KR102590121B1 - Navigation guide method and server, navigation device - Google Patents

Abstract

In one embodiment, the vehicle navigation guide server includes a lane determination unit that determines the driving lane of the vehicle based on the driving information of the vehicle, and a driving path of the vehicle based on the driving information of the vehicle and the location information of the vehicle. The turning zone is divided into a first zone and a second zone, and when the vehicle needs to change lane in the first zone, information about the lane to which the vehicle must change is generated as a guide for the first zone, When a lane change of the vehicle is required in the second zone, it may include a guidance guide unit that generates information about how many lanes to move in which direction based on the driving lane of the vehicle as a guide for the second zone. there is.

Description

Navigation guide method and server, navigation device}

The present invention relates to a navigation guide method, server, and navigation device. More specifically, the present invention relates to a navigation guide method, server, and navigation device. More specifically, the present invention provides different guide information for lane changes according to the situation of the vehicle's driving path, so that the vehicle can drive in the correct lane. It is an invention about technology.

A navigation device uses GPS signals received from a Global Positioning System (GPS) to display the current location of a moving object, such as a vehicle, on a map. These navigation devices are currently mounted on various moving objects such as ships, aircraft, and vehicles and are widely used to check the current location and moving speed of the moving object or to determine the moving path.

In general, when a user inputs a destination, a navigation device used in a vehicle searches for a driving route to the destination using map information and guides the vehicle to the driving route selected by the user. In addition, the navigation device visually or audibly provides various information such as the driving route to the destination, geographical features located around the driving route, road congestion, etc., thereby providing a guide to help the user reach the destination.

On the other hand, if you have to pass through a point containing a turning point, such as an intersection or an IC (Inter Change) where a general road meets a highway, or a JC (Junction) where a highway meets a highway, you must accurately identify the turning point to prevent accidents. Guidance is essential.

However, in the case of navigation devices according to the prior art, they only provide information about turns on the driving route and do not provide information about when and where exactly to turn, so accidents occur when driving in a straight lane and forcibly changing lanes to a turning lane. There was a problem that occurred.

In addition, when driving in a turning lane and having to drive straight on the driving route, there was a problem of not recognizing this in advance and forcibly changing lanes to the straight lane, causing congestion and causing accidents.

Therefore, the navigation guide method, server, and navigation device according to one embodiment are inventions designed to solve the above-described problem. When a turn must be made in the driving route, the turn area is divided into a turn preparation area and a turn proximity area and the turn is made. The purpose is to enable vehicles to drive in the correct lane by providing different guidance in the preparation area and the turning area.

In one embodiment, the vehicle navigation guide server includes a lane determination unit that determines the driving lane of the vehicle based on the driving information of the vehicle, and a driving path of the vehicle based on the driving information of the vehicle and the location information of the vehicle. The turning zone is divided into a first zone and a second zone, and when the vehicle needs to change lane in the first zone, information about the lane to which the vehicle must change is generated as a guide for the first zone, When a lane change of the vehicle is required in the second zone, it may include a guidance guide unit that generates information about how many lanes to move in which direction based on the driving lane of the vehicle as a guide for the second zone. there is.

The guide guide unit may determine a recommended lane of the turning zone, calculate a difference value between the vehicle's driving lane and the recommended lane, and determine the first zone and the second zone based on the difference value. .

The guide unit may determine the first zone and the second zone based on the driving speed of the vehicle and the static speed or congestion information of the road on which the vehicle travels.

The guidance unit may collect the frequency of deviation from the route of the driver of the vehicle and determine the first zone and the second zone based on the frequency of deviation from the route.

A navigation guide method according to an embodiment includes determining a driving lane of the vehicle based on driving information of the vehicle, determining a turning area included in the driving path of the vehicle based on the driving information of the vehicle and location information of the vehicle. dividing the zone into a first zone and a second zone, and when a lane change of the vehicle is required in the first zone, information about the lane that the vehicle must change into is generated as a guide for the first zone, If the vehicle needs to change lane in Zone 2, it may include generating information on which direction and how many lanes to move based on the vehicle's driving lane as a guidance guide for Zone 2.

A navigation device according to an embodiment includes a lane determination unit that determines a driving lane of the vehicle based on driving information of the vehicle, a turning area included in the driving path of the vehicle based on the driving information and location information of the vehicle. is divided into a first zone and a second zone, and when the vehicle needs to change lane in the first zone, information about the lane that the vehicle needs to change is generated and output as a guide for the first zone, and If the vehicle needs to change lane in the second zone, it may include a guide unit that generates and outputs information about how many lanes to move in which direction based on the driving lane of the vehicle as a guide for the second zone. You can.

When a lane change of the vehicle is required in the second zone, the guide unit may use a geographical feature included in the turning zone to output the information as a guide for the second zone.

The guide guide may simultaneously guide the guide in the first zone using a speaker and guide the guide in the second zone using a display unit and the speaker.

The navigation guide method, server, and navigation device according to an embodiment divide the turning area into a turning preparation area and a turning proximity area according to the driving route situation and provide guidance in different ways, thereby providing accurate guidance appropriate to the driving situation. can be provided.

In addition, the navigation guide method, server, and navigation device according to one embodiment provide different guidance guides provided in the turn preparation area and guidance provided in the turn proximity area, thereby preventing the driver from driving outside the turn area. This has the effect of suppressing road congestion and reducing the risk of accidents.

Figures 1 and 2 are diagrams for explaining an example of dividing a rotation preparation area and a rotation approach area.
Figure 3 is a table for explaining criteria for dividing the first zone and the second zone according to one embodiment.
Figure 4 is a block diagram showing some components of a vehicle navigation device according to an embodiment.
Figure 5 is a block diagram showing some components of a lane determination unit using an artificial neural network according to an embodiment.
Figure 6 is a diagram illustrating input information input and output information output to a lane prediction artificial neural network module according to an embodiment.
Figure 7 is a diagram showing the structure of an artificial neural network module applied to the present invention.
Figure 8 is a schematic diagram showing the calculation process at the node of the artificial neural network module.
FIG. 9 is a diagram illustrating the relationship between an artificial neural network module and each component, according to an embodiment.
Figure 10 is a diagram for explaining another embodiment of the output layer of the present invention.
FIG. 11 is a diagram illustrating a screen containing information output by an artificial neural network module according to an embodiment.
Figure 12 is a flowchart for explaining the operation of a vehicle navigation device according to an embodiment.
Figure 13 is a diagram for explaining cases in which a guidance guide is needed and cases in which it is not required depending on the vehicle's driving lane.
Figure 14 is a diagram illustrating an example of outputting different guides in a first zone and a second zone according to an embodiment.
Figure 15 is a diagram illustrating an example of outputting different guides in a first zone and a second zone according to another embodiment.
Figure 16 is a diagram illustrating an example of outputting different guides in a first zone and a second zone according to another embodiment.
FIG. 17 is a diagram illustrating the relationship between a navigation guide server, a vehicle, and a user terminal according to an embodiment.

Hereinafter, embodiments according to the present invention will be described with reference to the attached drawings. When adding reference signs to components in each drawing, it should be noted that the same components are given the same reference numerals as much as possible even if they are shown in different drawings. Additionally, when describing embodiments of the present invention, if detailed descriptions of related known configurations or functions are judged to impede understanding of the embodiments of the present invention, the detailed descriptions will be omitted. In addition, embodiments of the present invention will be described below, but the technical idea of the present invention is not limited or limited thereto and may be modified and implemented in various ways by those skilled in the art.

Additionally, the terms used in this specification are used to describe embodiments and are not intended to limit and/or limit the disclosed invention. Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this specification, terms such as “comprise,” “provide,” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification. It does not exclude in advance the existence or addition of other features, numbers, steps, operations, components, parts, or combinations thereof.

In addition, throughout the specification, when a part is said to be “connected” to another part, this refers not only to the case where it is “directly connected” but also to the case where it is “indirectly connected” with another element in between. Terms including ordinal numbers, such as “first” and “second,” used in this specification may be used to describe various components, but the components are not limited by the terms.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. In order to clearly explain the present invention in the drawings, parts unrelated to the description are omitted.

In addition, the navigation device 1 described below not only refers to an independent device configured separately from the vehicle that provides only navigation services, but also may refer to a device that is implemented as a component of the vehicle and provides navigation services, It can be interpreted as a concept that includes both a server that provides navigation services to a user terminal or vehicle, or a user terminal that provides navigation services.

Figures 1 and 2 are diagrams for explaining an example of dividing a rotation preparation area and a rotation approach area.

The disclosed navigation device 1 can guide a driving route that includes a turning area. Here, the turning area may be a rampway for incorporating an existing road into an automobile-exclusive road to create or expand an automobile-exclusive road, or for connecting to another automobile-exclusive road, or may include an intersection provided on a general road.

Referring to FIG. 1, a vehicle including a navigation device 1 can drive on an automobile road including at least two floating roads. The driving route may be guided by using the second subway road rather than the first subway road.

The disclosed navigation device 1 can distinguish between the turn preparation area 10 and the turn proximity area 20 based on the distance of the floating road guiding the current location based on the GPS signal.

In other words, the turn preparation area 10 is an area where the driver does not need to take direct action to turn, but must be aware of the turn. The turn proximity zone 20 refers to an area where the driver must be aware of the surrounding driving environment and take actions such as changing lanes in order to make a turn.

Meanwhile, the rotation preparation area 10 and rotation proximity area 20 are names established for convenience of explanation, so hereinafter, the rotation preparation area 10 will be referred to as the first zone, and the rotation proximity zone 20 will be referred to as the first zone. This will be described by referring to area 2 (20).

Referring to FIG. 2, unlike FIG. 1, a vehicle including the navigation device 1 can drive on public roads. A general road may include an intersection as shown in FIG. 2.

When it is necessary to turn right at an intersection on the driving route, the navigation device 1 divides the driving route into a first zone 10 and a second zone 20 based on the GPS signal and the distance to the turning zone.

For example, the navigation device 1 may be divided into a first zone 10 up to 250 m from the current location of the vehicle and a second zone 20 up to 100 m from the turning point.

Thereafter, the navigation device 1 outputs different guidance guides in the divided first zone 10 and second zone 20 based on the lane in which the vehicle is currently traveling, allowing the vehicle to safely pass through the turning zone. You can do it. A detailed explanation related to this will be described later with reference to the drawings.

Meanwhile, in addition to FIGS. 1 and 2 , the navigation device 1 can distinguish a first zone and a second zone in a driving route including various turning zones. In addition, even if the guiding driving path does not include a turning path and includes a driving path that passes the turning path, the navigation device 1 can distinguish the first zone 10 and the second zone 20 at the current location. And, accordingly, it can be guided to drive in the straight lane rather than the turning lane.

FIG. 3 is a table for explaining criteria for dividing the first zone 10 and the second zone 20 according to an embodiment.

The disclosed navigation device 1 can set offsets for starting the first zone 10 and the second zone 20 in the turning zone for each road. Setting the first zone 10 and the second zone 20 for each road in this way is referred to as a static setting value. However, the navigation device 1 may change the first zone 10 and the second zone 20 appropriately according to driving environment factors while using a static set value as a standard.

Referring to FIG. 3, the navigation device 1 can classify roads into highways, city highways, roads with two or more lanes, and alleyways according to road information, and set different zone starting points. Road information may be included in map information, and the navigation device 1 may use static settings based on road information on the driving route.

Specifically, when a turning area is included on a highway, the navigation device 1 may divide the area from 1 km before the turning point to 300 m before the turning point as the first area 10. Additionally, the navigation device 1 may divide the area from 300 m before the turning point to the turning point into a second area 20.

When a turning zone is included on an urban highway, the navigation device 1 may distinguish the area from 700 m to 200 m before the turning point as a first zone 10. Additionally, the navigation device 1 may divide the area from 200 m before the turning point to the turning point into a second area 20.

If a turning area is included in a roadway with two or more lanes, the navigation device 1 may divide the area from 250 m to 100 m before the turning point into the first area 10. Additionally, the navigation device 1 may divide the area from 100 m before the turning point to the turning point into a second area 20.

If a turning area is included in an alley, the navigation device 1 may not distinguish the first area 10 . Additionally, the navigation device 1 may divide the area from 50 m before the turning point to the turning point into a second area 20.

In this way, the navigation device 1 divides the first zone 10 and the second zone 20 according to the road conditions through road information for each road included in the driving route, and then provides guidance based on this. . Drivers can prepare for turning points within sufficient distance.

Additionally, the navigation device 1 may change the static set value based on change factors according to driving environment factors.

Specifically, the navigation device 1 may determine the current driving lane based on GPS signals and surrounding information received from the vehicle. If the driving lane does not match the recommended driving lane included in the driving route, the navigation device 1 may adjust the length of the first zone 10 and the second zone 20.

For example, on a highway, the recommended driving route has 10 lanes, but if the vehicle drives in 1 lane, there are many lanes to move to, so the navigation device 1 statically sets the starting point of the first area 10. Depending on the value, it can be set longer than 1km, or the starting point of the second area 20 can be set longer.

The navigation device 1 may change the starting points of the first zone 10 and the second zone 20 by comparing the driving speed of the vehicle and the static speed of the road.

For example, when a vehicle is traveling at a speed of more than 100 km/h on a city highway where 80 km is the static road speed, the navigation device 1 sets the starting point of the first zone 10 of the vehicle 700 m to allow safe lane changes. It can be set longer, or the starting point of the second area 20 can be set longer. Through this, the driver can quickly recognize the turning point.

Additionally, the navigation device 1 may change the starting points of the first zone 10 and the second zone 20 based on congestion information.

For example, when the driving route is congested, the driver can secure more time to recognize the turning point than during normal driving. In this case, the navigation device 1 may shorten the static set values for the first zone 10 and the second zone 20 and provide appropriate guidance to the driver accordingly.

The navigation device 1 may change the starting points of the first zone 10 and the second zone 20 based on the driver's driving habits collected from driving information.

For example, the navigation device 1 can determine the frequency of the driver's route departure from the guided driving route and calculate the driver's driving skill level through this.

For example, if the driver's driving skill is high (e.g., the driving skill satisfies a threshold value), the navigation device 1 shortens the length of the first zone 10 and the second zone 20, thereby Appropriate guidance can also be provided to the driver. On the contrary, if the driver's driving skill is low (e.g., the driving skill does not meet the threshold), the navigation device 1 increases the length of the first zone 10 and the second zone 20, Accordingly, appropriate guidance may be provided to the driver. And this dynamic setting value change factor is only an example. In other words, the navigation device 1 can change the static set value according to the driving environment through various other change factors.

FIG. 4 is a block diagram showing some components of the navigation device 1 according to one embodiment.

Referring to FIG. 4, the navigation device 1 includes a communication unit 30 that receives various information from the vehicle and external servers, a display unit 40 that outputs a driving route that guides the vehicle to the entered destination and various user interfaces. , an output unit 50 that outputs information necessary for the driving route and a guide such as recommended lanes in sound, a storage unit 60 that stores various information received from the vehicle and external servers, etc., and determines the lane of the vehicle being driven. It may include a lane determination unit 100 that determines the lane and a guidance guide unit 80 that controls the above-described configuration. In FIG. 4, for convenience of explanation, the configuration that controls the overall processor of the navigation device 1 is described as the guidance guide unit 80. However, the guidance unit 80 may be referred to as a control unit depending on its characteristics. there is.

The communication unit 30 can receive driving information and GPS signals from the vehicle.

Driving information is information that includes various information about the vehicle's navigation guide, and may include the route to the destination, the current speed and location of the vehicle, and information necessary for the lane determination unit 100 to determine the lane, which will be described later. there is. Such driving information may be independently generated by the navigation device 1, or may be received from the vehicle or a server providing a navigation guide service through the communication unit 30.

Accordingly, the communication unit 30 may include a communication interface and may be connected to the vehicle to receive information about the vehicle's driving speed and the driving lane through wired or wireless means. Additionally, the communication unit 30 may receive GPS signals from outside the vehicle based on a wireless interface. Additionally, the communication unit 30 may receive map information from the outside or receive information necessary to update map information previously stored in the storage unit 60.

The display unit 40 is composed of a display and can visually display the driving route, vehicle driving speed, map information, and guidance guide. The display may include a variety of display panels, such as a Liquid Crystal Display (LCD) panel, a Light Emitting Diode (LED) panel, or an Organic Light Emitting Diode (OLED) panel.

Meanwhile, if the display includes a GUI (Graphical User Interface), that is, a software device, such as a touch pad, it may serve as an input unit that receives user input.

The output unit 50 is configured to output a guide as sound and may include a speaker and an interface necessary therefor.

The storage unit 60 can store various information received by the communication unit 30 and programs necessary for the operation of the navigation device 1.

Specifically, the driving information stored by the storage unit 60 may include information about driving speed received from the vehicle, engine status, and driving lane. Additionally, the storage unit 60 can temporarily store the GPS signal received by the communication unit 30 and transmit it to the guidance unit 70. Additionally, the storage unit 60 may store map information in advance and provide information for the guidance unit 70 to search for a driving route to reach the destination. The map information may include information about geographical features, recommended lanes for the turning point.

The storage unit 60 can store information necessary for the information guide. For example, the storage unit 60 stores the guide “Turn to the right” in data form, and stores it in advance in the display unit 40 and the output unit 50 under the control of the guide unit 70. data can be provided.

The storage unit 60 is a non-volatile memory device or RAM such as cache, read only memory (ROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), and flash memory. It may be implemented as at least one of a volatile memory device such as (Random Access Memory) or a storage medium such as a hard disk drive (HDD) or CD-ROM, but is not limited thereto. The storage unit 60 may be a memory implemented as a separate chip from the processor described above in relation to the guide unit 70, which will be described later, or may be implemented as a single chip with the processor.

The lane determination unit 100 may determine which lane of the entire road the driving vehicle is currently traveling in. Specifically, based on driving images acquired through cameras installed in the vehicle, an artificial neural network module is used to infer information about which lane the currently driving vehicle is from the leftmost lane or which lane is from the rightmost lane. This can be judged. Information on the lane of the currently driving vehicle determined by the lane determination unit 100 may be transmitted to the information guide unit 70.

Hereinafter, we will look in detail at how the lane determination unit 100 determines the lane through FIGS. 5 to 11.

Figure 5 is a block diagram showing some components of the lane determination unit 100 using an artificial neural network according to an embodiment of the present invention, and Figure 6 is a block diagram showing the input to the lane prediction artificial neural network module 120 according to an embodiment of the present invention. This diagram shows input information and output information. Hereinafter, for convenience of explanation, the lane determination unit 100 using an artificial neural network will be referred to as the lane determination unit 100.

Referring to FIG. 5, the lane determination unit 100 includes an image information collection module 110, a lane prediction artificial neural network module 120, an output information distribution calculation module 130, a reference information distribution calculation module 140, and reliability calibration. It may include a module 150, a feature extraction module 160, and a lane change confirmation artificial neural network module 170.

The image information collection module 110 collects driving image information 210 of the front and sides of the vehicle captured through at least one camera mounted on the vehicle, and converts the collected images into the lane prediction artificial neural network module 120. Can be sent.

The lane prediction artificial neural network module 120 uses the vehicle's driving image information 210 collected by the image information collection module 110 as input information, and lane prediction information ( 220) and reliability information 230 for the inferred lane as output information, and the lane prediction artificial neural network module 120 is a learning session 121 that performs learning based on the input information and output information. and an inference session 122 that infers output information based on input information.

The learning session 121 of the lane prediction artificial neural network module 120 is a session that can perform learning based on input information and output information, and the inference session 122 uses the learned lane prediction artificial neural network module 120. By analyzing the driving image information 210 input in real time, lane prediction information 220 that infers which lane the vehicle is currently driving in and reliability information 230 related thereto can be output together.

For example, when an image is input to the lane prediction artificial neural network module 120, as a result of analyzing the input image and inferring the lane for the currently driving vehicle, if it is determined that the driving lane is the first lane, the first lane can be output as lane prediction information 220, and at the same time, reliability information 230 (for example, 0.8) determined as the first lane can be output as output information.

Additionally, the lane prediction information 220 output from the lane prediction artificial neural network module 120 may be specifically output as information about which lane the lane is based on a specific lane. For example, you can output lane information about which lane the vehicle is currently traveling in based on the first lane of the road, and conversely, how many lanes the vehicle is currently traveling in based on the last lane of the road. Lane information about whether it is the second lane can be output.

In providing lane information, as in the present invention, when information is provided on which lane is based on a specific lane, the driver can know which lane is his/her lane based on the reference lane closest to the vehicle. , there is an effect of being able to prepare and change lanes more stably when changing lanes according to the driving route.

Figure 7 is a diagram showing the structure of an artificial neural network module applied to the present invention, and Figure 8 is a schematic diagram showing the calculation process at the node of the artificial neural network module.

Referring to FIG. 7, the multi-layer neural network model of the lane prediction artificial neural network module 120 may be composed of an input layer (260), a hidden layer (270), and an output layer (280).

The input layer 260 is composed of nodes corresponding to each input factor, and the number of nodes is equal to the number of input factors. The hidden layer 270 may process a linear combination of argument values transmitted from the input layer 260 into a non-linear function such as a sigmoid function and transmit it to the output layer or another hidden layer. In FIG. 7, the lane prediction artificial neural network module 120 is shown as having one hidden layer 270 due to the limitations of the ground, but it is not limited to this, and the lane prediction artificial neural network module 120 includes a plurality of hidden layers 270. can do. The output layer 280 is a node corresponding to an output factor, and in a classification model, output nodes can be created as many as the number of classes. In the present invention, the output information consists of lane prediction information 220 about which lane the vehicle is currently traveling in and reliability information 230 about this as output information. The output layer 280 is shown in FIG. 7. As shown, it is depicted as one layer. However, the present invention is not limited to this, and the lane prediction artificial neural network module 120 may be composed of a plurality of output layers 280 depending on the utilization environment.

As shown in FIG. 8, when input information is input to the lane prediction artificial neural network module 120, calculations actually occur at each node. The calculation process of the lane prediction artificial neural network module 120 is performed using the neurons constituting the human neural network. It is mathematically designed to simulate the processes that occur in

A node responds when it receives stimulation of a certain size or more, and the size of the response is roughly proportional to the value multiplied by the input value and the node's parameters (or weights), excluding the bias value. Generally, a node receives multiple inputs and has as many parameters as the number of inputs. Therefore, by adjusting this parameter, different weights can be assigned to various inputs. Finally, all multiplied values are added and the sum is input to the activation function, which is the output layer 280. The result of the activation function corresponds to the output of the node, and this output is ultimately used for classification or regression analysis.

Each layer of the neural network model consists of at least one node, and activation/deactivation of each node is determined depending on the input value. The input information becomes the input of the first layer (input layer), and after that, the output of each layer becomes the input of the next layer. All coefficients continue to change slightly during the learning process, ultimately reflecting which input each node considers important. And ‘training’ of the artificial neural network model described above refers to the process of updating this coefficient.

A representative artificial neural network applied to the car road prediction artificial neural network module 120 of the present invention may be a CNN network.

CNN (Convolutional neural network) is a type of feed-forward deep neural network (DNN) used to analyze visual images. It consists of one or several convolutional layers, a pooling layer, It refers to a neural network composed of fully connected layers. In Korean, it is referred to as a synthetic neural network. CNN has a structure suitable for learning two-dimensional data and can be trained through the backpropagation algorithm.

The CNN process largely repeats the tasks of feature extraction, impact minimization, and classification, and can obtain global features that can represent the entire image from local features.

In the case of CNN, by repeatedly applying filters with the same coefficients to the entire image, the number of variables is dramatically reduced, so there is an effect of obtaining invariance that is independent of topology changes, and this effect is achieved with the present invention. There is an effect that can improve accuracy when determining a lane based on an image that is also input.

In addition, in this specification, the neural network applied to the lane prediction artificial neural network module 120 of the present invention has been described based on CNN, but the neural network structure applied to the lane prediction artificial neural network module 120 of the present invention is limited to CNN. Rather, various known artificial neural network models such as Google Mobile Net v2, VGGNet16, and ResNet50, which are useful for image detection, can be applied.

Figure 9 is a diagram illustrating the relationship between an artificial neural network module and each component, according to an embodiment of the present invention, and is specifically a diagram explaining the process by which parameters of the artificial neural network module are updated through learning.

Referring to FIG. 9 , lane prediction information 220 and corresponding reliability information 230 output by the lane prediction artificial neural network module 120 may be input to the output information distribution calculation module 130.

The output information distribution calculation module 130 is a module that specifically calculates the data distribution for the lane prediction information 220 and the reliability information 230 output from the lane prediction artificial neural network module 120.

For example, the lane prediction artificial neural network module 120 infers and outputs lane prediction information 220 about which lane each is driving on based on the 100 input images, and reliability information 230 about this. If so, the output information distribution calculation module 130 receives the lane prediction information 220 and reliability information 230 output by the lane prediction artificial neural network module 120, and then creates a distribution map based on the received information. Through analysis, a first data distribution chart (X) can be generated. The first data distribution chart (X) refers to information about what values the output information inferred and output for each image input to the lane prediction artificial neural network module 120 is distributed.

The reference information distribution calculation module 140 may collect reference information about the vehicle's actual driving lane prediction information and calculate the data distribution of the reference information 240 to generate a second data distribution (Y).

Reference information 240 is information that can serve as a standard when updating parameters of an artificial neural network module, and is also called ground truth information. In the present invention, actual lane information for images input to the lane prediction artificial neural network module 120 may be included in the reference information 240.

The reliability calibration module 150 may perform calibration to change various parameter values of the artificial neural network model so that the output value of the artificial neural network model reflects actual reliability. For example, when the output of the model for output information B of input information A is 0.9, calibration can be performed to change various parameter values of the artificial neural network model so that it means that there is a 90% probability that it will be B.

When calibrating the model of the lane prediction artificial neural network module 120, the reliability calibration module 150 receives the first data distribution diagram (X) from the output information distribution calculation module 130 and uses the reference information distribution calculation module 140 The second data distribution map (Y) is received from the second data distribution map (Y), and the difference between the first data distribution map (X) and the second data distribution map (Y) is reduced to reduce the difference prediction artificial neural network module 120. Calibration can be performed by updating parameters.

To describe an embodiment in relation to lane prediction, the lane prediction information inferred by the lane prediction artificial neural network module 120 for 100 input images is 20% predicted as the first lane, and 20% predicted as the second lane. If the ratio of one lane is 50%, the predicted ratio of 3 lanes is 30%, and according to the reference information (240), the ratio of 1 lane is 30%, the ratio of 2 lanes is 45%, and the ratio of 3 lanes is 25%. , the reliability calibration module 150 may update the parameters of the lane prediction artificial neural network module 120 to match the actual reference information 240 ratio.

According to this, the reliability information 230 output from the lane prediction artificial neural network module 120 has the effect of becoming closer to the actual probability of the lane prediction information 220.

In addition, as one embodiment, the reliability calibration module 150 can perform calibration by softening the softmax function corresponding to the output layer. Specifically, the reliability calibration module 150 can perform calibration by softening the softmax function corresponding to the output layer. In a classification problem situation, calibration can be performed by converting the logic vector Z with Equation 1 below using T, a single scalar parameter.

(Equation 1)

q^ means calibrated probability, and Equation 3 above is a logic vector in a multi-classification problem with K labels attached to a single scalar parameter, T This means performing calibration by dividing by .

In Equation 3, if T, a single scalar parameter, is 1, it becomes the original equation for calculating reliability using Softmax. As T increases, the final q converges to 1/K, and as T approaches 0, As the number increases, q gets closer to 1.

In addition, the optimal value of the single scalar parameter T can be determined through learning, specifically, calibration validation, which is another validation set that has the same characteristics as the validation set of the car lane prediction artificial neural network module 120. Learning can be performed on a single scalar parameter T using a set.

Specifically, the reliability calibration module 150 may use the calibration validation set to perform learning on a single scalar parameter T so that the Negative Log Likelihood (NLL) value in the calibration validation set is minimized. When performing calibration in this way, T, a single scalar parameter, can be calibrated without changing the maximum value of the output of the soft max. Therefore, this method has the advantage of being applicable to conventionally trained artificial neural network modules because it only affects the calibration of the conventional model and does not affect the accuracy.

Figure 10 is a diagram for explaining another embodiment of the output layer of the present invention, and Figure 11 is a diagram showing information output according to the artificial neural network of Figure 10 displayed on the display unit 40 of the navigation device.

Referring to FIG. 10, the input information input to the lane prediction artificial neural network module 120 of the present invention is the driving image information 210, which is the same as FIG. 3, but the output layer is not one layer, but the first output layer 81 and the It may include a second output layer 82.

The first output layer 81 and the second output layer 82 serve as an activation function, and typically a softmax function or a cross entropy function may be used. For convenience of explanation, the explanation below will be based on the softmax function.

As shown in Figure 10, when the lane prediction artificial neural network module 120 of the present invention uses the first softmax function and the second softmax function in the output layer, the first softmax function is based on the first lane. The first lane prediction information (221) and the first lane reliability information (231) about which lane the currently driving vehicle is traveling in are output, and the second softmax function outputs the current driving lane based on the last lane. Second lane prediction information 222 about which lane the vehicle is traveling in and corresponding second lane reliability information 232 can be output.

Therefore, as shown in FIG. 11, the output information of the first softmax function includes first lane prediction information 221, which is determined to be the second lane based on the first lane, and first lane reliability information 231 for this, respectively. It can be output as 2 lanes and 0.999, and the output information of the second softmax function is the second lane prediction information 222, which is judged to be the second lane based on the last lane, and the reliability information 232 for this, respectively, as the second lane and 0.999. It can be output as 0.994.

If the reliability information is greater than a preset standard based on the output lane prediction information and the corresponding reliability information, the lane determination unit 100 determines that the output lane prediction information is lane information of the currently driving vehicle and provides the determined lane information. It can be transmitted to the guide unit 70. The preset standard can be set in various ways, for example, it may be 0.8 or more. Hereinafter, we will return to FIG. 4 and look at the guidance unit 70 that generates a guidance guide using the lane information determined by the lane determination unit 100.

Referring to FIG. 4 , the guidance unit 70 can generate a guidance guide for the navigation device 1 and provide it to the driver while simultaneously controlling the overall operation of the navigation device 1.

Specifically, the guidance unit 70 may divide the turning area included in the driving route into the first area 10 and the second area 20 based on the vehicle's driving information and GPS signals. As described above in FIG. 3, the guidance unit 70 divides the first area 10 and the second area 20 according to road information based on static settings pre-stored in the storage unit 60, The first zone 10 and the second zone 20 can be determined based on the currently driving recommended lane, the static speed of the road, the driving speed, and the driver's route deviation frequency.

The guide unit 70 may generate a guide that is output in the first zone 10 and a guide that is output in the second zone. Specifically, the guidance unit 70 provides a guidance guide in the first area 10 and a guidance guide in the second area 20 based on the driving information and the driving lane information of the current vehicle determined by the lane determination unit 100. can be created identically or differently.

For example, the guidance unit 70 may determine whether it is necessary to change the lane in which the vehicle is traveling in the first zone 10 and the second zone 20. If the vehicle needs to change the driving lane to the recommended lane in the second zone 20, the second zone 20 is closer to the point where it must turn than the first zone 10, so the guidance unit 70 In order to induce the driver to make a quick turn, the guide to change the driving lane from the first zone 10 to the recommended lane is announced louder or at a shorter cycle than the guide to be output in the first zone 10, or So that the driver can easily recognize this, more specific and detailed guidance can be provided than the guidance guide in the first area 10 of the display unit 40.

Additionally, the guidance unit 70 may use geographical features when determining a guidance guide. For example, the guide output from the first area 10 may not include a geographical feature, but the guide output from the second area 20 may include information about the geographical feature. In this case, the driver has the advantage of being able to more accurately perceive information about the turning zone in the second zone 20.

A specific example in which the guidance unit 70 determines a different guidance guide will be described later with reference to other drawings.

The guidance unit 70 has a memory (not shown) that stores data for an algorithm for controlling the operation of the components of the navigation device 1 or a program that reproduces the algorithm, and uses the data stored in the memory to perform the above-mentioned functions. It may be implemented with a processor (not shown) that performs the operation. At this time, the memory and processor may each be implemented as separate chips. Alternatively, the memory and processor may be implemented as a single chip.

Meanwhile, the navigation device 1 may further include other configurations in addition to the configuration described above in FIG. 4, and may be provided with a configuration necessary for the above-described operation without being limited by the name. In FIG. 4, the guidance unit 70 Although the lane determination unit 100 is shown as a separate component, the guidance guide unit 70 and the lane determination unit 100 may be implemented as one component.

FIG. 12 is a flowchart for explaining the operation of the disclosed navigation device 1, and FIG. 13 is a diagram for explaining cases in which a guidance guide is needed and cases in which it is not required depending on the vehicle's driving lane.

Referring to FIG. 12, the navigation device 1 may divide the turning area included in the driving route into a first area and a second area (S100).

Specifically, as described above in FIG. 4, the navigation device 1 divides the first zone 10 and the second zone 20 according to road information based on pre-stored static settings, and determines whether the vehicle is currently driving. The first zone 10 and the second zone 20 may be determined based on changing factors such as the actual lane, the recommended lane, the static speed of the road, the driving speed, and the frequency of the driver deviating from the route.

The navigation device 1 may determine whether the area in which the vehicle is currently driving is in the first area 10 or the second area 20 based on GPS information (S200, 300).

If the vehicle is driving in the first zone 10, the navigation device 1 may determine whether the driving lane is in the recommended lane (S210).

Specifically, the navigation device 1 may determine whether the vehicle is currently driving in the recommended lane based on lane information determined by the lane determination unit 100.

If it is not determined that the vehicle is driving in the recommended lane, the navigation device 1 may output a guidance guide indicating that a change in the driving lane is necessary (S220).

The guidance guide output by the navigation device 1 in the first area 10 may vary. For example, as shown in FIG. 13, in a situation where the first vehicle 11 is driving in the first zone and driving in the first lane, the vehicle may move to the third or fourth lane in order to proceed straight according to the driving path. If a change is necessary, the display unit 40 may output a user interface displaying the recommended lane while including the guidance message “Prepare to change to the right lane.”

If the third vehicle 13 is driving in the 4th lane as shown in FIG. 14, and the 4th lane is the recommended lane, the navigation device 1 outputs a guide to continue driving in the driving lane, or provides a separate Guidance may not be provided (S400).

If the vehicle is driving in the second zone 20, the navigation device 1 may determine whether the driving lane is in the recommended lane (S310).

Specifically, the navigation device 1 may determine whether the driving lane is in the recommended lane based on the GPS signal and the vehicle's driving lane information determined by the lane determination unit 100.

If the driving lane is not the recommended lane, the navigation device 1 outputs a guidance guide indicating that the driving lane needs to be changed (S320).

For example, as shown in FIG. 13, in a situation where the second vehicle 12 is driving in the second zone and driving in two lanes, it must drive in three or four lanes in order to proceed straight according to the driving path. When it is necessary to change, the display unit 40 may output a user interface displaying the recommended lane while including the guidance message “Prepare to change to the right lane.”

At this time, the guidance guide output from the second zone 20 by the navigation device 1 makes a louder sound than the guidance guide output from the first zone 10 or is used so that the user can perceive the guidance guide more accurately. We can provide specific guidance.

For example, if the message "Prepare to change to the right lane" is printed in the first zone (10), the message "Please change lanes to the recommended lane 3" is printed in the second zone (20) or "Change to the left lane based on the current lane." You can print out a specific guidance guide that says, “Please move to the second lane.” In addition, when outputting the second guide, the navigation device 1 may output a screen that changes the color of the guide displayed on the display unit 40 in various ways, unlike the first guide. The guide can be output louder than the guide. Through this, drivers can more effectively recognize notifications to change lanes.

Additionally, when the navigation device 1 outputs a guide in the second area 20, the navigation device 1 may output the guide using a user interface or a guidance message that includes geographical features that can be visually confirmed by the driver.

For example, if the recommended lane is 1 lane or the vehicle is driving in a straight lane, the navigation device 1 may output a guidance message such as “You are turning left at this traffic light. Please move the lane to the left.” If the recommended lane is a straight lane or the vehicle is driving in a left turn lane, the navigation device 1 may output a guidance message such as “The current driving lane is a left turn lane. Please move to the right lane.”

If the driving lane is a recommended lane, the navigation device 1 may output a guidance guide to continue driving in the driving lane in the second area 20 or may not provide separate guidance (400).

14 to 16 are diagrams showing examples of outputting different guides in the first zone 10 and the second zone 20. To avoid redundant explanation, they are explained together below.

The navigation device 1 may output a guidance guide in the first area 10 as shown in FIG. 14 . Specifically, the navigation device 1 outputs a user interface that displays each turning point (800m right turn, 500m right turn) on the display unit 40, while displaying the vehicle's current speed (85km/h) and destination based on driving information. Information including the estimated time required (15 minutes) can be displayed on the display unit 40.

The navigation device 1 determines that the vehicle is driving in a lane other than the recommended lane in the first area 10 based on the GPS signal and the driving lane information determined by the lane determination unit 100. The navigation device 1 outputs a user interface telling people to move to the right lane, which is the recommended lane, and "Please move to the right lane," and outputs a message through the output unit 50, "The current lane is a left turn lane. Change to the right lane." A voice signal saying “Get ready” can be output to the speaker 51.

The navigation device 1 may output a guidance guide in the second area 20 as shown in FIG. 15 . Specifically, the navigation device 1 outputs a user interface that displays each turning point (50 m left turn, 500 m right turn) on the display unit 40, while displaying the vehicle's current speed (35 km/h) and destination based on driving information. Information including the estimated time required (15 minutes) can be displayed on the display unit 40.

The navigation device 1 determines, based on the GPS signal, that the vehicle is driving in the second zone 20 in a straight lane rather than the recommended lane. As shown in FIG. 16, the navigation device 1 outputs a user interface indicating to move to the left lane, which is the recommended lane, and a user interface saying "Turn left," while providing topographic information saying "Turn left at this traffic light" through the output unit 50. A voice signal including the name of the water can be output to the speaker 51.

The navigation device 1 may output a guidance guide in the second area 20 as shown in FIG. 16 . Specifically, the navigation device 1 outputs a user interface that displays a recommended lane with an arrow in addition to a user interface that displays a turning point (500m right turn) on the display unit 40, and displays the vehicle's current speed (85km) based on driving information. /h) and information including the estimated time required to reach the destination (15 minutes) can be displayed on the display unit 40.

The navigation device 1 determines, based on the GPS signal, that the vehicle is traveling in the left turn lane rather than the recommended lane in the second zone 20. The navigation device 1 outputs the user interface "Please move to the 5th lane" as shown in FIG. 16 and a guidance message to move to the recommended right lane or the 5th lane through the output unit 50. The voice signal “The lane is a left turn lane. Please move to lane 5” can be output through the speaker 51.

In this way, the navigation device 1 outputs different guides for the first zone 10 and the second zone 20, thereby reducing the possibility of the driver deviating from the driving path.

Meanwhile, even if the navigation device 1 distinguishes between the first zone 10 and the second zone 20, if the vehicle is driving in the recommended lane in the first zone 10, it does not output a guidance guide and displays the second zone 10. The information guide can only be printed in area 20. Additionally, when the navigation device 1 must drive straight in the second zone 20 without entering a turning point on the driving path, the navigation device 1 may not output a guidance guide in the second zone 20 as well.

FIG. 17 is a diagram illustrating the relationship between a navigation guide server, a vehicle, and a user terminal according to an embodiment.

Specifically, FIG. 17 shows the relationship between the navigation guide server 200, the vehicle 300, and the user terminal 400 when the navigation guide explained in the previous drawing is implemented as the navigation guide server 200. This is a drawing.

The navigation guide server 200 may include at least some of the components described in FIG. 4 . Therefore, when the navigation service providing server 200 according to FIG. 17 is the entity that provides the navigation guide service to the driver, it determines the driving lane of the vehicle 300 based on the driving information of the vehicle 300 and determines the driving lane of the vehicle 300. Based on the driving information and the location information of the vehicle 300, the turning area included in the driving path of the vehicle 300 is divided into a first zone and a second zone, and the lane change of the vehicle 300 in the first zone is If necessary, information about the lane that the vehicle 300 needs to change is generated as a guide in the first zone, and if the lane of the vehicle 300 needs to be changed in the second zone, which lane should the vehicle 300 need to change be selected based on the driving lane of the vehicle 300? Information on how many lanes to move in the direction can be generated as a guide for Zone 2, and the information about the guide for Zone 1 and Zone 2 created in this way can be transmitted to the vehicle 300. can do.

On the other hand, when the entity that provides the navigation guide service to the driver is the user terminal 400, the navigation service providing server 200 provides information about the guide in the first zone and the guide in the second zone described above to the user terminal ( 400). A method of determining the driving lane of the vehicle 300, a method of determining a first zone and a second zone, a method of generating a guidance guide of the first zone and a guidance guide of the second zone, and various embodiments thereof are described in detail. As mentioned above, the explanation for this will be omitted.

The server described in FIG. 17 refers to a typical server. A server is computer hardware on which a program is running, and monitors and controls the entire network, such as printer control or file management, or other networks through a mainframe or public network. Connection to, or sharing of, software resources such as data, programs, files, modems, fax machines, printers. It can support sharing hardware resources such as other equipment.

The navigation device 1 and the guidance method of the navigation device according to one embodiment can provide accurate guidance suitable for various situations by dividing the turning area into a turning preparation area and a turning proximity area according to the conditions of the driving route.

In addition, the navigation device 1 and the guidance method of the navigation device according to one embodiment provide different guidance guides provided in the turn preparation area and guidance provided in the turn proximity area, thereby preventing the driver from driving outside the turn area. This has the advantage of suppressing road congestion, reducing the risk of accidents, and improving the reliability of navigation devices.

Meanwhile, the components, units, modules, components, etc. described in this specification as "~ part" may be implemented together or individually as separate but interoperable logic devices. The description of different features for modules, units, etc. is intended to highlight different functional embodiments and does not necessarily imply that they must be realized by individual hardware or software components. Rather, functionality associated with one or more modules or units may be performed by separate hardware or software components or may be integrated within common or separate hardware or software components.

Although operations are shown in the drawings in a particular order, it should not be understood that these operations are to be performed in the particular order shown, or sequential order, or that all depicted operations need to be performed to achieve the desired results. . In some environments, multitasking and parallel processing can be advantageous. Moreover, the distinction of various components in the above-described embodiments should not be construed as requiring such a distinction in all embodiments, and the described components may generally be integrated together into a single software product or packaged into multiple software products. It must be understood that it can be done.

A computer program (also known as a program, software, software application, script, or code) may be written in any form of a programming language, including a compiled or interpreted language, or an a priori or procedural language, as a stand-alone program or module; It can be deployed in any form, including components, subroutines, or other units suitable for use in a computer environment.

Additionally, the logic flow and structural block diagram described in this patent document describe corresponding actions and/or specific methods supported by corresponding functions and steps supported by the disclosed structural means, and correspond to It can also be used to build software structures and algorithms and their equivalents.

The processes and logic flows described herein can be performed by one or more programmable processors, each of which executes one or more computer programs to perform functions by operating on input data and generating output.

The present description sets forth the best mode of the invention and provides examples to illustrate the invention and to enable any person skilled in the art to make or use the invention. The specification prepared in this way does not limit the present invention to the specific terms presented.

Although the present invention has been described above with reference to preferred embodiments, those skilled in the art or have ordinary knowledge in the relevant technical field should not deviate from the spirit and technical scope of the present invention as set forth in the claims to be described later. It will be understood that the present invention can be modified and changed in various ways within the scope of the present invention.

Therefore, the technical scope of the present invention should not be limited to what is described in the detailed description of the specification, but should be determined by the scope of the patent claims.

1: Navigation device
30: Department of Communications
40: Display unit
50: output unit
60: storage unit
70: Information guide section
100: Lane judgment unit
120: Lane prediction artificial neural network module
200: Navigation guide server
300: vehicle
400: User terminal

Claims (8)

a lane determination unit that determines a driving lane of the vehicle based on driving information of the vehicle; and
Dividing the turning zone included in the driving path of the vehicle into a first zone and a second zone based on the driving information of the vehicle and the location information of the vehicle;
When the vehicle needs to change lanes in the first zone, information about the lane that the vehicle must change into is generated as a guide for the first zone,
When the vehicle needs to change lane in the second zone, a guide unit that generates information on which direction and how many lanes to move based on the vehicle's driving lane as a guide for the second zone; do
The information guide section,
The driver's driving skill is calculated based on the driver's route deviation frequency, and if the driving skill does not satisfy the threshold, the length of the first zone and the second zone is calculated so that the driving skill is equal to the threshold. Determine to be longer than the length of the first zone and the second zone when satisfied,
If the driving speed of the vehicle is higher than the static speed of the road on which the vehicle travels, the starting points of the first zone and the second zone are determined to be longer than the starting point according to the static set value,
If it is determined that the road on which the vehicle is traveling is a congested section based on the driving information, the starting point of the first zone and the second zone is determined to be shorter than the starting point according to the static setting value,
If it is determined that a lane change for the vehicle is necessary in the first zone, a guide indicating that a change in the vehicle's driving lane is necessary is output as a guide for the first zone,
If it is determined that the vehicle's lane change is necessary in the second zone, a guide is provided regarding the current driving lane of the vehicle and in which direction and which lane to use based on the current driving lane of the vehicle. A navigation guide server that outputs information as a guide for the second area. According to clause 1,
The information guide section,
A navigation guide server that determines a recommended lane of the turning zone, calculates a difference between the vehicle's driving lane and the recommended lane, and determines the first zone and the second zone based on the difference. delete delete determining a driving lane of the vehicle based on driving information of the vehicle;
dividing a turning area included in the driving path of the vehicle into a first area and a second area based on the driving information of the vehicle and the location information of the vehicle; and
If a lane change of the vehicle is required in the first zone, information about the lane to which the vehicle must change is generated as a guide for the first zone, and if a lane change of the vehicle is required in the second zone, the vehicle Generating information about how many lanes to move in which direction based on the driving lane as a guide for the second zone;
The step of dividing the rotation zone into a first zone and a second zone,
The driver's driving skill is calculated based on the driver's route deviation frequency, and if the driving skill does not satisfy the threshold, the length of the first zone and the second zone is calculated so that the driving skill is equal to the threshold. Determine to be longer than the length of the first zone and the second zone when satisfied,
If the driving speed of the vehicle is higher than the static speed of the road on which the vehicle travels, the starting points of the first zone and the second zone are determined to be longer than the starting point according to the static set value,
When it is determined that the road on which the vehicle is traveling is a congested section based on the driving information, determining the starting point of the first zone and the second zone to be shorter than the starting point according to a static set value,
The guide for the first area is,
If it is determined that a lane change for the vehicle is necessary in the first zone, a guide is generated indicating that a change in the vehicle's driving lane is necessary,
If it is determined that the vehicle's lane change is necessary in the second zone, a guide is created as guidance on the current driving lane of the vehicle and in which direction and which lane to use based on the current driving lane of the vehicle. This is a navigation guide method. a lane determination unit that determines a driving lane of the vehicle based on driving information of the vehicle;
Dividing the turning area included in the driving path of the vehicle into a first area and a second area based on the driving information and the location information of the vehicle,
When the vehicle needs to change lanes in the first zone, information about the lane to which the vehicle needs to change is generated and output as a guide for the first zone, and when the vehicle needs to change lanes in the second zone. A guide unit that generates and outputs information about how many lanes to move in which direction based on the driving lane of the vehicle as a guide for the second zone;
The information guide section,
The driver's driving skill is calculated based on the driver's route deviation frequency, and if the driving skill does not satisfy the threshold, the length of the first zone and the second zone is calculated so that the driving skill is equal to the threshold. Determine to be longer than the length of the first zone and the second zone when satisfied,
If the driving speed of the vehicle is higher than the static speed of the road on which the vehicle travels, the starting points of the first zone and the second zone are determined to be longer than the starting point according to the static set value,
If it is determined that the road on which the vehicle is traveling is a congested section based on the driving information, the starting point of the first zone and the second zone is determined to be shorter than the starting point according to the static setting value,
If it is determined that a lane change for the vehicle is necessary in the first zone, a guide indicating that a change in the vehicle's driving lane is necessary is output as a guide for the first zone,
If it is determined that the vehicle's lane change is necessary in the second zone, a guide is provided regarding the current driving lane of the vehicle and in which direction and which lane to use based on the current driving lane of the vehicle. A navigation device that outputs as a guide for the second area. According to clause 6,
The information guide section,
A navigation device that uses terrain features included in the turning zone and outputs them as a guide for the second zone when the vehicle needs to change lanes in the second zone. According to clause 6,
The information guide section,
A navigation device in which the first zone guide provides guidance using a speaker, and the second zone guide simultaneously provides guidance using a display unit and the speaker.