KR102438114B1 - Method and apparatus for determining a driving route of a vehicle - Google Patents

Abstract

The present invention relates to a method and apparatus for determining a vehicle driving route. In the method according to one embodiment of the present invention, a first driving route estimated that a vehicle is driving is obtained based on a GPS signal on a vector map displaying a plurality of driving routes, a second driving route estimated that the vehicle is driving is obtained based on a front image filming a front of the vehicle, the first driving route is corrected based on the second driving route, and as a result of correction of the first driving route on the vector map, a final driving route that the vehicle is driving is determined.

Description

METHOD AND APPARATUS FOR DETERMINING A DRIVING ROUTE OF A VEHICLE

The present invention relates to a method and apparatus for determining a travel route of a vehicle.

A vehicle traveling on a road may travel between any two lanes among a plurality of lanes included in the road, and the vehicle may frequently change a driving route while driving.

A GPS device may be used to determine on which driving route the vehicle is currently traveling. The device for determining the driving route of the vehicle may receive a GPS signal from a satellite and derive absolute position values on latitude and longitude of the vehicle from the GPS signal. Through this, the device for determining the driving path of the vehicle may estimate on which driving path the vehicle is currently on the basis of the GPS signal.

However, an error may exist in the vehicle location information estimated from the GPS signal. Accordingly, there is a need for research on a method for more accurately determining a driving path of a vehicle.

The above-mentioned background art is technical information possessed by the inventor for the derivation of the present invention or acquired in the process of derivation of the present invention, and cannot necessarily be said to be a known technique disclosed to the general public prior to the filing of the present invention.

SUMMARY OF THE INVENTION The present invention is to provide a method and apparatus for determining a travel route of a vehicle. The problem to be solved by the present invention is not limited to the above-mentioned problems, and other problems and advantages of the present invention not mentioned can be understood by the following description, and more clearly understood by the embodiments of the present invention will be In addition, it will be appreciated that the problems and advantages to be solved by the present invention can be realized by means and combinations thereof indicated in the claims.

As a technical means for achieving the above-described technical problem, a first aspect of the present disclosure is a method for determining a driving path of a vehicle, wherein the vehicle is traveling in a vector map in which a plurality of driving paths are displayed based on a GPS signal. obtaining a first travel route estimated to be acquiring a second driving route estimated to be driven by the vehicle based on a front image captured in front of the vehicle; correcting the first travel path based on the second travel path; and determining a final driving path in which the vehicle is traveling as a result of correcting the first driving path on the vector map.

In addition, in the step of correcting, when the number of lanes located on the right or left side of the first driving path is different from the number of lanes located on the right side or left side of the second driving path, the first driving path is set to the first driving path. correcting the first driving path as a third driving path in the vector map to correspond to the second driving path, wherein the third driving path is based on the number of lanes located on the right or left side of the second driving path. Based on the second driving path, it may correspond to a driving path on the vector map that is positionally corresponding to the second driving path.

In addition, the correcting may include, when the stop line is not included in the lane information obtained based on the front image, a lateral correction value of the third driving path so that the third driving path matches the second driving path. and deriving a heading angle correction value; and correcting the third driving path as a fourth driving path by applying the lateral direction correction value and the heading angle correction value to the third driving path. The determining of the final driving path may include determining the fourth driving path as the final driving path.

In addition, the correcting may include: when a stop line is included in the lane information obtained based on the front image, a lateral correction value of the third driving path so that the third driving path matches the second driving path; deriving a longitudinal correction value and a heading angle correction value; and correcting the third driving path as a fourth driving path by applying the lateral correction value, the longitudinal correction value, and the heading angle correction value to the third driving path. The determining of the final driving path may include determining the fourth driving path as the final driving path.

The acquiring of the first driving route may include: acquiring a current location of the vehicle based on the GPS signal; converting the vector map into a local vector map based on a Cartesian coordinate system having the current location of the vehicle as an origin; and acquiring a first driving path from among at least one driving path included in the local vector map. may include.

The acquiring of the second driving route may include: inputting the forward image into a deep neural network (DNN) to predict lanes in the forward image; and displaying lanes in the front image on a Cartesian coordinate system having a current location of the vehicle as an origin; and obtaining the second driving route based on the lanes displayed on the Cartesian coordinate system.

A second aspect of the present disclosure provides an apparatus for determining a driving route of a vehicle, comprising: a memory in which at least one program is stored; and a processor that performs an operation by executing the at least one program, wherein the processor selects a first driving path on which the vehicle is determined to be driving in a vector map including a plurality of driving paths based on a GPS signal. obtaining, based on a front image photographed in front of the vehicle, obtaining a second driving path in which the vehicle is determined to be driving, correcting the first driving path based on the second driving path, and the vector A final driving path in which the vehicle is traveling is determined as a result of correcting the first driving path on a map.

A third aspect of the present disclosure may provide a computer-readable recording medium recording a program for executing the method according to the first aspect on a computer.

In addition to this, another method for implementing the present invention, another system, and a computer-readable recording medium storing a computer program for executing the method may be further provided.

Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims, and detailed description of the invention.

According to the above-described problem solving means of the present disclosure, the vehicle can more accurately provide the current travel route.

In addition, according to the problem solving means of the present disclosure, it is possible to provide a simple and reliable method of correcting a driving path of a vehicle by using only a lane recognition result based on an image in front of the vehicle.

In addition, according to the problem solving means of the present disclosure, the lane recognition result based on the image in front of the vehicle and the correction value derived based on the GPS signal are stored in the memory, and the correction value is used even in the section where lane recognition is impossible. You can correct the driving path of

1 is a diagram illustrating a driving path of a vehicle according to an exemplary embodiment.
2 is a block diagram of an apparatus for determining a driving path of a vehicle according to an exemplary embodiment.
3 is a diagram illustrating a method of obtaining a first driving path in which a vehicle is estimated to be traveling from a vector map according to an exemplary embodiment.
4 is a diagram illustrating a method of acquiring a first driving path in which a vehicle is estimated to be traveling based on a front image of the vehicle according to an exemplary embodiment;
5 is a diagram exemplarily illustrating lanes predicted by a lane recognition unit according to an exemplary embodiment.
6 is a diagram exemplarily illustrating a method of correcting a first driving path based on a second driving path according to an exemplary embodiment.
7 is a diagram exemplarily illustrating a method of correcting a position and a heading angle of a driving path according to an exemplary embodiment.
8 is a diagram exemplarily illustrating a method of correcting a position and a heading angle of a driving path according to an exemplary embodiment.
9 is a diagram exemplarily illustrating a method of correcting a driving path of a vehicle using a lane keeping support system according to an exemplary embodiment.
10 is a flowchart of a method for determining a driving path of a vehicle according to an embodiment.
11 is a block diagram of a server that determines a driving route of a vehicle according to an exemplary embodiment.

Advantages and features of the present invention, and a method for achieving them will become apparent with reference to the detailed description in conjunction with the accompanying drawings. However, it should be understood that the present invention is not limited to the embodiments presented below, but may be implemented in a variety of different forms, and includes all transformations, equivalents, and substitutes included in the spirit and scope of the present invention. . The embodiments presented below are provided to complete the disclosure of the present invention, and to completely inform those of ordinary skill in the art to the scope of the present invention. In describing the present invention, if it is determined that a detailed description of a related known technology may obscure the gist of the present invention, the detailed description thereof will be omitted.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It is to be understood that this does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Some embodiments of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented in various numbers of hardware and/or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors, or by circuit configurations for a given function. Also, for example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented as an algorithm running on one or more processors. Further, the present disclosure may employ prior art techniques for electronic configuration, signal processing, and/or data processing, etc. Terms such as "mechanism", "element", "means" and "configuration" will be used broadly. and are not limited to mechanical and physical configurations.

In addition, the connecting lines or connecting members between the components shown in the drawings only exemplify functional connections and/or physical or circuit connections. In an actual device, a connection between components may be represented by various functional connections, physical connections, or circuit connections that are replaceable or added.

Hereinafter, a 'vehicle' may mean any type of transportation means used to move people or things with an engine, such as a car, a bus, a motorcycle, a kickboard, or a truck.

In addition, a road means a road on which vehicles travel, and may include, for example, various types of roads such as a highway, a national road, a local road, a high-speed national road, and an automobile-only road. A lane means a road space separated from each other through dividing lines displayed on the road surface. The dividing line means a solid line or a dotted line displayed on the road surface to distinguish a lane.

Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings.

1 is a diagram illustrating a driving path of a vehicle according to an exemplary embodiment.

A vehicle traveling on a road may travel between any two lanes among a plurality of lanes included in the road, and a path on which the vehicle is currently traveling may be referred to as a driving path. Meanwhile, the vehicle may frequently change the driving route while driving.

A GPS device may be used to determine on which driving route the vehicle is currently traveling. The device for determining the driving route of the vehicle may receive a GPS signal from a satellite and derive absolute position values on latitude and longitude of the vehicle from the GPS signal. Through this, the device for determining the driving path of the vehicle may estimate on which driving path the vehicle is currently on the basis of the GPS signal.

However, an error may exist in the vehicle location information estimated from the GPS signal. Accordingly, the driving path of the vehicle estimated based on the GPS signal may be different from the driving path on which the actual vehicle is driving. For example, referring to FIG. 1 , the driving path 120 of the vehicle 100 estimated from the GPS signal and the driving path 110 on which the vehicle 100 is actually driving on the road may be different. Accordingly, it is necessary to correct the driving route of the vehicle estimated based on the GPS signal.

2 is a block diagram of an apparatus for determining a driving path of a vehicle according to an exemplary embodiment.

Referring to FIG. 2 , the apparatus 200 for determining a driving path of a vehicle may include a memory 210 , a sensor unit 220 , a communication unit 230 , and a processor 240 . Only the components related to the embodiment are shown in the apparatus 200 for determining the driving route of the vehicle of FIG. 2 . Accordingly, it can be understood by those skilled in the art that other general-purpose components may be further included in addition to the components shown in FIG. 2 .

The memory 210 is hardware for storing various data processed in the apparatus 200 for determining the driving route of the vehicle, and may store a program for processing and controlling the processor 240 . For example, the memory 210 may store a vector map in which a plurality of driving paths through which the vehicle may travel are displayed.

The memory 210 is a random access memory (RAM), such as dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), CD- It may include ROM, Blu-ray or other optical disk storage, a hard disk drive (HDD), a solid state drive (SSD), or flash memory.

The sensor unit 220 includes a photographing device for photographing the surroundings of the vehicle, a sensor for measuring the mileage of the vehicle (eg, a vehicle speedometer, an odometer, an accelerometer, etc.) or a sensor for measuring the rotation angle of the vehicle (eg, the magnetic sensor, gyro sensor, etc.). The device for photographing the surroundings of the vehicle may be a still camera or a video camera configured to record the environment outside the vehicle. The imaging device may include a plurality of cameras, and the plurality of cameras may be disposed at a plurality of locations on the inside and outside of the vehicle. The sensor unit 220 may transmit to the processor 240 a front image of the vehicle obtained from the device for photographing the surroundings of the vehicle.

The communication unit 230 may include one or more components for performing wired/wireless communication with an external server or an external device. For example, the communication unit 230 may include at least one of a short-range communication unit (not shown), a mobile communication unit (not shown), and a broadcast receiving unit (not shown). For example, the communication unit 230 may receive a GPS signal from a Global Positioning System (GPS) satellite.

The processor 240 controls the overall operation of the device 200 for determining the driving route of the vehicle. For example, the processor 240 may generally control the input unit (not shown), the display (not shown), the communication unit 230 , the memory 210 , and the like by executing programs stored in the memory 210 . The processor 240 may control the operation of the apparatus 200 for determining the driving route of the vehicle by executing programs stored in the memory 210 . For example, the processor 240 may include a lane recognition unit 250 , a GPS signal processing unit 260 , and a driving path correcting unit 270 .

The lane recognition unit 250 may receive an image of the front of the vehicle from the sensor unit 220 , and may obtain a driving path estimated to be driven by the vehicle based on the image in front of the vehicle.

Also, the GPS signal processing unit 260 may obtain a GPS signal from the communication unit 230 , and obtain a vector map in which a plurality of driving paths on which the vehicle may travel are displayed from the memory 210 . The GPS signal processing unit 260 may obtain a driving path estimated to be driving the vehicle from a vector map in which a plurality of driving paths are displayed, based on the GPS signal.

On the other hand, since there may be an error in the location information of the vehicle estimated from the GPS signal, the driving path estimated by the GPS signal processing unit 260 that the vehicle is driving on the vector map may be different from the driving path on which the actual vehicle is driving.

Accordingly, the driving path corrector 270 may correct the driving path acquired from the GPS signal processing unit 260 based on the driving path acquired from the lane recognition unit 250 . Finally, the driving path corrector 270 may determine the final driving path in which the vehicle is traveling as a result of correcting the driving path obtained from the GPS signal processing unit 260 on the vector map.

Processor 240 is ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), controllers (controllers), microcontroller It may be implemented using at least one of (micro-controllers), microprocessors, and other electrical units for performing functions.

As an embodiment, the device 200 for determining the driving path of the vehicle may be an electronic device having mobility. For example, the apparatus 200 for determining the driving route of a vehicle may include a smartphone, a tablet PC, a PC, a smart TV, a personal digital assistant (PDA), a laptop, a media player, a navigation device, a device equipped with a camera, and other mobile electronic devices. It can be implemented as a device. Also, the apparatus 200 for determining the driving route of the vehicle may be implemented as a wearable device such as a watch, glasses, a hair band, and a ring having a communication function and a data processing function.

In another embodiment, the device 200 for determining the driving route of the vehicle may be an electronic device embedded in the vehicle. For example, the device 200 for determining the driving route of the vehicle may be an electronic device inserted into the vehicle through tuning after the production process.

As another embodiment, the apparatus 200 for determining the driving route of the vehicle may be a server located outside the vehicle. The server may be implemented as a computer device or a plurality of computer devices that communicate through a network to provide commands, codes, files, contents, services, and the like. The server may receive data necessary to determine a current driving path in which the vehicle is traveling from devices mounted on the vehicle, and determine the driving path of the vehicle based on the received data.

3 is a diagram illustrating a method of obtaining a first driving path in which a vehicle is estimated to be traveling from a vector map according to an exemplary embodiment.

According to an embodiment, the device for determining the driving route of the vehicle may acquire the current location of the vehicle based on the GPS signal. In addition, the apparatus for determining the driving path of the vehicle converts the vector map into a local vector map based on a Cartesian coordinate system having the current position of the vehicle as the origin, and the vehicle is running among at least one driving path included in the local vector map. The estimated first driving path may be acquired.

Referring to FIG. 3 , the GPS signal processing unit 260 may receive the vector map 300 stored in the memory 210 . For example, the vector map 300 may correspond to a driving route map in which a plurality of driving paths on which the vehicle can travel are displayed. An arbitrary vector on the vector map 300 passes through the middle of the lanes located on both sides of the arbitrary vector, and may be parallel to the lanes located on both sides of the arbitrary vector. The vector map 300 may correspond to a map based on a spherical coordinate system in the form of longitude, latitude, and height. For example, the vector map 300 may be a map based on the WGS 84 (World   Geodetic   System   1984) coordinate system, but is not limited thereto.

In addition, the GPS signal processing unit 260 converts a vector map based on a spherical coordinate system to a local ENU (East Northeast) coordinate system corresponding to an orthogonal coordinate system in order to obtain a driving route estimated that the vehicle is driving in the vector map 300. It can be converted to a vector map.

Meanwhile, the GPS signal processing unit 260 may receive a GPS signal from the communication unit 230 , and may obtain a current location of the vehicle based on the GPS signal. The current position of the vehicle based on the GPS signal may be expressed in the form of a spherical coordinate system. The GPS signal processing unit 260 may convert the current location of the vehicle expressed in the spherical coordinate system format into the local ENU coordinate system format.

Finally, the GPS signal processing unit 260 may convert the vector map based on the local ENU coordinate system into the local vector map 310 having a predetermined size with the current location of the vehicle converted into the local ENU coordinate system as the origin.

The GPS signal processing unit 260 may acquire a first driving path, on which the vehicle is estimated, from among at least one driving path included in the local vector map 310 . For example, as shown in FIG. 3 , driving paths a1 , a2 , and a3 may be included in the local vector map 310 , and finally, the GPS signal processing unit 260 determines that the vehicle travels in consideration of the current location of the vehicle. It can be assumed to be located on path a2.

Meanwhile, as described above, the vector map may correspond to a precise lane map rather than a driving path map in which a plurality of driving paths are displayed. The precision lane map may correspond to a map including only lane information among information of the precision road map. The precision road map may correspond to a three-dimensional digital map including lane information, regulatory and safety information, and various road facilities.

4 is a diagram illustrating a method of acquiring a first driving path in which a vehicle is estimated to be traveling based on a front image of the vehicle according to an exemplary embodiment;

According to an embodiment, the apparatus for determining the driving route of the vehicle inputs a front image photographing the front of the vehicle to a deep neural network (DNN) to predict lanes in the front image, and to determine the lanes in the front image of the vehicle. The position can be displayed on the Cartesian coordinate system as the origin. The apparatus for determining the driving path of the vehicle may acquire the second driving path, in which the vehicle is estimated to be traveling, based on the lanes displayed on the Cartesian coordinate system.

Referring to FIG. 4 , the lane recognition unit 250 may receive a front image 400 photographed in front of the vehicle from the sensor unit 220 . The lane recognition unit 250 may include a deep neural network (DNN) module.

The DNN module may be trained to receive the front image 400 and predict positions or properties of lanes included in the front image 400 . For example, the range of correction that can be performed by the driving path corrector 270, which will be described later, may vary according to the type of learning data used for learning the DNN module.

For example, the learning data used for learning the DNN module may correspond to data in which positions in images of both lanes of a path on which the vehicle is currently traveling are labeled. That is, the training data used for learning of the DNN module may correspond to data in which positions of two lanes are labeled in an image.

Alternatively, the learning data may correspond to data in which positions in an image of each of a plurality of lanes including other lanes as well as both lanes of a path on which the vehicle is currently traveling are labeled.

Alternatively, the learning data may correspond to data in which positions and attributes in images of each of a plurality of lanes including other lanes as well as both lanes of a path on which the vehicle is currently traveling are labeled. For example, the attribute of the lane may correspond to a 'center line', a 'stop line', or a 'general lane', but is not limited thereto.

As shown in FIG. 4 , the DNN module may include an encoder 410 , a lane instance decoder 420 , and a lane attribute decoder 430 . The encoder 410 of the DNN module may convert the input low-level front image 400 into high-level features. The lane instance decoder 420 may predict the lane instances from the front image converted into high-level features in units of pixels. The lane attribute decoder 430 may predict which attribute each lane instance in the front image has.

5 is a diagram exemplarily illustrating lanes predicted by a lane recognition unit according to an exemplary embodiment.

Referring to FIG. 5 , the lane recognition unit 250 may acquire lane instances included in the front image of the vehicle from the DNN module. Meanwhile, the obtained lane instances may correspond to the lane instances 500 displayed on the image coordinate system having the origin of the apparatus for photographing the front image.

The lane recognizer 250 may convert the lane instances 500 displayed on the image coordinate system to be displayed on the vehicle coordinate system. The vehicle coordinate system may correspond to a Cartesian coordinate system having the current position of the vehicle as an origin. That is, the lane recognizer 250 may convert the lane instances 500 displayed on the image coordinate system into lane instances 510 displayed on the vehicle coordinate system. In addition, each of the lane instances 510 displayed on the vehicle coordinate system may be expressed in a polynomial form.

The lane recognizer 250 may acquire at least one driving route 520 displayed on the vehicle coordinate system based on the lane instances 510 displayed on the vehicle coordinate system. The lane recognizing unit 250 may acquire a second driving path, in which the vehicle is estimated to be traveling, among at least one driving path 520 displayed on the vehicle coordinate system. For example, as shown in FIG. 3 , the driving paths 520 on the vehicle coordinate system obtained based on the front image of the vehicle may include b1, b2, and b3, and finally, the lane recognition unit 250 determines the vehicle It can be estimated that the vehicle is located on the driving path b3 by considering the current location of .

6 is a diagram exemplarily illustrating a method of correcting a first driving path based on a second driving path according to an exemplary embodiment.

According to an embodiment, the apparatus 200 for determining the driving path of the vehicle determines the first driving path in which the vehicle is estimated to be driving based on the GPS signal, and the second driving path in which the vehicle is estimated to be driving based on the front image of the vehicle. 2 Can be corrected based on the travel route. First, the apparatus 200 for determining the driving path of the vehicle determines that the first driving path is determined when the number of lanes located on the right or left side of the first driving path is different from the number of lanes located on the right or left side of the second driving path. The first driving path may be corrected as the third driving path in the vector map so as to correspond to the second driving path.

For example, it may be assumed that the lane recognizing unit 250 can recognize the position in the image of each of a plurality of lanes including other lanes as well as both lanes of the currently driving path. In this case, the driving path corrector 270 determines the number of lanes located on the right side of the first driving path in which the vehicle is estimated to be driving in the local vector map and the second driving path in which the vehicle is estimated to be driving in the front image of the vehicle. You can compare the number of lanes located to the right of The number of lanes located to the right of the first driving path is K (K is a natural number), the number of lanes located to the right of the second driving path is L (L is a natural number), and the lane recognition unit 250 can recognize The maximum number of lanes may be M. In this case, the maximum number of right lanes that the lane recognition unit 250 can recognize may be 0.5M.

For example, when K is greater than L and L is less than 0.5M, the first travel path may be corrected as a third travel path at a position moved left by (K-L) travel paths from the first travel path. . Alternatively, when K is smaller than L, the first travel path may be corrected as a third travel path at a position shifted to the right by (L-K) travel paths from the first travel path.

For example, when K is greater than L and L corresponds to 0.5M, since the number of lanes located on the right side of the first driving path is greater than the maximum number of right lanes that can be recognized by the lane recognition unit 250 , , it is not possible to correct the first travel path as the travel path on the vector map corresponding to the second travel path. Also, since it is not distinguished whether the lane located on the left side of the first driving path is a reverse driving lane that is beyond the center line, it may not be considered when correcting the driving path.

Meanwhile, it may be assumed that the lane recognizing unit 250 is capable of recognizing the location and properties in the image of each of a plurality of lanes including other lanes as well as both lanes of the currently driving path. In this case, since the centerline property can be utilized, the driving route can be corrected in consideration of the lanes located on the left. That is, when the lane recognizing unit 250 can recognize the position and properties of each of a plurality of lanes including other lanes as well as both lanes of the currently driving path, the position and properties of the lane located on the right or left In consideration of the number, the driving route may be corrected as described above.

On the other hand, it may be assumed that the lane recognizing unit 250 can recognize the positions in the image of only both lanes of the currently driving path. In this case, the first driving path is a vector map corresponding to the second driving path. It may not be calibrated with the driving route above.

Referring to FIG. 6 , the local vector map 600 may include driving paths a1, a2, and a3, and the GPS signal processing unit 260 determines that the vehicle is located on the first driving path a2 in consideration of the current position of the vehicle. can be estimated Meanwhile, b1, b2, and b3 may be included in the driving paths 610 on the vehicle coordinate system obtained based on the front image of the vehicle, and the lane recognition unit 250 determines that the vehicle is driven for the second time in consideration of the current location of the vehicle. It can be estimated that it is located on path b3. In this case, the driving path correcting unit 270 trusts the estimation result of the lane recognition unit 250 to determine the driving path of the vehicle in the vector map so that the first driving path a2 corresponds to the second driving path b3. It can be corrected from a2 to the third travel path a3. That is, the third driving path corresponds to a driving path on a local vector map that is positionally corresponding to the second driving path that the lane recognition unit 250 estimates that the vehicle is driving in the vehicle coordinate system based on the front image of the vehicle. can do. For example, the third driving path may correspond to a driving path on a local vector map that positionally corresponds to the second driving path based on the number of lanes located on the left or right side of the second driving path.

7 is a diagram exemplarily illustrating a method of correcting a position and a heading angle of a driving path according to an exemplary embodiment.

According to an embodiment, the apparatus 200 for determining the driving path of the vehicle may include the number of lanes located on the right or left side of the first driving path and the lanes located on the right or left side of the second driving path as described above with reference to FIG. 6 . When the number of is different from each other, the first driving path may be corrected as the third driving path in the vector map so that the first driving path corresponds to the second driving path. After correcting the first driving path as the third driving path, the apparatus 200 for determining the driving path of the vehicle may correct the position and the heading angle so that the third driving path matches the second driving path.

According to an embodiment, when the lane recognizing unit 250 does not include a stop line in the lane information obtained based on the front image, the driving path correcting unit 270 sets the third driving path to match the second driving path. A lateral correction value and a heading angle correction value of the third driving path may be derived. The driving path corrector 270 may correct the third driving path as the fourth driving path by applying the lateral direction correction value and the heading angle correction value to the third driving path. Finally, the fourth driving path may be determined as the final driving path in which the vehicle is traveling.

As described above in FIG. 6 , the driving path corrector 270 determines the driving path of the vehicle on the local vector map 600 so that the first driving path a2 on the local vector map 600 corresponds to the second driving path b3 . Correction may be performed from the first travel path a2 to the third travel path a3.

Also, the driving path corrector 270 may derive a lateral correction value Tx and a heading angle correction value θ of the third driving path a3 so that the third driving path a3 matches the second driving path b3 . The lateral correction value Tx is a position difference in the lateral direction between the second driving path b3 among the driving paths 610 on the vehicle coordinate system obtained based on the front image of the vehicle and the third driving path a3 on the local vector map 600 . is a value representing In addition, the heading angle correction value θ is the inclination angle difference between the second driving path b3 among the driving paths 610 on the vehicle coordinate system obtained based on the front image of the vehicle and the third driving path a3 on the local vector map 600 . is a value representing

The driving path corrector 270 may apply the lateral direction correction value Tx and the heading angle correction value θ to the third driving path a3 . Finally, the driving path corrector 270 may correct the third driving path a3 as the fourth driving path a4 , and may determine the fourth driving path a4 as the final driving path in which the vehicle is traveling.

As described above, when a stop line is not included in the lane information obtained by the lane recognition unit 250 based on the forward image, the longitudinal correction may not be performed.

8 is a diagram exemplarily illustrating a method of correcting a position and a heading angle of a driving path according to an exemplary embodiment.

According to an embodiment, when a stop line is included in the lane information obtained by the lane recognizing unit 250 based on the front image, the driving path correcting unit 270 sets the third driving path to match the second driving path. 3 It is possible to derive a lateral correction value, a longitudinal correction value, and a heading angle correction value of the driving path. The driving path corrector 270 may correct the third driving path as the fourth driving path by applying the lateral direction correction value, the longitudinal direction correction value, and the heading angle correction value to the third driving path. Finally, the fourth driving path may be determined as the final driving path in which the vehicle is traveling.

As described above in FIG. 6 , the driving path corrector 270 determines the driving path of the vehicle on the local vector map 600 so that the first driving path a2 on the local vector map 600 corresponds to the second driving path b3 . Correction may be performed from the first travel path a2 to the third travel path a3.

The driving path corrector 270 may derive a lateral correction value Tx, a longitudinal correction value Ty, and a heading angle correction value θ of the third driving path a3 so that the third driving path a3 matches the second driving path b3. . The lateral correction value Tx is a position difference in the lateral direction between the second driving path b3 among the driving paths 610 on the vehicle coordinate system obtained based on the front image of the vehicle and the third driving path a3 on the local vector map 600 . is a value representing The longitudinal correction value Ty is a position difference in the longitudinal direction between the second driving path b3 among the driving paths 610 on the vehicle coordinate system obtained based on the front image of the vehicle and the third driving path a3 on the local vector map 600 . is a value representing In addition, the heading angle correction value θ is the inclination angle difference between the second driving path b3 among the driving paths 610 on the vehicle coordinate system obtained based on the front image of the vehicle and the third driving path a3 on the local vector map 600 . is a value representing

That is, the driving path corrector 270 performs Iterative Closest Point (ICP) matching between the third driving path a3 and the second driving path b3, and the lateral correction value Tx, the longitudinal correction value Ty, and the heading angle correction value θ can be derived.

The driving path corrector 270 may apply the lateral correction value Tx, the longitudinal correction value Ty, and the heading angle correction value θ to the third driving path a3 . Finally, the driving path corrector 270 may correct the third driving path a3 as the fourth driving path a4 , and may determine the fourth driving path a4 as the final driving path in which the vehicle is traveling.

9 is a diagram exemplarily illustrating a method of correcting a driving path of a vehicle using a lane keeping support system according to an exemplary embodiment.

According to an embodiment, when the function for recognizing a lane does not exist in the apparatus 200 for determining the driving path of the vehicle, unlike described above with reference to FIGS. 1 to 8 , the driving path may be corrected. For example, when a lane keeping assist system (LKAS) is activated, it may be assumed that the vehicle is driving along the center of a lane located on both sides of a current driving path.

Referring to FIG. 9 , the local vector map 600 may include driving paths a1 , a2 , and a3 , and the GPS signal processing unit 260 determines that the vehicle is traveling on the first driving path a2 in consideration of the current location of the vehicle. can be presumed to be Meanwhile, when the lane keeping assist system is activated, it may be estimated that the vehicle is traveling on the second driving path b.

The driving path corrector 270 may derive a lateral correction value Tx and a heading angle correction value θ of the first driving path a2 so that the first driving path a2 matches the second driving path b. The lateral direction correction value Tx is a value representing a position difference in the lateral direction between the second driving path b, which is estimated by the lane keeping assisting system, that the vehicle is traveling, and the first driving path a2 on the local vector map 600 . In addition, the heading angle correction value θ is a value representing a difference in inclination angle between the second driving path b, which is estimated that the vehicle is driving, and the first driving path a2 on the local vector map 600 by the lane keeping support system.

The driving path corrector 270 may apply the lateral direction correction value Tx and the heading angle correction value θ to the first driving path a2 . Finally, the driving path corrector 270 may correct the first driving path a2 as the third driving path a4 , and may determine the third driving path a4 as the final driving path in which the vehicle is traveling.

10 is a flowchart of a method for determining a driving path of a vehicle according to an embodiment.

The method for determining the current lane of the vehicle shown in FIG. 10 is related to the embodiments described in the drawings described above, and therefore, even if omitted below, the contents described in the drawings are the same as those of FIG. 10 . method can also be applied.

Referring to FIG. 10 , in step 1010 , the processor may acquire a first driving path, in which the vehicle is estimated to be driving, from a vector map in which a plurality of driving paths are displayed based on a GPS signal.

According to an embodiment, the processor may obtain the current location of the vehicle based on the GPS signal and convert the vector map into a local vector map based on a Cartesian coordinate system having the current location of the vehicle as an origin. The processor may acquire a first driving path from among at least one driving path included in the local vector map.

In operation 1020 , the processor may acquire a second driving route, which is estimated to be driven by the vehicle, based on a front image captured in front of the vehicle.

According to an embodiment, the processor may input the front image to a deep neural network (DNN) to predict lanes in the front image, and display the lanes in the front image on a rectangular coordinate system having the current location of the vehicle as the origin. The processor may acquire the second driving route based on the lanes displayed on the Cartesian coordinate system.

In operation 1030, the processor may correct the first driving path based on the second driving path.

According to an embodiment, the processor is configured to determine that the first driving path is set to the second driving path when the number of lanes located on the right or left side of the first driving path is different from the number of lanes located on the right side or left side of the second driving path. To correspond to the first driving path in the vector map, the third driving path may be corrected.

According to an embodiment, when the stop line is not included in the lane information obtained based on the forward image, the processor corrects the lateral direction correction value and the heading angle of the third driving path so that the third driving path matches the second driving path value can be derived. The processor may correct the third driving path as the fourth driving path by applying the lateral correction value and the heading angle correction value to the third driving path, and may determine the fourth driving path as the final driving path.

According to an embodiment, when the stop line is included in the lane information obtained based on the forward image, the processor is configured to configure a lateral correction value and a longitudinal correction value of the third driving path so that the third driving path matches the second driving path. and a heading angle correction value may be derived. The processor may correct the third driving path as the fourth driving path by applying the lateral correction value, the longitudinal correction value, and the heading angle correction value to the third driving path, and determine the fourth driving path as the final driving path. can

In operation 1040, the processor may determine the final driving path in which the vehicle is traveling as a result of correcting the first driving path on the vector map.

11 is a block diagram of a server that determines a driving route of a vehicle according to an exemplary embodiment.

Referring to FIG. 11 , the server 1100 that determines the driving route of the vehicle may include a communication unit 1110 , a processor 1120 , and a DB 1130 . Only the components related to the embodiment are shown in the server 1100 for determining the driving route of the vehicle of FIG. 11 . Accordingly, it can be understood by those skilled in the art that other general-purpose components may be further included in addition to the components shown in FIG. 11 .

The communication unit 1110 may include one or more components for performing wired/wireless communication with an external server or an external device. For example, the communication unit 1110 may include at least one of a short-range communication unit (not shown), a mobile communication unit (not shown), and a broadcast receiving unit (not shown).

The DB 1130 is hardware for storing various data processed in the server 1100 that determines the driving route of the vehicle, and may store a program for processing and controlling the processor 1120 .

DB 1130 is a random access memory (RAM), such as dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), CD- It may include ROM, Blu-ray or other optical disk storage, a hard disk drive (HDD), a solid state drive (SSD), or flash memory.

The processor 1120 controls the overall operation of the server 1100 that determines the driving route of the vehicle. For example, the processor 1120 may generally control the input unit (not shown), the display (not shown), the communication unit 1110 , the DB 1130 , and the like by executing programs stored in the DB 1130 . The processor 1120 may control the operation of the server 1100 that determines the driving route of the vehicle by executing programs stored in the DB 1130 .

The processor 1120 may control at least a part of operations of the server 1100 that determines the driving route of the vehicle described above with reference to FIGS. 1 to 10 .

The processor 1120 is ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), controllers (controllers), microcontroller It may be implemented using at least one of (micro-controllers), microprocessors, and other electrical units for performing functions.

Embodiments according to the present invention may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded in a computer-readable medium. In this case, the medium includes a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM and DVD, a magneto-optical medium such as a floppy disk, and a ROM. , RAM, flash memory, and the like, hardware devices specially configured to store and execute program instructions.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and used by those skilled in the computer software field. Examples of the computer program may include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

According to an embodiment, the method according to various embodiments of the present disclosure may be included and provided in a computer program product. Computer program products may be traded between sellers and buyers as commodities. The computer program product is distributed in the form of a machine-readable storage medium (eg compact disc read only memory (CD-ROM)), or via an application store (eg Play Store™) or between two user devices. It can be distributed directly or online (eg, downloaded or uploaded). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium such as a memory of a server of a manufacturer, a server of an application store, or a memory of a relay server.

The steps constituting the method according to the present invention may be performed in an appropriate order, unless the order is explicitly stated or there is no description to the contrary. The present invention is not necessarily limited to the order in which the steps are described. The use of all examples or exemplary terms (eg, etc.) in the present invention is merely for the purpose of describing the present invention in detail, and the scope of the present invention is limited by the examples or exemplary terms unless defined by the claims. it's not going to be In addition, those skilled in the art will appreciate that various modifications, combinations, and changes may be made in accordance with design conditions and factors within the scope of the appended claims or their equivalents.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the spirit of the present invention is not limited to the scope of the scope of the present invention. will be said to belong to

Claims (8)

A method for determining a driving path of a vehicle, comprising:
obtaining a first driving path estimated to be driving the vehicle from a vector map in which a plurality of driving paths are displayed based on a GPS signal;
acquiring a second driving route estimated to be driven by the vehicle based on a front image captured in front of the vehicle;
correcting the first travel path based on the second travel path; and
determining a final driving path in which the vehicle is traveling as a result of correcting the first driving path on the vector map;
including,
The correcting step is
When the number of lanes located on the right or left side of the first driving path is different from the number of lanes located on the right side or left side of the second driving path,
correcting the first driving path as a third driving path in the vector map so that the first driving path corresponds to the second driving path;
The third driving path corresponds to a driving path on the vector map that is positionally corresponding to the second driving path based on the number of lanes located on the right or left side of the second driving path,
The correcting step is
When a stop line is not included in the lane information obtained based on the forward image,
deriving a lateral correction value and a heading angle correction value of the third driving path so that the third driving path matches the second driving path; and
correcting the third driving path as a fourth driving path by applying the lateral direction correction value and the heading angle correction value to the third driving path; including,
The correcting step is
When a stop line is included in the lane information obtained based on the front image,
deriving a lateral correction value, a longitudinal correction value, and a heading angle correction value of the third driving path so that the third driving path matches the second driving path; and
correcting the third driving path as a fourth driving path by applying the lateral correction value, the longitudinal correction value, and the heading angle correction value to the third driving path; including,
The step of determining the final driving route comprises:
determining the fourth travel route as the final travel route. delete delete delete The method of claim 1,
The step of obtaining the first travel route includes:
obtaining a current location of the vehicle based on the GPS signal;
converting the vector map into a local vector map based on a Cartesian coordinate system having the current location of the vehicle as an origin; and
acquiring a first driving path from among at least one driving path included in the local vector map;
A method comprising The method of claim 1,
The step of obtaining the second travel route includes:
predicting lanes in the forward image by inputting the forward image into a deep neural network (DNN);
displaying lanes in the front image on a Cartesian coordinate system having a current location of the vehicle as an origin; and
obtaining the second driving route based on the lanes displayed on the Cartesian coordinate system;
a method comprising An apparatus for determining a travel route of a vehicle, comprising:
a memory in which at least one program is stored; and
A processor for performing an operation by executing the at least one program,
The processor is
Obtaining a first driving route in which the vehicle is determined to be driving from a vector map including a plurality of driving routes based on a GPS signal,
Obtaining a second driving route in which it is determined that the vehicle is driving based on a front image photographed in front of the vehicle,
correcting the first travel path based on the second travel path;
As a result of correcting the first driving path on the vector map, the final driving path in which the vehicle is driving is determined,
The processor is
When the number of lanes located on the right or left side of the first driving path is different from the number of lanes located on the right side or left side of the second driving path,
correcting the first driving path as a third driving path in the vector map so that the first driving path corresponds to the second driving path;
The third driving path corresponds to a driving path on the vector map that is positionally corresponding to the second driving path based on the number of lanes located on the right or left side of the second driving path,
The processor is
When a stop line is not included in the lane information obtained based on the forward image,
deriving a lateral correction value and a heading angle correction value of the third driving path so that the third driving path matches the second driving path;
correcting the third driving path as a fourth driving path by applying the lateral correction value and the heading angle correction value to the third driving path;
The processor is
When a stop line is included in the lane information obtained based on the front image,
deriving a lateral correction value, a longitudinal correction value, and a heading angle correction value of the third driving path so that the third driving path matches the second driving path;
correcting the third driving path as a fourth driving path by applying the lateral correction value, the longitudinal correction value, and the heading angle correction value to the third driving path;
The processor is
and determining the fourth travel route as the final travel route. A computer-readable recording medium in which a program for executing the method of claim 1 in a computer is recorded.

Images