KR101500831B1 - Method and apparatus for searching and sharing motion data using similarity of articulation - Google Patents

Abstract

A method and apparatus for searching and sharing motion data using the similarity of joints are provided. A method for searching and sharing motion data includes: maintaining a database storing a plurality of motion data applied to the robot; Acquiring target motion data corresponding to an object motion as a search query; Extracting at least one motion data retrieved based on the similarity between the plurality of motion data and the target motion data in response to the search query; And returning the retrieved at least one motion data.

Description

TECHNICAL FIELD The present invention relates to a method and apparatus for searching and sharing motion data using the similarity of joints,

The following embodiments relate to a method and apparatus for searching and sharing motion data using the similarity of joints.

Motion capture may be a task of recording the movement of a human body in digital form by attaching a sensor to a human body, using infrared rays, or the like. With the development of the technology, motion capture is possible not only in simple motion but also in very precise motion, and the field of applying motion capture is also increasing. However, in most applications of motion capture, motion data is generated by capturing motion whenever motion capture is required. In addition, even when motion data representing motion similar to motion data generated by motion capture is required, motion data is generated by capturing a new motion without using existing motion data. To this end, efforts to store existing motion data and extract desired motion data from the stored motion data are continuing.

Embodiments of the present invention provide a method and apparatus for searching and sharing motion data that can control motion of a robot by retrieving motion data corresponding to motion of an object from a database and can share motion data.

In addition, embodiments of the present invention can search and share motion data that can utilize motion data more efficiently by searching and sharing motion data that can be used in various fields such as robot control, animation, movie, game production, Device.

According to an embodiment of the present invention, there is provided a method of searching for and sharing motion data, the method comprising: maintaining a database storing a plurality of motion data applied to the robot; Acquiring target motion data corresponding to an object motion as a search query; Extracting at least one motion data retrieved based on the similarity between the plurality of motion data and the target motion data in response to the search query; And returning the retrieved at least one motion data.

Wherein the acquiring of the target motion data comprises capturing motion of the object using a motion capture device; And generating the target motion data based on the motion of the captured object.

The step of extracting the searched at least one motion data may include extracting a similarity between the plurality of motion data and the target motion data, And retrieving at least one motion data associated with the target motion data from the database using the similarity.

Wherein the step of extracting the similarity between the plurality of motion data and the target motion data comprises: classifying the target motion data and the plurality of motion data according to a plurality of joints; Calculating joint similarities of the plurality of joints with respect to the classified target motion data and the plurality of motion data; And calculating a degree of similarity between the plurality of motion data and the target motion data using joint weight values of the plurality of joints based on the degree of similarity of the joints.

The step of retrieving at least one motion data associated with the target motion data may further comprise using at least one category as a search query to retrieve at least one motion data associated with the target motion data.

According to an embodiment of the present invention, there is provided a method of searching for and sharing motion data, the method comprising: receiving a selection of motion data for controlling at least one robot among the at least one motion data retrieved from a user; And controlling the at least one robot using motion data selected by the user.

Wherein the returning of the retrieved at least one motion data comprises: sorting the retrieved at least one motion data based on the degree of similarity; And returning the retrieved at least one motion data using the ordered sequence.

The step of returning the retrieved at least one motion data comprises: classifying the retrieved at least one motion data according to a category; And returning at least one motion data classified according to the category.

The method of searching for and sharing motion data according to an embodiment of the present invention further includes the step of identifying, from the user, a frequency with which a plurality of motion data stored in the database are selected as motion data for controlling the at least one robot .

Wherein the step of returning the retrieved at least one motion data comprises: sorting the retrieved at least one motion data based on the selected frequency; And returning the at least one motion data using the ordered sequence.

The method of searching for and sharing motion data according to an embodiment of the present invention may further include the step of evaluating a plurality of pieces of motion data included in the database based on the selected frequency.

The step of returning the retrieved at least one motion data may further include providing a preview of the retrieved at least one motion data to the user.

The step of maintaining the database may include uploading the target motion data to the database.

The method of searching for and sharing motion data according to an embodiment of the present invention may further include providing predetermined points to a user who has uploaded the target motion data to the database.

The apparatus for searching and sharing motion data according to an embodiment of the present invention includes a database holding unit for holding a database storing a plurality of motion data to be applied to a robot; A target motion data obtaining unit for obtaining target motion data corresponding to the motion of the object as a search query; A motion data extracting unit for extracting at least one motion data retrieved based on the similarity between the plurality of motion data and the target motion data in response to the search query; And a motion data returning unit for returning the searched at least one motion data.

The extraction unit may extract the motion data from the motion data and the target motion data. And a motion data retrieval unit for retrieving at least one motion data related to the target motion data from the database using the similarity.

The motion data search and sharing apparatus according to an embodiment of the present invention includes: a selection receiving unit that receives a selection of motion data for controlling at least one robot among the at least one motion data retrieved from a user; And a robot controller for controlling the at least one robot using motion data selected by the user.

Embodiments of the present invention provide a method and apparatus for searching and sharing motion data that can control motion of a robot by retrieving motion data corresponding to motion of an object from a database and can share motion data.

In addition, embodiments of the present invention can search and share motion data that can utilize motion data more efficiently by searching and sharing motion data that can be used in various fields such as robot control, animation, movie, game production, Device.

1 is a diagram for explaining an example of a method of searching for and sharing motion data according to an embodiment.
2 is a flowchart illustrating a method of searching for and sharing motion data according to an embodiment of the present invention.
FIGS. 3A and 3B are diagrams for explaining the retrieved motion data according to an embodiment.
4 is a diagram for explaining a database according to an embodiment.
5 is a block diagram for explaining a motion data search and sharing apparatus according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, the present invention is not limited to or limited by the embodiments. In addition, the same reference numerals shown in the drawings denote the same members.

1 is a diagram for explaining an example of a method of searching for and sharing motion data according to an embodiment.

Referring to FIG. 1, a motion data search and sharing apparatus 110 according to an exemplary embodiment of the present invention may include a motion capture apparatus 111, a database 112, and a control unit 113. Specifically, the motion capture device 111 may include at least one of a vision camera, a vision sensor, and a motion recognition sensor (e.g., a kinetic device) for capturing the motion of the user 120. Then, the control unit 113 can convert the motion of the user captured by the motion capture device 111 into motion data (e.g., three-dimensional motion data). Then, the control unit 113 can retrieve motion data similar to the converted motion data from the database 112. [ At this time, the controller 113 can search motion data similar to the converted motion data by using the similarities of the joints of the plurality of motion data stored in the database 112 and the joints of the converted motion data. The controller 113 may return a plurality of searched motion data to the user 120 and the user 120 may select at least one of the plurality of searched motion data. The motion data search and sharing device 110 can control the plurality of robots 130 to 150 using the motion data selected by the user. Then, the user 120 can store the converted motion data in the database, so that other users can use the motion data stored by the user.

For example, if the user 120 briefly operates speech, the motion capture device 111 may capture the speech of the user 120. The control unit 113 may convert the motion of the captured user 120 into motion data and retrieve motion data similar to the converted motion data from the database 112. [ Thus, although the user 120 has briefly operated speech, it can retrieve and select motion data relating to correct speech activity from the database 112. Then, by controlling the plurality of robots 130 to 150 using the motion data related to the correct speech dancing operation, the plurality of robots 130 to 150 can perform correct speech dancing operations.

2 is a flowchart illustrating a method of searching for and sharing motion data according to an embodiment of the present invention.

Referring to FIG. 2, a method for searching and sharing motion data according to an embodiment (hereinafter, referred to as a method for searching and sharing motion data) may maintain a database storing a plurality of motion data applied to the robot (210). Here, the motion data is the motion of the object stored in a file format. In the case of a human being, the human body is represented by a plurality of joints (for example, 17 to 23 joints), and x, y, z The amount of change and the amount of rotation about the shaft. At this time, in one embodiment, the amount of rotation may mean the amount of rotation of the respective joints in accordance with the vertical rotation (pitch), the left-right rotation (Yaw), and the forward rotation (roll). And, among the plural joints, the major joints may include joints such as head, chest, right shoulder, elbow, wrist, pelvis, knee, and ankle. Then, the motion data is applied to the robot to control the motion of the robot. Then, the database can store a plurality of motion data. Specifically, the database may include information such as file name, category, description, frame count, and frequency of selection of motion data. Then, the user can share the motion data with other users by uploading the motion data to the database. More specifically, as described below, the user may capture the motion of the object to obtain the target motion data. Then, not only the similar motion data is retrieved from the database using the target motion data, but also the target motion data uploaded to other users can be shared by uploading the target motion data to the database. At this time, one embodiment may provide a predetermined point to the user who uploaded the target motion data to the database. For example, for the user who uploaded the target motion data, the step 210 may provide a predetermined point, and the user may download the motion data uploaded by another user using the provided point.

In addition, the method of searching for and sharing motion data may acquire target motion data corresponding to the motion of the object as a search query (220). Specifically, the method for searching and sharing motion data can use target motion data as a search query to retrieve motion data from a database. Here, the target motion data may be a data file representing the motion of the object in the real world. More specifically, step 220 may capture motion of an object using a motion capture device. In this case, the motion capture device may include at least one of a vision camera, a vision sensor, or a motion recognition sensor, and the object may refer not only to a person but also to any object capable of moving, such as an animal, a machine, or the like. Then, step 220 may generate the target motion data based on the motion of the captured object. For example, step 220 may digitize the motion of the captured object and extract the physical quantities such as the mass, length, mass center, and mass momentum of the plurality of joints to generate the target motion data have. And, in one embodiment, the target motion data may be composed of a forming part constituting the information of the joints and an operating part constituting the rotation of the joint. The target motion data may include information on the amount of change with respect to each of the x, y, and z axes of the joints, and may be determined according to the pitch, yaw, And information about the amount of rotation. The target motion data may be used as a search query for searching other motion data, or may be stored in a database and shared with other users.

Also, the method for searching and sharing motion data may extract 230 at least one motion data retrieved based on the similarity between the plurality of motion data and the target motion data, in response to the search query. Specifically, step 230 may extract the similarity between the plurality of motion data and the target motion data. At this time, the motion data having a high degree of similarity may exhibit motion similar to the target motion data, and thus the degree of similarity may serve as a reference for providing accurate search results to the user. More specifically, the step 230 may classify the target motion data and the plurality of motion data according to a plurality of joints. For example, if the object is a person, step 230 may classify the human body according to major joints such as the head, chest, right shoulder, elbow, wrist, pelvis, knee, Then, the step 230 may calculate the degree of similarity of the plurality of joints with respect to the classified target motion data and the plurality of motion data. In this case, the step 230 may include information on the amount of change with respect to the x, y, and z axes and information on the amount of change in the vertical and horizontal directions of the target motion data and the plurality of motion data, It is possible to extract information on the amount of rotation according to the roll. By comparing the amount of change and the amount of rotation of the target motion data with the amount of change and the amount of rotation of a plurality of motion data for each joint, it is possible to calculate the degree of similarity between the target motion data and the plurality of motion data.

In step 230, the similarity between the plurality of motion data and the target motion data may be calculated using joint weight values of the plurality of joints based on the degree of similarity per joint. Specifically, the degree of importance of each joint may be different according to the motion indicated by the motion data. For example, when the motion data represents the arm motion, the amount of change and the amount of rotation may be larger in the arm portion than in the leg portion. This may mean that the motion of the arm rather than the motion of the legs may be important in determining the degree of similarity. Therefore, in this case, the weight of the joint of the arm portion (for example, the right and left shoulders, the wrist, and the elbow joint) may be higher than the weight of the joint of the leg portion (for example, the pelvis, the knee, and the ankle joint). At this time, in one embodiment, the joint-specific weight may be set based on a joint amount of change and rotation amount of motion data, or may be set according to a predetermined numerical value. In step 230, similarity between the plurality of motion data and the target motion data is calculated. For the joints having a high weight by joint, It is possible to less reflect the similarity of stars. Thus, step 230 can more accurately calculate the similarity between the plurality of motion data and the target motion data.

Then, step 230 may retrieve at least one motion data associated with the target motion data from the database using the similarity between the plurality of motion data and the target motion data. Accordingly, the step 230 can extract motion data having high similarity to the target motion data from the database. Then, step 230 may use the category as a search query to retrieve at least one motion data associated with the target motion data. Here, the category may be one or more. In this case, one embodiment may use the target motion data and the category simultaneously as a search query, or only one of the target motion data or the category may be used as a search query. Alternatively, the category may be used as a secondary search query after using the target motion data as a primary search query, or the target motion data may be used as a secondary search query after using the category as a primary search query.

In addition, the method of searching for and sharing motion data may return at least one motion data retrieved (240). Specifically, the step 240 may provide the user with at least one motion data retrieved, which is a search result corresponding to the search query, after the user inputs the search query, Can be selected. At this time, although a small amount of motion data may be searched according to the search query, a very large amount of motion data may be searched. Accordingly, in order to efficiently search the user, step 240 may provide search results sorted according to preset criteria. Here, the predetermined criteria may include the degree of similarity, the frequency of selection, and the category.

More specifically, if the preset criteria is similarity, step 240 may arrange at least one motion data retrieved based on the similarity. Then, at least one motion data retrieved using the sorted order can be returned. In this case, generally, one motion data searched can be sorted in descending order from the order of high similarity to the order of low order. Accordingly, the user can preferentially search for motion data having high similarity, so that the user can search for desired motion data more quickly.

If the preset reference is a selection frequency, step 240 can identify the frequency with which the plurality of motion data stored in the database is selected by the user as motion data for controlling at least one robot. Specifically, when motion data is selected as motion data for controlling the robot, the method of searching and sharing motion data may store the number of times the motion data is selected from the user in the database. Accordingly, step 240 may refer to the database to identify the frequency with which a plurality of motion data stored in the database is selected. Then, step 240 may sort the at least one motion data retrieved based on the selected frequency and return at least one motion data using the ordered sequence. Accordingly, the user can preferentially receive motion data with a high frequency of selection, that is, motion data having a high degree of popularity, so that the user can perform the search more conveniently.

And, one embodiment may evaluate a plurality of motion data included in the database based on the selected frequency. In general, motion data with a high frequency selected by users is more accurate than motion data with other frequencies, while motion data with a low frequency selected may show incorrect motion than other motion data. Accordingly, the step 240 may assign a high score to the motion data having a high frequency of selection and a low score to the motion data having a low frequency of the selected frequency. Then, the user can select the motion data for controlling the robot by referring to the scores added to the plurality of motion data.

And, if the preset reference is a category, step 240 may classify the at least one motion data searched for by category. Here, the category may indicate the attribute of the motion data. And, one category may include at least one subcategory so that the at least one motion data searched can be classified in detail. For example, if the first category is a person, the second category, which is a subcategory of the first category, may be a sport, and the third category, which is a subcategory of the second sport, may be soccer. Then, step 240 may return at least one motion data classified according to the category.

In one embodiment, the similarity, the frequency of selection, and the category, which are preset criteria, can be combined. For example, if the preset reference is a degree of similarity and a frequency of selection, the user can return to the user in step 240 by arranging the frequency of motion data with high degree of similarity and high frequency of motion. If the preset reference is the similarity degree, the selection frequency, and the category, the step 240 may provide the user with motion data having a high degree of similarity and a high selection frequency per category.

And, step 240 may provide a preview of at least one motion data retrieved. Specifically, if only the file name, description, etc. of at least one motion data searched for by the user is provided, the user can select the motion data without recognizing the specific motion of the motion data. In this case, since the user can select the undesired motion data, step 240 may provide the user with the motion represented by the motion data using the preview. In one embodiment, step 240 may convert the motion data that the user desires to preview into image data and provide the converted image data to the user. And, when converting motion data to image data, step 240 may convert only the approximate motion data of the motion data or the overall motion data of the motion data. Also, in another embodiment, step 240 may convert the motion data into a thumbnail image and provide it to the user.

Then, step 240 may receive a selection of motion data for controlling at least one of the at least one motion data retrieved from the user. In this case, step 240 may receive a selection of one or more motion data from the user. The method for searching and sharing motion data may control at least one robot using motion data selected by the user. Accordingly, although the method of searching for and sharing motion data is based on the approximate movement of the object, it is possible to provide the motion data indicating the accurate movement intended by the user, and to control at least one robot using the motion data .

FIGS. 3A and 3B are diagrams for explaining the retrieved motion data according to an embodiment.

Referring to FIG. 3A, the search results 310 and 320 may display a search result screen for returning the retrieved motion data. Specifically, when a user performs a jump shot operation of basketball, a method of searching and sharing motion data may convert a user's motion into target motion data. When inputting the target motion data into the search query, the motion data similar to the target motion data can be retrieved based on the similarity between the plurality of motion data stored in the database and the target motion data. In this case, the method of searching and sharing motion data can provide a category, a file name, a description, a selection number, and the like of the searched motion data. In this case, when the user aligns the retrieved motion data in order of similarity, the method of searching and sharing motion data may provide a screen such as the search result 310. [ In the example of the search result 310, since the target motion data indicates the jump shoot operation of the basketball, the method of searching and sharing motion data can preferentially provide the user with motion data similar in this action. At this time, when the user selects motion data having a file name of basket 7, the method of searching and sharing motion data can control the robot to perform the jump shooting operation of Michael Jordan according to the selected motion data.

In addition, when the user sorts the retrieved motion data in order of popularity, the method of searching and sharing motion data may provide motion data such as the search result 320. [ Accordingly, the method of searching for and sharing motion data can provide the user with motion data retrieved in the order of highest frequency selected from the users, regardless of category, similarity, or the like. At this time, when the user selects preview of the motion data having the file name child231, the method of searching and sharing the motion data can provide the motion (i.e., preview) indicated by the motion data having the file name child231. In this case, one embodiment may provide a preview of the motion data to the user using a pop-up window.

Referring to FIG. 3B, the search result 330 may indicate a search result screen for returning the retrieved motion data, and the search screen 340 may display a screen when the target motion data and the category are used as a search query . Specifically, when the user arranges the motion data searched for by category, the method of searching for and sharing motion data may provide motion data such as the search result 330. [ In this case, the method of searching and sharing motion data can provide a predetermined number of pieces of motion data for each category. In addition, the user can select any one category among all the categories, so that the method of searching and sharing motion data can provide only motion data corresponding to the selected category. And, as in the example of the search result 330, the user can select the popularity and the category by the sorting method. Accordingly, the method of searching for and sharing motion data can provide motion data with a high frequency of selection for each category.

In addition, the search screen 340 may display a screen when the target motion data and the category are used as a search query. Specifically, the method of searching for and sharing motion data can use not only target motion data but also a category as a search query, thereby providing a search result of a category desired by the user. In the example of the search screen 340, when the user selects soccer as the category 341 and selects abc0001 as the target motion data 342, the method of searching and sharing motion data is the same as the motion data similar to the target motion data abc0001 The motion data in which the category is soccer can be provided to the user as a search result. In this case, in one embodiment, the motion data search and sharing method captures the motion of the object in real time, converts the motion data into motion data, and then uses the motion data converted in real time to search for similar motion data.

4 is a diagram for explaining a database according to an embodiment.

Referring to FIG. 4, the database 410 may store a plurality of motion data to be applied to the robot. At this time, the database 410 may include a filename field, a category field, a description field, an uploader field, a storage time field, a selection frequency field, and a frame count field. Specifically, the file name field can indicate the file name of the motion data. And, the category field can represent the attribute of the motion data, can be plural, and each category can include subcategories. The description field indicates a description of the motion data. The description field may be input by a user uploading to the database, or a method of searching for and sharing motion data may be set after analyzing the motion data. In addition, the uploader field may include information on a user who uploaded the motion data, and the storage time field may include information on the time when the motion data is stored. And, the selection frequency field may include information on the frequency with which the motion data is selected as motion data for controlling the robot to the user, and the frame count field may include information on the number of frames included in the motion data . In addition, the database 410 may include fields shown in FIG. 4 as well as other fields for indicating information on motion data.

5 is a block diagram for explaining a motion data search and sharing apparatus according to an embodiment.

Referring to FIG. 5, the database maintenance unit 510 may maintain a database for storing a plurality of motion data applied to the robot.

In addition, the target motion data acquisition unit 520 may acquire target motion data corresponding to the motion of the object as a search query.

In addition, the motion data extracting unit 530 may extract at least one motion data retrieved based on the similarity between the plurality of motion data and the target motion data, in response to the search query.

In addition, the motion data return unit 540 may return at least one motion data that is searched.

The contents described in FIG. 1 through FIG. 4 may be applied to the motion data search and sharing apparatus shown in FIG. 5, so that detailed description will be omitted.

The method according to an embodiment may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions to be recorded on the medium may be those specially designed and configured for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. For example, it is to be understood that the techniques described may be performed in a different order than the described methods, and / or that components of the described systems, structures, devices, circuits, Lt; / RTI > or equivalents, even if it is replaced or replaced.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (21)

Maintaining a database storing a plurality of motion data to be applied to the robot;
Acquiring target motion data corresponding to an object motion as a search query;
Extracting at least one motion data retrieved based on the similarity between the plurality of motion data and the target motion data in response to the search query; And
Returning the retrieved at least one motion data
Lt; / RTI >
The step of returning the retrieved at least one motion data
Arranging the searched at least one motion data based on the similarity; And
And returning the retrieved at least one motion data using the sorted order
And searching for the motion data.
The method according to claim 1,
The step of obtaining the target motion data
Capturing a motion of the object using a motion capture device; And
Generating the target motion data based on the motion of the captured object
And searching for the motion data.
The method according to claim 1,
The step of extracting the retrieved at least one motion data
Extracting a degree of similarity between the plurality of motion data and the target motion data; And
Retrieving at least one motion data associated with the target motion data from the database using the similarity,
And searching for the motion data.
The method of claim 3,
The step of extracting the similarity between the plurality of motion data and the target motion data
Classifying the target motion data and the plurality of motion data according to a plurality of joints;
Calculating joint similarities of the plurality of joints with respect to the classified target motion data and the plurality of motion data; And
Calculating a degree of similarity between the plurality of motion data and the target motion data using the joint weight of the plurality of joints based on the degree of similarity per joint,
And searching for the motion data.
The method of claim 3,
Wherein the step of retrieving at least one motion data associated with the target motion data
Searching at least one motion data associated with the target motion data using a category as a search query
Further comprising the step of:
The method according to claim 1,
Receiving a selection from the user for motion data for controlling at least one of the retrieved at least one motion data; And
Controlling the at least one robot using motion data selected from the user
And searching for the motion data.
delete delete The method according to claim 6,
Identifying from the user a plurality of motion data stored in the database as frequency of motion data for controlling the at least one robot,
Further comprising the step of:
10. The method of claim 9,
The step of returning the retrieved at least one motion data
Sorting the searched at least one motion data based on the selected frequency; And
Returning the at least one motion data using the ordered sequence
Further comprising the step of:
10. The method of claim 9,
Evaluating a plurality of motion data included in the database based on the selected frequency;
Further comprising the step of:
The method according to claim 1,
The step of returning the retrieved at least one motion data
Providing a preview of the retrieved at least one motion data to a user
Further comprising the step of:
The method according to claim 1,
The step of maintaining the database
Uploading the target motion data to the database
And searching for the motion data.
14. The method of claim 13,
Providing a predetermined point to a user who has uploaded the target motion data to the database
Method for searching and sharing motion data further comprising
delete A database holding unit for holding a plurality of motion data to be applied to the robot;
A target motion data obtaining unit for obtaining target motion data corresponding to the motion of the object as a search query;
A motion data extracting unit for extracting at least one motion data retrieved based on the similarity between the plurality of motion data and the target motion data in response to the search query; And
And a motion data returning unit for returning the searched at least one motion data,
The motion data return unit
Sorting the searched at least one motion data based on the similarity, and returning the searched at least one motion data using the sorted order,
Motion data search and sharing device.
17. The method of claim 16,
The motion data extraction unit
A similarity extraction unit for extracting a similarity between the plurality of motion data and the target motion data; And
A motion data search unit for searching at least one motion data related to the target motion data from the database using the similarity,
And a motion data searching and sharing device.
17. The method of claim 16,
A selection receiver for receiving a selection of motion data for controlling at least one robot among the searched at least one motion data from a user; And
A robot controller for controlling the at least one robot using motion data selected by the user,
And a motion data searching and sharing device. Maintaining a database storing a plurality of motion data to be applied to the robot;
Acquiring target motion data corresponding to an object motion as a search query;
Extracting at least one motion data retrieved based on the similarity between the plurality of motion data and the target motion data in response to the search query; And
Returning the retrieved at least one motion data
Lt; / RTI >
The step of returning the retrieved at least one motion data
Classifying the searched at least one motion data according to a category; And
Returning at least one motion data classified according to the category
And searching for the motion data.
A database holding unit for holding a plurality of motion data to be applied to the robot;
A target motion data obtaining unit for obtaining target motion data corresponding to the motion of the object as a search query;
A motion data extracting unit for extracting at least one motion data retrieved based on the similarity between the plurality of motion data and the target motion data in response to the search query; And
And a motion data returning unit for returning the searched at least one motion data,
The motion data return unit
Classifying the searched at least one motion data according to a category and returning at least one motion data classified according to the category,
Motion data search and sharing device.
A computer-readable recording medium on which a program for performing the method of any one of claims 1 to 6, 9 to 14, and 19 is recorded.

Images