KR102630545B1 - Robot and robot control method carrying out management information according to the condition of the grass - Google Patents

Abstract

Obtaining a plurality of detection target areas predicted to be pest-damaged areas based on a plurality of lawn area data obtained from a plurality of sensors; By performing image analysis on the plurality of detection target areas, obtaining target area characteristic information including size information of each area, location information, and information on whether or not a similar shape is repeated within the area; determining a detection path representing the expected path of the robot based on the target area characteristic information; Obtaining pest prediction information for the plurality of detection target areas acquired as the robot moves along the detection path; and controlling the robot so that the robot sprays pesticide based on the pest prediction information. A robot control method and a robot are disclosed.

Description

Robot and robot control method carrying out management information according to the condition of the grass}

The technical field of the present disclosure relates to a robot and robot control method that performs management according to the state of the lawn. More specifically, it relates to a robot that controls the robot according to the monitoring of the state of the lawn to facilitate lawn management and pest prediction. It is related to the technical field.

As interest in leisure activities using the environment and nature increases, leisure activities on grass, such as golf, are increasing. In the case of sports using grass, such as golf and soccer, the quality of the sport may vary depending on the condition of the grass, so confirmation of this may be essential. Conventionally, the main system is a passive system in which pesticides are sprayed or managed as managers personally visit and check areas where turf abnormalities are predicted. Therefore, there is a limitation that it is difficult to manage the lawn if the manager is absent, and the time it takes for the manager to check and manage a large lawn area can be large, and it is difficult to go to check the area directly and check it. There is a problem that accuracy may decrease depending on the administrator's condition or situation. In addition, it is not possible to find a direction for improvement in this passive management aspect area. Therefore, as the convenience of managers improves, there is a need for robots that can automatically check the state of the lawn and manage them accordingly, and methods and measures to control the robots.

Korean Patent Publication No. 10-2020-0071884 (2020.06.22) Disease prediction service device and method for field crops

The problem to be solved in this disclosure is to disclose a method of controlling a robot and a robot that performs management according to the state of the lawn, and is intended to provide information on how to manage the lawn more efficiently.

As a technical means for achieving the above-described technical problem, the robot control method for performing management according to the lawn condition according to the first aspect of the present disclosure is to control the robot control method to control the pest-damaged area based on a plurality of lawn area data obtained from a plurality of sensors. Obtaining a plurality of predicted detection target areas; By performing image analysis on the plurality of detection target areas, obtaining target area characteristic information including size information of each area, location information, and information on whether or not a similar shape is repeated within the area; determining a detection path representing the expected path of the robot based on the target area characteristic information; Obtaining pest prediction information for the plurality of detection target areas acquired as the robot moves along the detection path; and controlling the robot to spray pesticide based on the pest prediction information.

Additionally, the pest prediction information may include at least one of brown leaf blight, summer leaf blight, Rhizoctonia blight, and coin blight.

In addition, the step of acquiring the detection target area includes obtaining a calibration image including a plurality of boundary lines from the plurality of grass areas using a camera sensor and a LiDAR sensor; and acquiring location information of the plurality of detection target areas based on the plurality of boundary lines.

Additionally, determining the detection path may include obtaining unstructured shape information about the plurality of detection target areas; and determining the detection path based on the median value indicating the center of the irregular shape and the distance of the robot.

In addition, the step of determining the detection path includes determining priorities for the plurality of detection target areas based on weights given in the order of the location information, the size information, and information on whether or not a similar shape is repeated in the area. ; and determining the detection path according to the priority order.

In addition, the step of obtaining the pest prediction information includes obtaining a coin blight prediction area by monitoring a surrounding area of the detection path; And counting the type and number of insect acquisitions for one or more insects obtained from a sensor as the robot moves the detection path, based on the coin blight prediction area for the plurality of detection target areas. updating priorities; and controlling the robot to spray pesticide based on the type of insect and the counted number of times the insect has been acquired.

A robot that performs management according to lawn conditions according to a second aspect of the present disclosure includes a receiver that acquires a plurality of lawn area data from a plurality of sensors; And obtaining a plurality of detection target areas predicted to be pest-damaged areas based on the plurality of lawn area data, and performing image analysis on the plurality of detection target areas, such as size information, location information, and area information of each area. Obtain target area characteristic information including information on whether or not a similar shape is repeated, determine a detection path indicating the expected path of the robot based on the target area characteristic information, and determine the detection path that is obtained as the robot moves along the detection path. It may include a processor that acquires pest prediction information for a plurality of detection target areas and controls the robot to spray pesticide based on the pest prediction information.

According to an embodiment of the present disclosure, the convenience of the manager can be improved in that the lawn care robot can automatically check the state of the lawn and manage it according to data obtained from a plurality of sensors.

Additionally, efficiency can be improved in that the time required can be reduced because an automatic lawn management system is provided through a robot.

In addition, like autonomous driving, the accuracy and efficiency of lawn management can be improved in that the robot checks the state of the grass by distinguishing between long distance and short distance as it moves along the detection path.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned may be clearly understood by those skilled in the art from the description below.

Figure 1 is a block diagram schematically showing the configuration of a robot according to an embodiment.
Figure 2 is a flowchart for explaining a robot control method according to an embodiment.
FIG. 3 is a diagram illustrating an example in which a robot acquires a plurality of detection target areas according to an embodiment.
Figure 4 is a diagram for explaining an example of a robot moving along a detection path according to an embodiment.
FIG. 5 is a diagram illustrating an example in which a robot acquires pest prediction information at a short distance along a detection path according to an embodiment.
Figure 6 is a flowchart schematically showing the overall flow of operation of a robot according to an embodiment.

Advantages and features in the present disclosure, and methods for achieving them, will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure is complete and to those skilled in the art. It is provided to provide complete information.

The terms used herein are for describing embodiments and are not intended to limit the disclosure. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements. Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and every combination of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be the second component within the technical spirit of the present disclosure.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art. Additionally, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly specifically defined.

Spatially relative terms such as “below”, “beneath”, “lower”, “above”, “upper”, etc. are used as a single term as shown in the drawing. It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms that include different directions of components during use or operation in addition to the directions shown in the drawings. For example, if a component shown in a drawing is flipped over, a component described as “below” or “beneath” another component will be placed “above” the other component. You can. Accordingly, the illustrative term “down” may include both downward and upward directions. Components can also be oriented in other directions, so spatially relative terms can be interpreted according to orientation.

Hereinafter, various embodiments will be described in detail with reference to the drawings.

Figure 1 is a block diagram schematically showing the configuration of a robot 100 according to an embodiment.

Referring to FIG. 1, the robot 100 may include a receiver 110 and a processor 120.

The receiver 110 according to one embodiment may obtain a plurality of grass area data from one or more sensors.

The processor 120 according to an embodiment may obtain a plurality of detection target areas predicted to be pest-damaged areas based on a plurality of lawn area data. Additionally, as the processor 120 performs image analysis on a plurality of detection target areas, it may obtain target area characteristic information including size information of each area, location information, and information on whether or not a similar shape is repeated within the area. Additionally, the processor 120 may determine a detection path representing the expected path of the robot based on target area characteristic information. Additionally, the processor 120 may obtain pest prediction information for a plurality of detection target areas acquired as the robot moves along the detection path. Additionally, the processor 120 may control the robot 100 so that the robot sprays pesticide based on pest prediction information.

In addition, the robot 100, which performs management according to the grass condition, acquires a plurality of lawn areas from the receiver 110, determines the detection target area, detection target characteristic information, and detection path from the processor 120 to provide pest prediction information. It should be noted that in the process of acquiring and controlling the robot to spray pesticides, it can be combined by various conventional network combinations such as the Internet network or mobile communication network, and there are no special restrictions on this.

In addition, those skilled in the art can understand that other general-purpose components in addition to the components shown in FIG. 1 may be further included in the robot 100 that performs management according to the state of the lawn. For example, the robot 100 that performs management according to the grass condition may include a drive control module, a path detection module, a data processing module, etc. for performing each step, and may acquire sensing data from a plurality of sensors. It may include a sensing unit. Additionally, the robot 100 may be controlled through a control unit and may further include a memory (not shown) that stores a plurality of information or a transmitter (not shown) that transmits turf condition information. Alternatively, according to another embodiment, those skilled in the art may understand that some of the components shown in FIG. 1 may be omitted.

The robot 100 and robot control method that performs management according to the lawn condition according to an embodiment can be used by a user and can be used by a mobile phone, smartphone, PDA (Personal Digital Assistant), PMP (Portable Multimedia Player), or tablet. It can be linked with all types of handheld wireless communication devices equipped with touch screen panels, such as PCs, and in addition, applications such as IPTV including desktop PCs, tablet PCs, laptop PCs, and set-top boxes. It can be included in or linked to a device with a ready base for installation and execution.

The robot 100 that performs management according to the state of the lawn may be implemented as a terminal such as a computer that operates through a computer program to realize the functions described in this specification.

The robot 100 that performs management according to the state of the lawn according to one embodiment may include, but is not limited to, a system (not shown) that controls the lawn management robot and a related server (not shown). The server according to one embodiment may support an application that controls a lawn care robot.

Hereinafter, the description will focus on an embodiment in which the robot 100, which performs management according to the state of the lawn, manages the lawn independently. However, as described above, this may be performed through interworking with a server. That is, the robot 100 and the server that perform management according to the lawn condition according to one embodiment may be integrated in terms of their functions, and the server may be omitted, and is not limited to any one embodiment. Able to know.

In one embodiment, the robot 100 and the server that controls the robot may be linked, and configuration of the system that controls the robot to perform lawn care may be performed by the server and may be automatically performed by the robot 100. It may be possible. For example, the robot 100 can operate as a server, and hereinafter it will be unified as the robot 100 and described later.

Figure 2 is a flowchart for explaining a robot control method according to an embodiment.

Referring to step S210, the robot 100 according to one embodiment may acquire a plurality of detection target areas predicted to be pest-damaged areas based on a plurality of grass areas obtained from one or more sensors. In one embodiment, the robot 100 may obtain a plurality of lawn-related information, such as an image of the lawn, the location of the robot 100, temperature, and humidity, from a plurality of sensors. Additionally, images may include color information. As the robot 100 acquires a plurality of lawn-related information, it can acquire a plurality of detection target areas that are part of the plurality of grass areas predicted to be pest-damaged areas. For example, the robot 100 according to one embodiment may acquire a calibration image including a plurality of boundary lines from a plurality of grass areas using a camera sensor and a lidar sensor among a plurality of sensors. A calibration image that can predict the target area can be obtained through a camera sensor that acquires the target location through images and videos and a lidar sensor that acquires the distance to the target location. The robot 100 compares and analyzes a plurality of boundaries included in the calibration image based on an AI-based abnormal area detection learning algorithm to obtain location information of a plurality of detection target areas, which are areas where abnormalities are detected among a plurality of grass areas. You can. The device 100 may provide color information using an image obtained from a camera to topographical information about the target location obtained from a sensor such as a 3D LiDAR sensor. For example, the device 100 may include multiple sensors and may perform a calibration process to determine the spatial location of a plurality of target positions included in images acquired from a camera sensor and multiple sensors. By detecting feature points for each location from data acquired from each sensor and matching them to one coordinate system, multiple corresponding pairs can be created by comparing each data feature point and matching points at the same distance. Accordingly, a plurality of boundary lines connecting each corresponding pair can be obtained. Accordingly, the plurality of borderlines may include lines of different colors obtained according to corresponding pairs, and thus, position information on the same line in the image can be obtained through the plurality of borderlines. Accordingly, the device 100 can predict the locations of a plurality of detection target areas through a calibration process and obtain distance information to the location of each target area.

Referring to step S220, as the robot 100 according to one embodiment performs image analysis on a plurality of detection target areas, the target includes size information of each area, location information, and information on whether or not a similar shape is repeated within the area. Area characteristic information can be obtained. In one embodiment, image analysis may be performed according to an AI-based anomaly detection learning algorithm as described above, and the robot 100 determines the size information, location information, and presence or absence of repetition of similar shapes in a plurality of detection areas. You can decide. In one embodiment, the size information may mean the size of the entire area within the area boundary where an abnormality is detected, and the location information is the location of the area where an abnormality is detected, and may be an element for checking the distance from the robot 100. You can. Additionally, the presence or absence of repetition of a similar shape within an area indicates the shape of the grass in which an abnormality is detected within the area, and may be an element for checking whether the shape appears repeatedly. Accordingly, the device 100 may obtain target area characteristic information including size information, location information, and information on whether or not a similar shape is repeated for each of the plurality of detection target areas.

Referring to step S230, the robot 100 according to one embodiment may determine a detection path indicating the expected path of the robot 100 based on target area characteristic information. In one embodiment, the detection path may mean a path along which the robot 100 moves to manage or analyze a plurality of areas determined as detection target areas. The robot 100 according to one embodiment may acquire non-standardized shape information about a plurality of detection target areas. The unstructured shape information may include information about the shape of the grass included within the boundary of the area where the abnormality is detected and information about a plurality of coordinate values according to the location. The robot 100 may determine a detection path based on the median value indicating the center of the irregular shape and the distance from the robot 100. For example, the robot 100 acquires the preset point position information closest to the median value in the unstructured shape for the plurality of detection target areas based on the positions of the plurality of preset points in the plurality of grass areas. The distance between the detection target area and the robot 100 can be inferred using LIDAR data. In addition, the robot 100 can determine the priority for a plurality of detection target areas based on weights given in the order of location information, size information, and information on whether or not a similar shape is repeated within the area. , the detection path can be determined in order of priority. In one embodiment, the robot 100 may preferentially manage a detection target area located nearby. Therefore, because location information is the most direct element that can confirm the degree of separation from the robot 100, the highest weight may be given to location information in determining the detection path. In addition, if a plurality of detection target areas are similar in distance from the robot 100 according to the location information, the size information is given the second highest weight because the area with a large detection target area is an area that needs to be managed more quickly. may be granted. In addition, it may be desirable to check information on the presence or absence of repetition of similar shapes because it can improve the accuracy in determining the detection target area in that there is a high probability that it is an abnormal detection area when similar shapes appear repeatedly. However, due to the nature of the disease, Given that there may be many diseases in which similar shapes do not appear repeatedly, information on the presence or absence of repetitions of similar shapes within an area may be given a high third-rank weight. Accordingly, by assigning high weights to a plurality of elements in the above-described order, the detection path order can be determined more easily. When the robot 100 manages the detection target area, the detection path is determined by assigning different weights to the location information, size information, and information about the presence or absence of repetition of similar shapes in the area so that nearby areas and areas requiring management are managed more quickly. This has the effect of improving lawn management efficiency.

Referring to step S240, the robot 100 according to one embodiment may acquire pest prediction information for a plurality of detection target areas acquired as it moves along the detection path. In one embodiment, the robot 100 may acquire a plurality of detection target areas at a distance, and acquire images of a plurality of detection target areas at a short distance along a detection path determined according to the acquired plurality of detection target areas. can do. Accordingly, the robot 100 can acquire images of each area as it moves the detection path, and obtain pest prediction information as a result of image analysis. In one embodiment, the pest prediction information may include at least one of brown leaf blight, summer leaf blight, Rhizoctonia blight, and coin blight corresponding to the disease name of the lawn. Brown leaf blight, summer leaf blight, Rhizoctonia blight, and coin blight may be diseases that mainly occur in lawns, and the robot 100 acquires images of grass in the detection target area, and analyzes the images to determine the size of the grass. Pest prediction information including disease name can be obtained. In one embodiment, the robot 100 provides location information, size information, and similar shapes within the area, as described above in the case of a plurality of lawn diseases other than brown leaf blight, summer leaf blight, Rhizoctonia blight, and coin blight. Priority for multiple detection target areas can be determined based on the weight given in the order of repetition presence or absence information. If the disease name of the lawn is brown leaf blight, size information, location information, and repetition presence or absence of similar shapes within the area can be determined. Priorities for a plurality of detection target areas can be determined based on weights assigned to a higher order. For example, in the case of brown leaf blight, the shape of the grass is often characterized by a lack of repetitive shapes, so individual shapes may appear, so if the size of the area is large, this means that the individual shape is large. Since the degree of damage to the target area may be very large, a higher weight is given to the size information, and when a single shape appears, the importance of whether or not a similar shape is repeated may be lowered, so the lowest weight is given to the presence or absence of a similar shape repeated in the area. can be given. In addition, if the disease name of the lawn is summer leaf blight, Rhizoctonia blight, and penny blight, multiple detection target areas are detected based on the weight given in the order of location information, information on the presence or absence of repetition of similar shapes in the area, and size information. You can decide your priorities. For example, in the case of summer leaf blight, Rhizoctonia blight, and coin blight, the shape of the lawn is often repetitive, so the extent of spread in the detection target area can be more accurately confirmed depending on the presence or absence of repetition of similar shapes. Next to location information, the next highest weight is given to information on whether similar shapes are repeated, and in the case of size information, the boundaries of the overall detection target area can be confirmed. However, if the degree of repetitive appearance within the detection target area is small, the size information is largely It can be obtained, but the degree of damage may be less than that, so the size information may be given a high third place weight in that the accuracy may be somewhat lower. Therefore, by varying the size of the weight assigned to each of the plurality of elements according to the disease name of the grass, the priority for a plurality of detection target areas can be updated and a more accurate detection path can be obtained.

Referring to step S250, the robot 100 according to one embodiment may be controlled to spray pesticide based on pest prediction information. In one embodiment, as the robot 100 acquires pest prediction information, it can determine the type and spray amount of pesticide corresponding to the predicted pest and the size and condition of the detection target area. In one embodiment, the robot 100 may spray pesticide to the detection target area according to the determined type and spray amount of pesticide. Additionally, the robot 100 according to one embodiment may obtain a coin blight prediction area by monitoring the surrounding area of the detection path. In one embodiment, the shape corresponding to the coin blight may be very small, making it difficult to predict, and in the case of a long distance, there is a high probability that it will not be recognized, so the robot 100 detects the surrounding area while moving the determined detection path. A coin blight identification process can be performed. Additionally, if a coin blight prediction area is acquired while moving the detection route, the detection route can be updated by updating the priorities for a plurality of detection target areas. For example, the robot 100 may determine the risk level for each of a plurality of detection target areas included in the detection target area list. The robot 100 may update the priority and modify the detection path by inserting the coin blight prediction area in the middle of the priority based on the risk for each of the plurality of detection target areas. For example, among multiple detection target areas, the priority of the detection target area with a risk of more than a preset percent (e.g., 70%) is maintained, and the priority of the detection target area with a risk of more than a preset percent (e.g., 50% or more but less than 70%) is maintained. In the case of a range, as the risk of the coin blight prediction area is obtained, the priority of multiple detection target areas can be updated by giving the area with a higher risk percentage a higher priority according to the comparison results of the risk. In addition, when the risk of the detection target area is less than a preset percent (for example, 50 percent), the coin blight prediction area is closer to the robot 100 at the current time, so the priority of the coin blight prediction area is that of the corresponding detection target area. The priority of multiple detection target areas can be updated by making it higher than the priority. Therefore, there is an effect that the robot 100 can perform an additional management process according to the coin blight prediction area acquired while moving. Additionally, the robot 100 may acquire information about insects obtained from one or more sensors as it moves along the detection path. For example, the robot 100 may acquire information about whether an insect is recognized in the surrounding area and the type of insect recognized from one or more sensors while moving through a plurality of grass areas along a detection path. You can count the number of acquisitions. Accordingly, the robot 100 can determine the type and spray amount of the corresponding pesticide based on the type of insect and the number of times it has acquired the insect, and can spray the pesticide to the corresponding area according to the determined type and spray amount of the pesticide. Accordingly, the robot 100 can obtain pest prediction information about insects while moving along the detection path, and can improve the efficiency of lawn management by spraying pesticides in areas where the number of insect acquisitions is more than a preset number.

FIG. 3 is a diagram illustrating an example in which the robot 100 acquires a plurality of detection target areas according to an embodiment.

Referring to FIG. 3, the robot 100 can confirm a plurality of boundary lines by acquiring a calibration image and acquire a plurality of detection target areas based on the plurality of boundary lines. In addition, the location of the detection target area can be acquired using a camera sensor, the median value of the expected detection area can be obtained, and the distance value from the robot 100 can be obtained using a LiDAR sensor.

FIG. 4 is a diagram illustrating an example in which the robot 100 moves along a detection path according to an embodiment.

Referring to FIG. 4, the robot 100 according to an embodiment can perform long-distance detection, and by performing long-distance detection, a plurality of detection target areas (areas 5M and 15M away in FIG. 4) can be acquired. . The robot 100 may perform detection of an area located at a closer distance among a plurality of detection target areas obtained through a long-distance detection process. As shown in FIG. 4, using the LiDAR sensor, the robot 100 can perform a short-distance A detection process to detect a detection target area located at a closer distance (an area 5M away in FIG. 4), and respond to the short distance. As the device moves to the detection target area, a short-range B detection process can be performed to analyze the detection target area. That is, in one embodiment, the long-distance detection process may be used to obtain a plurality of detection target areas, and the short-range A detection process may be used to obtain a detection target area corresponding to a short distance among the acquired plurality of detection target areas and the detection target area. It can be used to identify the shape of the grass according to the grass image and video. Additionally, the short-distance B detection process can be used to predict pest information by analyzing the shape of the grass in the area as the robot 100 moves to a detection target area corresponding to a short distance. Additionally, as shown in FIG. 4, the robot 100 may move to the detection target area corresponding to the next priority after performing the short-distance B detection process.

FIG. 5 is a diagram illustrating an example in which the robot 100 acquires pest prediction information at a short distance along a detection path according to an embodiment.

Referring to FIG. 5, the robot 100 identifies the shape of the grass obtained by performing the short-distance A detection process, and compares it with the control group to predict the disease name of the grass included in the pest prediction information. As described above, the pest prediction information may include the disease name of at least one of brown leaf blight, summer leaf blight, Rhizoctonia blight, and coin blight, and may also include disease names of other grasses. Additionally, as the robot 100 performs the short-range B detection process, it can perform a more detailed analysis based on the predicted grass disease name obtained through the short-range A detection process. Differences in grass leaf color, mold, bugs, larvae, etc. can be detected, and pests and diseases in the lawn can be predicted by comparing with the control group.

FIG. 6 is a flowchart schematically showing the overall operation flow of the robot 100 according to an embodiment.

Referring to FIG. 6 , the robot 100 may perform a remote detection process as described in FIG. 4 . Additionally, by performing a long-distance detection process, multiple detection target areas can be obtained. The robot 100 may obtain information on the distance from the detection target area using a plurality of sensors. For example, using a camera sensor and a lidar sensor, a plurality of detection target areas can be acquired according to an AI-based abnormal area detection algorithm process, and distance information indicating the degree to which the detection target area is separated from the robot 100 can be obtained. there is. In one embodiment, a plurality of acquired information may be provided to a manager account, and a management service that provides a plurality of information may be provided. Additionally, the robot 100 can determine the detection priority according to the distance between the plurality of detection target areas and can move to the detection target area according to the priority. The robot 100 can predict the name of a lawn disease as described in the plurality of steps of FIG. 2 and FIGS. 4 and 5, obtain the type of insect obtained from the sensor, and count the number of times the insect is acquired. Accordingly, the type and spray amount of pesticide corresponding to each detection target area can be determined, and the pesticide can be sprayed to the corresponding area according to the determined pesticide type and spray amount. In one embodiment, a plurality of various types of grass-related information obtained until pesticide spraying may be provided to the manager account, and a management service that the manager can monitor in real time may be provided.

According to one embodiment, the convenience of the manager can be improved in that the lawn management robot can automatically check the state of the lawn and manage it according to data acquired from a plurality of sensors, and automatically manage the lawn through the robot. Efficiency can be improved in that the time required to receive the system can be reduced. In addition, like autonomous driving, the accuracy and efficiency of lawn management can be improved in that the robot checks the state of the grass by distinguishing between long distance and short distance as it moves along the detection path.

Various embodiments of the present disclosure are implemented as software including one or more instructions stored in a storage medium (e.g., memory) that can be read by a machine (e.g., a display device or computer). It can be. For example, the processor 120 of the device (eg, processor 120) may call at least one instruction among one or more instructions stored from a storage medium and execute it. This allows the device to be operated to perform at least one function according to the at least one instruction called. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. A storage medium that can be read by a device may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain signals (e.g. electromagnetic waves). This term refers to cases where data is stored semi-permanently in the storage medium. There is no distinction between temporary storage cases.

According to one embodiment, methods according to various embodiments disclosed in the present disclosure may be included and provided in a computer program product. Computer program products are commodities and can be traded between sellers and buyers. The computer program product may be distributed in the form of a machine-readable storage medium (e.g. compact disc read only memory (CD-ROM)) or via an application store (e.g. Play StoreTM) or on two user devices (e.g. It can be distributed (e.g. downloaded or uploaded) directly between smartphones) or online. In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

Although the present invention has been described with reference to the illustrative drawings, it is not limited to the disclosed embodiments and drawings, and those skilled in the art in the technical field related to the present embodiments may make modifications without departing from the essential characteristics of the above-mentioned description. You will be able to understand that it can be implemented in a certain form. Therefore, the disclosed methods should be considered from an explanatory rather than a restrictive perspective. Even if the operational effects according to the configuration of the present invention are not explicitly described and explained in the description of the embodiment, the effects that can be predicted by the configuration may also be recognized. The scope of the present invention is indicated in the claims rather than the foregoing description, and all differences within the equivalent scope should be construed as being included in the present invention.

100: device
110: receiving unit 120: processor

Claims (7)

In a robot control method that performs management according to lawn conditions,
Obtaining a plurality of detection target areas predicted to be pest-damaged areas based on a plurality of lawn area data obtained from a plurality of sensors;
By performing image analysis on the plurality of detection target areas, obtaining target area characteristic information including size information of each area, location information, and information on whether or not a similar shape is repeated within the area;
determining a detection path representing the expected path of the robot based on the target area characteristic information;
Obtaining pest prediction information for the plurality of detection target areas acquired as the robot moves along the detection path; and
Comprising: controlling the robot so that the robot sprays pesticide based on the pest prediction information,
The step of determining the detection path is
determining priorities for the plurality of detection target areas based on weights given in the order of the location information, the size information, and information on whether or not a similar shape is repeated in the area; and
Method comprising: determining the detection path according to the priority order.
According to clause 1,
The method wherein the pest prediction information includes at least one of brown leaf blight, summer leaf blight, Rhizoctonia blight, and coin blight.
According to clause 1,
The step of acquiring the detection target area is
Obtaining a calibration image including a plurality of boundary lines from the plurality of grass areas using a camera sensor and a lidar sensor; and
A method comprising: acquiring location information of the plurality of detection target areas based on the plurality of boundaries.
According to claim 3,
The step of determining the detection path is
Obtaining non-standardized shape information about the plurality of detection target areas; and
Method comprising: determining the detection path based on a median value representing the center of an irregular shape and the distance of the robot.
delete According to claim 1,
The step of obtaining the pest prediction information is
Obtaining a coin blight prediction area by monitoring a surrounding area of the detection path; and
Counting the type and number of insect acquisitions for one or more insects obtained from the sensor as the robot moves the detection path,
updating priorities for the plurality of detection target areas based on the coin blight prediction area; and
The method further comprising controlling the robot to spray pesticide based on the type of insect and the counted number of times the insect has been acquired.
In a robot that performs management according to lawn conditions,
A receiving unit that acquires a plurality of lawn area data from a plurality of sensors; and
Obtaining a plurality of detection target areas predicted to be pest-damaged areas based on the plurality of lawn area data,
By performing image analysis on the plurality of detection target areas, target area characteristic information including size information of each area, location information, and information on whether or not a similar shape is repeated within the area is obtained;
Determine a detection path representing the expected path of the robot based on the target area characteristic information,
Obtain pest prediction information for the plurality of detection target areas obtained as the robot moves along the detection path,
A processor that controls the robot to spray pesticide based on the pest prediction information,
The processor is
Determining priorities for the plurality of detection target areas based on weights given in the order of the location information, the size information, and information on whether or not a similar shape is repeated in the area,
A robot that determines the detection path in order of priority.