Provision method and provision device for adaptive map for various autonomous travel navigation platforms

Abstract

To disclose a provision method and provision device for an adaptive map for various autonomous travel navigation platforms.SOLUTION: A method includes the steps of: generating peripheral environment information of a moving body based on recognition information obtained from the moving body equipped with a sensor; selecting at least one piece of map information from among a plurality of pieces of map information based on characteristic information of the moving body that includes at least one of the type of the moving body, the sensing performance of the moving body, the processing performance of the moving body, and the communication performance of the moving body, and the environmental information; adjusting the map information based on status information indicating the peripheral situation of the moving body recognized from the environmental information; and transmitting the adjusted map information to the moving body.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present disclosure relates to a method and apparatus for providing an adaptive map for various autonomous driving navigation platforms, and more particularly, to a method and apparatus for providing an adaptive map that dynamically applies map information in real time so as to realize a map service with various autonomous driving navigation devices having their own operation methods.

Background Art

[0002] Autonomous driving vehicles have been developed in various mobility fields such as vehicles, robots, unmanned mobile devices, and drones, and commercialization is being considered.

[0003] As the application targets of autonomous driving expand, the demand for accurate and flexible map information is increasing. Individually providing or generating map information suitable for various devices from unmanned drones to autonomous driving vehicles brings many challenges, and such diversity may lead to inefficiencies and operational fragmentation.

[0004] In addition, an autonomous driving vehicle can make a driving plan and judgment process by referring to a preset route on a map, and predict these predicted routes by referring to the moving routes of surrounding objects. However, if the actual moving routes of the vehicle and surrounding objects are different from the preset moving routes, the vehicle may malfunction or cause an accident.

[0005] Since a precise map for autonomous driving has high accuracy and a lot of information, a lot of resources are consumed for the construction and update of the precise map. As a result, there is a limit in providing data suitable for operating conditions, that is, requirements, for various autonomous driving navigation devices to cope with various types of environments on the route. In particular, due to changes in the environment and the state of the moving body, the real-time update and adaptation speed of information decrease, which may prevent the efficient operation of the device.

[0006] In addition, in order to prevent fragmentation, increasing the amount of data used for the map may cause problems in processing speed and communication efficiency. On the other hand, reducing the amount of data may reduce the accuracy of autonomous driving navigation.

[0007] In addition, the format of map data and the communication protocol may differ depending on the autonomous driving and navigation system, and it may be difficult to provide an integrated service.

Summary of the Invention

Problems to be Solved by the Invention

[0008] The technical problem of the present disclosure is to provide a method and apparatus for an adaptive map for a variety of autonomous driving navigation platforms that dynamically and real-time apply map information so as to realize a map service with a variety of autonomous driving navigation devices having unique operation methods.

[0009] Another technical problem of the present disclosure is to provide a method and apparatus for an adaptive map that supports autonomous driving that achieves higher flexibility and safety in various situations on the route by selecting and adjusting a map suitable for the surrounding environment and conditions using an algorithm based on real-time data and artificial intelligence.

[0010] The technical problems to be achieved in the present disclosure are not limited to the technical problems described above, and other technical problems not mentioned will be clearly understood by those having conventional knowledge in the technical field to which the present disclosure belongs from the following description.

Means for Solving the Problems

[0011] According to one aspect of the present disclosure, a method for providing an adaptive map for various autonomous driving navigation platforms is provided. The method for providing the adaptive map includes generating surrounding environment information of the moving body based on recognition information acquired from a moving body equipped with sensors; selecting at least one map information from a plurality of map informations based on characteristic information of the moving body including at least one of a type of the moving body, a sensing performance of the moving body, a processing performance of the moving body, and a communication performance of the moving body, and the environment information; adjusting the map information based on situation information indicating a surrounding situation of the moving body recognized from the environment information; and transmitting the adjusted map information to the moving body.

[0012] According to another embodiment of the present disclosure, the plurality of map informations may include a base map produced in a format according to a predetermined rule, a geometric map geometrically representing object elements of a road on which the moving body can travel, an occupancy map representing object elements dynamically behaving on the road in a grid form, a semantic map including at least connection relation information defining object elements associated with the road, a prior knowledge map including at least operation information of object elements for controlling travel of the moving body on the road, a real-time knowledge map including at least association relation information defining data mutually associated with the situation information, and a positioning map for assisting positioning of the moving body.

[0013] According to still another embodiment of the present disclosure, the recognition information includes direct recognition information and indirect recognition information acquired by the moving body, the direct recognition information is recognition information directly detected by the moving body, and the indirect recognition information is recognition information for detecting object elements exceeding a recognition range of the sensors of the moving body, and may be recognition information acquired from other moving bodies around the moving body.

[0014] According to still other embodiments of the present disclosure, the environmental information is generated based on recognition information of object elements transmitted from the moving body and other moving bodies around the moving body, and the recognition information may be collected as a plurality of recognition information so as to have a multiview in a time series.

[0015] According to still other embodiments of the present disclosure, the type of the moving body includes one of a ground moving body, an aerial moving body, and a marine moving body, and the map information is selected based at least on requirement specialization information determined according to the type of the moving body, and the requirement specialization information may include information required for the map information by at least one of a flow pattern of the moving body, route safety, and a function maintenance degree of a specific module of the moving body.

[0016] According to still other embodiments of the present disclosure, the map information is constructed to include route information of the moving body, and the map information may be determined based on additional data together with the characteristic information and the environmental information of the moving body. The additional data includes at least one of moving pattern information of the moving body confirmed by the history information of the moving body, similarity information on a route having similarity with a moving route or a traffic state of the route, a usage frequency of the route information on the route, a correction frequency of the route information, a user request frequency for the route information, and map evaluation information generated by a simulation using a potential traffic state inferred from the environmental information.

[0017] According to still other embodiments of the present disclosure, the step of adjusting the map information includes generating first map information selected by the environmental information in front of the existence area and second map information corresponding to the existence area with reference to the environmental information of the existence area when it is predicted that the moving body will enter the existence area of the situation information, and the first and second map information may be configured as different types of map information.

[0018] According to still other embodiments of the present disclosure, the step of adjusting the map information may include providing route information to the map information based on at least one of route information pre-generated by past data related to the situation information and route information derived from a prediction model by learning based on the situation information.

[0019] According to still other embodiments of the present disclosure, before the step of transmitting the adjusted map information to the moving body, the method may further include the step of further adjusting the map information in detail based on user information and mobility detail information. The user information includes at least one of a preferred route and a route pattern on the route along which the moving body moves, and the mobility detail information may include sensor information including detailed specifications and detailed performance of the sensor, and mobility constraint information according to the type and specifications of the moving body.

[0020] According to still other embodiments of the present disclosure, the method may further include the step of obtaining feedback information related to the use of the map information acquired while the movement of the moving body is controlled by the adjusted map information, and the step of updating the map information based on the feedback information. The step of updating may include updating the map information based on result data verified through a simulation using movement data of the moving body derived from the feedback information.

[0021] According to another aspect of the present disclosure, an adaptive map providing apparatus for various autonomous driving navigation platforms is provided. The adaptive map providing apparatus includes a communication unit that exchanges data with a moving body, 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 processor generates surrounding environment information of the moving body based on recognition information acquired from a moving body equipped with sensors, and selects at least one map information from a plurality of map informations based on characteristic information of the moving body including at least one of a type of the moving body, sensing performance of the moving body, processing performance of the moving body, and communication performance of the moving body, and the environment information. The processor is configured to adjust the map information based on situation information indicating a surrounding situation of the moving body recognized from the environment information, and transmit the adjusted map information to the moving body.

[0022] The features briefly summarized above with respect to the present disclosure are merely exemplary aspects of the detailed description of the present disclosure to be described later, and do not limit the scope of the present disclosure.

Effects of the Invention

[0023] According to the present disclosure, it is possible to provide a method and an apparatus for an adaptive map for various autonomous driving navigation platforms that dynamically and real-time apply map information so as to realize a map service with various autonomous driving navigation apparatuses having unique operation methods.

[0024] Further, according to the present disclosure, by reflecting the environment on the actual route on the map information, it is possible to improve the accuracy and safety of the recognition, planning, and determination processes of the autonomous driving moving body, and improve the accuracy and productivity of the map information for autonomous driving.

[0025] According to the present disclosure, by optimizing map information through real-time route analysis, continuous provision of road structure and dynamic road information, recognition of connection relationships between objects on the moving route, and map updates, it is possible to ensure predictability for the behavior of a moving object, improve the accuracy of a navigation system, and optimize traffic flow.

[0026] The effects obtained in the present disclosure are not limited to the effects described above, and other effects not mentioned will be clearly understood by those having conventional knowledge in the technical field to which the present disclosure pertains from the following description.

Brief Description of the Drawings

[0027]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Modes for Carrying Out the Invention

[0028] Hereinafter, with reference to the accompanying drawings, it will be described in detail so that those having conventional knowledge in the technical field to which the present disclosure pertains can easily implement embodiments of the present disclosure. However, the present disclosure can be realized in many different forms and is not limited to the embodiments described herein.

[0029] When describing embodiments of the present disclosure, if it is determined that a detailed description of a known configuration or function would obscure the gist of the present disclosure, the detailed description thereof will be omitted. Also, in the drawings, parts not relevant to the description of the present disclosure are omitted, and similar parts are denoted with similar reference numerals.

[0030] In the present disclosure, when a component is “connected,” “coupled,” or “joined” to another component, this can include not only a direct connection relationship but also an indirect connection relationship in which other components exist between them. Also, when a component “includes” or “has” another component, this means that, unless otherwise stated to the contrary, it does not exclude other components and can further include other components.

[0031] In the present disclosure, terms such as first, second, etc. are used only for the purpose of distinguishing one component from another and do not limit the order or importance, etc. between components unless otherwise specified. Therefore, within the scope of the present disclosure, the first component in one embodiment may be referred to as the second component in another embodiment, and similarly, the second component in one embodiment may be referred to as the first component in another embodiment.

[0032] In the present disclosure, components that are distinguished from each other are for clearly explaining their respective features and do not necessarily mean that the components are separated. That is, a plurality of components may be integrated to form one hardware or software unit, or one component may be dispersed to form a plurality of hardware or software units. Therefore, embodiments integrated or dispersed in this way are also included in the scope of the present disclosure even if not specifically mentioned.

[0033] In the present disclosure, the components described in various embodiments do not necessarily mean essential components, and some of them may be optional components. Therefore, embodiments composed of a subset of the components described in one embodiment are also included in the scope of the present disclosure. Further, embodiments that further include other components in the components described in various embodiments are also included in the scope of the present disclosure.

[0034] In the present disclosure, each of the phrases such as "A or B", "at least one of A and B", "at least one of A or B", "A, B or C", "at least one of A, B and C", and "at least one of A, B, or C (at least one of A, B, C or combination thereof)" may include any one of the items described together in the corresponding phrase, or all possible combinations thereof.

[0035] The advantages and features of the present disclosure, and the methods for achieving them, will become clear by referring to the embodiments described in detail below together with the accompanying drawings. However, the present disclosure is not limited to the embodiments presented below, and can be realized in various different forms. These embodiments are merely provided to completely disclose the present invention and enable those with conventional knowledge in the technical field to which the present invention belongs to fully understand the scope of the invention.

[0036] Hereinafter, with reference to FIGS. 1 to 3, a method and an apparatus for providing an adaptive map for various autonomous driving navigation platforms will be described. FIG. 1 is a diagram showing that a moving body communicates with a server and other devices to transmit and receive data. FIG. 2 is a block diagram of the moving body illustrated in the present disclosure. FIG. 3 is a block diagram of a server according to an embodiment of the present disclosure.

[0037] Referring to FIG. 1, the mobile object 100 may be a mobility device used for a specific purpose while moving on the ground, in the air, or on the sea. The mobile object 100 may be, for example, a vehicle, a robot, a drone, or a ship. As an example, the mobile object 100 may be a mobility device that communicates with the server 200 and other devices 300, 400 to achieve autonomous movement. The mobile object 100 transmits various information acquired during travel, 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 can transmit route information, map information, travel support information, and software to the mobile object 100 based on the above-mentioned information. As another example, the mobile object 100 can communicate with the server 200 and other devices 300, 400 to exchange the above information and obtain navigation information for guiding the travel route. In the present disclosure, the server 200 can be operated as an autonomous driving support device that constructs route information for autonomous driving based on the behavior of the mobile object 100 and the recognition information and positioning information of the object elements collected from the mobile object 100. In addition, the server 200 has route information and navigation information and can function as an adaptive map providing device that provides map information adapted to the surrounding environment of the mobile object 100, the characteristic information of the mobile object 100, and the information related to the user of the mobile object 100.

[0038] In the present disclosure, an example in which the mobile object 100 is a vehicle will be mainly described, but it can also be applied to other types of mobile objects listed above. Hereinafter, for the sake of convenience of explanation, the mobile object 100 and the vehicle may be used interchangeably in the description.

[0039] When the moving body 100 is a vehicle, the moving body 100 is driven based on electric energy or fossil energy. In the case of electric energy, the moving body 100 can be, for example, a pure battery-based vehicle driven only by a high-voltage battery, or a gas-based fuel cell can be adopted as an energy source. Also, the fuel cell can use various forms of gas that can generate electric energy, and hydrogen is an example of the gas. However, it is not limited to this, and various gases are applicable. In the case of fossil energy, the moving body 100 is driven based on fuels such as gasoline, diesel oil, or liquefied gas, and can be equipped with an engine that drives the wheel drive unit 114 by burning the fuel. The engine may be included in the energy generation unit 112 from the viewpoint of providing the driving rotational force of the wheel to the wheel drive unit 114.

[0040] The moving body 100 can be controlled and driven by autonomous driving, and the autonomous driving can be realized by semi-autonomous driving or fully autonomous driving. The fully autonomous driving is provided as an autonomous movement in which the control unit 120 of the moving body 100 completely controls the control right without the intervention of the user even when the driving situation is uncertain. The semi-autonomous driving is provided as an autonomous movement that requires the intervention of the driver according to a specific driving situation. When the above situation occurs, the semi-autonomous driving can be realized by the control unit 120 deactivating the autonomous driving and transferring the control right to the user so that the user can perform manual driving.

[0041] On the one hand, the mobile body 100 can communicate with other devices 200, 300 or other mobile bodies 400. The other devices may include, for example, a server 200 that supports various controls, state management, and driving of the mobile body 100, an ITS (Intelligent Transportation System) device 300 for receiving information from an ITS, and various types of user devices. The server 200 can transmit various information and software modules used for controlling the mobile body 100 to the mobile body 100 in response to requests and data transmitted from the mobile body 100 and the user device to support the autonomous driving and various services of the mobile body 100.

[0042] The ITS device 300 is, for example, a Road Side Unit (RSU). The ITS device 300 can assist the user's own vehicle driving or support the autonomous driving of the mobile body 100 by exchanging vehicle recognition data, driving control and state data, vehicle surrounding environment data, map data, etc. with the mobile body 100 through V2I. The mobile body 100 can support its own vehicle driving or autonomous driving by exchanging the above-mentioned data with other mobile bodies 400 through V2V.

[0043] The mobile body 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.

[0044] For example, for communication with the server 200, the ITS device 300, and other moving objects 400, the moving object 100 can use communication networks such as LTE (registered trademark), 5G, etc. as a cellular communication network, a WiFi (registered trademark) communication network, a WAVE communication network, etc. As another example, DSRC or the like used in the moving object 100 may be used for vehicle - to - vehicle communication. The communication methods among the moving object 100, the server 200, the ITS device 300, other moving objects 400, and the user device are not limited to the above - described embodiments.

[0045] Referring to FIG. 2, the moving object 100 may include a sensor unit 102, a transceiver unit 106, and a display 108.

[0046] The sensor unit 102 can be provided with various types of detectors that sense various states and situations occurring in the external and internal environments of the moving object 100 and grasp the positioning information of the moving object 100. That is, the sensor unit 102 is composed of a multi - sensor module including different types of sensors and can acquire sensing data detected from each sensor.

[0047] Specifically, the sensor unit 102 may be provided with an observation sensor so as to perceive (perceive) dynamic and static objects existing around the moving object 100 and have a positioning sensor 104d for acquiring the position information and direction information of the vehicle. The observation sensor may be composed of a multi - sensor having a lidar sensor 104a, a camera 104b functioning as an image sensor, and a radar sensor 104c. The sensor unit 102 can acquire sensor data including recognition information and positioning information, etc. by 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 for detecting the presence and movement state of surrounding objects.

[0048] 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 perceives the three-dimensional form of an object. Specifically, the lidar sensor 104a can obtain three-dimensional recognition data for the surrounding environment and objects by scanning a laser around the moving body 100. The three-dimensional recognition data may include a point cloud representing the three-dimensional form of the object, that is, detection data and observation image data that visually shows the surrounding environment. The detection data may be provided to identify each object, for example, by showing the three-dimensional contour shape of the object and the arrangement of the objects. The image data may be provided to identify the object and the surrounding environment, for example, through an image of the object and the surrounding environment.

[0049] The camera 104b can obtain two-dimensional image data or image data with depth information for the surrounding environment and objects of the moving body 100. The radar sensor 104c can detect the behavior of an object, for example, by irradiating radio waves of a predetermined wavelength around and based on the radio waves reflected from the object. The behavior of the object may include, for example, the presence of the object and the presence or absence of movement of the object, the distance between the moving body 100 and the object, the speed of the object, the moving direction, and the like.

[0050] 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., in order to confirm positioning information including its own position, traveling attitude, speed, etc.

[0051] In the present disclosure, the sensor of the sensor unit 102, which is merely referred to in the description of the embodiments, is mainly described, and sensors for sensing various situations not described herein may be further included.

[0052] The transmission / reception unit 106 can assist in mutual communication with the server 200, the ITS device 300, the surrounding moving bodies 400, and the like. In the present disclosure, the transmission / reception unit 106 can transmit data generated or stored during traveling to the server 200, and receive data and software modules transmitted from the server 200. In the present disclosure, the moving body 100 can transmit and receive data used in the method according to the present disclosure to and from the outside via the transmission / reception unit 106.

[0053] The display 108 can function as a user interface. The display 108 can be caused by the control unit 120 to display the operating state of the moving body 100, the control mode, route / traffic information, remaining energy amount information, content requested by the driver, and the like. The display 108 can display route information, map information, and various information related to the traveling route transmitted from the server 200. The display 108 is composed of a touch screen capable of detecting the driver's input, and can receive the driver's request for instructing the control unit 120.

[0054] On the other hand, the moving body 100 may include an actuating unit 110, an energy generation unit 112, a wheel drive unit 114, and a load device 116.

[0055] The actuating unit 110 includes at least one module for realizing a traveling operation, and can perform at least one of traveling operations such as longitudinal control such as acceleration and deceleration and lateral control such as steering. The actuating unit 110 may include, in addition to a pedal and a steering wheel that receive the user's request for the control, various operating modules for generating a traveling operation corresponding to the request in the wheel drive unit 114.

[0056] The energy generation unit 112 can generate and supply the power and electricity used for the traveling power system such as the wheel drive unit 114 and the load device 116. When the moving body 100 is driven based on electric energy, the energy generation unit 112 may be composed of, for example, an electric battery, or may be composed of a combination of an electric battery and a fuel cell that charges this battery. When the moving body 100 is driven based on fossil energy, the energy generation unit 112 may be composed of an internal combustion engine.

[0057] The wheel drive unit 114 may include a plurality of wheels, a driving force transmission module for generating a driving force and applying it to the wheels, a braking module for decelerating the driving of the wheels, and a steering module for realizing the lateral control of the wheels. When the moving body 100 is driven based on electric energy, the driving force transmission module may be composed of a motor module that generates a driving force based on the power output from the electric battery. When the moving body 100 is driven based on fossil energy, the driving force transmission module may include a transmission for transmitting the power of the internal combustion engine and a gear module.

[0058] The load device 116 may be an auxiliary device that is mounted on the moving body 100 and consumes the power supplied from the energy generation unit 112 or the power whose output from the energy generation unit 112 is converted by the use of a passenger or a user. The load device 116 may be a type of non-traveling electric device excluding the traveling power system such as the wheel drive unit 114 in the present disclosure. The load device 116 may be, for example, an air conditioning system, a lighting system, a seat system, and various devices installed in the moving body 100.

[0059] Also, the moving body 100 may include a storage unit 118 and a control unit 120.

[0060] The storage unit 118 stores applications and various data for the control of the moving body 100, and can load the applications and read and record the data in response to the request of the control unit 120.

[0061] In the present disclosure, the storage unit 118 can store an application that generates real-time environmental information based on the recognition information, positioning information acquired from the sensor unit 102 of the moving body 100, and external information received from an external device. The recognition information and the positioning information can be generated by recognizing the behavior of the moving body 100 and the object elements around the moving body 100. The recognition information may include direct recognition information and indirect recognition information acquired by the moving body 100. The direct recognition information may be recognition information directly detected by the moving body 100. The indirect recognition information is recognition information for detecting object elements beyond the recognition range of the observation sensors 104a to 104c of the moving body 100, and may be recognition information acquired from other moving bodies around the moving body. The external device may be, for example, the server 200, the ITS device 300, and / or the surrounding moving body 400.

[0062] The object elements may include road objects and external objects. The road objects may include an area where the moving body 100 moves, for example, road static objects and road dynamic objects existing on a road. The road static objects may be, for example, sign information for traffic control on the road, facilities, etc. The road dynamic objects may be mobile objects moving on the peripheral road of the driving lane of the moving body 100. The road dynamic objects may be, for example, vehicles moving on the peripheral road in the same direction or the opposite direction, vehicles traveling on each lane connected to an intersection, pedestrians / mobility crossing a crosswalk, etc. Although a vehicle is given as an example of the road dynamic object, the present disclosure is not limited thereto, and various types of ground mobility moving on a road or a detailed lane of a road may correspond to the road dynamic object.

[0063] The external objects may include static objects such as buildings and sidewalks installed outside the road, and dynamic objects such as pedestrians and bicycles moving around the road.

[0064] The environmental information may be information related to object elements around the moving body inferred from the recognition information and the positioning information. The information related to the object elements may include the type, position, shape, and movement trajectory of the object identified as the object element. The information related to the object elements may include the traffic flow state estimated from the behavior of the road dynamic objects, the operating state of the road traffic facilities recognized from the observation sensors 104a to 104c, the events recognized from the observation sensors 104a to 104c, and the like.

[0065] In addition, the environmental information may include external information received from an external device, for example, situation information and the operating information of the traffic safety facilities. The situation information is event information occurring on the route of the moving body 100, and may include, for example, the traffic flow state, accident information, construction information, weather information, and the like. The operating information may include, for example, the duration, waiting time, etc. related to the stop, running, and caution of the traffic lights installed on the road. That is, the environmental information is element information estimated to affect the movement control of the moving body 100, and can be generated by at least one of the state of the road static object, the state including the movement trajectory of the road dynamic object, the situation information, and the operating information.

[0066] On the other hand, the storage unit 118 can store and manage the map information including the route information and various information related to the driving route from the server 200. The map information can be used to generate the driving route set for the moving body 100 according to the request of the user or the control unit 120. In addition, the map information is used for autonomous driving, may include a low-precision map, and may include a high-precision map together with the above map. The map information may be provided to have various information and data included in the above-described object and environment.

[0067] The control unit 120 can perform overall control of the moving body 100. The control unit 120 may be configured to execute the applications and instructions stored in the storage unit 118. The control unit 120 can activate autonomous driving in response to a request for autonomous driving according to the settings of the user or the moving body 100 itself, and control the moving body 100. Further, the control unit 120 can deactivate autonomous driving in response to a request by the user's cancellation or automatic cancellation, and control the moving body 100 to perform manual driving.

[0068] In relation to the present disclosure, the control unit 120 can generate real-time environmental information based on the recognition information acquired from the sensor unit 102 of the moving body 100, the positioning information, and the external information received from an external device, using the applications, instructions, and data stored in the storage unit 118. Further, the control unit 120 can transmit the environmental information, the detailed information related to the moving body 100, and the user information related to the user of the moving body 100, and receive optimal map information. The characteristic information may include at least one of the type of the moving body 100, the sensing performance of the moving body 100, the processing performance of the moving body 100, and the communication performance of the moving body 100. The user information may include at least one of a preferred route and a route pattern on the route along which the moving body 100 moves. The user information is not limited to the above-described matters, and may include options related to the driving and route selected by the user and the driving experience and route experience inferred by learning.

[0069] In addition, the control unit 120 can transmit the mobility detailed information to the server 200. The mobility detailed information may be information that the server 200 refers to for adjusting or refining the detailed data and detailed settings of the map information. The mobility detailed information may include, for example, sensor information including the detailed specifications of the sensor unit 102 including the observation sensors 104a to 104c and the positioning sensor 104d and the detailed performance of the sensor unit 102, and mobility constraint information according to the type and specifications of the moving body 100. The sensor information may include, for example, the detailed specifications of the observation sensors 104a to 104c and the positioning sensor 104d, the observation ranges of the observation sensors 104a to 104c, the detailed resolution, the calibration method, the types of sensors constituting the positioning sensor 104d, the fine accuracy of the positioning sensor 104d, and the like. The mobility constraint information may be, for example, profile information including the limitations of the moving environment required based on the type of the moving body 100, that is, a ground, flight, or marine moving body, and the priority application elements required for the map information.

[0070] In the present disclosure, the control unit 120 may be realized by a single processing module as an example, or as another example, the above processing may be distributedly processed by a plurality of processing modules.

[0071] Referring to FIG. 3, the server 200 may function as the autonomous driving support device according to the present disclosure as described above and may include a communication unit 202, a memory 204, and a processor 206.

[0072] The communication unit 202 can assist in mutual communication with the mobile body 100, the ITS device 300, and surrounding mobile bodies 400. In the present disclosure, the communication unit 202 can receive data generated or stored during the travel of the mobile body 100 and surrounding mobile bodies 400, and transmit data and software modules to the mobile body 100 and surrounding mobile bodies 400. As shown in FIG. 1, the communication unit 202 can receive environmental information from a plurality of mobile bodies, that is, the mobile body 100 and other mobile bodies 400. Further, the optimal map information generated by the processor 206 to conform to each mobile body 100 based on the environmental information can be transmitted to each mobile body 100 via the communication unit 202. Also, real-time situation recognition, route update, emergency commands, etc. generated by the processor 206 can be transmitted to a plurality of mobile bodies 100 via the communication unit 202.

[0073] The memory 204 stores applications and various data for controlling the server 200, and can load an application and read and record data in response to a request from the processor 206. In the present disclosure, the memory 204 can store an application for providing optimal map information based on environmental information transmitted from the mobile body 100, performance information of the mobile body 100, and user information. The optimal map information may include the route information of the mobile body 100 itself. Also, the map information may transmit route information related to road dynamic objects existing around the mobile body in order to establish a route applied to the autonomous driving of the mobile body 100.

[0074] Specifically, the memory 204 can store an application and at least one instruction for processing the selection, adjustment, transmission, feedback, and update of map information.

[0075] On the one hand, the memory 204 may have a map library that holds multiple types of map information for transmitting optimal map information. The map library may manage, for example, multiple types of maps, or may manage the individual components that make up the maps in the form of layers. The individual components are map detail data required in a specific type to provide a specific type of map, and may be, for example, individual data related to the state of object elements, the movement trajectories of object elements, situation information, and the operation information of traffic safety facilities.

[0076] The processor 206 can perform overall control of the server 200. The processor 206 may be configured to execute the applications and instructions stored in the memory 204.

[0077] In relation to the present disclosure, the processor 206 can select map information based on the characteristic information, environmental information, and external information of the moving body 100, and adjust the map information based on the situation information, using the applications, instructions, and data stored in the memory 204. The processor 206 can adjust the map information in detail based on the user information and mobility detail information, transmit the adjusted map information to the moving body 100, and update the map information based on the feedback information of the map information transmitted from the moving body 100.

[0078] In the present disclosure, the processor 206 may be implemented as a single processing module as an example, and in other examples, the above processing may be distributed among multiple processing modules.

[0079] In the present disclosure, a plurality of moving bodies 100 generate and transmit real-time environmental information, and the server 200 uses learning based on the plurality of environmental information to infer the context on the path along which the plurality of moving bodies 100 move, and can generate integrated environmental information based on the inferred context. The context may be inferred to have the movement trajectories of the plurality of moving bodies 100 and the situational elements referred to in the movement control through the trajectories of the plurality of moving bodies 100. The integrated environmental information may include, in addition to the real-time environmental information, predicted environmental information predicted based on the inferred context. As another example, some of the plurality of moving bodies 100 transmit recognition information, observation information, and recognized situation information to the server 200, and the server 200 can also generate integrated environmental information based on the above information.

[0080] Hereinafter, for convenience of explanation, an embodiment in which a plurality of moving bodies 100 generate real-time environmental information and transmit it to the server 200 will be described. Specifically, it will be described in detail with reference to FIGS. 4 to 7 in relation to the processing of the control unit 120 of the moving body and the processor 206 of the server 200. However, the following embodiments can also be applied to other examples in which real-time environmental information is generated by the server 200.

[0081] FIG. 4 is a flowchart relating to a method for providing an adaptive map according to another embodiment of the present disclosure. Hereinafter, for convenience of explanation, the control unit 120 of the moving body 100 and the processor 206 of the server 200 that process the process of FIG. 4 may be abbreviated as the moving body 100 and the server 200, respectively, or these terms may be used interchangeably in the description.

[0082] Referring to FIG. 4, each of the plurality of moving bodies 100 shown in FIG. 1 can acquire recognition information and positioning information of object elements around the moving body by using the observation sensors 104a to 104c and the positioning sensor 104d, and generate object movement information related to the road dynamic objects including the moving body 100 and the surrounding moving bodies (S105). Since the plurality of moving bodies 100 perform the process of FIG. 5 substantially in the same manner, hereinafter, for convenience of explanation, the plurality of moving bodies are denoted as the moving body 100.

[0083] The recognition information may include direct recognition information and indirect recognition information acquired by the moving body 100. The direct recognition information is the recognition information directly detected by the moving body 100, and the indirect recognition information is the recognition information for detecting object elements beyond the recognition range of the sensors of the moving body 100, and can be acquired from other moving bodies around the moving body.

[0084] In order for the moving body 100 to use the sensor data acquired from the observation sensors 104a to 104c as recognition information, the sensor data may be pre-processed. The pre-processing can involve calibration, sensor fusion, feature extraction, etc. Calibration can formulate the geometric model and radiation model of the sensor to estimate and correct the internal parameters. Also, the defined geometric relationship between the multiple sensors of the moving body 100 can be used in the sensor fusion process. Sensor fusion can convert the spatial system of the sensor data so that the sensor data can be handled in the same reference system based on the geometric relationship between the multiple sensors. Regarding feature extraction, the moving body 100 can extract the main features for environmental analysis from the sensor data.

[0085] Regarding indirect recognition information, as shown in FIG. 1, the mobile body 100 may be communicably connected to surrounding mobile bodies 400. The surrounding mobile bodies 400 may be heterogeneous mobility devices such as drones, robots, etc., in addition to mobility devices of the same type as the mobile body 100. As shown in FIG. 5, the mobile body 502 can obtain recognition information for detecting object elements beyond its own sensor's recognition range from another mobile body 504. Object elements beyond the sensor's recognition range may be, for example, objects recognized due to the limitations of the sensing ability of the mobile body 100, objects in an occlusion area due to obstacles within the available sensing range, or objects in a blind spot area.

[0086] FIG. 5 is a diagram showing the connectivity of the positioning and observation of multiple mobile bodies. The mobile body 504 and other mobile bodies 502 move along a first travel route 506 and a second travel route 508, respectively. The mobile body 502 can directly recognize a first object 510 around the first travel route 506 using its own observation sensor. The association between the mobile body 502 and the directly recognized first object 510 can be defined as a first observation relationship 514. The other mobile body 504 directly recognizes second objects 512, 526 around the second travel route 508, and the association between the other mobile body 504 and the directly recognized second objects 512, 526 can be defined as a second observation relationship 516. The recognition information of the first and second objects 510, 512, 526 detected by the observation sensors of each mobile body 502, 504 may have recognition prediction errors 518, 520, 522, 524 for various reasons. The recognition prediction errors 518, 520, 522, 524 may be caused, for example, by the observation sensors of the mobile bodies 502, 504 and the observation recognition of the objects 510, 512, 526. Accordingly, each mobile body 502, 504 can generate an optimal position that minimizes the separation amount in the relative displacement information considering the recognition prediction errors 518, 520, 522, 524, and estimate the positions of the respective objects 510, 512, 526.

[0087] As shown in FIG. 5, the mobile object 502 may not be able to recognize the second object 526 existing around the first travel route 506 as an observation sensor. Accordingly, the mobile object 502 may continuously communicate with another mobile object 504 and receive the recognition information directly obtained by the other mobile object 504. The mobile object 502 can analyze the directly obtained recognition information and the recognition information of the other mobile object 504, and incorporate the recognition information of the second object 526 that the mobile object 502 could not recognize into the recognition information of the mobile object 502. The recognition information of the second object 526 is the indirect recognition information of the mobile object 502. Accordingly, the mobile object 502 regards the object as the re-observed object 526, and the association between the mobile object 502 and the re-observed object 526 can be defined as a re-observation relationship.

[0088] The sensor data directly and indirectly collected by each mobile object differs in sensor configuration, data format, and the target to be recognized. The mobile object 100 can process a process consisting of data conversion, similarity analysis, and optimal value selection in order to interpret the sensor data.

[0089] In addition, the recognition information may be collected as a plurality of recognition information so as to have a multi-view with respect to the target object in a time series. Features can be extracted for each of the plurality of recognition information, and relative displacement information between the observation sensors 104a to 104c and the above features can be generated by matching between the features. The features may be, for example, lines, edges of the target object, surfaces of a predetermined shape, or geometric forms having similarity to a specified shape. The extraction of the features and the matching between the features may be performed with reference to the movement information and the observation state information of the moving body 100. The observation state information can indicate the state in which the observation sensors 104a to 104c of the moving body 100 recognize the target object. The observation state information may include the directions, postures, etc. of the respective sensors constituting the observation sensors 104a to 104c that observe the object along the movement trajectory of the moving body 100 during traveling. The moving body 100 can identify the same target object in the multi-view recognition information by applying a tracking algorithm and / or filtering technology (e.g., Kalman filter) that employs an association technique, and track the trajectory of the identified target object, that is, the target object in motion. In addition, multi-view tracking can reduce temporary sensor noise or detection errors and can be used for accurate tracking of the object.

[0090] On the other hand, the moving body 100 can generate positioning information of the moving body 100 using the recognition information, the position, posture detected from the positioning sensor 104d, and the map information stored in advance. The recognition information may include direct recognition information and indirect recognition information. The positioning information can further include positioning information received from surrounding moving bodies in addition to the above-described information, thereby estimating the positions of multi-mobility including the moving body 100 and surrounding moving bodies. Thereby, the information deficiency of the moving body 100 can be overcome and the positioning accuracy can be improved.

[0091] Position estimation using multiple mobilities can be achieved by using data fusion, collaborative localization of multiple devices, an integrated approach, stable network connection, and adaptive algorithms.

[0092] Various sensors and mobilities can have their respective characteristics. For example, satellite positioning is accurate outdoors but may not work indoors, while positioning using Wi-Fi (registered trademark) or Bluetooth (registered trademark) exhibits excellent performance indoors but has limitations outdoors. Also, the recognition of object elements in a single moving object may have limitations and errors depending on dead zones in data collection and the performance of each sensor. Positioning based on sensor data requires reference information for obtaining position information on a map. By combining sensor data and various data through data fusion, the drawbacks of a single device can be complemented.

[0093] By sharing position information among multiple mobilities, the positioning accuracy of the entire network by multiple mobilities can be improved. For example, when a specific moving object has accurate position information, other moving objects can share the position information of the specific moving object to reduce positioning errors.

[0094] For accurate positioning, not only the data of multiple moving objects is integrated, but also the mobile object 100 can additionally use the map information received from the server 200 and the existing positioning information. Also, by updating and sharing the positioning information of each mobile object in real time, the uncertain positioning errors of each mobile object can be corrected. The mobile object 100 can obtain optimal results by dynamically adjusting the positioning algorithm according to the situation of object elements and environmental conditions on the route.

[0095] The mobile body 100 can continuously detect mobile objects including the mobile body 100 and road dynamic objects using recognition information and positioning information, and generate object movement information. The recognition by detecting the mobile object may be processed to grasp the form and attributes of the object. The mobile body 100 can obtain the movement route of the mobile object by tracking the object using the positioning information of the mobile object estimated from the positioning sensor 104d and the trajectory based on the optimal position of the mobile object. The trajectory of the mobile object based on the optimal position is the trajectory traveled by the continuously observed mobile object, and the optimal position based on the recognition information of the observation sensors 104a to 104c continuously acquired by the traveling mobile body 100 can be used to estimate the movement trajectory of the target object.

[0096] Next, the mobile body 100 transmits real-time environment information and various information to the server 200, and the server 200 can generate integrated environment information and route information based on the above information and analyze these information (S110).

[0097] The mobile body 100 can generate real-time environment information based on recognition information, positioning information, surrounding situation information of the mobile body, operation information, and regulation information, and transmit the real-time environment information to the server 200. The situation information, operation information, and regulation information can be received from an external device. The regulation information is information regarding mandatory requirements applied to the travel of the mobile body 100, such as speed limit, altitude limit, prohibited driving area, operation caution area, and the like.

[0098] The mobile body 100 can transmit various information used by the server 200 to select optimal map information to the server 200. The various information includes characteristic information of the mobile body 100, user information, and mobility detail information.

[0099] The characteristic information may include, for example, at least one of the type of the mobile object, the sensing performance of the mobile object 100, the processing performance of the mobile object 100, and the communication performance of the mobile object 100. The type of the mobile object may include one of a ground mobile object, an aerial mobile object, and a marine mobile object. The sensing performance may be, for example, the resolution of the observation sensors 104a to 104c, the data generation cycle, the synchronization method, the positioning accuracy of the positioning sensor 104d, and the like. The processing performance may be, for example, the processing specifications of resources such as the control unit 120 and the storage unit 118, the current available processing capacity of the resources, and the like. The communication performance may be, for example, the transmission rate of the mobile object 100, the communication protocol applied between the mobile object 100 and the server 200, the attributes of the network connected to the mobile object 100, the communication delay state of the mobile object 100, and the like.

[0100] The user information may include at least one of a preferred route and a route pattern on the route along which the mobile object 100 moves. The mobility detail information may include sensor information including the detailed specifications and detailed performance of the sensors, and mobility constraint information according to the type and specifications of the mobile object 100.

[0101] Based on the information transmitted from the mobile object 100, the server 200 can generate integrated environmental information and route information of mobile objects including at least the mobile object 100. The environmental information and the route information can be constructed based on the information transmitted from a plurality of mobile objects 100. The server 200 can generate integrated environmental information by learning and optimizing an artificial intelligence model based on the information collected from a plurality of mobile objects 100. By transmitting the environmental information to the map information stored in the server 200 and the mobile object 100, the recognition accuracy can be improved.

[0102] FIG. 6 is a diagram showing the generation process of environmental information.

[0103] The mobile object 100 can acquire the recognition information collected from the observation sensor and the positioning information of the positioning sensor, and receive the map information and external information used by the mobile object 100. The mobile object 100 can fuse the above information to recognize the real-time environment around the mobile object and estimate its position. By continuously tracking the environmental information due to the variation of the above information, the mobile object 100 can track the object movement path of the moving object. The mobile object 100 transmits the real-time environment information and the object movement path to the server 200, and the server 200 can generate the predicted environmental information and the predicted path expected in the route along which the mobile object 100 moves based on the information and the movement path received from a plurality of mobile objects 100.

[0104] Since the predicted environmental information and the predicted path are generated based on a plurality of mobile objects 100, they may have uncertainty. The server 200 can generate a single predicted environmental information and a single predicted path by post-processing a plurality of predicted environmental information in a geographically identical area and a plurality of predicted paths of the same moving object. The server 200 can, for example, perform geometric alignment between a plurality of predicted environmental information and cluster similar predicted environmental information based on statistical information according to the weight of the predicted environmental information. The server 200 can generate a single predicted environmental information by an environmental estimation model based on the clustered predicted environmental information. Thereby, the server 200 can generate integrated environmental information composed of real-time environmental information and predicted environmental information. The post-processing of the predicted path is performed in the same manner as the predicted environmental information, and the predicted path and the object movement path can be configured as path information.

[0105] Since the path information includes the aspect of the change of the moving object on the route, the time and history for each moving point of each moving object can be managed. For the accuracy of the map information and navigation, time synchronization between data may be involved.

[0106] In addition, the predicted environmental information may include potential environmental change information predicted based on past data accumulated in relation to the above information.

[0107] The above has described how the server 200 constructs environmental information from the information received from a plurality of mobile bodies 100 in a centralized manner. As another example, by establishing a connection relationship among the plurality of mobile bodies 100, the plurality of mobile bodies 100 communicate with the server 200, the plurality of mobile bodies 100 perform a local optimization process mutually, and the server 200 can perform a global optimization process. Since the centralized method is vulnerable to server 200 failures and large amounts of traffic, the plurality of mobile bodies 100 can generate local environmental information and local route information mutually, and the server 200 can construct wide-ranging environmental information and route information.

[0108] Next, the server 200 can select at least one piece of map information out of the plurality of pieces of map information stored in the memory 204 based on the characteristic information and environmental information of the mobile body 100 (S115).

[0109] Since the characteristic information and environmental information referred to for selecting the optimal map information have been described above, they are omitted. The selected map information may include the state of object elements, the surrounding situation of the mobile body, the operation information of traffic safety facilities, and regulation information. Further, the selected map information may be constructed to include the route information of the mobile body 100 and surrounding mobile bodies. For the validity of the route information, the map information may be determined based on additional data managed by the server 200 in addition to the characteristic information and environmental information. The additional data may include, for example, at least one of the movement pattern information of the mobile body 100, similarity information, the usage frequency of route information, the modification frequency of route information, the user request frequency for route information, and map evaluation information. The movement pattern information is confirmed by the history information of the mobile body 100, and the similarity information may be information on a route having similarity with the moving route or the traffic state of the route. The usage frequency is the frequency of using the route information on the said route, and the map evaluation information can be generated by a simulation using the potential traffic state inferred from the environmental information.

[0110] Server 200 can manage multiple map information in a map library. Server 200 can manage and process map information adapted to various navigation platforms and scenarios. The map information may include static information, dynamic information, and semi-dynamic information. The multiple map information can have different levels of detailed information, resolution, and structure depending on the characteristics of the moving object and the operating environment. The map information can be classified and managed based on regionalization, recognition technology, operating terrain, device type, type (static information, dynamic information, semi-dynamic information), and time-varying information. The map information can store and provide information used for the path planning and decision-making of the autonomous driving moving object in various formats. The individual components constituting the map information may be managed in the form of layers. The individual components are map detailed data that affects the path setting of the autonomous driving moving object and may be, for example, static information, dynamic information, semi-dynamic information, etc. The dynamic information may include, for example, the real-time behavior of vehicles, pedestrians, and various types of moving objects. The semi-dynamic information may include elements that change at predictable intervals or under specific conditions, such as traffic lights, pedestrian crosswalk signals, variable message signs, etc. The semi-dynamic information may include traffic flow conditions, weather conditions, regulations, and temporary changes to the road. Since the dynamic information and the semi-dynamic information are time-series, the timestamp at the time of generation and acquisition of the information is recorded, the currency and relevance of the information are evaluated, and it can be used at the time of update.

[0111] The map information to be managed may be, for example, a base map, a geometric map, an occupancy map, a semantic map, a prior knowledge map, a real-time knowledge map, and a positioning map, etc.

[0112] The base map may be a map produced in a format according to a predetermined specification. The base map provides the basic structure and information for spatial information, and compatibility can be ensured by superimposing a precise map on a map in a specified format, such as a satellite map, an aerial map, or a digital map. To ensure compatibility, information that can define a reference coordinate system such as a coordinate system scale, a center point, an axis, and an ellipsoid may be included, and other layers may also be arranged according to the reference coordinate system information.

[0113] The geometric map may be a map that geometrically represents object elements of roads on which the moving body 100 can travel. The geometric map can represent moving environment information, such as route information, in two-dimensional or three-dimensional geometric shapes such as polygons, lines, and columns.

[0114] The occupancy map can represent object elements that behave dynamically on roads in a two-dimensional or three-dimensional grid form. The occupancy map includes the occupancy state of a specific object in each grid, and various information such as object attribute information and movement route information can be further introduced. Also, since the grid is composed of multiple layers, multiple information can be recorded at a specific coordinate, and the resolution can be adjusted according to the system performance by the multi-resolution configuration.

[0115] The semantic map may at least include connection relationship information that defines object elements associated with roads. The semantic map can record lane, traffic sign, traffic signal position information, sign attribute information, child protection area information, etc. for the operation of navigation. A connection relationship can be defined between each piece of information. For example, a traffic sign that affects a lane can be associated, and a speed limit value corresponding to the lane can be set.

[0116] The prior knowledge map may at least include the operation information of the object elements that control the driving of the moving body 100 on the road. The prior knowledge map can provide information such as the waiting time of traffic signals, for example, and assist in real-time decision-making. At this time, by using the crowdsourcing data collected from multiple moving bodies and external devices and learning from the existing accumulated data, the aspect of change can be predicted. The connection relationship between the data is defined. For example, the stop line information and the signal information can be associated, and the mutual influence relationship can be defined.

[0117] The real-time knowledge map may at least include the association relationship information that defines the data that are mutually associated among the data belonging to the situation information. The real-time knowledge map can be maintained in the latest state by reflecting immediate driving environment changes such as traffic changes and road construction, for example. Also, by associating the lane belonging to the situation information with the road construction information, approach restriction information for the lane may be added to the real-time knowledge map.

[0118] The positioning map can assist in the positioning of the moving body 100. The positioning map may include, for example, a landmark map, an octree, and a cost map. The landmark map separately manages the characteristics of information that are advantageous for the alignment between sensor data, and when re-collecting the data of the area, the characteristics can be used for the purpose of alignment. The octree divides the space into octants and can reduce the search cost for accessing the data of the space. In addition to the octree, a data structure such as a KD-tree may also be used. The cost map can assist in decision-making by assigning navigation costs to various areas. By assigning a high cost to dangerous areas, traffic congestion areas, etc., driving in the area can be avoided.

[0119] The process of selecting map information may include evaluating the optimal SW and data combination based on algorithms, characteristic information, environmental information, and past information of these, and providing the navigation device with map information having the latestness.

[0120] When the server 200 receives environmental information, it can confirm and verify the consistency of the data belonging to the environmental information. The server 200 can analyze the time value of the data and extract the latest data.

[0121] The server 200 may identify the type of the moving body 100 through characteristic information and determine the required specialization information according to the type of the moving body 100. The required specialization information may include the information required for the map information by at least one of the flow pattern of the moving body, the route safety level, and the function maintenance level of the specific module of the moving body. The required specialization information can analyze, for example, the type of the moving body, the capabilities of the moving body, and the restrictions required for the moving body. As shown in this example, when the type is an autonomous vehicle, the required specialization information may include reflecting the road and traffic pattern in the map information and expressing the events on the road in the map information. When the type is a drone, the required specialization information may include, for example, requesting map information that ensures the route safety (clearance) in vertical movement and provides the altitude of surrounding objects and obstacle avoidance information.

[0122] Also, as described above, the server 200 can select map information based on characteristic information, environmental information, and additional data including at least one of the sensing performance of the moving body, the processing performance of the moving body, and the communication performance of the moving body.

[0123] The server 200 can analyze the network state, computer performance, and functional limitations of the mobile body 100. Specifically, the server 200 may determine map information based on, for example, the type of sensor, the capabilities of the sensor, the resolution of the sensor, the positioning accuracy, the periodicity, the communication method, the current transmission traffic state, the energy efficiency, etc. For example, when the resolution of the sensor is low, the transmission traffic is high, or the processing performance is low, instead of map information including a wide area around the mobile body to reduce the capacity of the map information, map information covering a narrow area may be selected. As another example, instead of map information having high accuracy and a large amount of detailed data, map information composed of data having a predetermined priority among the data belonging to the environmental information or having low accuracy may be selected. The map information may be determined so as to associate traffic flow information, surrounding event information, weather changes, etc.

[0124] The server 200 can analyze the driving and environmental context of the mobile body 100 using additional data. For example, by analyzing past data including driving patterns, signal paths, traffic flow, user experience, that is, the additional data, in the way applied by the existing navigation algorithm, the additional data by the above method can be referred to when selecting the optimal map information. Also, the influence of the operating environment by the additional data on the driving performance may be analyzed, and map information may be selected.

[0125] The server 200 continuously optimizes the performance of the algorithm and the variables used in the algorithm by analyzing the map usage experience and results of each mobile body. Through the map usage experience and driving experience, the weights applied to the algorithm and data can be strengthened.

[0126] Mobile data from various navigation platforms may be analyzed to derive a map selection strategy. The additional data to be analyzed may be, for example, navigation usage frequency, correction frequency, driving distance, user behavior, etc.

[0127] In addition, the server 200 can predict potential environmental awareness and driving results through various simulations. Thereby, the server 200 can pre-evaluate the performance of the map used in the mobile body 100 and select map information according to the evaluation results.

[0128] The server 200 can select a plurality of map information. For example, the server 200 may select different types of map information in the same area where the mobile body 100 moves, or may select different types of map information in different regions along the moving route. The different regions may be regions having different time intervals from each other.

[0129] The server 200 may evaluate a plurality of map information belonging to the map library based on characteristic information, environmental information, and additional data, and finally determine the map information. For example, the algorithm for each map in the library can calculate a fitness score based on the mediation variables by the above-mentioned information. The score can indicate how well the map matches the context of the current device, user, and environment. As an example, the map information with the highest score may be selected. As another example, the map information may be determined by heuristic selection considering user preferences, past feedback, or specific environmental nuances.

[0130] Next, the server 200 can adjust the map information in real time based on the situation information indicating the surrounding situation of the mobile body recognized from the environmental information (S120).

[0131] The real-time adjustment of the map information may mean that when the situation information is variable along the route of the mobile body 100, the map information in the area where there is an event related to the situation information is processed based on the selected map information. For example, individual components related to the event area may be provided as a layer on the selected map information. Also, the real-time adjustment of the map information can also mean providing only the map information in the area where there is an event as a map different from the selected map information.

[0132] The server 200 can determine whether real-time adjustment of the map information is necessary by analyzing the dynamic context through the latest situation information. For example, when the situation information is short-term traffic congestion, sudden accidents, sudden weather changes, etc., the server 200 can determine the adjustment of the map information based on the situation information, and add individual components that match the situation information to the selected map information.

[0133] In addition, the server 200 can change the route information of the selected map information based on at least one of the route information pre-generated by the past data related to the situation information and the route information derived from the prediction model by learning based on the situation information, and adjust the map information according to the changed route information. For example, when it is expected from the current situation information that the path of heavy rain or the continuous increase of traffic congestion, the route information by past data and / or the prediction model may be reflected in the map information.

[0134] The above-mentioned adjustment of the map information is tuning by predictive adaptation, and can be realized in various ways according to the type of the moving body. In the case of a robot, in an urban environment, environmental information related to events or construction in the pedestrian area is considered, and the map information may be adjusted to have route information with a low degree of congestion. In the case of a drone, environmental information predicting a storm in a specific area is considered, and the map information may be adjusted to have route information that bypasses the storm and turbulent flow areas or flies at a higher altitude. In the case of a marine moving body, environmental information in which a red tide or the proliferation of toxic algae occurs or is predicted is considered, and the map information may be adjusted to have route information that avoids harmful areas that may damage the sensors of the moving body.

[0135] An example of adjusting the map information by providing map information different from the selected map information is shown in FIG. 7. FIG. 7 is a diagram showing the real-time adjustment of the map information.

[0136] The selected map information, i.e., the first map information, is a vector map, and the first map information is a map constructed such that the moving body 530 and the surrounding moving bodies 532 autonomously travel along the first movement route 534 and the second movement route 536, respectively. When the server 200 receives situation information notifying that an event 538, such as a traffic accident, has occurred on the route along which the moving body 530 and the surrounding moving bodies 532 are scheduled to move, the server 200 can predict that the moving body 530 and the surrounding moving bodies 532 will encounter the traffic accident at the predicted position 540 of the moving body 530 and the predicted position 542 of the surrounding moving bodies 532 along the first and second movement routes 534 and 536. As a result, the server 200 can change the first movement route 534 and the second movement route 536 to the first predicted route 544 and the second predicted route 546, respectively, in the area of the event 538. Further, since the first map information based on vectors only shows the time-series positions and moving directions of the object elements, the server 200 can determine that it is not possible to avoid or guide safe driving in the area of the event 538 based on the first map information. The server 200 maintains the first map information as the map information for the time period t to t + 2 corresponding to the area where the event 538 does not occur, but can generate second map information, such as an occupancy map, as the map information for the time period t + 2 to t + 4 corresponding to the area where the event 538 occurs. The second map information may be constructed to include an event occupancy area 548 corresponding to the area where the event 538 occurs, a first route occupancy area 550 corresponding to the first predicted route 544, and a second route occupancy area 552 corresponding to the second predicted route 546. The server 200 can adjust the map information in real time by adopting the second map information that accurately provides safe avoidance route information instead of the first map information in the area where the event 538 has occurred.

[0137] In addition to the situation information, the server 200 can also adjust the map information in real time based on other information of the environmental information and the user information. For example, the route information of the map information may be changed and the map information may be adjusted according to the dynamic state of the object element, the user's preference, and the performance of the device mounted on the moving body 100. Specifically, even if the map information is selected by the characteristic information, the map information may be converted by the detailed sensor information of the mobility detail information. For example, within the range where the detailed sensing performance by the combination of the observation sensors 104a to 104c and the positioning sensor 104d is satisfied, the individual components included in the map information can increase or decrease.

[0138] Next, the server 200 can adjust the map information in detail based on the user information and the mobility detail information (S125) The user information may include, for example, at least one of a preferred route and a route pattern on the route along which the moving body moves. The mobility detail information may include sensor information including the detailed specifications and detailed performance of the sensor unit 102, and mobility constraint information according to the type and specifications of the moving body 100.

[0139] At least one of the server 200 and the mobile unit 100 accumulates knowledge from the routes experienced by the user and the behavior of the mobile unit 100, and this knowledge can be used for navigation decisions. The server 200 manages a unique behavioral map based on at least one of the preferred route and route pattern, and can adjust the details of the map information based on the behavioral map. For example, the detailed display items of the map information may be adjusted so that the Personalized Waypoints stand out on the map information. By designating Points of Interest (POIs) where the user's interest is presumed, such as charging stations, rest areas, or specific landmarks, the Points of Interest can stand out on the map information. The map information recommends route information and movement patterns to the mobile unit 100, but the map information may be adjusted so that the user's existing preferred route information and movement patterns are emphasized more than the recommended information and patterns. Also, while the mobile unit 100 is moving based on the selected map information, the server 200 may receive feedback from the user and adjust part of the route information based on the feedback.

[0140] In relation to the adjustment based on the mobility details, the server 200 can finely adjust the map information based on the sensor sensitivity and movement constraints. For example, the detailed data of the map information may be adjusted according to the detailed performance, resolution, and observation range of the sensor. When the type of the mobile unit is a ground robot or a drone, an object shown as an available route in the map information, such as a staircase, may be treated as an unavailable route, or detailed altitude restrictions may be added to the map information. According to the type of the mobile unit, the map information may be processed so that the ground routes and roads are shown in detail and the objects corresponding to the flight altitude or the sea terrain are shown simply. Alternatively, the map information may be processed so that the objects corresponding to the above altitude or the sea terrain are shown in detail and the ground roads are shown simply.

[0141] Next, the server 200 can transmit the adjusted map information to the mobile unit 100 according to a predetermined method (S130).

[0142] Transmission according to a predetermined method may mean transmitting map information by a communication protocol determined based on, for example, a communication network environment, bandwidth, communication performance of the mobile body 100, traffic, etc. The above transmission can involve authentication, error checking, data integrity checks, retransmission of transmission errors, and security protocols in the mobile body 100 and the server 200. Further, the above transmission may include encrypting and transmitting data exchanged between the server 200 and the mobile body 100 including map information, feedback information, etc., and processing security updates that change communication protocols for channels vulnerable to security.

[0143] Next, the server 200 can acquire feedback information related to the use of the map information acquired while the movement of the mobile body 100 is controlled by the map information, and update the map information based on the feedback information (S135).

[0144] The feedback information may be, for example, user feedback or environmental information that affects movement on an actual movement route different from the route information. The server 200 can update the map information based on result data verified through a simulation using movement data of the mobile body 100 derived from the feedback information. Specifically, the simulation can virtualize the driving result of the mobile body 100 and reproduce the reaction of the mobile body 100 to environmental information. The simulation can evaluate the map information and related algorithms by producing user intervention that requires behavior different from the information provided from the map information, and update the map information, etc. according to the evaluation result.

[0145] Server 200 can integrate feedback from multiple mobile bodies 100 and apply DevOps, MLOps, and MapOps principles to more effectively update map information and related algorithms. For example, through the application of a labeling algorithm and process to the data of map information collected by feedback, map information is generated, and the generated map information and the existing map information can be updated by mutual analysis and verification. Thereby, the map information is registered and MapOps can be configured. Also, the collected data and the updated map information are used as reference data and used in an artificial intelligence model related to the map information, and such a model can contribute to the automation of the labeling operation. In improving learning performance, insufficient reference data can be reinforced through Augmentation.

[0146] The exemplary methods of the present disclosure described above are presented as a series of operations for clarity of explanation, but this does not limit the execution procedures of the steps, and if necessary, each step may be performed simultaneously or in a different procedure. To implement the method according to the present disclosure, in addition to the exemplary steps, other steps may be included, 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.

[0147] The various embodiments of the present disclosure do not enumerate all possible combinations, but explain 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.

[0148] In addition, various embodiments of the present disclosure can be implemented by hardware, firmware, software, or a combination thereof. In the case of implementation by hardware, it can be implemented by 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.

[0149] The scope of the present disclosure includes software or machine-executable instructions (e.g., operating systems, applications, firmware, programs, etc.) that cause the operations of the various embodiments of the method to be executed on a device or computer, and non-transitory computer-readable media on which such software or instructions are stored and executable on a device or computer.

Claims

1. 1. A method for providing an adaptive map for a diverse autonomous navigation platform, comprising: generating surrounding environment information of a moving object based on recognition information acquired from the moving object equipped with a sensor; selecting at least one piece of map information from among the plurality of pieces of map information based on characteristic information of the moving object, the characteristic information including at least one of a type of the moving object, a sensing performance of the moving object, a processing performance of the moving object, and a communication performance of the moving object, and the environmental information; adjusting the map information based on situation information indicating a surrounding situation of the moving object recognized from the environmental information; transmitting the adjusted map information to the mobile unit.

2. 2. The method of claim 1, wherein the plurality of map information includes: a base map created in a predetermined format; a geometric map that geometrically represents object elements of a road on which the mobile object can travel; an occupancy map that represents object elements that dynamically behave on the road in a grid shape; a semantic map that includes at least connection relationship information that defines object elements associated on the road; a prior knowledge map that includes at least operation information of object elements that control travel of the mobile object on the road; a real-time knowledge map that includes at least association relationship information that defines data that are mutually associated in the situation information; and a positioning map for supporting positioning of the mobile object.

3. 2. The method for providing an adaptive map according to claim 1, wherein the recognition information includes direct recognition information and indirect recognition information acquired by the moving body, the direct recognition information being recognition information directly detected by the moving body, and the indirect recognition information being recognition information that detects object elements beyond the recognition range of the sensor of the moving body and is recognition information acquired from other moving bodies in the vicinity of the moving body.

4. The method for providing an adaptive map as described in claim 1, wherein the environmental information is generated based on recognition information of object elements transmitted from the moving body and other moving bodies around the moving body, and the recognition information is collected as multiple recognition information so as to have a multiview in a time series.

5. 2. The method for providing an adaptive map as described in claim 1, wherein the type of the moving body includes one of a ground moving body, an air moving body, and a sea moving body, the map information is selected based at least on requirement specific information determined according to the type of the moving body, and the requirement specific information includes information required for the map information based on at least one of a flow pattern of the moving body, a route safety degree, and a functional maintenance degree of a specific module of the moving body.

6. the map information is constructed to include route information of the moving object, the map information being determined based on additional data together with characteristic information of the moving object and the environmental information; 2. The method for providing an adaptive map according to claim 1, wherein the additional data includes at least one of information on the movement pattern of the moving object confirmed by historical information of the moving object, similar information on the moving route or a route having similarity to the traffic conditions of the route, a frequency of use of the route information on the route, a frequency of modification of the route information, a frequency of user requests for the route information, and map evaluation information generated by a simulation using potential traffic conditions inferred from the environmental information.

7. 2. The method for providing an adaptive map as described in claim 1, wherein the step of adjusting the map information includes, when it is predicted that the moving body will enter the existence area of ​​the situation information, generating second map information corresponding to the existence area by referring to first map information selected by the environmental information ahead of the existence area and the environmental information of the existence area, and the first and second map information are configured as heterogeneous map information.

8. 2. The method of claim 1, wherein adjusting the map information includes providing route information to the map information based on at least one of route information previously generated by past data related to the situation information and route information derived from a predictive model by learning based on the situation information.

9. The method further includes a step of fine-tuning the map information based on user information and mobility detail information before transmitting the adjusted map information to the mobile unit; The method for providing an adaptive map according to claim 1 , wherein the user information includes at least one of a preferred route and a route pattern on a route traveled by the mobile object, and the mobility detail information includes sensor information including detailed specifications of the sensor and detailed performance of the sensor, and mobility constraint information according to a type and specifications of the mobile object.

10. obtaining feedback information related to the use of the map information obtained while the movement of the moving object is controlled by the adjusted map information; updating the map information based on the feedback information; The method for providing an adaptive map according to claim 1 , wherein the updating step includes updating the map information based on result data verified through a simulation using movement data of the moving object derived from the feedback information.

11. An adaptive map providing device for various autonomous driving navigation platforms, comprising: A communication unit for exchanging data with the mobile unit; a memory storing at least one instruction; a processor for executing the at least one instruction stored in the memory using the data; The processor, generating surrounding environment information of a moving object based on recognition information acquired from the moving object equipped with a sensor; selecting at least one piece of map information from among the plurality of pieces of map information based on characteristic information of the moving object, the characteristic information including at least one of a type of the moving object, a sensing performance of the moving object, a processing performance of the moving object, and a communication performance of the moving object, and the environmental information; adjusting the map information based on situation information indicating a surrounding situation of the moving object recognized from the environmental information; An adaptive map providing device configured to transmit the adjusted map information to the vehicle.

Images