Patent Application
20200202738
Pursuant to 35 U.S.C. § 119(a), this application claims the benefit of earlier filing date and right of priority to Korean Patent Application No. 10-2018-0168554, filed on Dec. 24, 2018, the contents of which are all hereby incorporated by reference herein in their entirety.
The present disclosure relates to a robot, and more particularly, to a robot capable of interacting with a plurality of users and a method of controlling the robot.
A robot generally relates to a machine that automatically processes or operates a given task by its own ability, and the application fields of the robot may be variously classified into an industrial field, a medical field, an aerospace field, and a submarine field. Recently, there is a trend that communication robots capable of communicating or interacting with humans through voices or gestures are increasing.
Such communication robots may include various types of robots such as a guide robot located at a specific place to provide a variety of information to a user, or a home robot provided in a home. In addition, the communication robots may include an educational robot that guides or assists learning of a learner through interaction with the learner.
Meanwhile, an educational robot of the related art is generally used for one-to-one education with the learner, but an application place of such an educational robot may be limited to a home. In other words, in order for the educational robot to be spread to educational institutions such as daycare centers, kindergartens, private educational institutes, or schools, it is necessary to allow the educational robot to implement one-to-many education.
Embodiments provide a robot configured to provide contents such as learning contents to a plurality of users and manage learning information for each of the users so as to support one-to-many education.
Embodiments also provide a robot that may obtain and manage the learning information or life log data of the user through interaction with the user.
Embodiments further provide a robot that may track a location of a target person through sharing information with other robots that are remotely located.
According to an embodiment, a robot includes: a communication interface configured to establish connection with a server; an output interface including at least one of a display or a speaker; a memory configured to store user information for each user; an input interface including at least one of a camera or a microphone; and a processor configured to control the output interface to output a content, control the output interface to output a message related to the content during or after outputting the content, obtain an interaction data to the message from a selected interaction target person through the input interface when an interaction target person is selected from a plurality of users based on data obtained through the input interface, and
update user information of the interaction target person based on the obtained interaction data or transmit the obtained interaction data to the server.
The user information may include learning information of each of the users, and the processor may update the learning information of the interaction target person based on the obtained interaction data.
The user information may include identification information of a corresponding user, and the processor may recognize the users based on the identification information and at least one of image data obtained through the camera or voice data obtained through the microphone.
In some embodiments, the processor may recognize a user having an intention to interact among the recognized users to select the recognized user as the interaction target person based on at least one of image data obtained through the camera or voice data obtained through the microphone after outputting the message.
In some embodiments, the processor may select a user with a lowest learning level or a user with a smallest number of interactions as the interaction target person based on the learning information included in the user information of each of the recognized users.
The processor may output an interaction request message, which includes unique information included in the user information of the selected interaction target person, through the output interface.
In some embodiments, the processor may be configured to recognize the obtained interaction data to compare a result of the recognition with correct answer data for the message, and control the output interface to output a correct answer message when the result of the recognition of the interaction data is correct as a result of the comparison.
In some embodiments, the processor may be configured to receive voice data including the interaction data through the microphone, and output a message for inducing restriction of an utterance or a noise generated from other users except for the interaction target person through the output interface when a voice or a sound other than a voice of the interaction target person is detected from the received voice data by a reference value or more.
In some embodiments, the processor may generate the message based on metadata of the content.
In some embodiments, at least one of the user information or the content may be received from the server.
In some embodiments, the processor may be configured to transmit data obtained through the input interface to the server after outputting the message, receive information of the interaction target person selected by the server from the server, and output an interaction request message including the received information of the interaction target person through the output interface.
In some embodiments, the processor may be configured to transmit data including the interaction data obtained through the input interface to the server, and receive a message from the server depending on whether the interaction data is correct to output the received message through the output interface.
In some embodiments, the processor may be configured to obtain image data including a user or voice data spoken by the user through the input interface, and obtain life log data of the user based on the obtained image data or the obtained voice data.
The processor may be configured to generate life log based interaction data for interacting with the user based on the life log data, output the generated life log based interaction data through the output interface, receive a response of the user with respect to the output life log based interaction data through the input interface, and update the user information of the user based on the received response.
According to an embodiment, a method of controlling a robot includes: outputting a content through an output interface including at least one of a display or a speaker; outputting a message related to the content through the output interface during or after outputting the content; recognizing a plurality of users by using an input interface including at least one of a camera or a microphone; selecting an interaction target person for the message among the recognized users; obtaining an interaction data from the selected interaction target person through the input interface; and updating user information of the interaction target person based on the obtained interaction data.
The details of one or more embodiments are set forth in the accompanying drawings and the description below. Other features will be apparent from the description and drawings, and from the claims.
Hereinafter, embodiments disclosed herein will be described in detail with reference to the accompanying drawings. The accompanying drawings are provided so that the embodiments disclosed herein may be readily understood, and the technical idea disclosed herein is not limited by the accompanying drawings. Thus, it is to be understood that the present disclosure encompasses all changes, equivalents, and substitutes falling within the spirit and technical scope of the present disclosure.
Referring to
The robot 1 may be connected to a network 5 through an access point AP such as a router 4. Accordingly, the robot 1 may provide information (learning information, life log data, etc.) obtained for the user to a mobile terminal 2 or a server 3 through the network 5. In some embodiments, the robot 1 may obtain the information about the users from the server 3, and may obtain the contents from the server 3. In this case, the server 3 may store a plurality of contents, or may store and manage information on a plurality of users (identification information for user recognition, unique information of the user, the learning information, the life log data, etc.).
In some embodiments, the robot 1 may share a variety of information with other robots, such as robot 6. The other robot 6 may be connected to the network 5 through the router 7 to exchange information with the robot 1. The robot 6 may be configured in a manner that is the same or similar to that of robot 1, but is not necessarily limited thereto. In particular, the robot 1 may recognize presence of a target person by detecting the target person using a camera or a microphone, and provide a result of the recognition to the other robot 6. When the robots are provided at various places, the robots may track a location of the target person (e.g., a child) to provide related information to another person (e.g., a guardian). A control configuration of the robot 1 will now be described with reference to
The communication unit 11 may include communication modules configured to connect the robot 1 to the mobile terminal 2, the server 3, or the like, through the network 5, or to connect the robot 1 with the other robot 6. For example, the communication unit 11 may include a short range communication module such as Bluetooth, near field communication (NFC), a wireless Internet module such as Wi-Fi, and a mobile communication module such as that capable of communicating using a protocol such as long term evolution (LTE).
The input unit 12 may include at least one input device configured to input a predetermined or other signal or data to the robot 1 by an operation or other actions of the user. For example, the at least one input device may include a physical input device such as a button or a dial, a touch input unit 122 such as a touch pad or a touch panel, a microphone 124 that receives a voice of a user or other sound, and the like. The user may input a request or a command to the robot 1 by operating the input unit 12. In some embodiments, such as when there are a plurality of users, the controller 16 of the robot 1 may recognize a specific user based on a voice of the specific user received through the microphone 124.
The sensor unit 13 may include at least one sensor configured to sense a variety of information around or otherwise proximate to the robot 1. For example, the sensor unit 13 may include various sensors such as a camera 132 and a proximity sensor 134.
The camera 132 may obtain an image of a scene or object. In some embodiments, the controller 16 may obtain an image including a face of the user through the camera 132 to recognize the user. Alternatively, the controller 16 may obtain a gesture or a facial expression of the user through the camera 132. In this case, the camera 132 may function as the input unit 12.
The proximity sensor 134 may detect that an object such as the user approaches a periphery of the robot 1. For example, when the approach of the user is detected by the proximity sensor 134, the controller 16 outputs an initial screen or an initial voice through the output unit 14 to induce the user to use the robot 1.
The output unit 14 may output a variety of information related to an operation or a state of the robot 1, and various services, programs, applications, and the like that are executed in the robot 1. In addition, the output unit 14 may output various messages or information for allowing the robot 1 to interact with the user. For example, the output unit 14 may include a display 142 and a sound output unit 144.
The display unit 142 may output the above-described various information or messages in the form of graphics. In some embodiments, the display unit 142 may be implemented in the form of a touch screen including a touch pad. In this case, the display unit 142 may function as an input device as well as an output device. The sound output unit 144 may output the various information or messages in the form of voice or sound. For example, the sound output unit 144 may include a speaker.
The memory 15 may store various data such as control data for controlling operations of components included in the robot 1 and data for performing an operation corresponding to an input obtained through the input unit 12. In addition, the memory 15 may store program data of a software module executed by one of at least one processor or controller included in the controller 16. In addition, the memory 15 may store contents or other data to be provided to users. For example, the data may be received from the server 3 connected to the robot 1 so as to be stored in the memory 15.
The memory 15 may include various hardware storage devices such as a ROM, a RAM, an EPROM, a flash drive, a hard drive, and the like. In addition, the memory 15 may include a user DB 152. The user DB 152 may include user information for each of a plurality of users. The user information may include user identification information, unique information, learning information, life log data, and the like of the user. In some embodiments, the user DB 152 may be at least a part of a user DB which is stored in the server 3 and transmitted to the robot 1.
The identification information may include data for identifying the user separately from other users, such as data for identifying a face of the user and data for identifying a voice of the user. The unique information may include information which is unique for each user, such as a name of the user. The learning information may include a variety of information related to the learning of the user, such as the learning level, learning records (number of times, time, date, etc.), a question-and-answer history, or number of interactions of the user.
The learning level may represent a learning difficulty or a learning progress of the learner for a corresponding learning item. In some embodiments, the learning information may include a learning level of each of learning items of the learner. For example, each of the learning items represents any one learning category, and the learning items may include various items such as ‘speaking’, ‘reading’, ‘listening’, ‘Korean’, and ‘English’.
The robot 1 may update the learning level and the learning information by accumulating the learning records or the question-and-answer history. Alternatively, the robot 1 may transmit the learning records or the question-and-answer history to the server 3. In this case, the learning level and the learning information may be updated in the server 3.
In addition, the robot 1 may output the learning information through the output unit 14 or transmit the learning information to the mobile terminal 2 of the user or another person (e.g., a guardian, etc.) related to the user. Accordingly, the user or another person may check the learning information of the user.
The life log data may include a record or information of an overall daily life of the user. Accordingly, the robot 1 may obtain voice data uttered by the user or image data including the user by using the microphone 124 and/or the camera 132, and may obtain the life log data about the user based on the obtained voice data and/or the obtained image data.
The controller 16 may include at least one processor or controller configured to control the operation of the robot 1. In detail, the controller 16 may include at least one CPU, an application processor (AP), a microcomputer (or a micom), an integrated circuit, an application-specific integrated circuit (ASIC), and the like. The controller 16 may perform operations according to various embodiments of the robot 1 to be described below with reference to the various figures presented herein. As such, the at least one processor or controller included in the controller 16 may perform such operations by processing the program data of the software module stored in the memory 15.
Meanwhile, the power supply unit 17 of the robot 1 may supply power required for the operations of the components included in the robot 1. For example, the power supply unit 17 may include a power connection unit to which an external wired power cable is connected, and a battery configured to store power to supply the power to the above components. In some embodiments, the power supply unit 17 may further include a wireless charging module configured to wirelessly receive the power to charge the battery. Hereinafter, various embodiments related to the operation of the robot 1 will be described with reference to
In the following drawings, an example case will be described in which the content output by the robot 1 is a learning content. However, the content output related to the embodiments of the present invention is not limited to such learning content, and as such, the robot 1 may output various types of content. In this case, an answerer may correspond to an interaction target person, an answer may correspond to interaction data, and the number of answers may correspond to the number of interactions.
The controller 16 may obtain learning contents stored in the memory 15 or learning contents stored in an external device, the terminal 2, the server 3, or the like connected to the robot 1, and may output the obtained learning contents through the output unit 14.
The robot 1 may output a query message related to the learning contents during or after outputting the learning contents (S110). For example, at least one message (e.g., query message) related to the learning contents and correct answer data corresponding thereto may be stored in the memory 15 or the external device such as the server 3 connected to the robot 1. The controller 16 may obtain the at least one query message and output the obtained at least one query message through the output unit 14.
In some embodiments, the controller 16 may generate the at least one query message from metadata of the learning contents. The metadata is information related to the learning contents, and may include information representing content, keywords, situations, people, emotions, themes, and other characteristics of the learning contents. The controller 16 may generate the query message and the correct answer data from the information included in the metadata.
The robot 1 may select an answerer for the query message among the detected users (S120). The controller 16 may detect a plurality of users around the robot 1 by using the camera 132 and/or the microphone 124. In detail, the controller 16 may detect the users from identification information of the users stored in the user DB 152 and the image and voice data obtained through the camera 132 and/or the microphone 124. An operation of detecting the user may be performed at any time before, during, or after outputting the learning contents.
The controller 16 may select the answerer for the query message among the users. For example, the controller 16 may detect at least one user having an intention to answer (an intention to interact) among the users using the camera 132. The controller 16 may select, as the answerer, a user detected as a first person who expresses an intention to answer among the detected at least one user.
In some embodiments, the controller 16 may select the answerer based on the learning information of each of the users. For example, the controller 16 may select a user with the lowest learning level among the users as the answerer. Alternatively, the controller 16 may select a user with the smallest number of answers or a user whose latest answering date is oldest as the answerer based on the question-and-answer history of each of the users.
Alternatively, the controller 16 may arbitrarily select the answerer among the users. For example, when the users or the user having an intention to answer are not accurately recognized due to a quality problem of the image data obtained by the camera 132 or the like, the controller 16 may arbitrarily select the answerer.
In some embodiments, at least one of an operation of detecting the users or an operation of selecting the answerer may be performed by the server 3 connected to the robot 1. As such, in this aspect, the controller 16 may transmit the image data and/or the voice data obtained through the camera 132 and/or the microphone 124 to the server 3. The server 3 may detect the users based on any or all of the received data and may recognize the user having the intention to answer among the detected users. The server 3 may select the recognized user as the answerer and transmit information about the selected answerer (e.g., unique information (name, etc.)) to the robot 1.
The controller 16 may output an answer request message including the unique information (e.g., a name) of the selected answerer through the sound output unit 144 or the like. For example, the controller 16 may convert the unique information (name) of the answerer included in the user DB 152 into voice data and output the converted voice data through the sound output unit 144.
The robot 1 may obtain an answer from the selected answerer (S130). The controller 16 may output the answer request message including the unique information of the selected answerer, and then obtain an answer to the query message through the microphone 124 or the input unit 12. For example, the controller 16 may identify a voice of the answerer from a variety of voice and sound data obtained through the microphone 124 based on the identification information of the answerer (voice information) stored in the user DB 152.
In some embodiments, the voice of the answerer may not be easily recognized from the voice and sound data due to an utterance or a noise generated from other users. In other words, when other voices or sounds except for the voice of the answerer are detected by a reference value or more among the obtained voice and sound data, the controller 16 may output a message for inducing the answerer to answer or a message for inducing restriction of the utterance or noise generated from other users except for the answerer.
In some embodiments, the controller 16 may transmit the obtained voice and sound data to the server 3. The server 3 may identify the voice of the answerer based on the received voice and sound data.
The robot 1 may recognize the obtained answer and check whether the answer is correct based on a result of the recognition (S140). The controller 16 may recognize the answer included in the identified voice by using various generally-known voice recognition algorithms, and compare the recognized answer with correct answer data.
For example, the correct answer data corresponding to the query message may be stored in the memory 15 or the external device such as the server 3 connected to the robot 1. In some embodiments, when the controller 16 has generated the query message based on the metadata, the controller 16 may also generate the correct answer data corresponding to the query message based on the metadata.
The controller 16 may determine whether the answer of the answerer is correct by checking whether a keyword included in the recognized answer is included in at least one keyword included in the correct answer data.
In some embodiments, when the server 3 has identified the voice of the answerer, the server 3 may check whether the answer is correct by recognizing the answer included in the identified voice and comparing the recognized answer with the correct answer data.
If a check result corresponds to a correct answer (YES in S150), the robot 1 may output the correct answer message (S160). In some embodiments, when the checking operation is performed by the server 3, the server 3 may transmit the correct answer message to the robot 1. In this case, the controller 16 may output the received correct answer message.
However, if the check result corresponds to an incorrect answer (NO in S150), the robot 1 may output an incorrect answer message (S170), and may perform the operation S120 again. If the check result is the incorrect answer, the controller 16 may select another user except the answerer from the users to obtain the answer. Alternatively, the controller 16 may request the answerer to answer again if the check result is the incorrect answer.
In some embodiments, when the checking operation is performed by the server 3, the server 3 may transmit the incorrect answer message and/or the unique information about the other user. The controller 16 may output the received incorrect answer message, and may output the unique information about the other user to obtain the answer from the other user.
In some cases, the robot 1 may update the learning information about the answerer based on the check result of the answer (S180). For instance, the controller 16 may update the learning level among the learning information about the answerer, which is included in the user DB 152, based on the check result of the answer. For example, the controller 16 may update the learning information by increasing the learning level when the check result of the answer corresponds to the correct answer, or by decreasing the learning level when the check result of the answer corresponds to the incorrect answer. In addition, the controller 16 may record an answer date of the answerer, the check result of the answer, and the like in the question-and-answer history of the learning information of the answerer.
In some embodiments, the controller 160 may transmit the check result of the answer and the question-and-answer history to the server 3. In this case, the learning information about the answerer may be updated by the server 3.
In this case, the user information management module 162, the user detection module 163, the answerer selection module 164, and the answer recognition module 165 may be implemented as software modules. The processor 161 or another controller included in the controller 16 may execute the modules 162 to 165 to control operations of the modules 162 to 165. In other words, an operation performed by each of the modules 162 to 165 may be controlled by the processor 161 or another controller included in the controller 16.
The processor 161 may control overall operations of the components included in the robot 1. In particular, the processor 161 (or another controller included in the controller 16) may load program data of any one of the user information management module 162, the user detection module 163, the answerer selection module 164, and the answer recognition module 165 stored in the memory 15 to execute the module corresponding to the loaded program data.
The user information management module 162 may manage (create, load, update, delete, etc.) the user information of each of the users stored in the user DB 152. The user information management module 162 may load the user information of each of the users from the memory 15. As described above, the user information may include user identification information, unique information, learning information, life log data, and the like of the user. The loaded user information may be provided to the processor 161 and other modules 163 to 165.
In addition, when data in the user information is changed according to a processing result of the processor 161 and other modules 163 to 165, the user information management module 162 may update the user information using the changed data. The user information management module 162 may store the updated user information in the memory 15. The user detection module 163 may detect at least one user included in the image data obtained through the camera 132 and/or the voice data obtained through the microphone 124 by using the identification information of each of the users stored in the user DB 152.
For example, the user detection module 163 may recognize a face of each of at least one user from the obtained image data by using a generally-known face recognition algorithm, and may detect a user corresponding to each of the recognized faces by using the recognized face and the identification information. As such, the identification information may include characteristic data representing facial characteristics of each of the users.
Alternatively, the user detection module 163 may recognize voice characteristics (e.g., frequency) of each of the at least one user through frequency analysis of the obtained voice data or the like, and may detect or otherwise identify a user corresponding to each of the recognized voice characteristics using the recognized voice characteristic and the identification information.
The answerer selection module 164 may select the answerer for the query message among the detected users. As described above, the answerer selection module 164 may detect at least one user having an intention to answer among the users by using the camera 132. The answerer selection module 164 may select, as the answerer, a user detected as a first person who expresses the intention to answer among the detected at least one user.
In some embodiments, the answerer selection module 164 may select the answerer based on the learning information of each of the users. For example, the answerer selection module 164 may select a user with the lowest learning level among the users as the answerer. Alternatively, the answerer selection module 164 may select a user with the smallest number of answers or a user whose latest answering date is oldest as the answerer based on the question-and-answer history of each of the users.
Alternatively, the answerer selection module 164 may arbitrarily select the answerer among the users. For example, when the users or the user having the intention to answer are not accurately recognized due to a quality problem of the image data obtained by the camera 132 or the like, the answerer selection module 164 may arbitrarily select the answerer.
The answer recognition module 165 may receive the voice and sound data through the microphone 124 after outputting the query message. The answer recognition module 165 may extract the voice of the answerer through the frequency analysis of the received voice and sound data or the like. The answer recognition module 165 may recognize the extracted voice of the answerer using a generally-known voice recognition algorithm. The answer recognition module 165 may convert the recognized voice into text.
In some embodiments, the answer recognition module 165 may receive the image data including the answerer through the camera 132 after outputting the query message. The answer recognition module 165 may recognize the answer by extracting a gesture of the answerer based on the received image data and recognizing the extracted gesture.
One example related to the operation of the robot shown in
In
The controller 16 may also obtain at least one image data through the camera 132 before, during, or after outputting the learning contents, and may recognize the users 501 to 507 based on the obtained image data.
Referring to
The controller 16 may output an answer request message 600 including a name of the detected user 506 through the sound output unit 144. The user 506 may utter an answer 610 in response to the output answer request message 600. The controller 16 may receive the answer 610 through the microphone 124 and recognize the received answer 610. The controller 16 may determine whether the answer 610 of the user 506 is correct based on the recognized answer and the correct answer data. For example, when the answer 610 of the user 506 is correct, the controller 16 may output a correct answer message 620 through the sound output unit 144.
In addition, the controller 16 may update the learning information of the user 506 (such as the learning level and/or the question-and-answer history) based on the answer 610. In some embodiments, the controller 16 may transmit the answer 610 to the server 3. The server 3 may update the learning information of the user 506 based on the received answer 610.
Although not shown, the robot 1 may generate a learning report including a learning state, a learning record, a learning level, and the like based on the learning information of each of the users stored in the user DB 152, and may output the generated learning report through the output unit 14 or transmit the generated learning report to the mobile terminal 2 or the server 3 through the communication unit 11.
According to the embodiment shown in
In addition, in a case such as a school where a large number of students are managed by one teacher, the teacher may have difficulty in managing the students. However, the learning information of the students such as the learning level or the learning state can be managed more effectively by utilizing the robot 1 according to an embodiment.
The robot 1 may generate interaction data for interacting with the user based on the stored life log data (S220). The robot 1 according to an embodiment may continuously or regularly update the user information through interaction with the user to obtain more accurate and detailed learning information or life log data about the user. Example of learning information have been described above with reference to
The controller 16 may generate the interaction data based on the life log data in order to interact with the user. For example, the interaction data may include a query message or an emotional message related to the action record or the utterance record of the user. In some embodiments, the controller 16 may generate the interaction data based on the life log data and the learning information. In some embodiments, the controller 16 may transmit the life log data to the server 3. The server 3 may generate the interaction data based on the received life log data. The controller 16 may receive the interaction data from the server 3.
The robot 1 may output the generated interaction data to interact with the user (S230). The controller 16 may output the generated interaction data through the display unit 142 and/or the sound output unit 144. The controller 16 may obtain a response of the user to the output interaction data through the camera 132 and/or the microphone 124. The controller 16 may recognize the meaning of the response by recognizing the obtained response. In some embodiments, the controller 16 may generate the interaction data based on the obtained response, and may repeatedly perform the interaction with the user.
Although not shown, the robot 1 may update the user information included in the user DB 152 based on the response of the user obtained through the interaction with the user. The controller 16 may update the learning information and/or the life log data of the user information based on a recognition result for the response of the user. Accordingly, since the robot 1 may obtain and update user information more accurately, the robot 1 may have greater management capability for the user information.
In some embodiments, the controller 16 may transmit the response of the user to the server 3. In this case, the server 3 may recognize the response and update the user information based on a result of the recognition.
The life log data collection module 166 may obtain the life log data of the user from the image data and the voice data obtained from the camera 132 and/or the microphone 124. For example, similar to the user detection module 163 (see
In addition, similar to the user detection module 163, the life log data collection module 166 may recognize the user from the voice data and extract the voice of the recognized user. The life log data collection module 166 may recognize the extracted voice of the user using a voice recognition algorithm and obtain the life log data based on a result the recognition.
The interaction data generation module 167 may generate the interaction data for interacting with the user from the life log data. The interaction data may include a message for inducing the response of the user, such as a query message related to the obtained life log data. In some embodiments, the interaction data generation module 167 may generate the interaction data based on the life log data and the learning information of the user. The processor 161 may interact with the user by outputting the interaction data generated by the interaction data generation module 167 through the output unit 14.
Based on the interaction with the user, the processor 161 may obtain the response such as a voice, a touch input, a gesture, or a facial expression of the user through the input unit 12, and recognize the obtained response. The processor 161 may update the life log data and/or the learning information based on the recognized response. Alternatively, the processor 161 may transmit the obtained response to the server 3.
The controller 16 may recognize an action, a gesture, a facial expression, a carried object, and the like of each of the users 901 to 903 from the image data 900, and may obtain the life log data of each of the users 901 to 903 based on a result of the recognition. For example, the controller 16 may recognize a picture drawing action of a second user 902 from the image data 900 and acquire the life log data representing that the second user 902 has drawn a picture based on a result of the recognition.
Referring to
The controller 16 may obtain a response 1010 to the output interaction message 1000 from the second user 902. As the controller 16 recognizes the obtained response 1010, the controller 16 may recognize that the second user 902 has drawn a ‘cloud’ and ‘sun’. Based on a result of the recognition, the controller 16 may update the life log data obtained in
Referring to
In this regard, referring to
The first robot 1a may share a result of the recognition with a second robot 1b located in a second place (S310). For instance, the controller 16 of the first robot 1a may transmit the recognition result for the presence of the target person to the second robot 1b through the communication unit 11. As an example with reference to
The second robot 1b may output information related to a location of the target person (S320). The controller 16 of the second robot 1b may output the information related to the location of the target person through the output unit 14 based on the recognition result received from the first robot 1a.
Referring to
Based on the recognition result, the controller 16 of the second robot 1b may output a notification 1320 indicating that the target person 1210 is located in the kindergarten to a user 1310 (e.g., a guardian) present in the home 1300. In other words, the user 1310 may conveniently obtain information about the location of the target person 1210 through the robots 1a and 1b.
Although the location sharing performed by using two robots 1a and 1b has been described with reference to
According to an embodiment, the robot may support learning or education for a plurality of users by managing learning information of the users through recognition and question-and-answer of the users. In other words, since the robot may support one-to-many learning, the application of the robot can be extensively increased from a home to a kindergarten, a private educational institute, or the like.
In addition, in a case such as a school where a large number of students are managed by one teacher, the teacher may have difficulty in managing the students. However, learning information of the students such as a learning level or a learning state can be managed more effectively by utilizing the robot according to an embodiment.
Moreover, the robot may continuously obtain the life log data of the user by using a camera, a microphone, and the like, and may continuously update the life log data and the learning information through the interaction based on the obtained life log data. Accordingly, the robot may obtain accurate and detailed data on the learning or an action of the user so as to effectively manage the learning of the user.
In addition, the robot may provide information on the location of the target person to the user such as a guardian through sharing information with robots disposed in different places, so that the guardian can conveniently track the location of the target person through the robots.
As described above, the technical idea of the present disclosure has been described for illustrative purposes, and various changes and modifications can be made by those of ordinary skill in the art to which the present disclosure pertains without departing from the essential characteristics of the present disclosure.
Therefore, the embodiments disclosed in the present disclosure are not intended to limit the technical idea of the present disclosure but to describe the technical idea of the present disclosure, and the scope of the technical idea of the present disclosure is not limited by the embodiments.
The scope of the present disclosure should be defined by the appended claims, and should be construed as encompassing all technical ideas within the scope of equivalents thereof.
| Number | Date | Country | Kind |
|---|---|---|---|
| 10-2018-0168554 | Dec 2018 | KR | national |
