Method for constructing autonomous driving route using sensor recognition information and autonomous driving support device

Abstract

To provide an autonomous traveling route construction method using sensor recognition information, and an autonomous traveling support device.SOLUTION: A construction method includes the steps of: acquiring, on the basis of recognition information acquired from a moving body having an observation sensor and a positioning sensor, a movement route by tracking the moving body and at least one target object among surrounding dynamic objects around the moving body; generating a predicted route whose movement is estimated from the movement route on the basis of the movement route; generating route information comprising the movement route and the predicted route to incorporate the route information into map information; updating the route information on the basis of actual information when verification of the map information reveals a deviation of a predetermined range or more between the route information and the actual information in which the target object has actually moved at least in an area corresponding to the predicted route; and incorporating the updated route information into the map information.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present disclosure relates to a method for constructing an autonomous driving route using sensor recognition information and an autonomous driving assistance device, and more specifically, to a method for constructing an autonomous driving route and an autonomous driving assistance device that utilizes recognition information collected from an autonomous driving mobility device when constructing and updating route information on map information for autonomous driving, to precisely and efficiently generate route information similar to an actual driving route. [Background technology]

[0002] Autonomous vehicles are being developed in various mobility fields, including vehicles, robots, unmanned mobile devices, and drones, and commercialization is being explored. After various tests, algorithms and data used in autonomous vehicles, such as perception / judgment / control software, precise maps, and learning data, are developed and constructed, and services are provided by installing these algorithms and data in autonomous devices.

[0003] Although precise maps for autonomous driving have high accuracy and a large amount of information, they have the disadvantage of being expensive to build and update. Furthermore, the driving route on a precise map may be virtual information that represents the route a vehicle will travel on a map, rather than physically installed facilities such as lanes, signs, and traffic signals. Therefore, the virtual driving route may differ from the actual driving route depending on the algorithm or creator that creates the virtual driving route.

[0004] The autonomous vehicle performs a driving plan and decision process by referring to the driving route provided in the precision map, and also predicts the movement route of surrounding objects by referring to the driving route data. However, if the actual driving route differs from the virtually set driving route on the map, there is a high possibility that the autonomous vehicle may malfunction or have an accident. Summary of the Invention [Problem to be solved by the invention]

[0005] The technical objective of the present disclosure is to provide a method for constructing an autonomous driving route and an autonomous driving assistance device that utilizes recognition information collected from an autonomous driving mobility device when constructing and updating route information on map information for autonomous driving, to accurately and efficiently generate route information similar to an actual driving route.

[0006] Another technical objective of the present disclosure is to provide a method for constructing an autonomous driving route and an autonomous driving assistance device that provide optimal driving route information by utilizing time-series, multi-view data collected from a large number of autonomous driving vehicles.

[0007] The technical problems to be solved by the present disclosure are not limited to the above-mentioned technical problems, and other technical problems not mentioned above will be clearly understood by a person having ordinary skill in the technical field to which the present disclosure pertains from the following description. [Means for solving the problem]

[0008] According to one aspect of the present disclosure, there is provided a method for constructing an autonomous driving path using sensor recognition information, the method including the steps of: acquiring a movement path by tracking at least one target object among the moving object and peripheral dynamic objects around the moving object based on recognition information acquired from the moving object having an observation sensor and a positioning sensor; generating a predicted route by estimating movement from the movement path based on the movement path; generating route information including the movement path and the predicted route and incorporating the route information into map information; and, if verification of the map information reveals a deviation of at least a predetermined range between actual information of the target object's actual movement in at least an area corresponding to the predicted route and the route information, updating the route information based on the actual information; and incorporating the updated route information into the map information.

[0009] According to another embodiment of the present disclosure, the step of acquiring the movement path may include tracking the target object using positioning information of the target object estimated from the positioning sensor and a trajectory based on an optimal position of the target object. The recognition information may be collected as a plurality of pieces of recognition information to have multiple views of the target object in a time series, features may be extracted for each of the plurality of pieces of recognition information, relative displacement information between the observation sensor and the features may be generated by matching the features, and the optimal position may be generated so as to minimize a gap amount in the relative displacement information.

[0010] According to another embodiment of the present disclosure, the extraction of features and matching between the features are performed with reference to movement information and observation state information of the mobile body, and the observation state information can indicate the state in which the observation sensor of the mobile body recognizes the target object.

[0011] According to another embodiment of the present disclosure, the method may further include providing the optimal position of the target object to the positioning information and the map information.

[0012] According to another embodiment of the present disclosure, the step of generating the predicted route may include generating the predicted route based on displacement information of the target object, speed information of the target object, the movement route, environmental information of the route along which the target object will travel, regulation information applied to the route along which the target object will travel, movement pattern information of a route identical or similar to the route along which the target object will travel, and cumulative route information of a route identical or similar to the route along which the target object will travel.

[0013] According to another embodiment of the present disclosure, displacement information of the target object and velocity information of the target object are provided in a time series, and the step of generating the predicted path may be configured to generate the predicted path using trajectory modeling including a nonlinear state transition method based on the time series displacement information and the time series velocity information, and the trajectory modeling may be configured to feedback an error between a predicted trajectory derived from the trajectory modeling and a trajectory derived based on the recognition information.

[0014] According to another embodiment of the present disclosure, generating the path information includes determining as the path information a single object movement information derived by matching the target object against multiple object movement information, and the multiple object movement information may be transmitted from each of multiple moving bodies that generate the movement path and predicted path of the target object.

[0015] According to another embodiment of the present disclosure, matching the plurality of object movement information may include performing geometric matching between the object movement information, clustering similar object movement information based on statistical information according to the weighting degree of the object movement information, and generating the single object movement information using a path model based on the clustered object movement information and adopting it as the path information.

[0016] According to another embodiment of the present disclosure, the step of incorporating the route information into the map information may include generating link relationship information that links at least one of road information of the route along which the target object travels, infrastructure information provided on the route along which the target object travels, weather information of the route along which the target object travels, and regulation information applied to the route along which the target object travels with the route information.

[0017] According to another embodiment of the present disclosure, the verification of the map information may include performing an initial verification to check at least one of the integrity, continuity, and regularity of the route information, performing a simulation verification to check for interference and collision between the multiple moving bodies through a virtual simulation of the movement of the multiple moving bodies, and correcting at least one of the objects, metadata, and the route information included in the map information based on errors occurring in the initial verification and the simulation verification.

[0018] According to another aspect of the present disclosure, there is provided an autonomous driving assistance device that constructs an autonomous driving path using sensor recognition information. The device includes a communication unit that exchanges data with a mobile object, a memory that stores at least one instruction, and a processor that executes the at least one instruction stored in the memory using the data. The mobile object tracks at least one target object among the mobile object and peripheral dynamic objects around the mobile object based on recognition information acquired from the mobile object having an observation sensor and a positioning sensor to acquire a movement path, and generates a predicted route that estimates movement from the movement path based on the movement path. The processor is configured to generate route information including the movement path and the predicted route, incorporate the route information into map information, and, if a deviation between the route information and actual information of the target object's actual movement in at least an area corresponding to the predicted route is greater than a predetermined range through verification of the map information, update the route information based on the actual information and incorporate the updated route information into the map information.

[0019] The features of the present disclosure, briefly described above, are merely exemplary aspects of the detailed description of the present disclosure that follows and are not intended to limit the scope of the present disclosure. [Effects of the Invention]

[0020] According to the present disclosure, it is possible to provide an autonomous driving route construction method and an autonomous driving assistance device that utilizes recognition information collected from an autonomous driving mobility device when constructing and updating route information on map information for autonomous driving, to accurately and efficiently generate route information similar to an actual driving route.

[0021] Furthermore, according to the present disclosure, by reflecting the actual driving route on map information, the accuracy and safety of the recognition, planning, and decision-making processes of autonomous driving vehicles can be improved, and the accuracy and productivity of map information for autonomous driving and conventional navigation systems can be improved.

[0022] The present disclosure can be used to aid in traffic management and operations by helping to understand and analyze overall traffic flow, thereby helping to reduce traffic congestion and optimize traffic flow.

[0023] The effects obtained by the present disclosure are not limited to the effects described above, and other effects not described above will be clearly understood by those having ordinary skill in the art to which the present disclosure pertains from the following description. [Brief explanation of the drawings]

[0024] [Figure 1] FIG. 1 illustrates a mobile device communicating with a server and other devices to send and receive data. [Figure 2] FIG. 1 is a block diagram of a moving body according to one embodiment of the present disclosure. [Figure 3] FIG. 10 is a block diagram of a server according to another embodiment of the present disclosure. [Figure 4] FIG. 10 is a diagram showing modules for each detailed function of a mobile unit and a server. [Figure 5] 10 is a flowchart illustrating a process performed by a moving body in a method for constructing an autonomous driving path according to another embodiment of the present disclosure. [Figure 6] 10 is a flowchart illustrating a process executed by a server in a method for constructing an autonomous driving route according to another embodiment of the present disclosure. [Figure 7]FIG. 10 is a diagram illustrating an example of a result of estimating the position of an object. [Figure 8] FIG. 10 is a diagram illustrating an example of path information generated by aligning object movement information collected from multiple devices and multiple viewpoints. [Figure 9] FIG. 10 is a diagram illustrating another example of route information. [Figure 10] FIG. 10 is a diagram showing an example of linkage relationship information. [Figure 11] FIG. 10 is a diagram showing another example of link relationship information. [Figure 12-14] FIG. 10 is a diagram illustrating an example of verifying map information due to an update of route information. [Figure 15] FIG. 10 is a diagram illustrating an example of updating route information through verification. DETAILED DESCRIPTION OF THE INVENTION

[0025] The present disclosure will be described in detail below with reference to the accompanying drawings, so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein.

[0026] In describing the embodiments of the present disclosure, if it is determined that a detailed description of a known configuration or function may obscure the gist of the present disclosure, the detailed description thereof will be omitted. In addition, in the drawings, parts that are not related to the description of the present disclosure will be omitted, and similar parts will be designated by similar reference numerals.

[0027] In this disclosure, when a component is referred to as being "coupled," "coupled," or "connected" to another component, this includes not only a direct connection, but also an indirect connection where another component exists between them. Furthermore, when a component is referred to as "including" or "having" another component, this does not mean that the other component is excluded, but that the component can further include the other component, unless otherwise specified.

[0028] In this disclosure, terms such as "first" and "second" are used only to distinguish one component from another, and do not limit the order or importance of the components unless otherwise specified. Therefore, within the scope of this disclosure, a first component in one embodiment may be referred to as a second component in another embodiment, and similarly, a second component in one embodiment may be referred to as a first component in another embodiment.

[0029] In this disclosure, components that are distinguished from one another are used to clearly describe the characteristics of each component and do not necessarily mean that the components are separate. In other words, multiple components may be integrated into a single hardware or software unit, or a single component may be distributed into multiple hardware or software units. Therefore, even if not otherwise specified, such integrated or distributed embodiments are also included within the scope of this disclosure.

[0030] In this disclosure, the components described in various embodiments do not necessarily mean essential components, and some may be optional components. Therefore, an embodiment consisting of a subset of the components described in one embodiment is also within the scope of this disclosure. Furthermore, an embodiment including other components in addition to the components described in various embodiments is also within the scope of this disclosure.

[0031] In this disclosure, each of the phrases "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, C or combination thereof" can include any and all possible combinations of the items listed together in that phrase.

[0032] The advantages, features, and methods of achieving the same of the present disclosure will become more apparent from the following detailed description of the embodiments in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and can be realized in various different forms. However, the embodiments are provided solely to complete the disclosure of the present invention and to fully convey the scope of the invention to those skilled in the art.

[0033] Hereinafter, a vehicle and an autonomous driving assistance device that realize a process for constructing an autonomous driving route using sensor recognition information will be described with reference to Figures 1 to 3. Figure 1 is a diagram illustrating an example in which a moving body communicates with a server and other devices to transmit and receive data. Figure 2 is a block diagram of a moving body according to one embodiment of the present disclosure. Figure 3 is a block diagram of a server according to another embodiment of the present disclosure.

[0034] Referring to FIG. 1 , the mobile object 100 may be a mobility device utilized for a specific purpose while moving on land, in the air, or on the sea. The mobile object 100 may be, for example, a vehicle, a robot, a drone, or a ship. For example, the mobile object 100 may be a mobility device that achieves autonomous movement by communicating with a server 200 and other devices 300 and 400. The mobile object 100 may transmit various information acquired while traveling, such as recognition information based on multiple sensors, positioning information, and environmental information related to the travel route, to the server 200, and the server 200 may transmit route information, map information, travel assistance information, and software to the mobile object 100 based on the information. As another example, the mobile object 100 may communicate with the server 200 and other devices 300 and 400 to exchange the information and obtain navigation information for guiding the travel route. In the present disclosure, the server 200 can function as an autonomous driving assistance device that constructs route information for autonomous driving based on the behavior of the moving body 100 and recognition information and positioning information of surrounding objects collected from the moving body 100.

[0035] In this disclosure, the moving body 100 will be mainly described as a vehicle, but the present disclosure may also be applied to other types of moving bodies as described above. For convenience of explanation, the moving body 100 and the vehicle may be used interchangeably below.

[0036] When the mobile object 100 is a vehicle, the mobile object 100 can be powered by electric energy or fossil energy. In the case of electric energy, the mobile object 100 can be a purely battery-based vehicle powered only by a high-voltage battery or a gas-based fuel cell as an energy source. The fuel cell can also use various forms of gas capable of generating electric energy, such as hydrogen. However, various gases can be used without being limited thereto. In the case of fossil energy, the mobile object 100 can be powered by a fuel base such as gasoline, diesel, or liquefied gas, and can be equipped with an engine that drives the wheel drive unit 114 by burning the fuel. The engine can be included in the energy generation unit 112 to provide the wheel drive unit 114 with a driving force for rotating the wheels.

[0037] The vehicle 100 can be controlled and driven in an autonomous driving mode, and the autonomous driving can be realized as semi-autonomous driving or fully autonomous driving. Fully autonomous driving can be provided as autonomous driving in which the control unit 120 of the vehicle 100 completely controls the control without user intervention even when the driving situation is uncertain. Semi-autonomous driving can be provided as autonomous driving in which driver intervention is required depending on the driving situation. Semi-autonomous driving can be realized by the control unit 120 deactivating the autonomous driving when the situation occurs and handing over control to the user, allowing the user to perform manual driving.

[0038] Meanwhile, the mobile object 100 may communicate with other devices 200, 300 or other vehicles 400. The other devices may include, for example, a server 200 that supports various controls, status management, and driving of the mobile object 100, an ITS device 300 for receiving information from an ITS (Intelligent Transportation System), various types of user devices, etc. The server 200 may transmit various information and software modules used to control the mobile object 100 to the mobile object 100 in response to requests and data transmitted from the mobile object 100 and the user devices to support the autonomous driving and various services of the mobile object 100.

[0039] The ITS device 300 is, for example, a Road Side Unit (RSU), and can mutually exchange vehicle recognition data, driving control and status data, environmental data around the vehicle, map data, etc. with the mobile object 100 via V2I to assist the user in driving the vehicle or support the autonomous driving of the mobile object 100. The mobile object 100 can mutually exchange the data listed above with another vehicle 400 via V2V to support the driving of the vehicle or autonomous driving.

[0040] The mobile object 100 can communicate with other vehicles or other devices based on cellular communication, WAVE (Wireless Access in Vehicular Environment) communication, DSRC (Dedicated Short Range Communication) or short-range communication, or other communication methods.

[0041] For example, the mobile object 100 may use a cellular communication network such as LTE or 5G, a WiFi communication network, or a WAVE communication network to communicate with the server 200, the ITS device 300, and other vehicles 400. As another example, DSRC or the like used in the mobile object 100 may be used for communication between vehicles. The communication method between the mobile object 100, the server 200, the ITS device 300, other vehicles 400, and user devices is not limited to the above-described embodiment.

[0042] Referring to FIG. 2, the mobile object 100 may include a sensor unit 102, a transceiver unit 106, and a display 108.

[0043] The sensor unit 102 may include various types of detectors that sense various states and situations occurring in the external and internal environments of the mobile object 100 and obtain positioning information of the mobile object 100. That is, the sensor unit 102 may be configured as a multi-sensor module including different types of sensors and may acquire sensing data detected by each sensor.

[0044] Specifically, the sensor unit 102 may include an observation sensor that recognizes dynamic and static objects present around the mobile unit 100 and a positioning sensor 104d that acquires vehicle position and direction information. The observation sensor may be configured with multiple sensors, such as a LiDAR sensor 104a, a camera 104b that functions as an image sensor, and a radar sensor 104c. The sensor unit 102 may acquire sensor data including recognition information and positioning information using the above-mentioned sensors. The recognition information may include LiDAR data including three-dimensional recognition data of surrounding objects acquired by the LiDAR sensor 104a, two-dimensional image data of surrounding objects acquired by the camera 104b, and radar data that detects the presence and movement state of surrounding objects.

[0045] The lidar sensor 104a may be a type of three-dimensional perception sensor according to the present disclosure. The lidar sensor 104a may be a sensor that observes the surrounding environment based on laser scanning and recognizes the three-dimensional shapes of objects. Specifically, the lidar sensor 104a may acquire three-dimensional recognition data of the surrounding environment and objects by illuminating the area around the vehicle 100 with a laser. The three-dimensional recognition data may include a point cloud representing the three-dimensional shapes of the objects, i.e., detection data and observation image data visually representing the surrounding environment. The detection data may be provided to identify each object by indicating, for example, the three-dimensional contour shape of the object and the arrangement of the object. The image data may be provided to identify the object and the surrounding environment through, for example, images of the object and the surrounding environment.

[0046] The camera 104b can acquire two-dimensional image data or image data having depth information about the environment around the mobile object 100 and objects. The radar sensor 104c can, for example, irradiate the surroundings with radio waves of a predetermined wavelength and detect the behavior of the object based on the radio waves reflected from the object. The behavior of the object can include, for example, the presence or absence of the object and its movement, the distance between the mobile object 100 and the object, the speed and direction of movement of the object, etc.

[0047] The positioning sensor 104d may be composed of a GNSS (Global Navigation Satellite System), an IMU (Inertial Measurement Unit), an INS (Inertial Navigation System), a wheel encoder, a steering sensor, etc. to confirm positioning information including the vehicle's own position, driving posture, speed, etc.

[0048] In the present disclosure, only the sensors of the sensor unit 102 referred to in the description of the embodiments will be described, and sensors for detecting various conditions not listed therein may be further included.

[0049] The transceiver 106 may support mutual communication with the server 200, the ITS device 300, nearby vehicles 400, etc. In the present disclosure, the transceiver 106 may transmit data generated or stored during driving to the server 200 and receive data and software modules transmitted from the server 200. In the present disclosure, the mobile object 100 may transmit and receive data used in the method according to the present disclosure with the outside via the transceiver 106.

[0050] The display 108 can function as a user interface. The display 108 can display and output the operating status of the vehicle 100, control status, route / traffic information, remaining energy information, content requested by the driver, etc., under the control of the control unit 120. The display 108 can display route information, map information, and various information related to the driving route transmitted from the server 200. The display 108 is configured as a touch screen capable of detecting inputs from the driver, and can receive the driver's request to instruct the control unit 120.

[0051] Meanwhile, the moving body 100 may include an actuating unit 110, an energy generating unit 112, a wheel driving unit 114, and a load device .

[0052] The actuating unit 110 includes at least one module for realizing a driving operation, and can perform at least one of longitudinal control such as acceleration / deceleration and lateral control such as steering. The actuating unit 110 can include various operating modules, such as pedals and a steering wheel, that receive user requests for the control, and cause the wheel driving unit 114 to perform the driving operation according to the request.

[0053] The energy generating unit 112 can generate and supply power and electricity to be used for a driving power system such as a wheel drive unit 114 and a load device 114. When the vehicle 100 is driven by electric energy, the energy generating unit 112 can be configured, for example, by an electric battery, or a combination of an electric battery and a fuel cell that charges the battery. When the vehicle 100 is driven by fossil energy, the energy generating unit 112 can be configured by an internal combustion engine.

[0054] The wheel driving unit 114 may include a plurality of wheels, a driving force transmission module for generating driving force and applying it to the wheels or transmitting the driving force, a braking module for slowing down the driving force of the wheels, and a steering module for realizing lateral control of the wheels. When the vehicle 100 is driven by electric energy, the driving force transmission module may be configured with a motor module that generates driving force based on power output from an electric battery. When the vehicle 100 is driven by fossil energy, the driving force transmission module may include a transmission and a gear module that transmit power from an internal combustion engine.

[0055] The load device 116 may be an auxiliary device mounted on the vehicle 100 and consuming power supplied from the energy generating unit 112 by a passenger or user or power converted from the output of the energy generating unit 112. In the present disclosure, the load device 116 may be a type of non-driving electrical device excluding the driving power system such as the wheel drive unit 114. The load device 114 may be, for example, an air conditioning system, a lighting system, a seat system, and various devices installed in the vehicle 100.

[0056] The mobile object 100 may also include a memory unit 118 or a control unit 120 .

[0057] The memory unit 118 stores applications and various data for controlling the mobile object 100 and can load applications or read and write data upon request of the control unit 120. In the present disclosure, the memory unit 118 may store an application for generating object movement information related to the mobile object itself and surrounding dynamic objects for constructing route information and generating map information in the server 200. Specifically, the memory unit 118 may store an application and at least one instruction for tracking at least one target object among the mobile object 100 and surrounding dynamic objects around the mobile object based on recognition information acquired from the mobile object 100 to obtain a movement path, generating a predicted path based on the movement path, and transmitting the movement path and object movement information including the predicted path to the server 200. Here, the surrounding dynamic object is a mobile object that moves on lanes surrounding the lane on which the mobile object 100 is traveling, such as a vehicle moving in the same or opposite direction as a surrounding vehicle, or a vehicle traveling on each lane connected to an intersection. Although a vehicle is described as an example of a peripheral dynamic object, it is not limited thereto, and various types of ground mobility that moves on a road or a detailed roadway can be considered a peripheral dynamic object.

[0058] Meanwhile, the memory unit 118 may store and manage map information including route information and various information related to a driving route from the server 200. The map information may be used to generate a driving route to be set for the mobile unit 100 at the request of a user or the control unit 120. The map information may be used for autonomous driving and may include a low-resolution map or a high-resolution map together with the low-resolution map. The map information may be provided to have various information and data including the above-mentioned objects and environment.

[0059] The control unit 120 can perform overall control of the vehicle 100. The control unit 120 can be configured to execute applications and instructions stored in the memory unit 118. The control unit 120 can activate autonomous driving in response to an autonomous driving request set by a user or the vehicle 100 itself, and control the vehicle 100. In addition, the control unit 120 can deactivate autonomous driving in response to a user request for deactivation or automatic deactivation, and control the vehicle 100 to drive manually.

[0060] In relation to the present disclosure, the control unit 120 can use applications, instructions, and data stored in the memory unit 118 to track at least one target object among the moving body 100 and peripheral dynamic objects around the moving body, based on recognition information acquired from the moving body 100 having the observation sensors 104a to 104c and the positioning sensor 104d, and acquire a movement path. The control unit 120 can generate a predicted path in which movement is estimated from the movement path, based on the movement path, and transmit object movement information including the movement path and the predicted path to the server 200.

[0061] In the present disclosure, the control unit 120 can be realized by a single processing module, for example.

[0062] As another example, as shown in FIG. 4, the above-described processes may be distributed among multiple processing modules. FIG. 4 is a diagram showing detailed functional modules of a mobile object and a server. The sensor module corresponds to the sensor unit 102 of the present disclosure, and may include observation sensors 104a to 104c and a positioning sensor 104d, and may be configured as a functional module of the recognition information acquisition and analysis unit 122. The sensor module performs sensor fusion and data processing, and can communicate with the server 200 as needed.

[0063] The recognition information acquisition and analysis unit 122 may further include a localization module and a perception module in addition to the sensor module. The localization module may accurately estimate and correct the position of an object using recognition information and positioning information. The localization model may process conversion between global and local coordinate systems. The recognition module may recognize and analyze the surrounding environment and objects, grasp characteristics such as the size, shape, and speed of the object, and acquire the trajectory or movement path of a nearby dynamic object moving on the road. The prediction module corresponds to the object prediction unit 124 and may estimate the future trajectory or predicted path of a recognized object, for example, a nearby dynamic object. The predicted path may be used for driving path and traffic flow analysis. These modules may correspond to multiple processing modules constituting the control unit 120. In this disclosure, the control unit 120 may also be referred to collectively as multiple processing modules.

[0064] Referring to FIG. 3 , the server 200 functions as an autonomous driving assistance device according to the present disclosure as described above, and may include a communication unit 202, a memory 204, and a processor 206.

[0065] The communication unit 202 can support mutual communication between the moving object 100, the ITS device 300, and the surrounding vehicles 400. In the present disclosure, the communication unit 202 can receive data generated or stored while the moving object 100 and the surrounding vehicles 400 are traveling, and can receive data and software modules from the moving object 100 and the surrounding vehicles 400. As illustrated in FIG. 4, there may be a plurality of moving objects 100 shown in FIGS. 1 and 2, and the communication unit 202 can receive object movement information from the plurality of moving objects 100. The plurality of moving objects are denoted as Mobility Devices #1 to #4 in FIG. 4, and the moving objects may also be referred to as drivable mobility devices. Each of the plurality of moving objects 100 can track a target object based on recognition information and positioning information of at least one target object among itself and surrounding dynamic objects, acquire a movement path, generate a predicted path based on the movement path, and configure object movement information including the movement path and the predicted path. In addition, real-time situation awareness, route updates, emergency commands, etc. generated by the processor 206 based on the object movement information and various information can be transmitted to multiple mobile units 100 via the communication unit 202.

[0066] The memory 204 stores applications and various data for controlling the server 200, and can load applications and read and write data according to requests from the processor 206. In the present disclosure, the memory 204 can store an application for constructing map information including route information based on object movement information transmitted from the mobile unit 100. Specifically, the memory 204 can store an application and at least one instruction for generating route information based on a movement route and a predicted route, incorporating the route information into map information, verifying the map information to reflect the actual movement route of the target object, i.e., the actual route, in the map information, and processing corrections to match various characteristics required for the route information.

[0067] Meanwhile, the memory 204 may manage map information constructed to include route information and various information for planning driving routes, and transmit the information to multiple moving bodies 100 to support autonomous driving. In the present disclosure, "constructing" may refer to both generating map information based on route information generated initially and updating map information with route information reflecting an actual route. In the present disclosure, the route information may provide not only real-time movement trajectories of the moving body 100 and surrounding dynamic objects, but also predicted movement trajectories of the moving body 100 for each detailed road in the map information. The real-time movement trajectories may be useful for establishing real-time route plans for the moving body 100 performing autonomous driving and other moving bodies 100. The movement trajectories predicted on the detailed roads may be registered in map information and may correspond to estimated trajectories typically realized on the detailed roads. The estimated trajectories may be used to virtually guide the path of the moving body 100 moving in an area including the trajectory, or to establish route plans for multiple moving bodies 100 to prevent interference between the multiple moving bodies 100. The estimated trajectory can also be used for overall traffic analysis of the area.

[0068] The processor 206 may provide overall control of the server 100. The processor 206 may be configured to execute applications and instructions stored in the memory 204.

[0069] In connection with the present disclosure, the processor 206 can use applications, instructions, and data stored in the memory 204 to receive object movement information of target objects, including movement paths and predicted paths, from multiple moving bodies 100, generate route information based on the object movement information, and incorporate the route information into map information. The processor 206 can update the map information with the actual route by verifying the map information, and process corrections to match various characteristics required for the route information.

[0070] In this disclosure, the processor 206 may be implemented as a single processing module, by way of example.

[0071] As another example, as shown in FIG. 4, the above-described processes may be distributed among multiple processing modules. FIG. 4 is a diagram illustrating modules for each detailed function of a mobile unit and a server. The functions of the processor 206 described above may be combined and executed by a map creation module, an evaluation or verification module, a map update module, a machine learning module, and an algorithm module. These modules may correspond to the route information construction unit 208. The map creation module may generate a precise map including route information based on recognition information of static and dynamic objects and positioning information of these objects. The verification module may evaluate and verify the accuracy and efficiency of all data and processes of the map information. The map update module may continuously update and keep the map information up to date based on real-time data received from the mobile unit 100 and user feedback. The machine learning module may train and optimize a model for supporting autonomous driving, for example, a model for constructing route information and map information, based on object movement information and various data. This may improve tasks such as object recognition and trajectory prediction. The algorithm module can control and optimize mathematical operations to perform specific tasks to support autonomous driving, such as route planning and traffic analysis.

[0072] The functional modules of the server 200 may include a map database and a map service module in addition to the modules constituting the processor 206. The map database corresponds to the map storage unit 210 and may be built into the memory 204. The map database may hold route information and map information constructed by the server 200. The map service module corresponds to the map information providing unit 212 and may share the map constructed by the map information server 200 with other systems, for example, multiple mobile units, and provide various map-based services.

[0073] In the present disclosure, it is described that multiple moving bodies 100 generate object movement information of target objects and transmit it to the server 200, and the server 200 constructs map information including route information based on the object movement information. As another example, multiple moving bodies 100 may transmit recognition information and positioning information detected from surrounding dynamic objects to the server 200, and the server 200 may construct map information based on this information. As another example, a moving body 100 may receive recognition information, positioning information, and various information from other moving bodies and the server 200 and construct map information including route information. For convenience of explanation, the process of constructing an autonomous driving route will be described below according to the examples shown in FIGS. 2 and 3. Specifically, the processing of the control unit 120 of the moving body and the processor 206 of the server 200 described above will be described in detail with reference to FIGS. 5 to 13.

[0074] The method for constructing an autonomous driving path according to the present disclosure may be performed by combining the processes shown in Figures 5 and 6. Figure 5 is a flowchart of a process performed by a mobile body in a method for constructing an autonomous driving path according to another embodiment of the present disclosure. Figure 6 is a flowchart of a process performed by a server in a method for constructing an autonomous driving path according to another embodiment of the present disclosure. Hereinafter, for convenience of explanation, the control unit 120 of the mobile body 100 and the processor 206 of the server 200, which process the processes in Figures 5 and 6, may be abbreviated as the mobile body 100 and the server 200, respectively, or these terms may be used interchangeably.

[0075] 5, each of the plurality of moving bodies 100 illustrated in FIG. 4 can acquire recognition information and positioning information of at least one target object among the moving body and the peripheral dynamic objects around the moving body using the observation sensors 104a-104c and the positioning sensor 104d (S105). Since the plurality of moving bodies 100 perform the process of FIG. 5 in substantially the same manner, hereinafter, for convenience of explanation, the plurality of moving bodies will be referred to as moving bodies 100.

[0076] Next, the moving body 100 can estimate the position of the target object based on the recognition information (S110).

[0077] The recognition information may be collected as multiple pieces of recognition information to have multiple views of the target object in a time series. Features may be extracted for each piece of recognition information, and relative displacement information between the observation sensors 104a-104c and the features may be generated by matching the features. The features may be, for example, lines, edges, surfaces of a predetermined shape, or geometric shapes similar to a previously specified shape of the target object. The feature extraction and feature matching may be performed with reference to movement information and observation status information of the mobile object 100. The observation status information may indicate a state in which the observation sensors 104a-104c of the mobile object 100 recognize the target object. The movement information of the mobile object 100 may be generated based on, for example, positioning information and recognition information of the mobile object 100 equipped with the observation sensors 104a-104c that recognize surrounding dynamic objects. The mobile object 100 may analyze change data of the positioning information and change data of the recognition information to determine its own movement trajectory. The observation state information can include the direction and posture of each of the sensors constituting the observation sensors 104a to 104c that observe the target object according to the movement trajectory of the moving body 100 while it is moving.

[0078] The relative displacement information may be the relative distance between the target object and the observation sensors 104a to 104c of the moving body 100, the direction of the target object, etc. The moving body 100 may communicate with other moving bodies that are peripheral dynamic objects, and calculate the relative displacement information based on the positioning information of the other moving bodies and the positioning information of the moving body itself.

[0079] The position of the target object can be estimated by generating the relative displacement information in a way that minimizes the amount of gap.

[0080] 7 is a diagram illustrating an example of an object position estimation result. A moving body 502 may observe a target object 504 using an observation sensor while moving along a driving path 506. The driving path 506 may be data included in the moving information of the moving body 502, and an observation relationship 508 of the moving body 502 with respect to the target object 504 may be data included in the observation state information. The moving body 502 may collect multiple pieces of recognition information along the driving path 506, and features may be extracted for each piece of recognition information by referring to the driving path 506 and the observation relationship 508 of the moving body 502. The moving body 502 may generate relative displacement information between the observation sensor and the feature through feature matching based on the driving path 506 and the observation relationship 508.

[0081] The recognition information of the target object 504 derived by the observation sensor may have recognition prediction errors 510, 512 due to various causes. The recognition prediction errors 510, 512 may be caused by, for example, the observation sensor of the moving body 502 and the observation recognition of the target object 504. As a result, the moving body 502 can estimate the position of the target object 504 by generating an optimal position that minimizes the amount of deviation in the relative displacement information, taking into account the recognition prediction errors 510, 512.

[0082] Meanwhile, the mobile unit 100 may further include a process of providing the optimal position of the target object to the positioning information and map information at this stage. Specifically, estimated positions represented by the optimal positions of multiple target objects and the collected information of the mobile unit 100 may form a geometric network. The position information of the target object may be corrected through a process of minimizing the gap or error between estimated positions in the network. By combining the above, precisely corrected position information is estimated, and the corrected position information may be combined with the positioning information of the target object and map information managed in the memory 204 to contribute to the operation of other systems and map generation. In addition, feature-related information used for estimating the optimal position and minimizing it in the network may be provided to the map information. Thus, when performing position estimation and route planning for the mobile unit 100 and other mobile units based on the recognition information and map information of the mobile unit 100, processes related to feature and object position identification due to sensor position changes may refer to the feature-related information. For example, position information may be estimated by combining position information estimated from sensor position changes, and the calculation result of feature position changes in the sensor data may be used to extract and match feature information.

[0083] Next, the mobile unit 100 determines the target object whose position has been estimated as a target object for generating object movement information, and continuously detects the target object using the observation sensors 104a-104c and the positioning information to generate object information (S115). The recognition through the detection of the target object can be processed to grasp the shape and attributes of the target object. Details of the object information will be described later in step S120.

[0084] Next, the mobile body 100 can acquire the movement path of the target object by tracking the target object using the positioning information of the target object estimated from the positioning sensor 104d and a trajectory based on the optimal position of the target object.

[0085] The trajectory of the target object based on the optimal position is the trajectory of the target object that is continuously observed, and the movement trajectory of the target object can be estimated using the optimal position according to the recognition information of the observation sensors 104a to 104c that is continuously acquired by the moving mobile body 100.

[0086] As described above, object information of a tracked target object basically includes the position and orientation of the target object, and may also include the object's shape, color, class, identifier, movement speed, angular velocity, observation time, etc. In the case of the target object's position information, the movement position of the target object's center point can be used as the position information. The position information can be expressed as three-dimensional or two-dimensional coordinates in a predetermined coordinate system, and different coordinate systems can be used depending on the situation. Relative coordinates can indicate the relative relationship between the target object and the sensor according to the coordinate system of the observation sensor. Absolute coordinates can indicate a fixed position related to the Earth or a specific map. Position information is important for accurate tracking and analysis of target objects and can be used with other data to model the movement and behavior of the object throughout the system. Object position information can be selectively converted from sensor relative coordinates to map absolute coordinates. This conversion helps to determine the exact distance and directional relationship between the object and the vehicle.

[0087] The orientation of a target object can indicate the direction the target object is facing. Orientation can represent, for example, the target object's heading, or it can be expressed as a rotation value for each axis in two or three dimensions, a quaternion, or a rotation matrix. Heading can simply represent the object's forward direction, or more complex rotation information can be expressed as a rotation value for each axis in two or three dimensions. Quaternions and rotation matrices can describe rotation in three-dimensional space.

[0088] The object identifier, class, and velocity information can be used for object re-identification in tracking of target objects. When the same target object is tracked through multiple frames or observations of lidar data and / or image data, the target object's unique identifier can be used to consistently identify the target object. The class indicates the type or classification of the target object, and can be categorized as, for example, a vehicle, a pedestrian, a bicycle, etc. The velocity information indicates the speed and direction of movement of the object, which can be used as an important variable in predicting the object's future position and behavior.

[0089] Meanwhile, the recognition information of the observation sensors 104a-104c can be acquired from multiple viewpoints, e.g., t, t+1, and t+2. The same target object can be repeatedly detected in the recognition information from multiple viewpoints. The moving body 100 can apply a tracking algorithm and / or filtering technique (e.g., a Kalman filter) employing related techniques to identify the same target object in the recognition information from multiple viewpoints and track the trajectory of the identified target object, i.e., the target object while moving. Furthermore, multi-view tracking can mitigate temporary sensor noise or detection errors and be used for accurate tracking of the object.

[0090] As a result of the above, the mobile body 100 generates position and attribute information of target objects based on the recognition information from the observation sensors 104a to 104c, and can track the trajectory of each object by linking object information detected from multiple viewpoints. In summary, the detected object information is linked over time, and the mobile body 100 can track the motion and trajectory of each target object and obtain the movement path of the target object based on the motion, trajectory, and positioning information. This allows the movement pattern and behavior of the object to be analyzed, which can contribute to safe vehicle driving.

[0091] Next, the moving body 100 can generate a predicted route in which movement is estimated from the travel route based on the travel route of the target object (S125).

[0092] The mobile object 100 may generate a predicted route for the target object based on at least one of the following: displacement information of the target object, speed information of the target object, the moving route, environmental information of the route along which the target object will travel, regulation information applied to the traveling route, movement pattern information of a route identical or similar to the traveling route, and accumulated route information of a route identical or similar to the traveling route. The displacement information includes the position and direction of the target object based on the moving route, and the position and direction are substantially the same as those described in step S120. The environmental information may include, for example, road configuration, traffic flow conditions, weather, road event information, etc. related to the traveling route. The environmental information may be used as a driving scenario composed of a combination of the exemplary data listed above, and the driving scenario may be provided in a traffic dictionary for route planning and traffic analysis. The driving scenario corresponding to the traveling route may be provided for generating a predicted route.

[0093] The regulation information may include, for example, information related to speed limits, driving caution zones, no parking / stopping zones, etc. The movement pattern information may be received from the server 200 and may include behavior patterns analyzed based on the past trajectories of a moving object on a currently traveling route and / or a route similar to the currently traveling route. The accumulated route information may be a set of trajectories accumulated on a route that is the same as or similar to the currently traveling route.

[0094] Displacement information of the target object and velocity information of the target object may be provided in a time series. The moving body 100 may generate a predicted path using trajectory modeling including a nonlinear state transition method based on the time series displacement information and the time series velocity information. The trajectory modeling may be configured to provide feedback based on an error between a predicted trajectory derived from the trajectory modeling and a trajectory derived based on recognition information.

[0095] Specifically, in trajectory modeling, the movement path of a target object based on multi-viewpoint observation information can be expressed as the change in the position, velocity, and direction of the target object over time. Data related to the movement path can be used to form a state space model of a dynamic system, which can describe the transition from the system's current state to a future state. Nonlinear filtering techniques, such as an extended Kalman filter (EKF) or a particle filter, can be used to model the data.

[0096] TIFF0007787138000001.tif53170

[0097] Next, the moving body 100 may generate object movement information by combining the movement path generated for each target object with the predicted path, and transmit the object movement information to the server 200 (S130). As illustrated in Fig. 4, multiple moving bodies 100 may transmit object movement information generated by each moving body recognizing the target object.

[0098] Referring to FIG. 6, the server 200 can acquire object movement information from a plurality of moving objects 100 as illustrated in FIG. 4 (S205).

[0099] Then, the server 200 may integrate the plurality of pieces of object movement information of the target object to derive a single piece of object movement information (S210).

[0100] The server 200 may perform geometric matching between the object movement information to match the object movement information. Then, the server 200 may cluster the same object movement information based on statistical information according to the weighting of the object movement information. The server 200 may generate a single object movement information by a path model based on the clustered object movement information.

[0101] The object movement information transmitted from each moving body 100 can be matched using filtering, correction, and optimization techniques to ultimately generate accurate and reliable final object movement information. This process plays an important role in enabling the autonomous moving body to recognize and understand its environment in real time. This allows the moving body 100 to have detailed insight into its surrounding environment and make safe and effective autonomous driving control decisions. Furthermore, this improves its ability to respond quickly and accurately to complex road conditions and unexpected situations.

[0102] In relation to the above-mentioned matching, when object movement information is collected from multiple viewpoints of multiple moving objects along their travel paths, the object movement information from the multiple moving objects may have uncertainty due to position estimation errors, detection, tracking, and prediction errors. The multiple object movement information with uncertainty can be matched into a single object movement information represented as an optimal estimate through a matching process using mathematical and statistical techniques. Uncertainties that arise during the object movement information collection process can stem from various causes. For example, sensor accuracy limitations, environmental noise, and occlusions from other objects can cause position estimation errors. Complex situational judgment during the detection, tracking, and prediction processes can also increase uncertainty.

[0103] The process of integrating multiple pieces of uncertain object movement information into a single piece of object movement information can be performed using techniques such as data fusion, filtering, smoothing, etc. Uncertainty can be reduced by considering the correlation and continuity between the object movement information collected from each of the multiple viewpoints.

[0104] The matching process can be performed through statistical modeling and optimization. For example, Bayesian filtering, such as a Kalman filter or a particle filter, can be used to estimate state changes over time and fuse various measurements to minimize uncertainty. An optimal single object movement path can be derived as illustrated in FIG. 8. FIG. 8 is a diagram showing an example of path information generated by matching object movement information collected from multiple devices and multiple viewpoints. FIG. 8 shows the trajectories of two target objects. Multiple pieces of object movement information 514 corresponding to each trajectory are collected, and the server 200 can generate single object movement information for each trajectory through the matching.

[0105] As an example of matching multiple object movement information collected from multiple viewpoints of multiple moving objects, a matching process that takes into account the geometric characteristics of the data can be used. The geometric matching process can perform matching using coordinate information and statistical information, and the information can be selectively used.

[0106] When handling coordinate information, each object's movement information may be recorded as a relative coordinate. The object's movement information must be converted into a unified coordinate system. In this process, the relative coordinates are converted into a common reference system, thereby ensuring consistency between different data. The location data is analyzed based on the converted coordinate information, and this process may analyze common information between location information, the entire set of location information, and the similarity between location information. Through this analysis, related data may be grouped, or a clustering process that identifies connectivity may be performed. This allows for a clearer understanding of the relationship between data, laying the foundation for appropriately processing complex spatial information.

[0107] Statistical information reflects the weight and reliability of collected data and can affect the accuracy of location estimation and object recognition. Statistical information plays an important role in evaluating the quality and accuracy of data, and can be used to understand the characteristics or patterns of object movement information under certain conditions. In the clustering process, statistical information is used to group or classify data with similar characteristics together.

[0108] Data clustering is an important process for understanding and interpreting complex patterns of driving paths, and can be performed by selecting an appropriate geometric model of the driving path. Geometric models can be expressed in various forms, such as points, lines, and surfaces, but lines are commonly used. Linear models can be expressed as polynomials, lines, curves, etc. depending on the geometric characteristics of the driving path, and the path can be clearly represented by estimating coefficients depending on the selected mathematical model.

[0109] When estimating the model coefficients from a large number of clustered travel paths, the error between each travel path and the estimated model can be measured, and the coefficients that minimize the error can be obtained using optimization techniques such as the least squares method, thereby obtaining a more accurate and consistent travel path model from the clustered data.

[0110] A specific approach may be used to estimate the model coefficients for computational efficiency. It may be important to generate an initial model through random sampling and evaluate its consistency with the overall data or the sampled data. By selecting the most accurate model estimated through repeated sampling and estimation processes, data complexity can be managed, and an optimal driving path model can be effectively derived.

[0111] Next, the server 200 can generate path information based on the single object movement information determined in the above process (S215).

[0112] The single object movement information inferred by the optimal driving path linear model in step S210 can be expressed in various ways to generate path information. This can fully reflect the complexity and diversity of the path information. From a geometric perspective, the path information can be expressed as linear path information 516 with vertices, as illustrated in FIG. 8, or as polygonal path information 518, as illustrated in FIG. 9. FIG. 9 is a diagram showing another example of path information. As illustrated in FIG. 10, linear path information with vertices can be expressed as a driving path 526, with a node 528 intersecting a road sign object, for example, a stop line 524.

[0113] As another example, route information may be constructed by utilizing a specific mathematical model and coefficients applied thereto. This representation method can accurately reflect the shape and structure of the line. The representation method can also define various attribute information of the driving route. For example, the representation method can include route ID, direction of travel, road type, speed limit, lane number, etc. Complex link information, such as the connection relationship between driving routes and road facilities, can also be included, contributing to improved consistency and efficiency with the overall transportation system. This integrated approach can improve the performance of the driving system by constructing route information flexibly and accurately.

[0114] Next, the server 200 can edit the route information (S220).

[0115] Editing the route information can involve noise removal and linear representation optimization processes, which can remove unwanted noise on the estimated route information and convert the route into a smooth, continuous, linear form.

[0116] For this purpose, various techniques and procedures can be applied, and each procedure can be tailored to a specific purpose. In addition to initial steps such as random sampling and model estimation, there are other ways to process the data in detail. For example, various filtering techniques can be applied. Such filtering is useful for reducing noise from the original data and highlighting key features. Filtering techniques can include, for example, moving average, Gaussian filter, median filter, spline interpolation, Kalman filter, Fourier transform, contour tracing, deep learning-based filtering, morphological operations, and probabilistic modeling of data within a specific window.

[0117] A moving average calculates the average of data within a specified window size, allowing the window to move along the data set. A moving average can reduce noise by smoothing out short fluctuations along the path. A Gaussian filter can calculate a weighted average of peripheral points using a Gaussian distribution. Points closer to the center are weighted more heavily than points further away, allowing a Gaussian filter to effectively remove noise while preserving signal details. A median filter can use the median value of data points within a given window. It selects the value located in the middle of all values ​​within the window, potentially eliminating the influence of extreme or outlier values.

[0118] Spline interpolation can smoothly connect a series of points on a driving path to generate a more natural driving path. Spline interpolation can form long, stretched curves to remove unnecessary noise and angles. Kalman filters can be used to estimate the uncertainty of dynamic systems and are useful for reducing uncertainty such as sensor noise. Fourier transforms can separate noise through frequency domain analysis of the driving path, retaining only the desired frequency components. This method is particularly effective for removing periodic noise from complex paths.

[0119] Contour tracing can be used to draw lines according to specific features on a route, and can be corrected as needed to form linear or curved routes. Deep learning-based filtering can utilize artificial neural networks to learn and remove complex noise patterns. This method can be particularly effective at separating noise and signal in complex environments. Morphological operations can be used to manipulate the geometry of a route, such as for noise removal, hole filling, and contour extraction. Probabilistic modeling can use probabilistic models to quantify the uncertainty in route information and derive optimal routes. Techniques such as Bayesian filtering fall under the category of probabilistic modeling.

[0120] Furthermore, by carefully combining measured values ​​with model values, noise can be more effectively removed. This comprehensive editing process improves the accuracy of the route and increases its applicability in real driving environments. The processed results provide more precise route information and ensure robust performance in various driving scenarios and environments.

[0121] Next, the server 200 may generate connection relationship information that links at least one of static objects, quasi-static objects, and environmental information of a road related to the route along which the target object travels to the route information (S225).

[0122] Static objects on a road may be, for example, road information on the route along which the target object travels and infrastructure information provided along the travel route. Road information is information that indicates or guides the route along which a mobile object travels on a road, and may include, for example, road lanes, stop lines, road forks, junctions, U-turns, and travel direction signs (e.g., go straight, turn left). Infrastructure information is facilities installed on the road that affect the travel route, and may include, for example, traffic signals and road signs. Quasi-static objects are not objects that physically exist on the road, but are factors that affect travel or the route, and may include, for example, regulatory information assigned to the road, such as speed limits and caution zones. Environmental information may include, for example, traffic flow conditions, weather, road event information, and the like.

[0123] To explain in detail how the connection relationship information is generated, not only the interactions between driving routes based on the route information of the target object but also the complex connection relationship between the driving route and related information can be defined and analyzed. The connection relationship can comprehensively consider various factors, such as traffic flow, road type, and safety regulations. This can be utilized in application fields such as efficient driving route planning, traffic management, and safety analysis. The definition and analysis of the connection relationship can consider complex interactions in conjunction with the topology of the road network as well as geometric and statistical analysis.

[0124] FIG. 10 is a diagram illustrating an example of connection relationship information. FIG. 10 illustrates an example of the result of setting connection relationships between driving routes based on the center line and the direction of travel. Lanes can be divided into an east (E) group and a west (W) group based on the direction of travel, and each lane can be classified and grouped based on the divided groups. This classification plays an important role when an autonomous vehicle plans a driving route and moves between lanes. Based on the center line, driving routes can be assigned sequentially for each lane, such as E-1, E-2, and E-3. The driving route allows the vehicle to make more accurate and efficient decisions regarding lane changes, left / right turns, and speed adjustments. This structured representation can also be linked to a traffic management system and used for traffic flow prediction and safety analysis.

[0125] A driving path can play an important role in defining the connection relationships between road structures such as stop lines, lanes, traffic signals, and signboards. As illustrated in FIG. 11 , a node object 528 is generated at an intersection by geometric intersection analysis of the connection relationship between a stop line 524 and a driving path 526 of a road having a centerline 520 and lanes 522, and the connection relationships can be recorded in attribute information of the driving path 526, the stop line 524, and the node object 528. FIG. 11 is a diagram showing another example of connection relationship information. This allows for more precise and diverse design of driving plans and judgment logic for an autonomous vehicle in response to changes in traffic signals, events at crosswalks, etc. In addition, the connection relationships can be used to improve the response capability of an autonomous vehicle to changes in real-time traffic conditions, road work information, emergency situations, etc.

[0126] As an additional example of linking route information with related information to generate link relationship information, a link between a driving route and speed limit sign information is possible. Complex link relationships, such as those indicating speed limits for each driving section, restrictions on driving direction, and lane change information, can be precisely defined. This allows an autonomous vehicle to recognize and understand road conditions in real time and determine safe and efficient driving. Information related to speed limits plays an important role, particularly in adjusting the speed of an autonomous vehicle and complying with traffic laws.

[0127] Another example is linking a route to a traffic light system. Linking the status and timing of traffic lights to a route allows an autonomous vehicle to predict traffic light changes in advance and create an efficient route plan.

[0128] Another example is the linking of driving routes with emergency facilities. Linking the location information of emergency facilities, such as fire stations and hospitals, located along a driving route with the driving route can enable faster and more accurate responses in the event of an emergency. This linking can be used not only to optimize the routes of emergency vehicles, but also to display evacuation routes for moving objects.

[0129] Another example is the linking of driving routes with weather information. By linking weather information with driving routes, road conditions that change with the weather can be grasped in advance and addressed. For example, when weather conditions such as rain, snow, or fog are predicted, appropriate measures can be taken, such as adjusting the driving speed in the relevant section or changing the route.

[0130] Another example is the linking of driving routes with parking facilities. By linking driving routes with information about currently available parking spaces in parking lots, an autonomous vehicle can search for the nearest available parking lot in real time.

[0131] As described above, the driving route of the route information can be expressed in polygon form, as shown in Figure 9. Figure 9 shows a driving route 518 expressed in polygon form. Each road section is made up of a series of vertices, and by combining these vertices, the width, curvature, lane structure, etc. of the road can be accurately expressed.

[0132] The method of representing a driving path using polygons can accurately reflect the actual width and shape of a road. A polygon model, which defines a driving path using polygonal shapes, can represent the shape of a road in more detail than a linear model, which is represented by multiple vertices that define the road's outline. For example, while a typical linear model can only consider the centerline of the road, a polygonal representation can accurately model complex shapes such as road boundaries on both sides, lane markings, medians, and sidewalks.

[0133] This representation method helps autonomous vehicles establish accurate route plans even in complex road environments, enabling safer and more efficient driving. Furthermore, since information on connections with other traffic structures can be included as attributes within polygons, the overall characteristics of the road can be grasped comprehensively.

[0134] Next, the server 200 incorporates the route information linked with the connection relationship information into the map information to generate map information including the route information (S230), and can verify the map information and correct or update the map information according to predetermined conditions (S235).

[0135] The server 200 can correct or update the map information according to predetermined conditions while inspecting the map information through initial verification, simulation verification, and correction. The estimated driving route is inspected for errors, and if an error is found, the server 200 performs an error correction process and registers the correction in the map database in the memory 204. The inspection and correction processes of the estimated driving route are necessary to ensure the accuracy and reliability of the data. The inspection and correction processes are important for improving the quality of the estimated driving route and providing a driving route that matches the actual driving environment. In particular, the above processes are required for the safe driving of an autonomous vehicle, and continuous updates and management are required.

[0136] The initial verification can check at least one of the integrity, continuity, and regularity of the path information. For example, the initial verification can automatically check the geometric integrity, continuity, regularity, etc. of the path information through a predetermined algorithm. If clear errors or inconsistencies are identified during this verification, initial filtering can be achieved.

[0137] After the initial verification, a human inspection can be added. Human inspection can be performed on route information and map information that has passed automatic verification. During this process, a human can check the accuracy of the data using reference data such as maps and satellite images. In addition, complex factors such as the logical connectivity of the route, the relationship with adjacent roads, and whether road signs and traffic lights match can be considered.

[0138] The simulation verification may be performed to check for interference and collision between the multiple moving bodies 100 through a simulation that virtualizes the traveling of the multiple moving bodies 100. Specifically, the server 200 may virtualize the traveling of at least one autonomous traveling moving body, examine whether there is interference or collision between the moving bodies, and analyze whether the moving bodies are moving at an appropriate speed and direction. Depending on the case, the size and height of the moving body, the field of view of the sensor, weather, road conditions, etc. may be included as simulation input values.

[0139] Then, if a condition occurs in which an error exists in at least one of the initial verification, worker acceptance, and simulation verification, the server 200 can correct at least one of the objects, metadata, and route information included in the map information based on the error.

[0140] If an error is detected, the server 200 can correct the error-related data according to a correction algorithm or a request from an operator. In this process, the shape, connectivity, attributes, etc. of the driving path can be corrected. Among the correction items described above, an example will be described in which, when the driving path belonging to the path information of the target object differs from the actual path information, the path information of the target object is corrected and updated.

[0141] If there is a deviation between the actual information of the target object's actual movement at least in an area corresponding to the predicted route of the route information and the route information that exceeds a predetermined range, the server 200 can update the route information based on the actual information. The actual route can be determined based on subsequent object movement information transmitted by the moving body 100 through the process of FIG. 5 after the route information is generated. More specifically, while the target object actually travels along the predicted route of the route information, the moving body 100 acquires the movement path actually traveled on the predicted route of the target object and can transmit subsequent object movement information of the target object corresponding to the actual movement path to the server 200 in chronological order. The server 200 can generate subsequent route information based on the subsequent object movement information through at least steps S205 to S220. The server 200 can compare the previous route information before the target object moves to the predicted route with the subsequent route information and determine whether there is a deviation that exceeds a predetermined range. If there is a deviation that exceeds the predetermined range, the server 200 can update the route information by replacing the previous route information with the subsequent route information.

[0142] 12 to 14 are diagrams showing an example of verifying map information due to update of route information.

[0143] As shown in Fig. 12, route information related to a moving object and surrounding moving objects may be generated. The moving object and surrounding moving objects may be target objects associated with reference numerals 530 and 532, respectively, in Fig. 12. Route information 534 and 536 illustrated in Fig. 12 may include movement routes 530 and 532 having positions and directions of the moving object and surrounding moving objects for time points t and t+1, and may have connection relationship information linking stop lines with the travel routes of each moving object. The route information at time points t and t+1 may correspond to movement routes traveled by the moving object and surrounding moving objects up to time points t and t+1.

[0144] 13, the route information 534, 536 includes predicted routes 538, 540 for roads on which the moving object and surrounding moving objects are not traveling. The route information illustrated in Fig. 13 includes movement routes 530, 532 at times t and t+1, as well as predicted routes 538, 540 for the moving object and surrounding moving objects at times t+2 and t+3. Like the movement routes 530, 532, the predicted routes 538, 540 at times t+2 and t+3 can be estimated to include the positions and directions of the moving object and surrounding moving objects.

[0145] As shown in FIG. 14 , when subsequent route information 542, 544 including the moving object traveling along predicted routes 538, 540 and the actual routes of surrounding moving objects is acquired, the server 200 can determine whether there is a deviation between the predicted routes 538, 540 and the actual routes, based on the preceding route information 534, 536 and the subsequent route information 542, 544, that exceeds a predetermined range. Because the deviation between the moving object's predicted route 538 and its actual route is less than the predetermined range, the server 200 maintains the predicted route 538 and does not update the preceding route information 534. In contrast, because the deviation between the surrounding moving object's predicted route 540 and its actual route exceeds the predetermined range, as shown in FIGS. 14 and 15 , the server 200 modifies the predicted route 540 to the actual route and changes the preceding route information 536 to the subsequent route information 544, thereby updating the route information. FIG. 15 is a diagram illustrating an example of updating route information based on verification.

[0146] Meanwhile, the server 200 can incorporate the updated route information according to the above into the map information, update the map information, and register it in the map database. The server 200 transmits the map information including the updated route information to the mobile body, and the mobile body can control its autonomous driving based on the updated map information.

[0147] Although the exemplary method of the present disclosure described above is expressed as a series of operations for clarity of explanation, this is not intended to limit the order in which the steps are performed, and the steps may be performed simultaneously or in a different order if necessary. To realize the method according to the present disclosure, other steps may be included in addition to the steps shown in the examples, or some steps may be excluded and the remaining steps may be included, or some steps may be excluded and additional other steps may be included.

[0148] The various embodiments of the present disclosure are not intended to enumerate all possible combinations, but are intended to describe representative aspects of the present disclosure, and the matters described in the various embodiments may be applied independently or in combination of two or more.

[0149] Furthermore, various embodiments of the present disclosure may be implemented using hardware, firmware, software, or a combination thereof, etc. In the case of a hardware implementation, the implementation may be using one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general processors, controllers, microcontrollers, microprocessors, etc.

[0150] The scope of the present disclosure includes software or machine-executable instructions (e.g., operating systems, applications, firmware, programs, etc.) that cause operations according to the methods of the various embodiments to be performed on a device or computer, as well as non-transitory computer-readable media on which such software or instructions, etc., are stored and executable on a device or computer.

Claims

1. A method for updating route information, comprising: a step of tracking at least one target object among a moving body and peripheral dynamic objects around the moving body to acquire a movement path of the target object, the movement path of the target object being acquired based on recognition information acquired from the moving body having an observation sensor and a positioning sensor, the observation sensor observing the target object and including at least one of a radar sensor, a camera, and a lidar sensor; generating a predicted route based on the travel route, the predicted route being estimated from the travel route; generating subsequent path information including the movement path of the target object moving along the predicted path; a step of replacing the preceding route information with the following route information and updating the preceding route information when there is a deviation of a predetermined range or more between the travel route of the following route information and a predetermined travel route of the preceding route information included in the map information; updating map information based on the subsequent route information, which is the updated preceding route information.

2. the step of acquiring the movement path includes tracking the target object using positioning information of the target object estimated from the positioning sensor and a trajectory based on an optimal position of the target object; 2. The construction method of claim 1, wherein the recognition information is collected as a plurality of pieces of recognition information so as to have multiple viewpoints (multiviews) in time series with respect to the target object, features are extracted for each of the plurality of pieces of recognition information, relative displacement information between the observation sensor and the feature is generated by matching the features, and the optimal position is generated so as to minimize the amount of gap in the relative displacement information.

3. The construction method of claim 2, wherein the extraction of features and the matching between features are performed with reference to movement information and observation state information of the mobile body, and the observation state information indicates a state in which the observation sensor of the mobile body recognizes the target object.

4. The construction method of claim 2 , further comprising providing the best location of the target object to the positioning information and the map information.

5. 2. The construction method according to claim 1, wherein the step of generating the predicted route includes generating the predicted route based on displacement information of the target object, speed information of the target object, the movement route, environmental information of the route along which the target object travels, regulation information applied to the route along which the target object travels, movement pattern information of routes identical or similar to the route along which the target object travels, and cumulative route information of routes identical or similar to the route along which the target object travels.

6. 6. The construction method according to claim 5, wherein displacement information of the target object and velocity information of the target object are provided in a time series, and the step of generating the predicted path generates the predicted path using trajectory modeling including a nonlinear state transition method based on the time series displacement information and the time series velocity information, and the trajectory modeling is configured to receive feedback based on an error between a predicted trajectory derived from the trajectory modeling and a trajectory derived based on the recognition information.

7. The construction method of claim 1, wherein generating the subsequent path information includes determining a single object movement information derived by matching the target object against multiple object movement information as the subsequent path information, and the multiple object movement information are transmitted from each of multiple moving bodies that generate the movement path and predicted path of the target object.

8. The construction method of claim 7, wherein the matching of the plurality of object movement information includes performing geometric matching between the object movement information, clustering similar object movement information based on statistical information according to the weighting degree of the object movement information, and generating the single object movement information using a path model based on the clustered object movement information and adopting it as the subsequent path information.

9. 2. The construction method according to claim 1, wherein the step of updating the map information based on the subsequent route information includes generating connection relationship information that links at least one of road information of the route traveled by the target object, infrastructure information provided for the route traveled, weather information of the route traveled, and regulation information applied to the route traveled with the subsequent route information.

10. the preceding route information is updated by verifying the map information; 2. The construction method of claim 1, wherein the verification of the map information includes performing an initial verification to check at least one of the integrity, continuity, and regularity of the subsequent route information, performing a simulation verification to check whether there is interference and collision between the multiple moving objects through a simulation that virtualizes the travel of the multiple moving objects, and correcting at least one of the objects, metadata, and the subsequent route information included in the map information based on errors generated in the initial verification and the simulation verification.

11. An autonomous driving assistance device that updates route information, a communication unit for exchanging data with the mobile unit; a memory for storing at least one instruction; a processor that uses the data to execute the at least one instruction stored in the memory; the moving body tracks at least one target object among the moving body and peripheral dynamic objects around the moving body to acquire a movement path of the target object, and generates a predicted path by which movement is estimated from the movement path based on the movement path; the movement path of the target object is acquired based on recognition information acquired from the moving body having an observation sensor and a positioning sensor; the observation sensor observes the target object and includes at least one of a radar sensor, a camera, and a lidar sensor; The processor: generating subsequent path information including the movement path of the target object moving along the predicted path; If there is a deviation of a predetermined range or more between the movement route of the subsequent route information and a predetermined movement route of the preceding route information included in the map information, updating the preceding route information including the movement route of the target object moving along the predicted route; An autonomous driving assistance device that updates map information based on subsequent route information, which is the updated preceding route information.

Images