Method for correcting vehicle location and apparatus carrying out same

Abstract

A method for correcting vehicle location is disclosed. The method according to an embodiment may comprise the steps of: obtaining the location of a vehicle; obtaining an image captured at the location by a camera installed in the vehicle; generating, on the basis of information about a road candidate corresponding to the location at which the image is obtained, a prompt that queries an identification element of a road included in the image; inputting the prompt into a generative model to obtain context information about the identification element of the road included in the image; and on the basis of the information about the road candidate and the context information, determining, on a map, a road on which the vehicle is located.

Description

Method for correcting the position of a vehicle and apparatus for performing the same

[0001] The following disclosure relates to a method for correcting the position of a vehicle and an apparatus for performing the same.

[0002] Map matching technology is being developed to accurately match a vehicle's position on a map by utilizing sensed information acquired through an inertial measurement unit (IMU) installed in the vehicle, along with Global Positioning System (GPS) coordinates. However, even after performing map matching, there may be cases where the position cannot be calculated accurately depending on road conditions and the status of the GPS module. For example, it may be difficult to accurately match the road where the vehicle is located when driving through an underpass or on a road running parallel to an overpass. Therefore, there may be a need for technology that accurately matches the vehicle's position on the map while addressing these issues.

[0003] The background technology described above is possessed or acquired by the inventor in the process of deriving the content of the disclosure of the present application, and cannot necessarily be considered as prior art disclosed to the general public prior to the filing of this application.

[0004] One embodiment can provide a technology that uses an artificial intelligence model to accurately identify the road on which a vehicle is traveling.

[0005] One embodiment can obtain context information about the environment in which the vehicle is driving based on an image captured through a camera installed on the vehicle.

[0006] However, technical challenges are not limited to the technical challenges described above, and other technical challenges may exist.

[0007] A method according to one embodiment may include the operation of acquiring the location of a vehicle; the operation of acquiring an image captured through a camera installed on the vehicle at the location; the operation of generating a prompt for querying an identification element of a road included in the image based on information about a road candidate corresponding to the location where the image was acquired; the operation of acquiring context information about the identification element of a road included in the image by inputting the prompt into a generative model; and the operation of determining the road where the vehicle is located on a map according to the information about the road candidate and the context information.

[0008] According to one embodiment, the context information may include at least one of information about the type of road where the vehicle is located and information about the lane where the vehicle is located.

[0009] According to one embodiment, the method may further include the operation of determining a link candidate that matches the location of the vehicle in a street network and the operation of determining a road corresponding to the link candidate as the road candidate.

[0010] According to one embodiment, the operation of determining a link candidate that is the location of the vehicle may include determining at least one link among the links included in the road network as the link candidate, wherein the weight assigned according to the location of the vehicle exceeds a threshold value.

[0011] According to one embodiment, the operation of acquiring the captured image may include acquiring an image captured through a camera installed on the vehicle in response to the link candidate satisfying a predetermined condition.

[0012] According to one embodiment, the determining operation may include adjusting a weight corresponding to a road candidate to match the vehicle on the map based on the context information, and determining a road among the road candidates where the vehicle is located based on the weight corresponding to the road candidate.

[0013] According to one embodiment, the identification element may be for identifying the road on which the vehicle is traveling.

[0014] According to one embodiment, the operation of generating the prompt may include the operation of extracting a criterion for determining the road where the vehicle is located among the road candidates based on information about the road candidates and identification elements of the road included in the image, and the operation of generating a prompt that queries the identification elements of the road included in the image based on the criterion.

[0015] According to one embodiment, a computer-readable recording medium storing one or more computer programs may include instructions for performing the method in a processor.

[0016] A device according to one embodiment may include at least one processor. The device may include a memory containing instructions. Based on the instructions being executed individually or collectively by the at least one processor, the device may be configured to acquire the location of a vehicle, acquire an image captured through a camera installed on the vehicle at the location, generate a prompt for querying an identification element of a road included in the image based on information regarding a road candidate corresponding to the location where the image was acquired, input the prompt into a generative model to acquire context information regarding the identification element of a road included in the image, and determine the road where the vehicle is located on a map according to the information regarding the road candidate and the context information.

[0017] According to one embodiment, the context information may include at least one of information about the type of road where the vehicle is located and information about the lane where the vehicle is located.

[0018] According to one embodiment, based on the instructions being executed individually or collectively by at least one processor, the device may determine a link candidate that matches the location of the vehicle in a street network and determine a road corresponding to the link candidate as the road candidate.

[0019] According to one embodiment, based on the instructions being executed individually or collectively by the at least one processor, the device may determine as the link candidate at least one link among the links included in the road network for which the weight assigned according to the location of the vehicle exceeds a threshold value.

[0020] According to one embodiment, based on the instructions being executed individually or collectively by the at least one processor, the device may be able to acquire an image captured through a camera installed in the vehicle in response to the link candidate satisfying a predetermined condition.

[0021] According to one embodiment, based on the instructions being executed individually or collectively by the at least one processor, the device may be configured to adjust a weight corresponding to a road candidate to match the vehicle on the map based on the context information, and to determine the road among the road candidates where the vehicle is located based on the weight corresponding to the road candidate.

[0022] According to one embodiment, the identification element may be for identifying the road on which the vehicle is traveling.

[0023] According to one embodiment, based on the instructions being executed individually or collectively by the at least one processor, the device may be able to extract a criterion for determining the road where the vehicle is located among the road candidates based on information about the road candidates and identification elements of the road included in the image, and generate a prompt for querying identification elements of the road included in the image based on the criterion.

[0024] In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0025] FIG. 1 is a drawing for explaining a navigation system according to one embodiment.

[0026] FIGS. 2a and FIGS. 2b are diagrams illustrating the operation of matching the position of a vehicle in a road network.

[0027] FIGS. 3a to 3d are drawings for explaining the operation of determining the road where a vehicle is located according to one embodiment.

[0028] FIG. 4 is a flowchart illustrating a method according to one embodiment.

[0029] FIG. 5 is a flowchart illustrating a method according to one embodiment.

[0030] FIG. 6 is a schematic block diagram of an electronic device according to one embodiment.

[0031] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, actual implementations are not limited to the specific embodiments disclosed, and the scope of this specification includes modifications, equivalents, or substitutions included in the technical concept described by the embodiments.

[0032] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0033] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or joined to that other component, or that there may be other components in between.

[0034] Singular expressions include plural expressions unless the context clearly indicates otherwise. In this document, phrases such as “A or B,” “at least one of A and B,” “at least one of A or B,” “A, B or C,” “at least one of A, B and C,” and “at least one of A, B, or C” may each include any one of the items listed together with the corresponding phrase, or all possible combinations thereof. In this specification, terms such as “comprising” or “having” are intended to designate the existence of the described feature, number, step, action, component, part, or combination thereof, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0035] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification.

[0036] As used herein, the term "module" may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0037] As used in this document, the term "part" refers to a software or hardware component, such as an FPGA or ASIC, that performs certain roles. However, "part" is not limited to software or hardware. "Part" may be configured to reside in an addressable storage medium or configured to operate one or more processors. For example, "part" may include components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." Furthermore, components and "parts" may be implemented to operate one or more CPUs within a device or secure multimedia card. Additionally, '~part' may include one or more processors.

[0038] Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the attached drawings, identical components are given the same reference numeral regardless of the drawing number, and redundant descriptions thereof will be omitted.

[0039]

[0040] FIG. 1 is a drawing for explaining a navigation system according to one embodiment.

[0041] Referring to FIG. 1, according to one embodiment, a navigation system (10) may include a navigation device (100), a vehicle (110), and a server (130). The navigation device (100) may include a device that reflects the real-time location of the vehicle (110) on a map and provides a route from the current location of the vehicle (110) to a destination. The navigation device (100) may be installed inside the vehicle (110) or implemented through an end-device (e.g., a terminal such as a smartphone or tablet PC) of a user (e.g., a user of the vehicle (110)). For example, the navigation device (100) may include an electronic device (e.g., a terminal) on which a navigation device and / or a navigation application is installed, which is installed on the dashboard of the vehicle (110). A vehicle (e.g., vehicle (110)) means a vehicle capable of transporting goods and / or people, and may include, for example, a car, train, ship, boat, aircraft, kickboard and / or bicycle. The server (130) may collect information necessary for route generation, such as road conditions, accident information, and traffic conditions. The server (130) may transmit the collected information to the navigation device (100).

[0042] According to one embodiment, a navigation device (100) can acquire the location of a vehicle (110). The navigation device (100) can acquire the location of the vehicle (110) through a location tracking module installed in the vehicle (110) (e.g., a module such as a GPS (global positioning system) module, a GNSS (global navigation satellite system) module, or an INS (inertial navigation system) module). Based on the location of the vehicle (110), the navigation device (100) can perform map matching to match a road network on a digital map. Since the location information acquired from the vehicle (110) may contain errors, the navigation device (100) can determine the road where the vehicle (110) is located by performing map matching for accurate route guidance. A road network can be used for navigation and location matching of a vehicle's (e.g., vehicle (110)) route by defining a path that a vehicle can travel within a digital map. The road network may include nodes corresponding to intersections, junctions, or the start and / or end points of a road, and links corresponding to road sections connecting each node. The navigation device (100) may determine a link among the links included in the road network that has a weight (e.g., cost) assigned according to the location of the vehicle (110) that exceeds a threshold value as the link corresponding to the road where the vehicle (110) is located. The navigation device (100) may generate a driving path based on information regarding the road where the vehicle (110) is determined to be located. The navigation device (100) may guide the route to a user (e.g., user of the vehicle (110)) through a display.

[0043] According to one embodiment, the navigation device (100) can determine a link candidate that matches the location of the vehicle (110) in a road network. The navigation device (100) can determine at least one link among the links included in the road network as a link candidate, wherein the weight assigned according to the location of the vehicle (110) exceeds a threshold value. In response to the link candidate satisfying a predetermined condition, the navigation device (100) can acquire an image captured through a camera installed on the vehicle (110). For example, the navigation device (100) can acquire an image captured through a camera installed on the vehicle (110) in response to the inability to determine a link corresponding to the road where the vehicle (110) is located, because the weights assigned to the link candidates are all similar. For example, the navigation device (100) can acquire an image captured through a camera installed on the vehicle (110) in response to at least some of the link candidates being of a specific type of road (e.g., a road type such as an overpass, an underpass, or a tunnel). For example, the navigation device (100) can acquire an image captured through a camera installed on the vehicle (110) in response to the fact that the link candidates in the road network have a complex structure and the link corresponding to the road where the vehicle (110) is located cannot be determined. For example, the navigation device (100) can acquire an image captured through a camera installed on the vehicle (110) in response to the fact that the link candidates are sections where there was an error in the map matching process in the road network based on the existing map matching log. In response to the inability to match the location of the vehicle (110) to a single link on the road network and thus to determine the road where the vehicle (110) is located, the navigation device (100) can acquire an image captured through a camera installed on the vehicle (110), and it should be noted that the conditions for the navigation device (100) to acquire the image are not limited to the above example.

[0044] According to one embodiment, the navigation device (100) may generate a prompt that queries an identification element of a road included in an image based on information about a road candidate corresponding to the location where an image captured by a camera installed on the vehicle (110) is acquired (e.g., the location where the image was captured). The road candidate may be a road corresponding to a link candidate. The navigation device (100) may input the prompt into a generative model to obtain context information about the identification element of a road included in the image. The generative model may be located inside and / or outside the navigation device (100) (e.g., a server (130)). The context information may include at least one of information about the type of road where the vehicle (110) is located and information about the lane where the vehicle (110) is located. It should be noted that context information may include all information for understanding a scene included in an image (e.g., a road where the vehicle (110) is located), but is not limited to the above examples. The navigation device (100) can determine the road where the vehicle (110) is located on a map (e.g., a digital map) based on information about road candidates and context information.

[0045] According to one embodiment, each constituent entity (e.g., navigation device (100), vehicle (110), and server (130)) can perform communication using a network (not shown). For example, the network may include a Local Area Network (LAN), a Wide Area Network (WAN), a Value Added Network (VAN), a mobile radio communication network, a satellite communication network, and combinations thereof. The network is a comprehensive data communication network that enables each constituent entity (e.g., navigation device (100), vehicle (110), and server (130)) to communicate seamlessly with one another, and may include wired internet, wireless internet, and mobile wireless communication networks. In addition, wireless communication networks may include, for example, Wi-Fi, Bluetooth, Bluetooth Low Energy, Zigbee, Wi-Fi Direct (WFD), Ultra-Wideband (UWB), Infrared Data Association (IrDA), and Near Field Communication (NFC), but are not limited to these.

[0046]

[0047] FIGS. 2a and FIGS. 2b are diagrams illustrating the operation of matching the position of a vehicle in a road network.

[0048] Referring to FIG. 2a, figures (201) through (205) may be examples for explaining the operation of a navigation device (e.g., the navigation device (100) of FIG. 1) matching the location of a vehicle (e.g., the vehicle (110) of FIG. 1) on a digital map. Figure (201) may represent the actual route taken by the vehicle (110) on the road. Figure (203) may represent the navigation device (100) not performing map matching, but displaying only the location obtained from the vehicle (110) (e.g., a location such as a GPS location or a GNSS location) on the digital map. If map matching is not performed, the road on which the vehicle (110) travels on the digital map is not clear as in Figure (203), and the navigation device (100) may not be able to accurately perform route guidance. Figure (205) may show the result of the navigation device (100) performing map matching to match the location of the vehicle (110) to a road on a digital road. By matching the location of the vehicle (110) to a road included in the digital map as shown in Figure (205), the navigation device (100) can enable the driver to accurately determine the current driving location.

[0049] Meanwhile, referring to FIG. 2b, even if the navigation device (100) has performed map matching, there may be a difference between the position of the vehicle (110) on the digital map and the actual position of the vehicle (110) depending on road conditions and / or the status of the GPS. A difference may occur between the actual position of the vehicle (110) and the position of the vehicle (110) on the digital map due to road conditions, such as when driving on a Y-shaped road with a small angle difference, a complex intersection, or a road where adjacent parallel roads exist (e.g., a road parallel to an overpass). For example, when a vehicle (e.g., vehicle (110)) is driving on a ground road (213) that is parallel to at least a portion of an overpass (211), it may not be possible to match which road the vehicle (110) is driving on based solely on the GPS location (213). When driving through a section where GPS signals are distorted, such as an underpass, tunnel, building forest, or underground parking lot, or when the signal is weakened because an object is placed over the GPS antenna, there may be a difference between the actual location of the vehicle (110) and the location of the vehicle (110) on the digital map.

[0050]

[0051] FIGS. 3a to 3d are drawings for explaining the operation of determining the road where a vehicle is located according to one embodiment.

[0052] Referring to FIG. 3a, according to one embodiment, FIG. 3a may be intended to explain the operation of a navigation device (e.g., the navigation device (100) of FIG. 1) determining the road where the vehicle (e.g., the vehicle (110) of FIG. 1) is located in a situation where the vehicle (e.g., the vehicle (110) of FIG. 1) is traveling on a ground road that is parallel to an overpass. The navigation device (100) may acquire an image (e.g., image (301)) captured through a camera installed on the vehicle (110). The navigation device (100) may acquire an image captured through a camera installed on the vehicle (110) in response to a link candidate satisfying a predetermined condition. The navigation device (100) may determine at least one link among the links included in the road network as a link candidate, wherein the weight (e.g., cost) assigned according to the location of the vehicle (110) exceeds a threshold value. A weight (e.g., cost) that can be assigned to a link included in a road network can be determined based on information such as the connectivity of the road network, the heading angle of the vehicle (e.g., vehicle (110)), location, and speed. In response to the inability to match the location of the vehicle (110) to a single link on the road network and thus to determine the road where the vehicle (110) is located, the navigation device (100) can acquire an image (e.g., image (301)) captured through a camera installed on the vehicle (110). For example, in response to the inability to determine a single link corresponding to the location of the vehicle (110) (e.g., GPS location) as a link corresponding to a ground road and a link corresponding to an overpass, the navigation device (100) can acquire an image (301) captured through a camera installed on the vehicle (110). The image (301) may be a picture of the front of the vehicle (110) taken through a camera installed on the vehicle (110).For example, the image (301) may be an image of the front of the vehicle (110) taken while the vehicle (110) is traveling on a ground road that is parallel to an overpass.

[0053] According to one embodiment, a navigation device (100) may generate a prompt based on an image (e.g., image (301)) and information (310) about a road candidate corresponding to the location where the image (e.g., image (301)) was acquired. The information (310) about the road candidate may be associated with a link candidate that the navigation device (100) determines to be matched to the location of the vehicle (110). The navigation device (100) may determine a link candidate that is matched to the location of the vehicle (110) in a road network and determine a road corresponding to the link candidate as a road candidate. The information (310) about the road candidate may include map meta-information of the road candidates. For example, the information (310) about the road candidate may include meta-information such as the type of road, the grade of the road, whether it is a bridge, location information, and coordinates. For example, information (310) about road candidates may include information about ground roads and overpasses corresponding to link candidates that the navigation device (100) determines to match the location of the vehicle.

[0054] According to one embodiment, the navigation device (100) may generate a prompt to query the identification elements of a road included in an image (e.g., image (301)) based on information (310) about a road candidate corresponding to the location where the image (e.g., image (301)) was acquired. The navigation device (100) may extract a criterion for determining the road where the vehicle (110) is located among the road candidates based on the information (310) about the road candidate and the identification elements of the road included in the image (e.g., image (301)). The identification elements of the road included in the image (e.g., image (301)) may include elements for identifying a road that can be extracted from the image (e.g., image (301)), such as an overpass, a lane, a tunnel, or an underpass. The identification elements may be for identifying the road on which the vehicle (e.g., vehicle (110)) is traveling. The navigation device (100) can generate a prompt that queries the identification elements of a road included in an image (e.g., image (301)) based on criteria for determining the road where the vehicle (110) is located. For example, the navigation device (100) can generate a prompt such as, 'Are you currently driving on an upper road? Or are you driving on a lower road?' based on the image (301) and information about road candidates, such as ground roads and overpasses (e.g., information about road candidates (310)). The navigation device (100) can input the prompt into a generative model (e.g., model (340)) to obtain context information (360) about the identification elements of a road included in the image (e.g., image (301)). The context information may include at least one of information about the type of road where the vehicle (e.g., vehicle (110)) is located and information about the lane where the vehicle (e.g., vehicle (110)) is located.

[0055] According to one embodiment, the model (340) may include a generative artificial intelligence model such as a large language model (LLM) or a large multimodal model (LMM). The model (340) may be located inside and / or outside the navigation device (100) (e.g., the server (130) of FIG. 1). The navigation device (100) may determine the road where the vehicle (110) is located on the map based on information (310) about road candidates and context information (360) about road identification elements. Based on the context information, the navigation device (100) may adjust the weight corresponding to the road candidates to match the vehicle (110) on the map. For example, based on the context information, the navigation device (100) may adjust the weight for ground roads, which are road candidates, to be higher than that for overpasses. The navigation device (100) can determine the road where the vehicle (110) is located among the road candidates based on weights corresponding to the road candidates. For example, the navigation device (100) can determine the ground road to which the vehicle (110) is located as the road to which the vehicle (110) is located, provided that the vehicle (110) is located. Based on the road where the vehicle (110) is located (e.g., the road where the vehicle is located (370)), the navigation device (100) can provide an accurate route to the destination.

[0056]

[0057] Referring to FIG. 3b, according to one embodiment, FIG. 3b may be intended to explain the operation of a navigation device (100) determining the road where the vehicle (110) is located in a situation where the vehicle (110) is traveling on an elevated road that is parallel to at least a portion of a ground road. The navigation device (100) may acquire an image (e.g., image (302)) captured through a camera installed on the vehicle (110). The navigation device (100) may acquire an image captured through a camera installed on the vehicle (110) in response to a link candidate satisfying a predetermined condition. The navigation device (100) may determine at least one link among the links included in the road network as a link candidate, wherein the weight (e.g., cost) assigned according to the location of the vehicle (110) exceeds a threshold value. A weight (e.g., cost) that can be assigned to a link included in a road network can be determined based on information such as the connectivity of the road network, the heading angle of the vehicle (e.g., vehicle (110)), location, and speed. In response to the inability to match the location of the vehicle (110) to a single link on the road network and thus to determine the road where the vehicle (110) is located, the navigation device (100) can acquire an image (e.g., image (302)) captured through a camera installed on the vehicle (110). For example, in response to the inability to determine a single link corresponding to the location of the vehicle (110) (e.g., GPS location) as a link corresponding to a ground road and a link corresponding to an overpass, the navigation device (100) can acquire an image (302) captured through a camera installed on the vehicle (110). The image (302) may be a picture of the front of the vehicle (110) taken through a camera installed on the vehicle (110). For example, the image (302) may be an image of the front of the vehicle (110) taken while the vehicle (110) is driving on an overpass.

[0058] According to one embodiment, a navigation device (100) may generate a prompt based on an image (e.g., image (302)) and information (310) about a road candidate corresponding to the location where the image (e.g., image (302)) was acquired. The information (310) about the road candidate may be associated with a link candidate that the navigation device (100) determines to be matched to the location of the vehicle (110). The navigation device (100) may determine a link candidate that is matched to the location of the vehicle (110) in a road network and determine a road corresponding to the link candidate as a road candidate. The information (310) about the road candidate may include map meta-information of the road candidates. For example, the information (310) about the road candidate may include meta-information such as the type of road, the grade of the road, whether it is a bridge, location information, and coordinates. For example, information (310) about road candidates may include information about an overpass and a ground road placed parallel to the overpass that corresponds to a link candidate that the navigation device (100) determines to match the location of the vehicle.

[0059] According to one embodiment, the navigation device (100) may generate a prompt to query the identification elements of a road included in an image (e.g., image (302)) based on information (310) about a road candidate corresponding to the location where the image (e.g., image (302)) was acquired. The navigation device (100) may extract a criterion for determining the road where the vehicle (110) is located among the road candidates based on the information (310) about the road candidate and the identification elements of the road included in the image (e.g., image (302)). The identification elements of the road included in the image (e.g., image (302)) may include elements for identifying a road that can be extracted from the image (e.g., image (302)), such as an overpass, a lane, a tunnel, or an underpass. The identification elements may be for identifying the road on which the vehicle (e.g., vehicle (110)) is traveling. The navigation device (100) can generate a prompt that queries the identification elements of a road included in an image (e.g., image (302)) based on criteria for determining the road where the vehicle (110) is located. For example, the navigation device (100) can generate a prompt such as, 'Are you currently driving on an upper road? Or are you driving on a lower road?' based on the image (302) and information about the road candidates, such as ground roads and overpasses (e.g., information about road candidates (310)). The navigation device (100) can input the prompt into a generative model (e.g., model (340)) to obtain context information (360) about the identification elements of a road included in the image (e.g., image (301)). The context information may include at least one of information about the type of road where the vehicle (e.g., vehicle (110)) is located and information about the lane where the vehicle (e.g., vehicle (110)) is located.

[0060] According to one embodiment, the model (340) may include a generative artificial intelligence model such as a large language model (LLM) or a large multimodal model (LMM). The model (340) may be located inside and / or outside the navigation device (100) (e.g., the server (130) of FIG. 1). The navigation device (100) can determine the road where the vehicle (110) is located on the map based on information (310) about road candidates and context information (360) about road identification elements. Based on the context information (e.g., context information (360) about road identification elements), the navigation device (100) can adjust the weight corresponding to the road candidate to match the vehicle (110) on the map. For example, based on the context information, the navigation device (100) can adjust the weight for an elevated road candidate to be higher than that for a ground road candidate. The navigation device (100) can determine the road where the vehicle (110) is located among the road candidates based on weights corresponding to the road candidates. For example, the navigation device (100) can determine an elevated road with a higher weight as the road where the vehicle (110) is located. Based on the road where the vehicle (110) is located (e.g., the road where the vehicle is located (370)), the navigation device (100) can provide an accurate route to the destination.

[0061]

[0062] Referring to FIGS. 3c and 3d, according to one embodiment, FIGS. 3c and 3d may be for a navigation device (100) to predict the road that the vehicle (110) will enter in a situation where an overpass and another road next to the overpass are located in front of the vehicle (110). The navigation device (100) may acquire an image (e.g., image (303)) captured through a camera installed on the vehicle (110). The navigation device (100) may acquire an image captured through a camera installed on the vehicle (110) in response to a link candidate satisfying a predetermined condition. For example, the navigation device (100) may acquire image (303) in response to the vehicle (110) failing to determine which road to drive on in relation to a road located parallel to the overpass. The navigation device (100) can generate a prompt to query the identification elements of a road included in an image (e.g., image (302)) based on information (310) about a road candidate corresponding to the location where the image (e.g., image (303)) was acquired. The navigation device (100) can extract criteria for determining the road where the vehicle (110) is located among the road candidates based on information (310) about the road candidate and the identification elements of the road included in the image (e.g., image (303)). The identification elements of the road included in the image (e.g., image (303)) may include elements for identifying a road that can be extracted from the image (e.g., image (303)), such as an overpass, a lane, a tunnel, or an underpass. The identification elements may be for identifying the road on which the vehicle (e.g., vehicle (110)) is traveling. The navigation device (100) can generate a prompt to query identification elements of a road included in an image (e.g., image (303)) based on criteria for determining the road where the vehicle (110) is located.For example, the navigation device (100) can generate a prompt such as, "There is an overpass ahead, and a road next to the overpass is drivable on the right. Where do you think the vehicle will enter in the current state?" based on an image (303) and information about a road candidate, such as an overpass and a road next to the overpass (e.g., information about a road candidate (310)). The navigation device (100) can input the prompt into a generative model (e.g., model (340)) to obtain context information (360) about the identification elements of the road included in the image (e.g., image (303)). The context information may include at least one of information about the type of road where the vehicle (e.g., vehicle (110)) is located and information about the lane where the vehicle (e.g., vehicle (110)) is located. The navigation device (100) can determine the road that the vehicle (110) will enter on the map based on information (310) about road candidates and context information (360) about road identification elements. The navigation device (100) can adjust the weight corresponding to the road candidates to match the vehicle (110) on the map based on the context information (e.g., context information (360) about road identification elements). For example, the navigation device (100) can adjust the weight to be higher for an overpass, which is a road candidate that the vehicle (110) can enter, than for a road next to the overpass, which is another road candidate, based on the context information. The navigation device (100) can determine the road among the road candidates that the vehicle (110) is predicted to enter based on the weight corresponding to the road candidates. For example, the navigation device (100) can determine the overpass to which the vehicle (110) is predicted to enter as the road to which the vehicle (110) will enter. The navigation device (100) can additionally acquire an image (304) at a time after acquiring an image (303).The navigation device (100) can predict the road that the vehicle (110) will enter by regenerating a prompt and using a model (340). For example, the navigation device (100) can generate a prompt such as 'Where do you think the vehicle will enter from the current state?' based on an image (304) and information (314) about road candidates.

[0063]

[0064] FIG. 4 is a flowchart illustrating a method according to one embodiment.

[0065] Referring to FIG. 4, according to one embodiment, operations 410 to 480 may be operations performed by the navigation device (100) of FIG. 1 described with reference to FIG. 1 to 3d.

[0066] According to one embodiment, operations 410 to 480 can be understood as being performed in a processor (e.g., processor (630) of FIG. 6) of a navigation device (100) (e.g., electronic device (600) of FIG. 6) described with reference to FIG. 1.

[0067] In operation 410, the navigation device (100) can acquire the location of the vehicle. The navigation device (100) can acquire the location of the vehicle (110) through a location tracking module installed in the vehicle (110) (e.g., a module such as a GPS (global positioning system) module, a GNSS (global navigation satellite system) module, or an INS (inertial navigation system) module).

[0068] In operation 420, the navigation device (100) can determine a link candidate corresponding to the location where the image was acquired as a road candidate. The navigation device (100) can determine at least one link among the links included in the road network as a link candidate in which a weight (e.g., cost) assigned according to the location of the vehicle (110) exceeds a threshold value. The navigation device (100) can determine a link candidate that matches the location of the vehicle (110) in the road network and determine a road corresponding to the link candidate as a road candidate.

[0069] In operation 430, the navigation device (100) can determine whether a link candidate matching the vehicle's location in the road network satisfies a predetermined condition. The navigation device (100) can perform operation 440 in response to the link candidate matching the vehicle's location in the road network satisfying a predetermined condition. The navigation device (100) can terminate the operation in response to the link candidate matching the vehicle's location in the road network not satisfying a predetermined condition.

[0070] In operation 440, the navigation device (100) can acquire an image captured by a camera installed on the vehicle at the corresponding location. The navigation device (100) can acquire an image captured by a camera installed on the vehicle (110) in response to a link candidate satisfying a predetermined condition. For example, the navigation device (100) can acquire an image captured by a camera installed on the vehicle (110) in response to the fact that the weights assigned to the link candidates are all similar, so that a link corresponding to the road where the vehicle (110) is located cannot be determined. For example, the navigation device (100) can acquire an image captured by a camera installed on the vehicle (110) in response to at least some of the link candidates being a specific type of road (e.g., a road type such as an overpass, an underpass, or a tunnel). In response to the inability to match the location of the vehicle (110) to a single link on the road network and thus to determine the road where the vehicle (110) is located, the navigation device (100) can acquire an image captured through a camera installed on the vehicle (110), and it should be noted that the conditions for the navigation device (100) to acquire the image are not limited to the above example.

[0071] In operation 450, the navigation device (100) can generate a prompt. The navigation device (100) can generate a prompt based on information about a road candidate corresponding to an image and the location where the image was acquired. The navigation device (100) can generate a prompt that queries an identification element of a road included in the image.

[0072] In operation 460, the navigation device (100) can obtain context information regarding identification elements of the road. The context information may include at least one of information about the type of road where the vehicle (110) is located and information about the lane where the vehicle (110) is located.

[0073] In operation 470, the navigation device (100) can adjust the weight corresponding to the road candidates based on context information. The navigation device (100) can adjust the weight of the road where the vehicle (110) is determined to be located among the road candidates to be higher based on context information.

[0074] In operation 480, the navigation device (100) can determine the road where the vehicle (110) is located. The navigation device (100) can determine the road with the highest weight among the road candidates as the road where the vehicle (110) is located.

[0075] Operations 410 through 480 may be performed sequentially, but are not limited thereto. For example, two or more operations may be performed in parallel.

[0076]

[0077] FIG. 5 is a flowchart illustrating a method according to one embodiment.

[0078] Referring to FIG. 5, according to one embodiment, operations 510 to 590 may be operations performed by the navigation device (100) of FIG. 1 described with reference to FIG. 1 to FIG. 4.

[0079] According to one embodiment, operations 510 to 590 may be understood to be performed in a processor (e.g., processor (630) of FIG. 6) of a navigation device (100) (e.g., electronic device (600) of FIG. 6) described with reference to FIG. 1.

[0080] In operation 510, the navigation device (100) can obtain the location of the vehicle.

[0081] In operation 530, the navigation device (100) can obtain an image captured through a camera installed in the vehicle at the above location.

[0082] In operation 550, the navigation device (100) can generate a prompt to query identification elements of a road included in the image based on information about a road candidate corresponding to the location where the image was acquired.

[0083] In operation 570, the navigation device (100) can input a prompt into a generative model to obtain context information about the identification elements of the road included in the image.

[0084] In operation 590, the navigation device (100) can determine the road where the vehicle is located on the map based on information about road candidates and context information.

[0085] Operations 510 through 590 may be performed sequentially, but are not limited thereto. For example, two or more operations may be performed in parallel.

[0086]

[0087] FIG. 6 is a schematic block diagram of an electronic device according to one embodiment.

[0088] Referring to FIG. 6, according to one embodiment, an electronic device (600) (e.g., a navigation device (100) of FIG. 1) may include a memory (610) and a processor (630).

[0089] The memory (610) can store instructions (or programs) executable by the processor (630). For example, the instructions may include instructions for executing the operation of the processor (630) and / or the operation of each component of the processor (630).

[0090] The memory (610) may include one or more computer-readable storage media. The memory (610) may include non-volatile storage devices (e.g., magnetic hard disc, optical disc, floppy disc, flash memory, EPROM (electrically programmable memories), EEPROM (electrically erasable and programmable)).

[0091] The memory (610) may be a non-transitory medium. The term "non-transitory" may indicate that the storage medium is not implemented by a carrier wave or a propagated signal. However, the term "non-transitory" should not be interpreted as meaning that the memory (610) is immobile.

[0092] The processor (630) can process data stored in memory (610). The processor (630) can execute computer-readable code (e.g., software) stored in memory (610) and instructions triggered by the processor (630).

[0093] The processor (630) may be a data processing device implemented in hardware having a circuit having a physical structure for executing desired operations. For example, the desired operations may include code or instructions included in a program.

[0094] For example, a data processing device implemented in hardware may include a microprocessor, a central processing unit, a processor core, a multi-core processor, a multiprocessor, an Application-Specific Integrated Circuit (ASIC), and a Field Programmable Gate Array (FPGA).

[0095] The processor (630) can cause the electronic device (600) to perform one or more operations by executing code and / or instructions stored in memory (610). The operations performed by the electronic device (600) may be substantially the same as the operations performed by the navigation device (100) described with reference to FIGS. 1 through 6. Such redundant descriptions are omitted.

[0096]

[0097] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using a general-purpose computer or a special-purpose computer, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.

[0098] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or instruct the processing unit independently or collectively. Software and / or data may be stored on any type of machine, component, physical device, virtual equipment, computer storage medium, or device so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on computer-readable recording media.

[0099] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may store program instructions, data files, data structures, etc., either individually or in combination, and the program instructions recorded on the medium may be those specifically designed and configured for the embodiment or those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0100] The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0101] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based thereon. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0102] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

1. An operation to acquire the position of a vehicle; The operation of acquiring an image captured through a camera installed on the vehicle at the above location; An operation to generate a prompt for querying identification elements of a road included in an image based on information about a road candidate corresponding to the location where the image was acquired; The operation of inputting the above prompt into a generative model to obtain context information regarding identification elements of a road included in the image; and The operation of determining the road where the vehicle is located on a map based on information about the road candidates and context information. including, method.

2. In Paragraph 1, The above context information is, including at least one of information on the type of road where the vehicle is located and information on the lane where the vehicle is located. method.

3. In Paragraph 1, An operation to determine a link candidate that matches the location of the vehicle in a road network; and The operation of determining the road corresponding to the above link candidate as the above road candidate including more, method.

4. In Paragraph 3, The operation of determining a link candidate that matches the location of the above vehicle is, The operation of determining at least one link among the links included in the above road network as a link candidate, wherein the weight assigned according to the location of the vehicle exceeds a threshold value. including, method.

5. In Paragraph 3, The operation of acquiring the above-mentioned captured image is, The operation of acquiring an image captured through a camera installed on the vehicle in response to the above link candidate satisfying a predetermined condition. including, method.

6. In Paragraph 1, The operation determined above is, An operation to adjust the weight corresponding to the road candidate to match the vehicle on the map based on the above context information; and An operation to determine the road where the vehicle is located among the road candidates based on weights corresponding to the road candidates. including, method.

7. In Paragraph 1, The above identification element is, For identifying the road on which the above vehicle is traveling, method.

8. In Paragraph 1, The operation of generating the above prompt is, An operation to extract a criterion for determining the road where the vehicle is located among the road candidates based on information about the road candidates and identification elements of the road included in the image; and An operation to generate a prompt querying the identification elements of the road included in the image based on the above criteria. including, method.

9. A computer program stored on a computer-readable recording medium in combination with hardware to execute the method of any one of claims 1 through 8.

10. In the device, At least one processor; and memory that stores instructions Includes, Based on the above instructions being executed individually or collectively by the at least one processor, the device, Obtain the location of the vehicle, and An image captured through a camera installed on the vehicle at the above location is obtained, and Based on information regarding a road candidate corresponding to the location where the above image was acquired, a prompt is generated to query the identification element of the road included in the above image, and Input the above prompt into a generative model to obtain context information regarding the identification elements of the road included in the above image, and Determining the road where the vehicle is located on the map based on information about the road candidate and the context information. device.

11. In Paragraph 10, The above context information is, including at least one of information on the type of road where the vehicle is located and information on the lane where the vehicle is located. device.

12. In Paragraph 10, Based on the above instructions being executed individually or collectively by the at least one processor, the device, Determine link candidates that match the location of the vehicle in the road network, and Determining the road corresponding to the above link candidate as the above road candidate, device.

13. In Paragraph 12, Based on the above instructions being executed individually or collectively by the at least one processor, the device, Determining at least one link among the links included in the road network above as a link candidate, wherein the weight assigned according to the location of the vehicle above exceeds a threshold value. device.

14. In Paragraph 12, Based on the above instructions being executed individually or collectively by the at least one processor, the device, In response to the above link candidate satisfying a predetermined condition, an image captured through a camera installed on the vehicle is obtained. device.

15. In Paragraph 10, Based on the above instructions being executed individually or collectively by the at least one processor, the device, Based on the above context information, adjust the weight corresponding to the road candidate to match the vehicle on the above map, and Determining the road where the vehicle is located among the road candidates based on weights corresponding to the road candidates, device.

Images