WO2021137483A1

WO2021137483A1 - Method and system for updating map by using autonomous driving robot

Info

Publication number: WO2021137483A1
Application number: PCT/KR2020/018503
Authority: WO
Inventors: 장경석; 장정인; 이준구
Original assignee: (주)원익로보틱스
Priority date: 2019-12-30
Filing date: 2020-12-17
Publication date: 2021-07-08
Also published as: KR102169283B1

Abstract

Disclosed are a method and a system for updating a map by using an autonomous driving robot. The method for updating a map by using an autonomous driving robot comprises the steps of: configuring a driving route of an autonomous driving robot on the basis of a variable probability distribution map having an area-specific variable probability according to accumulated environmental changes in a space; generating a map by using space information obtained by a second-dimensional laser scanner according to the driving route; and updating an existing map with the generated map when a change in an environment different from the existing map is recognized from the generated map.

Description

Map update method and system using autonomous driving robot

The present disclosure relates to a method and system for updating a map using an autonomous driving robot, and more particularly, to a method and system for updating a map using an autonomous driving robot for improving the efficiency and convenience of updating a map.

The autonomous driving robot autonomously moves to the destination using driving means such as wheels while detecting obstacles by grasping its surroundings. Autonomous driving robots have recently been used to provide various services such as voice, screen or accompanying information, and delivery of goods in large spaces such as public places such as train stations, bus terminals and airports, conventions, shopping centers, hotels, and resorts. provided to space users. In addition, the autonomous driving robot simultaneously creates a map to recognize its location and provide services.

Since the autonomous driving robot does not have information about the surrounding environment to move in an unknown environment, it creates a map about the environment using sensor information and estimates the current location of the moving object from the created map. A map creation method using an autonomous driving robot is mainly a method of generating a map while estimating the position of the robot.

On the other hand, in most cases, the space associated with a specific place has a different environment as time passes because the arrangement or shape of facilities in the indoor and outdoor space is changed with time. Accordingly, it is necessary to continuously update the maps created by the robot in the past. A typical update using a robot is to place the robot in a corresponding space, and then apply the above-described process of simultaneous location estimation and map generation. Although this process suffices if only a partial area change is performed on the existing map, a new map is created without using a recently created map or using a part, and the existing map is completely replaced.

This update process does not cause much inconvenience in a space composed of fixed facilities such as pillars, walls, and permanent structures, but the location of floating facilities such as temporary booths, temporary rest areas, temporary ticket offices, and various large decorations for expositions In large spaces such as conventions and airports that change frequently, efficiency is greatly reduced.

This inefficiency is that floating facilities may not exist at the time of the update, so the path of the robot is set only with an existing map that stores only the location of fixed facilities, or even when the environment changes in some areas, it is very difficult to create and update a map of all areas This is because it takes a lot of time.

In order to solve this problem, various methods for updating the map with high precision while shortening the update time are being tried.

The technical task of the present disclosure is to provide a map update method and system using an autonomous driving robot with improved efficiency and convenience by executing the map update of the autonomous driving robot according to the driving route based on the accumulated change probability distribution for each area each time the map is updated. will be.

Another technical task of the present disclosure is a map update method using an autonomous driving robot capable of extracting a region in which an environment is frequently changed from a space, as well as grasping information on an object located in the corresponding region, to determine a space utilization tendency, and to provide a system.

Another technical problem of the present disclosure is that, when the map service provider clearly recognizes the environmental change in a part of the space, autonomous driving starts updating the map from the area where the change occurs to further increase the efficiency and precision of the update It is to provide a method and system for updating a map using a robot.

The technical problems to be achieved in the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those of ordinary skill in the art to which the present disclosure belongs from the description below. will be able

According to an aspect of the present disclosure, a map update method using an autonomous driving robot may be provided. The map update method using the autonomous driving robot includes: setting a driving path of the autonomous driving robot based on a change probability distribution map having a change probability for each area according to an environment change accumulated in space; generating a map with spatial information obtained by a laser scanner; and updating the existing map with the generated map when an environment change different from the existing map is recognized in the generated map.

According to another embodiment of the present disclosure, the setting of the driving route may include connecting regions having the lowest change probability in the change probability distribution map to set the driving route.

According to another embodiment of the present disclosure, before the step of setting the driving route, the method further includes generating the change probability distribution map, wherein the generating of the change probability distribution map includes: the accumulated environment change of the space collecting the accumulated and updated maps each time the map is updated by , analyzing the accumulated updated maps to infer the change probability for each area, and preparing the change probability distribution map in which the change probability for each area is reflected may include

In addition, in the step of inferring the change probability for each area, machine learning is performed on the accumulated updated maps, and the machine learning is performed by assigning a higher weight as the last map of the last updated time is approached, so that the cumulative update Learning can be performed on the maps.

In addition, the step of inferring the change probability for each area analyzes the location of the fixed facility determined to be constantly disposed on the accumulated updated map, and calculates the change probability according to the accumulated environment change, The change probability distribution map may reflect the location of the fixed facility and the change probability for each area.

According to another embodiment of the present disclosure, the updated map may include object information that has not been updated in the existing map in association with the area along with object information updated in relation to an environment change at the time of update.

According to another embodiment of the present disclosure, the generating the map generates the map by detecting a change in the location of the facility to which the location notification device is attached, and the updating the existing map includes the location notification device by the location notification device. The existing map may be updated with a map generated by at least reflecting the facility in which the location change is detected.

In addition, in the generating of the map, when a change in the location of the facility to which the location notification device is attached is detected, the travel route may change the travel route toward the facility where the location has been changed.

In addition, the location notification device includes a module capable of recognizing the facility when the robot approaches a predetermined distance range, and the module includes a short-range wireless communication module, an infrared signal transmitting module, an ultrasonic transmitting module, an RF signal transmitting module , it may be at least one of a broadband signal transmission module, a Zigbee signal transmission module, and a laser signal module.

According to another embodiment of the present disclosure, generating the map further includes acquiring image data of spatial information including facilities, and after generating the map, the location of the map from the image data Analyzing object information related to a separate facility, and at least one of the existence of a location where an environment change occurs according to the update of the existing map and a change of an object at a location where the environment change does not occur on the existing map If satisfied, the method may further include incorporating the landmark as the updated object location information in association with the location of the facility together with the object information information updated according to the satisfied at least one.

According to another embodiment of the present disclosure, before the step of setting the driving route, deletion of the partial region related to the environmental change from the most recent map updated by the operator who recognized the environmental change of the partial region of the space The method further comprising the steps of: accepting a request; and receiving a request to start driving of the robot at a location estimated to be an undeleted area near the deleted area on the map, wherein the setting of the travel route includes the change probability distribution The driving route may be set by connecting regions having the lowest change probability in the deleted region of the map.

In addition, the step of generating the map is executed when the robot enters the deleted area, and the updating step includes an existing map of the non-deleted area and a map generated by updating the deleted area. can be combined

According to another aspect of the present disclosure, a map update system using an autonomous driving robot and a cloud server may be provided. In the map update system using the autonomous driving robot, the autonomous driving robot is a path setting unit configured to set the driving path of the autonomous driving robot based on a change probability distribution map having a change probability for each area according to an environment change accumulated in space. , a map processing unit that generates a map with spatial information obtained by a two-dimensional laser scanner according to the driving route, and updates the existing map with the generated map when recognizing an environment change different from the existing map in the generated map It includes an update unit.

The features briefly summarized above with respect to the present disclosure are merely exemplary aspects of the detailed description of the present disclosure that follows, and do not limit the scope of the present disclosure.

According to the present disclosure, it is possible to improve the efficiency and convenience of map update by executing the update of the autonomous driving robot according to the driving route based on the change probability distribution for each area related to the facility variable frequency in the map of the space accumulated at each update. have.

According to another aspect of the present disclosure, it is possible to extract a region in which an environment frequently varies from space and to grasp information on an object located in the corresponding region, thereby identifying a space utilization tendency.

According to another aspect of the present disclosure, when the map service provider is clearly aware of the environmental change in a part of the space, the update efficiency and precision of the update can be further increased by starting the map update from the area where the change occurred. have.

Effects obtainable in the present disclosure are not limited to the above-mentioned effects, and other effects not mentioned may be clearly understood by those of ordinary skill in the art to which the present disclosure belongs from the description below. will be.

1 is a diagram schematically illustrating a map update system using an autonomous driving robot according to an embodiment of the present invention.

2 is a block diagram showing the configuration of an autonomous driving robot capable of providing various services including map creation and update in space.

3 is a block diagram illustrating a configuration of a cloud server that operates in conjunction with an autonomous driving robot.

4 is a flowchart illustrating a process of generating a change probability distribution map.

5 is a diagram illustrating generation of a change probability distribution map, setting of a driving route, and updating according to the driving route for each map.

6 is a flowchart illustrating a map update method along a driving route based on a change probability distribution map as an embodiment of the present invention.

7A and 7B are flowcharts illustrating a map update method associated with a location notification device attached to a facility according to another embodiment of the present invention.

8 is a diagram illustrating that the autonomous driving robot recognizes a change in the location of a facility through a location notification device.

9 is a flowchart illustrating a process of incorporating a landmark as object information and object location information of a facility based on image data obtained from a surrounding environment into a map as another embodiment of the present invention.

10 is a flowchart illustrating a map update method when a partial region of a map is changed as another embodiment of the present invention.

11 is a diagram exemplifying a previous map in which a partial area is deleted and a map in which a deleted area is updated.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art to which the present disclosure pertains can easily implement them. However, the present disclosure may be implemented in several different forms and is not limited to the embodiments described herein.

In describing an embodiment of the present disclosure, if it is determined that a detailed description of a well-known configuration or function may obscure the gist of the present disclosure, a detailed description thereof will be omitted. And, in the drawings, parts not related to the description of the present disclosure are omitted, and similar reference numerals are attached to similar parts.

In the present disclosure, when a component is "connected", "coupled" or "connected" with another component, it is not only a direct connection relationship, but also an indirect connection relationship in which another component exists in the middle. may also include. In addition, when a component is said to "include" or "have" another component, it means that another component may be further included without excluding other components unless otherwise stated. .

In the present disclosure, terms such as first, second, etc. are used only for the purpose of distinguishing one component from other components, and unless otherwise specified, the order or importance between the components is not limited. Accordingly, within the scope of the present disclosure, a first component in one embodiment may be referred to as a second component in another embodiment, and similarly, a second component in one embodiment is referred to as a first component in another embodiment. can also be called

In the present disclosure, components that are distinguished from each other are for clearly explaining each characteristic, 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 distributed to form a plurality of hardware or software units. Accordingly, even if not specifically mentioned, such integrated or distributed embodiments are also included in the scope of the present disclosure.

In the present disclosure, components described in various embodiments do not necessarily mean essential components, and some may be optional components. Accordingly, an embodiment composed of a subset of components described in an embodiment is also included in the scope of the present disclosure. In addition, embodiments including other components in addition to components described in various embodiments are also included in the scope of the present disclosure.

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings.

A map update system using an autonomous driving robot according to an embodiment of the present invention will be described with reference to FIGS. 1 to 3 .

1 is a diagram schematically illustrating a map update system using an autonomous driving robot according to an embodiment of the present invention. 2 is a block diagram showing the configuration of an autonomous driving robot capable of providing various services including map creation and update in space. 3 is a block diagram illustrating a configuration of a cloud server that operates in conjunction with an autonomous driving robot.

The map update system 10 using the autonomous driving robot is the autonomous driving robot 100 that provides various services to users of indoor and outdoor spaces, including map creation and update, and the map creation, update, and various services request or to the robot 100 . In order to receive and analyze the result of the performed task, the cloud server 200 for controlling the robot 100 is included.

Here, the space is a tangible space having a structure including a fixed facility and a moving facility, and may be, for example, at least one of an indoor structure and an outdoor structure in a large space, and a floating facility such as a temporary stand and fixed facilities It may be a mixed outdoor place of a specific range or the like.

Large spaces may be public places such as train stations, bus terminals, airports, conventions, shopping centers, hotels, resorts, and the like. The fixed facility may be a column, a wall, a permanent installation, or the like in a large indoor/outdoor space. The floating facility may be a temporary booth, a temporary rest facility, a temporary ticket office, various large decorations, and the like. In the present specification, the fixed facility and the floating facility are referred to as a facility, but the fixed facility and the floating facility are separately described according to embodiments. Even in a fixed facility, as time passes, a permanent installation may be destroyed, changed in shape, or newly constructed. The autonomous driving robot 100 is a device designed to be movable in a predefined manner, and can move in indoor and outdoor spaces using moving means such as wheels and walking legs. The autonomous driving robot 100 may move according to the collected information after collecting information on the surrounding environment using a sensor or the like, or may move according to a separate command by an operator providing a service.

The autonomous driving robot 100 provides various services while driving indoors and outdoors used by a large number of space users, such as public places such as train stations, bus terminals, airports, conventions, shopping centers, hotels, resorts, factories, and the like. Services other than map creation and update provide space users with various services such as voice, screen, or accompanying information for specific locations requested by space users, and delivery of goods. That is, the autonomous driving robot 100 performs map creation and update operations in a predetermined space, and also performs a service according to a user's request in the corresponding space.

Specifically, the autonomous driving robot 100 may include a sensor unit 102 , a map receiving unit 104 , a driving unit 106 , a communication unit 108 , and a control unit 110 .

The sensor unit 102 obtains sensing data for the surrounding environment in space, and may include a two-dimensional laser scanner 112 , an odometer 114 , an external detection unit 116 , and a camera 118 .

The two-dimensional laser scanner 112 acquires two-dimensional spatial information in the form of two-dimensional point cloud data by scanning the space in which the robot 100 is located. The two-dimensional spatial information is a layout of a space created based on a predetermined plane without height information about the environment. The two-dimensional laser scanner 112 may acquire distance information of an omnidirectional or partial region, and may be implemented as a two-dimensional lidar. The two-dimensional lidar emits a laser signal, measures the time it takes to reflect and return, and measures the distance information of the reflector using the speed of light. The laser signal is converted into an electrical signal through a photodiode, and the laser signal may have a preset wavelength band.

The odometer 114 may acquire odometry information of the robot 100 together with distance information of the 2D laser scanner 112 . The odometer 114 obtains odometry information, such as the number of rotations, inclination, and rotation amount, from an encoder or IMU (Inertial Measurement Unit) sensor connected to the driving unit 106 of the robot 100, and the robot 100 in space. ) and position data can be obtained. The IMU sensor may be implemented as an acceleration sensor, a gyro sensor, or the like.

The external detection unit 116 detects a signal transmitted from a location notification device attached to, for example, a frequently variable floating facility among fixed and moving facilities constituting the environment of the space, and according to the sensed signal, the robot 100 and the moving facility The distance between them can be measured.

The location notification device includes a module capable of recognizing a facility when the robot 100 approaches a predetermined distance range, and the module includes a short-range wireless communication module, an infrared signal transmission module, an ultrasonic transmission module, an RF signal transmission module, and a broadband signal transmission It may be at least one of a module, a Zigbee signal transmission module, and a laser signal module.

Accordingly, when the robot 100 is put into a distance range capable of communicating with the facility to which the location notification device is attached, the external detection unit 116 receives the signal of the above-described module and calculates the relative distance as well as generates a map. The location of the facility in the map produced during the process may be identified and transmitted to the map processing unit 126 and the update unit 128 .

The camera 118 acquires image data of spatial information including facilities while the robot 100 is running and transmits it to the object analysis unit 206 of the cloud server 200 . The image data is analyzed based on the object information of the image database machine learned by the object analyzer 206 . Accordingly, the object analysis unit 206 may generate object information such as the type of facility, for example, the type, shape, and color of objects such as temporary booths, ticket offices, and rest facilities such as temporary benches.

When the robot 100 starts running in the space where the operator wants to update the map, the map receiving unit 104 changes the last updated most recent map and the space stored in the map storage unit 202 of the server 200 . Receive a probability distribution map. The change probability distribution map has a change probability for each area according to the accumulated environment change in space. A detailed description thereof will be given later. If the robot 100 creates a map for the environment of a new space, the map receiving unit 104 does not receive a map of the corresponding space from the server 200, and the map processing unit 126 according to a typical map creation method, A map of the environment in space is generated at the same time as the location estimation according to the driving of the robot 100 , and the map of the new space is transmitted to the server 200 and stored in the map storage unit 202 .

The driving unit 106 may include a device for moving the autonomous driving robot 100 but having a shape such as wheels or legs.

The communication unit 108 transmits the data sensed through the sensor unit 102 and the update map to the cloud server 200 through the network, and a communication function for receiving a command, a change probability distribution map, etc. from the server 200 may include

The control unit 110 may be a physical process built into the autonomous driving robot 100 , and may include an initial position estimator 120 , a route setting unit 122 , a sensing data processing unit 124 , a map processing unit 126 , and an update. It may include a unit 128 , and a robot control unit 130 . Here, the components included in the control unit 110 may be expressions of different functions performed by the control unit 110 as a physical processor. For example, the controller 110 may process various functions according to a control command according to a code of a computer program such as an OS or firmware.

The initial position estimating unit 120 is determined by scan matching through geometric matching of maps such as relative rotation and movement between the map generated at the driving start point of the robot 100 and the most recent map received from the map receiving unit 104. The initial position of the robot 100 is estimated on the previous map.

The path setting unit 122 sets the driving path of the autonomous driving robot based on the change probability distribution map and path estimation obtained from the path estimation unit 216 . The change probability distribution map reflects the location of fixed facilities determined to be constantly disposed and the change probability by area according to the accumulated environmental change in the map accumulated and updated in the map storage unit 202 of the server 200. . The route setting unit 122 may set the driving route by connecting regions with the lowest change probability while avoiding the location of the fixed facility on the change probability distribution map. The route setting unit 122 may change the detailed travel route for each intermediate node while avoiding the facility in a changed environment due to the new facility on the travel route while the robot 100 moves according to the initially set travel route.

The sensing data processing unit 124 applies a Kalman filter to the probability information related to the 2D point cloud of the surrounding environment obtained from the 2D laser scanner 112 to apply a weight of particles related to the 2D point cloud. By updating , the position of the robot 100 and particles associated with the two-dimensional point cloud are corrected. In addition, the sensing data processing unit 124 converts the odometry information that measured the position of the robot 100 to the scan matching of the map based on the two-dimensional point cloud for the odometry error caused by the slip of the wheel, etc. corrected by

The map processing unit 126 generates a map from spatial information based on a two-dimensional point cloud obtained while the robot 100 is traveling. The error correction results related to particle filtering and odometry information generated in the map generation are received from the sensing data processing unit 124 and reflected on the map.

The map processing unit 126 may generate a map by projecting spatial information based on the two-dimensional point cloud in the form of a two-dimensional grid.

When an operator providing a map service recognizes a change in the environment of a partial area of a space and receives a request to delete a partial area from the most recent updated map, the map processing unit 126 determines when the robot 100 enters the deletion area. create a map from

As a result of comparing the generated map with the previous map, the update unit 128 updates the most recent map with the generated map when recognizing a change in the environment of the space including the facility. In addition, the update unit 128 transmits the updated map to the server 200 while notifying the server 200 of the update event of the map, and accumulates and stores the map in the map storage unit 202 together with previous maps of the corresponding space. . In this embodiment, the update unit 128 is described as an example in which the robot 100 is embedded, which prevents transmission delay caused by transferring a large amount of data such as a generated map to the server 200, and This is to prevent errors. However, in another embodiment, the function of the update unit 128 may be built into the cloud server 200 .

The robot control unit 130 controls each component of the robot 100 to be executed according to various service requests from the server 200 . For example, when there is a request for map creation or update from the server 200 , the sensor unit 102 is activated and the robot 100 is moved according to the travel path by controlling the path setting unit and the driving unit 106 . while making the map.

The robot control unit 130 may receive various service requests other than the map transmitted from the server 200 and control the robot 100 to suit the request.

Meanwhile, the cloud server 200 may be implemented as one or more physical server devices, and may include a map storage unit 202 , a change probability distribution map generation unit 204 , an object analysis unit 206 , and a control command unit 208 . ) and a server communication unit 210 .

The map storage unit 202 accumulates and stores updated maps for each space. An update map notified of an update event from the robot 100 is also stored. In addition, the map storage unit 202 may store an updated map including object information that has not been updated in the existing map in association with an area along with object information updated in connection with an environment change at the time of update, for example, a change in the location of a facility. have. Of course, the map storage unit 202 stores object information in association with each area of the initially created map, and may include and store object information in the updated map every time it is updated. In a public place such as an airport, a train station, a bus terminal, or a large space such as a convention, an area where the environment is frequently changed is frequently the same. For example, temporary booths, temporary rest facilities, etc. installed in the convention venue are frequently installed in the same area with reference to the previous area only using facilities having a shape different from that of the previous event venue. Accordingly, by extracting an area in which the environment frequently changes from a space and grasping information on an object located in the corresponding area, it contributes to, for example, a planner who intends to install a facility in an indoor space to understand the tendency of use of the indoor space.

The change probability distribution map generating unit 204 generates a change probability distribution map having a change probability for each area according to an environment change accumulated in space. Specifically, the change probability distribution map generation unit 204 may include a collection unit 212 , an inference unit 214 , and a path estimation unit 216 .

The collection unit 212 collects the updated maps from the map storage unit 202, which are accumulated each time a map is updated due to an environment change in the same space.

The inference unit 214 analyzes the accumulated updated maps to infer a change probability for each area. Specifically, the reasoning unit 214 analyzes the location of the fixed facility determined to be constantly disposed on the cumulatively updated map, and calculates a change probability according to the accumulated environment change. Accordingly, the change probability distribution map calculated by the inference unit 214 may reflect the location of the fixed facility and the change probability for each area. The inference unit 214 infers a change probability by performing machine learning on the accumulated updated maps, and the machine learning may be a technique such as deep learning or CNN. Considering that machine learning is similar to the environment at the time of the current update the closer it is to the recent map, the closer it is to the last map at the last updated time, the higher the weight is given, and learning can be performed on the accumulated updated maps. .

The route estimator 216 may connect the regions with the lowest change probability in the change probability distribution map while avoiding the location of the fixed facility to transmit the estimated optimal travel route to the robot 100 when an update request is requested.

The object analysis unit 206 analyzes object information related to facilities for each location on the map from the image data of the space obtained from the camera 118 . The object analysis unit 206 extracts a feature point of a facility expressed in the image data, and estimates the type of the facility by comparing it with an object of the machine-learned image database and the feature point. The types of facilities may be divided into temporary booths, rest facilities such as benches, and ticket offices. The object analysis unit 206 may extract the color, displayed text, texture, etc. of the object through more precise analysis in addition to the type of facility, and include related features as object information.

When at least one of whether there is a location where the environment change occurs according to the update of the last map and whether only the object is changed at the location where the environment change does not occur in the last map occurs, the object analysis unit 206 is In some cases, the updated object information is linked with the location of the facility. When only the object is changed at a location where the environment change does not occur, for example, a facility recognized in substantially the same shape through spatial information of a two-dimensional point cloud, such as a temporary booth, a ticket office, or text recognized through the exterior wall of the facility This may be a situation in which the object information of the existing map is recognized as a different event name. Accordingly, when only the object is changed at the same location, the updated object information may generate detailed information of the changed object. In this case, the event planner can not only easily check the area of the space where the temporary facility is located, but also the type of event based on detailed information or detailed data included in the object information.

In addition, the object analysis unit 206, together with the updated object information, together with the object information that has not been updated in the last map, the landmark as object location information of the corresponding facility of the updated map stored in the map storage unit 202 Record the corresponding location. The landmark may be calculated based on the location of the corresponding object generated during the map creation process. The control command unit 208 transmits a corresponding command to the robot 100 for a service requested by a space user or a map service provider, receives a result according to the service, and controls processing according to the result in components of the server 200 . can do.

The server communication unit 210 exchanges data between the communication unit 108 of the robot 100 while communicating through a network.

Hereinafter, a process of generating a change probability distribution map applied to a map update method using an autonomous driving robot according to an embodiment of the present invention will be described with reference to FIGS. 4 and 5 . 4 is a flowchart illustrating a process of generating a change probability distribution map. This is performed by the change probability distribution map generator 204 of the cloud server 200 . 5 is a diagram illustrating generation of a change probability distribution map, setting of a driving route, and updating according to the driving route for each map.

First, the collection unit 212 of the change probability distribution map generation unit 204 collects accumulated and updated maps from the map storage unit 202 each time a map is updated due to an environment change in the same space (S405).

As shown in FIG. 5( a ), maps updated by an environment change are collected and transmitted to the inference unit 214 .

Next, the inference unit 214 analyzes the accumulated updated maps through machine learning to infer the change probability for each area, and analyzes the location of the fixed facility determined to be constantly disposed ( S410 ).

Change probability The change probability for each area used in the generation of the change map indicates the degree of environmental change for each area according to the number of map updates. Even when an environment change occurs in one of a plurality of areas of the space, the map is updated and updated the number of times also increases. The inference of the change probability for each area fuses the accumulated updated maps into one spatial information while including the location and shape of the facilities in the space, and the degree of change of the two-dimensional point cloud for each area of the single spatial information, for example, according to the point cloud. Whether the shape or the plurality of feature points is the same or fluctuates is analyzed, and a change probability is calculated for each region using the correlation between the degree of change and the number of updates, as shown in FIG. 5( b ).

In analyzing the change of the location and/or shape of the facility in the corresponding area due to the change according to the geometric shape according to the point cloud, machine learning may be applied. Also, in inferring the correlation between the degree of change and the number of updates, machine learning may be applied to calculate a change probability for each region. Machine learning may be a technique such as deep learning or CNN. Since machine learning is more likely to be similar to the environment at the time of the current update the closer it is to the recent map, in spatial information in which the accumulated updated maps are fused, learning can be performed by assigning a higher weight as it approaches the most recent map. .

As shown in FIG. 5( b ), after matching the geometries of the accumulated updated maps and merging them into one piece of spatial information, the change probability 22 according to the environment change for each area is calculated by machine learning. The scattering pattern indicated by reference numeral 22 in FIG. 5(b) indicates that facilities in the corresponding area frequently change and thus exhibiting a higher change probability than other areas, and the scattering pattern indicated by reference number 24 indicates a lower change probability than other areas. is foreshadowing As can be seen from FIG. 5(b), the location of a fixed facility installed at all times without changing the location on the accumulated map is also analyzed.

Next, the inference unit 214 generates a change probability distribution map in which the location of the fixed facility and the change probability for each area are reflected, and is stored in the map storage unit 202 ( S415 ).

In addition, the route estimator 216 connects the regions of the lowest change probability in the change probability distribution map while avoiding the location of the fixed facility as shown in FIG. can be included in advance in the change probability distribution map.

Hereinafter, a map update method along a driving route based on a change probability distribution map as an embodiment of the present invention will be described with reference to FIG. 6 .

First, the robot control unit 130 controls the driving unit 106 according to the instruction of the control command unit 208 that has received the operator's map update request, so that the robot 100 travels in a space where the operator desires to create and update the map. to start (S605).

Next, the map receiving unit 104 receives the last updated map and the spatial change probability distribution map stored in the map storage unit 202 of the server 200 ( S610 ). The change probability distribution map may reflect the change probability for each area according to the accumulated environmental change in the space and the location of the fixed facility. The change probability distribution map may also include the optimal driving path estimated by the path estimator 216 .

Next, the initial position estimator 120 estimates the initial position of the robot 100 by scan matching between the map generated at the starting point of the robot 100 and the most recent map received from the map receiving unit 104 ( S615).

Scan matching may be a geometric matching process of maps such as relative rotation and movement between two maps.

Next, the route setting unit 122 of the robot 100 sets a travel route connecting the areas of the lowest change probability while avoiding fixed facilities based on the change probability distribution map (S620).

The setting of the travel route may be executed by the route setting unit 122 or may be performed based on the travel route already estimated by the route estimation unit 216 of the server 200 . The travel route 26 may be set as illustrated in FIG. 5( c ). The path setting unit 122 may determine a modified driving path suitable for movement between intermediate nodes when there is an obstacle on the initially set driving path.

Then, the map processing unit 126 generates a map from the spatial information based on the two-dimensional point cloud obtained by scanning the space of the two-dimensional laser scanner 112 while the robot 100 is running (S625). The error correction results related to particle filtering and odometry information generated in the map generation are received from the sensing data processing unit 124 and reflected on the map. The map processing unit 126 may generate a map by projecting spatial information based on the two-dimensional point cloud in the form of a two-dimensional grid.

Next, the update unit 128 compares the generated map with the most recent map ( S630 ), and when recognizing a change in the environment including facilities, updates the most recent map with the generated map ( S635 ). In addition, the update unit 128 transmits the updated map to the server 200 while notifying the server 200 of the update event of the map, and accumulates and stores the map in the map storage unit 202 together with previous maps of the corresponding space. .

According to this embodiment, by executing the update of the autonomous driving robot according to the driving route based on the change probability distribution for each area related to the variable frequency of the facilities calculated for each area in the map of the space accumulated at each update, the efficiency of the map update is executed. and convenience may be improved. It can be inferred that the area where changes of facilities occur frequently in public places, conventions, etc. are substantially the same as in FIG. 5(b). By setting the driving route of the update, it is possible to prevent unnecessary time consumption of the update due to the avoidance operation of the facility or the long-distance movement to the changed facility. In addition, since the robot 100 runs adjacent to an area with a high probability of changing the environment, the 2D laser scanner 112 more precisely scans the changed facilities in the area with a high probability of change, so that the precision of the 2D point cloud is good will do

Hereinafter, a map update method associated with a location notification device attached to a facility as another embodiment of the present invention will be described with reference to FIGS. 7A and 7B .

7A and 7B are flowcharts illustrating a map update method associated with a location notification device attached to a facility according to another embodiment of the present invention. In this embodiment, a detailed description of the steps substantially identical to those of FIG. 6 will be omitted, and differences will be mainly described. Accordingly, steps S705 to S725 of FIG. 7A are substantially the same as steps S605 to S625 of FIG. 6 and thus will be omitted, and FIG. 7B with differences will be mainly described.

In FIG. 7B, the external detection unit 116 detects a signal transmitted from a location notification device attached to a movable facility, and measures the distance between the robot 100 and the floating facility according to the detected signal to determine whether the location of the facility is changed. is detected (S730).

The movable facility may be a temporary booth, a temporary resting facility, a temporary ticket office, various large decorations, and the like, unlike a fixed facility such as a column, a wall, or a permanent structure.

As shown in FIG. 8 , the location notification device 302 includes a module capable of recognizing the facility 300 when the robot 100 approaches a predetermined distance range, and the module includes a short-range wireless communication module, an infrared signal transmission module, and an ultrasonic wave. It may be at least one of a transmission module, an RF signal transmission module, a broadband signal transmission module, a Zigbee signal transmission module, and a laser signal module.

When the robot 100 is put into a communication distance range with the facility 300 to which the location notification device 302 is attached, the external detection unit 116 receives the signal of the above-described module and calculates a relative distance.

As a result of the detection, when the location of the facility to which the external notification device is attached is changed, the route setting unit 122 changes the driving route toward the location-changed facility to more quickly acquire environmental changes such as the location change of the facility ( S735 ).

In addition, the external detection unit 116 may determine the location of the facility in the map produced during map generation and transmit it to the map processing unit 126 and the update unit 128 .

Meanwhile, the update unit 128 determines whether the environment of the space including the facility to which the location notification device is not attached has changed (S740). This is substantially the same as step S630, and the update unit 128 compares the generated map with the most recent map to detect a change in the unattached facility.

When shifting to Y in steps S735 and S740, the update unit 128 updates the most recent map with the generated map, transmits the updated map to the server 200, and transfers the space to the map storage unit 202 It is accumulated and stored together with the maps of (S745).

In the embodiment according to FIGS. 7A and 7B , when the location notification device 302 detects a change in the location of the attached facility 300, the route setting unit 122 changes the driving route to the location of the facility 300, step S735 contains However, in another embodiment, based on the distance calculated by the external detection unit 116 without changing the travel route according to step S735 and the two-dimensional point cloud of the facility 300 of the location change obtained according to the original travel route, The most recent map may be updated with a map generated by reflecting at least the location-changed facility 300 .

Hereinafter, a process of incorporating object information of a facility based on image data obtained from a surrounding environment into a map will be described as another embodiment of the present invention with reference to FIG. 9 .

First, the camera 118 acquires image data of spatial information including facilities during map generation according to the driving of the robot 100 according to FIGS. 6, 7A, 7B and 10 , and analyzes the object of the cloud server 200 . It is transmitted to the unit 206 (S905).

Next, the object analysis unit 206 analyzes object information related to facilities by location on the map by machine learning (S910).

The object analysis unit 206 extracts a feature point of a facility expressed in the image data, and estimates the type of the facility by comparing it with an object of the machine-learned image database and the feature point. The types of facilities may be divided into temporary booths, rest facilities such as benches, and ticket offices. The object analysis unit 206 may extract the color, displayed text, texture, etc. of the object through more precise analysis in addition to the type of facility, and include related features as object information.

Next, the object analysis unit 206 determines whether at least one of whether there is a location where the environment change occurs according to the update of the last map and whether only the object is changed in the location where the environment change does not occur in the last map It is determined whether it has occurred (S915).

When only the object is changed at a location where the environment change does not occur, for example, a facility recognized in substantially the same shape through spatial information of a two-dimensional point cloud, such as a temporary booth, a ticket office, or text recognized through the exterior wall of the facility It may be a situation in which the object information of the existing map is recognized as a different event name through the

When at least one of the above two situations occurs, the object analysis unit 206 associates the landmark as the object location information with the location of the facility together with the updated object information ( S920 ). The landmark may be calculated based on the location of the corresponding object generated in the map generation process according to FIGS. 6, 7A, 7B, and 10 .

The object analysis unit 206 records the object information and landmarks that have not been updated in the last map along with the updated object information and landmarks in correspondence with the location of the corresponding facility in the updated map stored in the map storage unit 202 . .

According to the present embodiment, it is possible to extract a region in which an environment is frequently changed from a space, and grasp information on an object located in the corresponding region, thereby identifying a space utilization tendency.

Hereinafter, as another embodiment of the present invention with reference to FIGS. 10 and 11 , a map update method when a partial area of a map is changed will be described.

10 is a flowchart illustrating a map update method when a partial region of a map is changed as another embodiment of the present invention. 11 is a diagram exemplifying a previous map in which a partial area is deleted and a map in which a deleted area is updated.

First, in response to a request of an operator who is aware of changes in the environment of some areas in an existing map, the map storage unit 202 deletes some areas requested from the previous most recent map (S1005).

As shown in FIG. 11A , the operator requests the server 200 to delete a region requiring an update, and maintains an unnecessary region.

Next, when the operator requests driving after placing the robot 100 in a position estimated to be an undeleted area near the deleted area, the robot control unit 130 controls the driving unit 106 according to the instruction of the control command unit 208 . ) to start the driving of the robot 100 at the position placed by the operator (S1010).

Next, the map receiving unit 104 receives the latest updated map in which some regions are deleted and stored together with the change probability distribution map of the space stored in the map storage unit 202 of the server 200 ( S1015 ). The change probability distribution map is substantially the same as described in step S610.

Next, the initial position estimator 120 estimates the initial position of the robot 100 by scan matching between the map generated at the location of the undeleted area of the robot 100 and the most recent map received from the map receiving unit 104 . do (S1020).

Next, the route setting unit 122 sets a driving route connecting the regions with the lowest change probability while avoiding fixed facilities based on the change probability distribution map of the deleted area (S1025).

The reason for setting the driving route based on the change probability distribution map even in the deleted area is that it is highly likely that the area where the change of facilities occurs frequently in the corresponding area is the area that appears on the change probability distribution map.

Subsequently, the map processing unit 126 determines whether the robot 100 has entered the deletion area (S1030), and when it is determined that the entry is entered, the 2D laser scanner 112 scans the surrounding environment from the deletion area. A map is generated by generating spatial information based on a two-dimensional point cloud, and the updater 128 combines the region deleted from the previous map into the generated map as shown in FIG. 11(b) (S1035).

In addition, the update unit 128 transmits the updated map to the server 200 while notifying the server 200 of an update event due to map combination, and accumulates it in the map storage unit 202 together with previous maps of the corresponding space. Save.

According to the present embodiment, when the map service provider clearly recognizes the environmental change in a part of the space, the update efficiency and precision of the update can be further increased by starting the map update from the area where the change occurs.

Meanwhile, in the above embodiments, the map update of the indoor space is mainly described as an example. However, the present embodiments described above are applicable if the space is a space having a structure including a fixed facility and a moving facility. Specifically, it is possible to create and update a map according to the present embodiments while the autonomous driving robot 100 drives for at least one of indoor and outdoor desired by the operator in a space having indoor and outdoor structures. Of course, the present embodiments may also be applied to an outdoor place in a specific range in which floating facilities and fixed facilities, such as a temporary kiosk, are mixed.

Example methods of the present disclosure are expressed as a series of operations for clarity of description, but this is not intended to limit the order in which the steps are performed, and if necessary, each step may be performed simultaneously or in a different order. In order to implement the method according to the present disclosure, other steps may be included in addition to the illustrated steps, steps may be excluded from some steps, and/or other steps may be included except for some steps.

Various embodiments of the present disclosure do not list all possible combinations, but are intended to describe representative aspects of the present disclosure, and the details described in various embodiments may be applied independently or in combination of two or more.

In addition, various embodiments of the present disclosure may be implemented by hardware, firmware, software, or a combination thereof. For implementation by hardware, 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 purpose It may be implemented by a processor (general processor), a controller, a microcontroller, a microprocessor, and the like.

The scope of the present disclosure includes software or machine-executable instructions (eg, operating system, application, firmware, program, etc.) that cause an operation according to the method of various embodiments to be executed on a device or computer, and such software or and non-transitory computer-readable media in which instructions and the like are stored and executed on a device or computer.

Claims

setting a driving path of the autonomous driving robot based on a change probability distribution map having a change probability for each area according to an accumulated environment change in space;

generating a map with spatial information obtained by a two-dimensional laser scanner according to the driving route; and

When recognizing an environment change different from the existing map in the generated map, updating the existing map with the generated map;

The updated map includes object information that has not been updated in the existing map along with object information updated in relation to the environment change at the time of update in connection with the area, and the object information includes detailed information of facilities located in the space and,

Before setting the driving route,

Receiving a request for deletion of a partial area related to the environmental change in the most recently updated last map by an operator who has recognized the environmental change in the partial area of the space;

Receiving a request to start driving of the robot at a location estimated to be an undeleted area near the area deleted from the map,

In the step of setting the driving path, the driving path is set by connecting the regions of the lowest change probability in the deleted region of the change probability distribution map,

The step of generating the map is executed when the robot enters the deleted area, and the step of updating is a combination of an existing map of the undeleted area and a map generated and updated for the deleted area. How to update a map using an autonomous robot.
The method of claim 1,

The setting of the driving route is a map update method using an autonomous driving robot for setting the driving route by connecting regions with the lowest change probability in the change probability distribution map.
The method of claim 1,

Before setting the driving route, the method further comprises generating the change probability distribution map,

The step of generating the change probability distribution map comprises:

collecting the accumulated and updated maps each time the map is updated due to the accumulated environment change of the space;

inferring a change probability for each area by analyzing the cumulatively updated maps; and

and creating the change probability distribution map in which the change probability for each area is reflected.
4. The method of claim 3,

In the step of inferring the change probability for each area, machine learning is performed on the accumulated updated maps, and the machine learning is performed by assigning a higher weight to the accumulated updated map as it approaches the most recent map of the last updated time. A map update method using an autonomous driving robot that performs learning on the field.
4. The method of claim 3,

The step of inferring the change probability for each area analyzes the location of the fixed facility determined to be constantly disposed on the accumulated updated map, and calculates the change probability according to the accumulated environment change, and the change probability The distribution map is a map update method using an autonomous driving robot in which the location of the fixed facility and the change probability for each area are reflected.
The method of claim 1,

In the step of generating the map, the map is generated by detecting the location change of the facility to which the location notification device is attached, and the updating of the existing map reflects at least the facility detecting the location change by the location notification device A map update method using an autonomous driving robot that updates the existing map with the generated map.
7. The method of claim 6,

In the generating of the map, when a change in the location of the facility to which the location notification device is attached is detected, the travel route changes the travel route toward the facility where the location is changed. A map update method using an autonomous driving robot.
7. The method of claim 6,

The location notification device includes a module capable of recognizing the facility when the robot approaches a predetermined distance range, and the module includes a short-range wireless communication module, an infrared signal transmission module, an ultrasonic transmission module, an RF signal transmission module, and a broadband signal. A map update method using an autonomous driving robot that is at least one of a transmission module, a Zigbee signal transmission module, and a laser signal module.
The method of claim 1,

Generating the map further includes acquiring image data of spatial information including facilities,

After generating the map,

analyzing object information related to facilities by location of the map from the image data; and

When at least one of the existence of the location where the environment change occurs according to the update of the existing map and the change of the object at the location where the environment change does not occur in the existing map are satisfied, the updated according to the satisfied at least one The map update method using the autonomous driving robot further comprising the step of incorporating the landmark as the updated object location information together with the object information in association with the location of the facility.
In a map update system using an autonomous driving robot and a cloud server,

The autonomous driving robot is

a path setting unit configured to set a driving path of the autonomous driving robot based on a change probability distribution map having a change probability for each area according to an accumulated environment change in space;

a map processing unit for generating a map with spatial information obtained by a two-dimensional laser scanner according to the driving route; and

and an update unit configured to update the existing map with the generated map when recognizing an environment change different from the existing map in the generated map;

The cloud server,

a map storage unit for receiving a request for deletion of a partial area related to the environmental change from the most recently updated map by an operator recognizing the environmental change in a partial area of the space; and

and a control command unit for receiving a request to start driving of the robot at a location estimated to be an undeleted area near the area deleted from the map,

The route setting unit sets the driving route by connecting the regions with the lowest change probability in the deleted region of the change probability distribution map,

The map processing unit is executed when the robot enters the deleted area, and the update unit combines an existing map of the non-deleted area and a map generated and updated for the deleted area,

The updated map includes object information that has not been updated in the existing map along with object information updated in relation to the environment change at the time of update in connection with the area, and the object information includes detailed information of facilities located in the space A map update system using autonomous driving robots and cloud servers.