collision is expressed by the following Equation 1.

The weight represented by [Equation 1] may be applied to the edges in graphic modeling, and may be displayed in different shapes of trunk lines in the graphic modeling output to the display device for user convenience.

As an example, to illustrate the relationship between the weight and the trunk line having a weight, it is shown in Table 2 below.

Division (S / N) Weight (less than) Trunk shape One 0 to less than 20 (none) 2 20 to less than 40 Dashed line 3 40 to less than 60 Thinnest line 4 Less than 60 to 80 A line of medium thickness 5 80-100 Thickest line

In Table 2 above, the absence of a trunk shape may indicate a relationship between vehicles in which the collision time is infinite or the possibility of collision is rare.

FIG. 2 is a diagram for describing a vehicle network on a specific road for explaining the method of FIG. 1. 3 is an exemplary diagram for graphical modeling of the vehicle network of FIG. 2.

The vehicle collision prediction method according to the present embodiment includes a network between vehicles 30 running on a road 20 of a specific area 10 including predetermined buildings 12 as shown in FIG. , Referred to as a 'vehicle network' can be modeled in a graphical form as shown in FIG.

In FIGS. 2 and 3, triangles and circles may represent vehicles using long term evolution (LTE) and wireless access for vehicle environment (WAVE) communication technologies, respectively. In the present embodiment, a case of using LTE and WAVE will be described. However, the present invention is not limited to such a configuration, and is selected from a wireless local area network, an ad-hoc network, and a communication access for land mobiles (CALM). At least one or more may be used.

In FIG. 2, the moving directions and the speeds of the vehicles 30 and the respective vehicles in the road network 20 are indicated by arrows 40. The length of arrow 40 may indicate the magnitude of the velocity.

In FIG. 3, the vehicle on the road network of FIG. 2 is abstracted and shown graphically. If there is an edge between the vertices in the graph, it means that there is a possibility of collision between two vehicles. The possibility of collision (WT) means that there is a possibility of collision someday, given the direction and speed of movement of the two vehicles. In FIG. 3, there is no edge between V0 and V2, which means that collision potential (WT) is infinite. In other words, considering the direction and speed of the current two vehicles, there is little possibility of collision with each other. There is an edge between V0 and V3, which indicates that there is a possibility of collision at the current speed when the direction of movement of V0 changes from the intersection to the direction of V3.

In addition, when searching for the three vehicles closest to the route based on V2, it can be seen that V2 has a high possibility of collision with V7 and V5 as well as V6.

On the other hand, in the above embodiment, in calculating the collision probability of the vehicle, the collision time with the neighboring vehicle that can communicate in one hop in the vehicle network is calculated for each vehicle, but the present invention is not limited to such a configuration. The collision time with neighboring vehicles that can communicate in two hops can be calculated. In that case, the delay time can be calculated in consideration of being doubled. This setting increases the number of road networks or target vehicles that calculate the likelihood of collision and can therefore be set appropriately depending on the performance of the device. In addition, if more than two hops, there are many remote vehicles that do not need to calculate the possibility of collision, so it is not necessary to use it unless it is a special case.

4 is an exemplary diagram for describing a trunk line having a weight in the vehicle network of FIG. 3.

In the vehicle collision prediction method according to the present embodiment, the collision probability reflecting the collision time between the vehicles and the delay time of the communication network of each vehicle while graphically modeling the vehicle network, in the form of a weight in the form of a weight on the trunk line connecting the vehicles in the graphic modeling By applying, the vehicle collision prediction can be easily and accurately. The vehicle collision prediction method may be displayed on the display device 140 of a device (hereinafter, referred to as a vehicle collision prediction device) using the vehicle collision prediction method.

As shown in FIG. 4, the weighted edges 70, 72, 74, 76, and 78 are displayed on the screen 142 of the display device as line segments having different shapes according to the weights among the vertices 60. Can be.

In addition, when the vehicle collision prediction method according to the present embodiment is output on the display device 140 in the specific vehicle V0 or the screen 142 of the vehicle navigation, the remaining area is displayed while displaying the partial region 144 around the vehicle. By darkening the area relatively, vehicle-centered vehicle collision prediction information can be output.

5 is a schematic block diagram of a vehicle collision prediction apparatus according to another embodiment of the present invention.

Referring to FIG. 5, the vehicle collision prediction apparatus according to the present embodiment may be any one of various devices using the aforementioned vehicle collision prediction method. The vehicle collision prediction apparatus may include a controller 110, a memory 120, and an interface 130. The interface 130 may be connected to the network and the input / output device 150, and the input / output device may include a display device.

The controller 110 may perform the steps of the vehicle collision prediction method by executing a software module or a program stored in the memory 120. The controller 110 may perform a series of procedures according to, for example, FIG. 1 and the detailed description thereof.

The controller 110 may be implemented as a processor or a microprocessor including at least one central processing unit (CPU) or a core. The central processing unit or core stores a register that stores the instructions to be processed, an arithmetic logical unit (ALU) that is responsible for comparison, determination, and operation, and internally the CPU to interpret and execute the instructions. It may be provided with a control unit (control unit) for controlling, and an internal bus connecting them. The CPU or core may be implemented as a system on chip (SOC) in which a micro control unit (MCU) and a peripheral device (an integrated circuit for an external expansion device) are arranged together, but is not limited thereto.

In addition, the controller 110 may include one or more data processors, an image processor, or a codec, but is not limited thereto. The controller 110 may include a peripheral device interface and a memory interface. The peripheral interface may connect the controller 110 to the input / output device 150 or another peripheral device, and the memory interface may connect the controller 110 to the memory 120.

The memory 120 may store a software module for implementing the vehicle crash prediction process. The software module may include a first acquirer for acquiring vehicle information or a first module 121 corresponding thereto, a second acquirer for acquiring characteristic information of a communication network or a second module 122 corresponding thereto, and vehicle information. Graphic modeling unit for graphically modeling the vehicle network based on the characteristic information or the third module 123 corresponding thereto, delay time extraction unit for extracting the different delay time according to the network type from the characteristic information, or read the stored delay time in advance Or a fourth module 124 corresponding thereto, a collision time calculator for calculating a collision time of the vehicle based on the vehicle moving direction and speed in the vehicle information, or a fifth module 125 corresponding thereto, according to the possibility of collision. Edge generating portion or corresponding sixth module 126 that applies weights to edges connecting the vertices, different models for collision potential The module 7, and the like 127 to the screen control unit or the corresponding outputting a graphical traffic information with the main screen of the display device.

The above-described memory 120 may include non-volatile random access memory (NVRAM), semiconductor memory such as dynamic random access memory (DRAM), which is a typical volatile memory, hard disk drive (HDD), and optical storage. It may be implemented as a device, a flash memory, or the like. The memory 120 may store an operating system, a program, a command set, etc. in addition to a software module for performing a vehicle collision prediction method.

Meanwhile, in the above-described embodiment, the components of the vehicle collision prediction apparatus may be implemented as functional blocks or modules executed by processors of various computing devices based on nonvolatile memory (NVRAM). For example, a software module stored in a memory of a device implementing the vehicle collision prediction method of FIG. 1 may be stored in a computer readable medium (recording medium) in software form for implementing a series of functions they perform or remotely in a carrier form. It may be implemented to download and perform the function from the vehicle collision prediction device that is stored in and connected via a network with a computing device or communication device of a remote location. Here, the computer-readable medium may include a plurality of computer devices or cloud systems connected through a network, and at least one or more of the plurality of computer devices or cloud systems may be a program or source for executing the vehicle collision prediction method of the present embodiment. You can save the code.

In addition, the computer readable medium may be embodied in the form of a single or combination of program instructions, data files, data structures, and the like. The programs recorded on the computer readable medium may be those specially designed and configured for the present invention, or may include those known and available to those skilled in computer software.

In addition, the computer readable medium may include a hardware device specifically configured to store and execute program instructions, such as a ROM, a RAM, a flash memory, or the like. The program instructions may include not only machine code such as produced by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to be operated by at least one software module to operate the vehicle collision prediction method of the present embodiment, and vice versa.

The interface 130 may include a means for obtaining vehicle information and characteristic information in a vehicle collision prediction apparatus or a component for performing such a function. The interface 130 may include an input port, a wired or wireless communication line, and the like. The interface 130 may function as an input device or an image acquisition unit that prepares a standard brain image or query image.

In addition, the interface 130 may include means for connecting the brain image matching device to a network or a component corresponding to such means. This interface 130 may include one or more wired and / or wireless communication subsystems that support one or more communication protocols as a communication means or communication device.

The wired communication subsystem may be connected to a wireless communication subsystem, and may be connected to a public switched telephone network (PSTN), an asymmetric digital subscriber line (ADSL) or very high-data rate digital subscriber line (VDSL) network, or a PSTN Emulation Service (PES). Subsystems, Internet Protocol (IP) Multimedia Subsystems (IMS), and the like. The wireless communication subsystem may include a radio frequency (RF) receiver, an RF transmitter, an RF transceiver, an optical (eg, infrared) receiver, an optical transmitter, an optical transceiver, or a combination thereof for a wireless network connection. Here, the wireless network basically refers to Wi-Fi, but is not limited thereto. In this embodiment, the interface 130 may be implemented to support various wireless networks. In addition to LTE and WAVE, wireless networks include Global System for Mobile Communication (GSM), Enhanced Data GSM Environment (EDGE), Code Division Multiple Access (CDMA), W-Code Division Multiple Access (W-CDMA), and LET-A (LET). -May further include Advanced, Orthogonal Frequency Division Multiple Access (OFDMA), WiMax, Wireless Fidelity (Wi-Fi), Bluetooth, and the like.

As described above, if the graphical modeling of the present embodiment is used, the possibility of collision between the reference vehicle and the vehicle at one or more hop distances as well as the reference vehicle and the vehicle at a distance of two or more hops using the path search method in the weight graph. Up to predictable.

Although described above with reference to a preferred embodiment of the present invention, those skilled in the art various modifications and variations of the present invention without departing from the spirit and scope of the invention described in the claims below I can understand that you can.

Claims (7)

Obtaining vehicle information including a moving direction and a speed of the vehicles in a road network of a predetermined area;
Obtaining characteristic information including wireless network characteristics of the vehicles; And
Modeling a network between vehicles based on the vehicle information and the characteristic information;
The modeling of the graph may include modeling vehicles on a vehicle network coupled with a heterogeneous communication network as a weighted graph having a direction in which weights of collisions between vehicles are weighted.
Each vehicle in the vehicle network is a vertex, each vehicle is given a vehicle identifier, and the segments connecting the vertices correspond to the difference in the delay time previously determined according to the network characteristics of the vehicle in the collision time. With edges between vehicles having a weight or the likelihood of collision and likely to collide with one another via a road network,
After the modeling, calculating a collision time for each vehicle with a neighboring vehicle that is capable of communicating in one hop in the vehicle network; And
And after the calculating, applying the collision time to all neighboring vehicles to generate the trunk as a trunk having a weight. delete delete delete delete A first obtaining unit obtaining vehicle information including a moving direction and a speed of the vehicles in a road network of a predetermined area;
A second acquiring unit acquiring characteristic information including wireless network characteristics of the vehicles;
A graphic modeling unit for modeling a network between vehicles based on the vehicle information and the characteristic information;
A collision time calculator configured to calculate, for each of the vehicles, a collision time with a neighboring vehicle that can communicate in one hop in the inter-vehicle network after modeling the graphic modeling unit; And
After the calculation of the calculation unit includes an edge generating unit for generating or converting the trunk to a trunk with a weight by applying the collision time to all neighboring vehicles,
The graphic modeling unit models vehicles on a vehicle network coupled with a heterogeneous communication network as a weighted graph having a direction in which weights of collisions between vehicles are weighted, where each vehicle in the vehicle network becomes a vertex and each vertex. Is assigned a vehicle identifier, and the line segments connecting the vertices have the weight or the likelihood of collision corresponding to the difference of the delay time previously determined according to the network characteristics of the vehicle in the collision time, and the likelihood of collision with each other through the road network A vehicle collision prediction apparatus having an edge between the vehicles present. delete

Images