Map correction system and map correction program

Abstract

To reflect the situation of a real space to improve the accuracy of map data, and enable reference management of the map data and BIM data.SOLUTION: A map correction system uses three-dimensional or two-dimensional map data for every type of a robot defining a movable range of a robot according to structures in a space, and a self-position estimation result obtained from a result of collation with the positions of the structure performed by a robot having received control information, to issue an instruction to detect the shapes of the structures to another robot not having received the control information, acquires a self-position estimation result transmitted by the other robot, uses a result of detection performed by the robot having received the control information and the self-position estimation result from the other robot, to correct map information of the robot having received the control information so as to reflect the situation of the structures, and performs management to allow selection as to whether to refer to the map data or to refer to BIM data.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to correction of map information necessary for controlling a robot.

Background Art

[0002] Conventionally, a technique related to position estimation of a robot that estimates its own position even at a construction site is known (for example, Patent Document 1). In this technique, mapping information is obtained by extracting it from construction data of a measurable construction object, and the self-position in the space is calculated based on the measurement data and the mapping information.

[0003] Also, a technique related to a moving body that can be easily applied even when the layout in the moving space is changed, has a low introduction cost, and can recognize its own position quickly and accurately is known (for example, Patent Document 2). As a similar technique, a technique is known in which a moving body estimates its own position and can autonomously control its movement to a designated destination to stably obtain the position of the moving body (for example, Patent Document 3).

[0004] Also, a technique for providing an autonomous mobile device that can accurately estimate its own position within a construction site in consideration of the circumstances unique to a building construction site is known (for example, Patent Document 4). In this technique, shape data of a plurality of target parts existing within the construction site of a building is acquired, drawing data is referred to, and a reference target part is specified from among the plurality of target parts based on information regarding the dimensions of each of the plurality of target parts. Also, the self-position within the construction site is estimated based on the collation result between the position of the reference target part included in the drawing data and the actual position of the reference target part in the shape data.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

[0006] According to the technologies described in Patent Documents 1 to 4 above, the robot's own position in real space can be estimated with high accuracy. Such accurate estimation of the robot's own position suggests that it can move along its path accurately and smoothly. However, discrepancies may occur between the map data showing the path and the actual data from the construction site. This is because the actual construction site undergoes various changes depending on the situation, such as changes in the placement of materials and changes in layout due to design modifications. Therefore, simply being able to accurately estimate the robot's own position does not guarantee the accuracy of the robot's movement.

[0007] In consideration of the above facts, the present invention aims to improve the accuracy of map data by reflecting the conditions of real space, and to enable the reference management of map data and BIM data. [Means for solving the problem]

[0008] To achieve the above objective, the map correction system of the present invention uses three-dimensional or two-dimensional map data for each type of robot that defines the range of movement of the robot according to the structure in space, and a self-position estimation result obtained by comparing the position of the structure with the position of the structure by a robot that has received control information, to detect the difference or error between the map data and the real space, and when such a difference or error is detected, in order to identify the shape of the structure, it instructs another robot that has not received control information to detect the shape of the structure, and acquires the self-position estimation result transmitted by the other robot, which is obtained by the other robot patrolling the structure, and the control information Using the detection results of the robot receiving the control information and the self-position estimation results of the other robot during its patrol of obstacles, the map data of the robot receiving the control information is corrected to reflect the status of the structure. The space is the actual space of the building construction site, and the structure is a movable structure in the building construction site in the actual space, and is at least one of the installations, materials, and construction tools at the construction site. The system manages whether to refer to the corrected map data that reflects the status of the structure in the actual space, or to refer to the BIM data, which is the source data used to generate the map data. This improves the accuracy of the map data by reflecting the status of the actual space, and enables the reference management of map data and BIM data. [Effects of the Invention]

[0009] According to the present invention, the accuracy of map data is improved by reflecting the conditions in real space, and the reference management of map data and BIM data is made possible. [Brief explanation of the drawing]

[0010] [Figure 1] This is an illustrative diagram of a robot management platform. [Figure 2] This is a block diagram showing the configuration of a map correction system according to an embodiment of the present invention. [Figure 3]This figure shows an example of detecting and correcting differences when an obstacle is removed. [Figure 4] This figure shows an example of detecting and correcting differences when a new obstacle is installed. [Figure 5] This figure shows an example of error detection and correction when an obstacle is moved. [Figure 6] This is a sequence diagram showing the map correction process in a map correction device according to an embodiment of the present invention. [Modes for carrying out the invention]

[0011] [Embodiments of the present invention] Hereinafter, an embodiment of the map correction system of the present invention will be described with reference to the drawings.

[0012] An overview of embodiments of the present invention will now be described. In the method according to the embodiment of the present invention, a three-dimensional map (or two-dimensional map) and the results of the robot's self-position estimation in real space are used to detect differences or errors in structures between the three-dimensional map and real space, and the three-dimensional map is corrected using the detection results. The three-dimensional map is an environmental map in which structures are arranged in space and the movable range in which the robot can move in said space is defined. The three-dimensional map is generated by simulation based on BIM data for each type of robot. Real space is the space in which the robot actually operates, such as a construction site.

[0013] Furthermore, as a prerequisite for this method, the robot utilizes a self-localization method called SLAM (Simultaneous Localization and Mapping). SLAM is a technology that accurately estimates the robot's own position and orientation while simultaneously recognizing the surrounding environment using the robot's sensors, and generates an environmental map at the same time as estimating its own position. In SLAM, the robot performs environmental recognition by combining multiple sensors. The sensors vary depending on the robot, but may include rangefinders, cameras, gyroscopes, magnetic sensors, accelerometers, radar sensors (scanners), bumper sensors, etc. As an example of self-localization using sensors, we will explain the example of a four-wheel drive robot for cleaning purposes (hereinafter referred to as a cleaning robot). For example, a cleaning robot has a laser scanner and bumper sensors as sensor information. The laser scanner is a sensor that detects surrounding walls and obstacles, and by using the laser scanner, the cleaning area can be determined by detecting reflective markers placed at the four corners of the area to be cleaned. In addition, since the cleaning robot moves within the cleaning area in a path that allows all the dirt within the cleaning area surrounded by reflective markers to be cleaned, the movement path can be automatically generated within the cleaning area. The bumper sensor is a sensor that detects contact with an obstacle, and it detects and avoids obstacles within the cleaning area.

[0014] The robot moves while constantly monitoring its surroundings at its own location through self-localization. In self-localization, the robot uses sensors to compare the positions of structures in real space and obtains its own localization result from the comparison. Here, differences or errors may occur between the space of the 3D map and the real space. Specifically, there may be differences or errors between the structures at the construction site in real space and the structures included in the 3D map obtained by simulation. Structures assumed in space may be fixed structures or movable structures. Such movable structures include installed objects, construction site materials, and construction tools. Therefore, in the construction site in real space, the arrangement of movable structures changes due to movement, addition, and use. In such cases, differences or errors occur between the structures in real space and the structures included in the 3D map. Difference refers to a situation where the number and arrangement of structures in space differ from that of the 3D map due to the addition or removal of placed structures. Error refers to a situation where the arrangement of structures that were placed on the 3D map is shifted. In this embodiment, these differences or errors are detected using a three-dimensional map and self-localization estimation results. Based on the detection results, the arrangement of structures in the three-dimensional map is corrected to reflect the state of the structures in the three-dimensional map. This corrects the coordinate information of structures included in the three-dimensional map, making it possible to improve the accuracy of the map data for robot control. Furthermore, this can be achieved not only for the arrangement of structures as three-dimensional data captured on a three-dimensional map, but also for updating the accuracy of two-dimensional point cloud data. Normally, SLAM is processed in two dimensions, so if the map data for robot navigation extracted from the three-dimensional data of BIM is a two-dimensional map, the two-dimensional data is updated. In addition, the data actually detected is updated according to the actual situation during building construction, while after completion, the original BIM data is used, so the system is managed to allow selection of whether to use the current data or the original data. Accordingly, it is possible to improve the accuracy of the robot management system that manages the various robots described below.

[0015] Here, the robot management platform on which this embodiment is premised will be described. FIG. 1 is an image diagram of the robot management platform. As shown in FIG. 1, the robot management platform is a platform for managing robots in a cloud environment. Programs for executing functions for managing robots are implemented as various modules in the robot management platform, and the modules are appropriately coordinated to perform necessary processing. Thereby, the robot management platform realizes the automation of construction work by robots. The list of modules shown in FIG. 1 is merely an example of functional means and is not limited to these examples. By utilizing such a robot management platform, it is possible to eliminate as much as possible the setting work for troublesome robot operations. Also, by estimating the self-position of the robot based on the BIM (Building Information Modeling) data of the construction target, the on-site staff can give instructions to the robot by referring to the BIM data, so intuitive operations can be provided to the on-site staff. Also, functions necessary during construction, such as state monitoring of the robot in remote operation, can be deployed as services of the platform.

[0016] In the robot management platform shown in FIG. 1, the method of this embodiment is used, for example, for SLAM·BIM data linkage of a certain kind. Also, it can be used for robot operation management, path simulation, data accumulation·visualization, etc. In the functions of these modules, it is positioned as a method for optimizing the control in the real space when the robot moves and improving the performance.

[0017] FIG. 2 is a block diagram showing the configuration of the map correction system according to the embodiment of the present invention. As shown in FIG. 2, the map correction system 100 includes a map correction device 110, a terminal 140, and a plurality of robots 150 connected via a network N. The network N is, for example, an Internet line or a public wireless LAN.

[0018] The terminal 140 is a terminal that inputs the control input data of the robot 150, checks the self-position estimation result of the robot 150, checks the corrected three-dimensional map, etc. The control input data is information including, for example, a destination, an object to be transported, etc. Note that the terminal 140 is a terminal operated by various responsible persons and performs input / output necessary for the processing of the map correction device 110. The various responsible persons here are applied to the above-described robot management platform. For example, in the present embodiment, the "on-site person in charge" responsible for remotely operating the robot or the "equipment management person in charge" responsible for route simulation becomes the person in charge according to the operation. When the terminal 140 logs in, authorities corresponding to various responsible persons are allocated, but since it is not the main processing of the map correction system 100, the description is omitted here.

[0019] The robot 150 is a plurality of robots to be controlled and includes various sensors. Also, the robot 150 receives control information and moves along the route included in the control information while performing self-position estimation. The robot 150 transmits the current location and the self-position estimation result to the map correction device 110 at regular intervals. Note that the robot 150 is implemented as an agent for each type in the simulation environment of the robot environment platform and can perform operation emulation. In the present embodiment, a three-dimensional map defining the movable range has been generated in advance by operation emulation. Also, the route of the robot 150 on the three-dimensional map is generated by the route simulation of the route generation unit 114 described later. Note that in the present embodiment, the case of using a three-dimensional map is described as an example, but as described above, it can be similarly applied to a two-dimensional map.

[0020] The map correction device 110 includes a communication unit 112, a route generation unit 114, a detection unit 116, a map correction unit 11, and a storage unit 120. Also, the map correction device 110 can be configured by a computer including a CPU, a RAM, and a ROM that stores a program for executing each processing unit and various data (not shown). The map correction device 110 of the present embodiment is a server constructed by modularizing some functions of the robot management platform of FIG. 1 described above, and each functional unit is an example of a function.

[0021] The communication unit 112 transmits and receives various types of data through communication with the terminal 140 and the robot 150. For example, the communication unit 112 receives a three-dimensional map from the terminal 140 and stores it in the storage unit 120. The communication unit 112 receives control input data from the robot 150 from the terminal 140. The communication unit 112 periodically receives the robot 150's current location. The communication unit 112 receives the robot 150's self-position estimation results. The communication unit 112 also transmits control information to the robot 150.

[0022] The memory unit 120 stores each of the three-dimensional maps received from the terminal 140. The three-dimensional map defines the range of movement the robot can perform in space. The memory unit 120 also stores the path of the robot 150 generated by the path generation unit 114. The memory unit 120 also stores the corrected three-dimensional map.

[0023] The route generation unit 114 generates a route for the robot 150 in the three-dimensional map of the storage unit 120 according to the control input data for the robot 150 received from the terminal 140. Then, it transmits control information including the route on the three-dimensional map to the robot 150. The control information including the route generated here includes information on the route from the starting point to the destination included in the control input data, as well as the necessary work steps. The starting point is the latest current location received from the robot 150.

[0024] The detection unit 116 uses the three-dimensional map from the memory unit 120 and the self-position estimation result received from the robot 150 to detect the difference or error between the three-dimensional map and the real space.

[0025] The map correction unit 118 uses the detection results from the detection unit 116 to correct the three-dimensional map in the storage unit 120 so that it reflects the status of the structures.

[0026] Here, we will explain a specific example of detection by the detection unit 116 and correction by the map correction unit 118. Figure 3 shows an example of detection and correction of differences when an obstacle is removed. In the example shown in Figure 3, it is assumed that a cleaning area and a non-cleaning area are set as the movable range in the space of the three-dimensional map. The cleaning area is the path of the cleaning robot and is set as an area without obstacles. The non-cleaning area is arbitrarily set as an area where cleaning is not possible due to the presence of obstacles. These settings are assumed to be set in advance at the stage of generating the three-dimensional map. Now, suppose the cleaning robot is operated in real space and the difference in space where an obstacle has been removed is detected in the self-position estimation result. In this case, the map correction unit 118 corrects the three-dimensional map using the detection result of the removed obstacle. In addition, the path generation unit 114 sets a new cleaning area and generates a path. In this way, when an obstacle is newly installed, the three-dimensional map is corrected so that the movable range expands.

[0027] Detection and correction can be performed in the same way when obstacles are newly placed or moved. Figure 4 shows an example of detection and correction of differences when obstacles are newly placed. As shown in Figure 4, when obstacles are newly placed, the 3D map is corrected so that the traversable range is narrowed. Figure 5 shows an example of detection and correction of errors when obstacles are moved. As shown in Figure 5, when obstacles are moved (or shifted), the 3D map is corrected to adjust the traversable range. In this way, real-time conditions can be fed back into the 3D map, and a path that the robot can travel can be regenerated.

[0028] Next, the operation of the map correction device 110 according to an embodiment of the present invention will be described. Figure 6 is a sequence diagram showing the map correction process in the map correction device 110 according to an embodiment of the present invention. The CPU reads a program and various data from ROM and executes it to perform the map correction process. The CPU functions as one of the parts of the map correction device 110. It is assumed that a three-dimensional map received in advance from the terminal 140 is stored in the storage unit 120. The robot 150 also periodically receives the current location. Furthermore, the explanation that each functional unit performs the transmission and reception of various information of the map correction device 110 is assumed to be done via the communication unit 112.

[0029] In step S100, terminal 140 transmits control input data for robot 150 to map correction device 110. A specific robot 150 is specified in the control input data.

[0030] In step S102, the path generation unit 114 generates a path in the three-dimensional map corresponding to the specified robot 150 in the storage unit 120 according to the control input data, and generates control information including the path.

[0031] In step S104, the path generation unit 114 transmits control information to the robot 150.

[0032] In step S106, the robot 150 moves while estimating its own position according to the control information, including the received reference area.

[0033] In step S108, the robot 150 transmits the self-position estimation result to the map correction device 110.

[0034] In step S110, the detection unit 116 uses the three-dimensional map in the memory unit 120 and the self-position estimation result received from the robot 150 to detect any difference or error.

[0035] In step S112, the map correction unit 118 corrects the three-dimensional map in the storage unit 120 using the detection results from step S110.

[0036] In step S114, the route generation unit 114 regenerates the route using the corrected three-dimensional map and transmits control information including the route to the robot 150. Thereafter, the process proceeds from step S106 until the robot 150 reaches its destination, and map correction processing is performed.

[0037] As described above, the map correction system 100 according to the embodiment of the present invention makes it possible to improve the accuracy of map data by reflecting the conditions in real space.

[0038] It should be noted that the present invention is not limited to the embodiments described above, and various modifications and applications are possible without departing from the spirit of the invention.

[0039] For example, if a difference or error is detected between the real space and the space of the three-dimensional map, a robot that is not busy with other tasks may be instructed to take measurements to estimate the shape of the structure in order to perform a correction that precisely captures the three-dimensional shape of the structure. This is because the robot in question only incidentally captures the structure as a result of self-position estimation during its own work movement, and it is conceivable that it may only be able to capture a part of the situation. The robot 150 that receives the instruction moves to circle around the difference or the surroundings and transmits the self-position estimation result to the map correction device 110. The map correction device 110 performs the same processing as described above for the detection unit 116 and the map correction unit 118 to correct the three-dimensional map that captures the shape of the structure. In this way, by having another robot perform the task of capturing the overall picture of the structure in which a difference or error has been detected, the situation of the structure in the real space can be accurately reflected in the three-dimensional map. [Explanation of Symbols]

[0040] 100 Map Correction Systems 110 Map Correction Device 112 Communications Department 114 Path generation unit 116 Detection Unit 118 Map Correction Section 120 Storage section 140 devices 150 robots

Claims

1. Using three-dimensional or two-dimensional map data for each type of robot that defines the range of movement of the robot according to the structure in space, and the self-position estimation result obtained by matching the position of the structure with the control information received by the robot, the difference or error between the map data and the real space is detected. When the aforementioned difference or error is detected, in order to correct the map data that captures the shape of the structure in which the difference or error was detected, another robot that is not receiving control information and is free to work is instructed to take measurements to estimate the shape of the structure. The other robot obtains a self-position estimation result obtained by moving around the structure in which the difference or error was detected, and the other robot obtains the self-position estimation result transmitted by the other robot. Using the detection results of the robot receiving the control information and the self-position estimation results obtained by the other robots patrolling around the structure, the shape of the structure is captured, and the map data corresponding to the type of robot receiving the control information is corrected to reflect the state of the structure. The aforementioned space is the actual space of the building construction site, and the aforementioned structure is a movable structure within the actual space of the building construction site, and is at least one of the installations, materials, and construction tools of the construction site. The correction involves correcting the map data to reflect changes in the arrangement due to at least one of the movement, addition, and use of the movable structures, so that the movable range of the robot receiving control information changes. When the structure is removed, the map data is corrected so that the movable range expands; when the structure is newly installed, the map data is corrected so that the movable range narrows; and when the structure is moved, the map data is corrected so that the movable range adjusts. Using the corrected map data, the movement path of the robot receiving the control information is regenerated, and new control information including the regenerated movement path is transmitted to the robot. The system manages the system so that it can choose to refer to the map data that has been corrected to reflect the actual state of structures in space, or to refer to the BIM data, which is the original data used to generate the map data. Map correction system.

2. The map correction system according to claim 1, wherein, in the management described above, during the construction of the building, the system is configured to refer to the map data updated by the correction described above according to the actual conditions of the construction site, and after the completion of the building, it is configured to refer to the BIM data.

3. Using three-dimensional or two-dimensional map data for each type of robot that defines the range of movement of the robot according to the structure in space, and the self-position estimation result obtained by matching the position of the structure with the control information received by the robot, the difference or error between the map data and the real space is detected. When the aforementioned difference or error is detected, in order to correct the map data that captures the shape of the structure in which the difference or error was detected, another robot that is not receiving the control information and is not currently working is instructed to take measurements to estimate the shape of the structure. The other robot obtains a self-position estimation result obtained by moving around the structure in which the difference or error was detected, and the other robot obtains the self-position estimation result transmitted by the other robot. Using the detection results of the robot receiving the control information and the self-position estimation results obtained by the other robots patrolling around the structure, the shape of the structure is captured, and the map data corresponding to the type of robot receiving the control information is corrected to reflect the state of the structure. The aforementioned space is the actual space of the building construction site, and the aforementioned structure is a movable structure within the actual space of the building construction site, and is at least one of the installations, materials, and construction tools of the construction site. The correction involves correcting the map data to reflect changes in the arrangement due to at least one of the movement, addition, and use of the movable structures, so that the movable range of the robot receiving the control information changes. When the structure is removed, the map data is corrected so that the movable range expands; when the structure is newly installed, the map data is corrected so that the movable range narrows; and when the structure is moved, the map data is corrected so that the movable range adjusts. Using the corrected map data, the movement path of the robot receiving the control information is regenerated, and new control information including the regenerated movement path is transmitted to the robot. The system manages the system so that it can choose to refer to the map data that has been corrected to reflect the actual state of structures in space, or to refer to the BIM data, which is the original data used to generate the map data. A map correction program that has a computer perform the processing.

Images