JP2993867B2 - Robot system that responds variously from audience information - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a robot system, and more particularly, to a robot system which performs various responses from audience information.

[0002]

2. Description of the Related Art Conventionally, as a robot used for various events and the like and capable of performing two-way communication with a spectator, for example, a spectator's reaction sound such as applause or cheering, a spectator's spoken word, etc. are specified. By identifying the audience information and performing corresponding actions and audio output,
Various proposals have been made to enable dialogue with individuals or groups.

[0003]

Many of the above-mentioned conventional robots are designed to always perform the same operation for the same contents of the audience information. For example, if applause comes, the robot always performs a joyful operation. The operation pattern was uniform. As a result, there is a disadvantage that the audience can immediately recognize the operation pattern of the robot, and the expectation for the next operation is spoiled.

[0004] It is an object of the present invention to provide a robot system in which the robot has various operation patterns with respect to specific audience information and can increase the expectation of the audience for the next operation.

[0005]

SUMMARY OF THE INVENTION The present invention relates to a robot system which performs various responses from spectator information. In order to solve the above-mentioned problems, the first configuration is as follows.
It is characterized by including the following requirements. Audience information detection means: Detects specific audience information including at least one of sound information and visual information from the audience. Robot operation unit: Performs any one of a plurality of predetermined operations corresponding to the audience information to the audience. Operation data storage means: stores operation data corresponding to the plurality of operations. Data selection means: Selects any one of the stored operation data. Robot control unit: controls the robot operation unit based on the selected operation data.

In the above-mentioned robot system, a plurality of robot operation data are prepared for one or a plurality of specific spectator information, and a robot operation unit is selected based on one of the operation data selected by the data selection means. Is controlled. As a result, the robot selects and executes an arbitrary one of a plurality of operation patterns for the same audience information, so that the operation is not uniform, and thus a robot system capable of various operations and expressions. Can be realized.

Here, the data selection means can be provided with a random number generation means, and the operation data can be automatically selected based on the random numbers generated by the random number generation means. In this way, since the motion data is selected at random based on the random numbers, it is difficult to predict the next motion performed by the robot, and thus the audience can be excited about “what will happen next”.

[0008] The above robot system can be further configured to include the following requirements. Waveform detecting means: provided in the audience information detecting means for detecting a waveform of sound information. Waveform data storage means: stores waveform data of a plurality of pieces of sound information. Sound information discriminating means: The type of sound information is discriminated by comparing the waveform of the sound information detected by the waveform detecting means with the waveform data stored in the waveform data storage means. Operation data storage means: Stores a set of operation data corresponding to each piece of sound information to be determined. Correspondence storage means: A plurality of types of correspondence between sound information and motion data are stored. Correspondence selection means: Selects any of the stored correspondences. The data selection means selects the operation data corresponding to the determined sound information based on the correspondence selected by the correspondence selection means.

In the robot system configured as described above, the type of sound information such as applause, laughter, booing, and throbbing of the audience is determined by detecting the waveform.
A specific robot operation or correspondence is assigned to each of the determined sound information. The correspondence between the sound information and the robot operation is selected from a plurality of types prepared at any time. According to the selected correspondence, the operation content of the robot with respect to the detected sound information is determined. It is determined. Thereby, the operation content of the robot with respect to various kinds of sound information can be further diversified.

Here, a random number generating means may be provided in the correspondence selecting means, and the correspondence may be automatically selected based on a random number generated by the random number generating means. If the selection (or change) of the correspondence based on such random numbers is performed during the operation of the robot, it is possible to give the audience the impression that the character of the robot has suddenly changed in the middle. Change,
In other words, it is possible to give the robot a "whimsical" character.

Next, a second configuration of the robot system according to the present invention is characterized by including the following requirements. Audience information detection means: detects specific audience information including sound information from the audience. Robot operation unit: performs a predetermined operation corresponding to the detected sound information. Operation data storage means: stores operation data corresponding to the above operation. Volume detection means: detects the volume of the sound information. Robot control means: reads operation data corresponding to the sound information detected by the audience information detection means from the operation data storage means, controls the robot operation part based on the read operation data, and controls The magnitude of the operation by the robot operation unit is changed based on the detected volume. Here, the robot control means can be configured to increase the operation by the robot operation unit as the detected volume is higher.

In the robot system having the above configuration,
Even if the type of audience information is the same, if the sound volume changes, the magnitude of the robot operation corresponding to the sound information changes, for example, if "applause" corresponds to "applause" operation If the volume of the applause is large, the robot is controlled to perform an operation that makes the robot exaggerate. As a result, it is possible to further change the operation or response of the robot to the sound information, and the effect of appealing to the audience is improved.

The first and second configurations of the robot system can be combined with each other, thereby realizing a more emotional operation of the robot.

Here, in the above first and second configurations, the audience information detecting means detects at least two types of applause, roar, laugh, cheer, and boo of the audience as sound information. Can be configured.
In addition, it can be configured to include a word detection unit that detects one or more words pronounced by the audience, and word identification means for identifying the detected words. In addition, the motion data may include data corresponding to at least one of joy, discouragement, sadness, and anger.

[0015]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Some embodiments of the present invention will be described below with reference to the drawings. FIG. 1 shows a configuration example of the robot system of the present invention. The robot system 100
Robot 101 (robot operation unit) and robot control unit 1
02.

As shown in FIG. 2, the robot 101 has a skeleton 19 having the following skeleton units connected to each other by joint mechanisms 31 to 37. Head 20: Eye 20a and mouth 20 that can be driven respectively
c, and a blinkable lamp 20b is arranged in the eye 20a. The opening 20c can be opened and closed. Here, as shown in FIG. 1, the opening / closing drive of the mouth 20 c is controlled by the mouth opening / closing control unit 111, and the blinking of the lamp 20 b is controlled by the lamp lighting control unit 112. Further, a speaker 115 for the robot 101 to output a message or the like by voice is provided corresponding to the mouth 20c,
The amplifier 114 and the voice synthesizer 113 are connected to this. The opening and closing of the mouth 20c is controlled in synchronization with the audio output from the speaker 115. The speaker 115 may be provided integrally with the robot 101 or may be provided separately from the robot 101. -Shoulder 21, spine 22, hip bone 23: these are joined together to form a body. -Left and right arms: provided with a humerus 24, a lower humerus 25, and a wrist 29, respectively. Left and right legs: provided with an upper limb bone 26, a lower limb bone 27, and an ankle 30, respectively. Here, each skeleton unit is driven by a skeleton drive actuator 110 (FIG. 1) such as a pulse motor, a servo motor, or a piston cylinder provided in the joint mechanisms 31 to 37, and its drive control is performed by the skeleton drive control unit of FIG. 109 performs.

Next, the robot controller 102 includes an I / O port 150, a CPU 151 connected to the I / O port 150, and a RAM.
152, a ROM 153, and the like. In this embodiment, the CPU 151 includes a data selection unit, a random number generation unit,
The ROM 153 and the RAM 152 are the main components of the operation data storage unit and the correspondence storage unit.

A reaction sound detecting microphone 105 is connected to the I / O port 150 via an amplifier 104 and an A / D converter 103. As shown in FIG. 3, for example, as shown in FIG. 3, the microphone 105 is installed above a stage 250 where the robot 101 operates in a hall, an event hall, or the like, and has a reaction sound 253 from a spectator 252 accommodated in a spectator seat 251. Is detected. On the other hand, a word detection microphone 108 for detecting a word spoken by a specific audience is connected to an I / O port 150 via an amplifier 107 and an A / D converter 106.

Next, the I / O port 150 is provided with an image sensor such as a two-dimensional CCD sensor (hereinafter simply referred to as CCD sensor) 120 as means for detecting visual information. The CCD sensor 120 includes a sequencer 121, an amplifier 122, an A / D converter 123, and a sensor output of two.
It is connected to an I / O port 150 via a sensor controller 119 having a comparator 124 for converting into a value. For example, as shown in FIG. 4, such a CCD sensor 120 is installed at a position above the stage 250 so as to look into the spectator seat 251, and as shown in FIG. 5, an image of a group of spectators 252 seated in the spectator seat 251. Is detected. The CCD sensor 120 and the aforementioned microphones 105 and 108 form the main part of the audience information detecting means.

Returning to FIG. 1, to the I / O port 150, the above-described skeleton drive control unit 109, mouth opening / closing control unit 111, lamp lighting control unit 112, and voice synthesis unit 113 are connected.

The ROM 153 stores the following programs and data. (1) Robot operation control program 154: Operation data 1
62 (described later) while selecting the skeleton 19 shown in FIG.
The robot 101 controls the driving of the mouth 20c, the blinking of the lamp 20b, and the sound output from the speaker 115.
Perform a predetermined operation. (2) Reaction sound determination program 155: Reaction sound detection microphone 1
05 identifies the type of the reaction sound of the audience detected and calculates the sound volume. (3) Word identification program 156: Word detection microphone 108
Identifies the type of the word to be detected, and calculates its volume. (4) Image identification program 157: Visually detects the number of spectators based on the spectator images detected by CCD sensor 120. (5) Random number generation program 158: Generates random numbers required for the selection processing of operation data 162 and the like.

(6) "Applause" standard waveform data 159, "laughing" standard waveform data 160, "booing" standard waveform data 161: standard waveform data of audience "applause" sound, "laughing" sound, "booing" sound And serves as reference data for identifying the type of audience reaction sound detected by the reaction sound detection microphone 105. (7) Motion data 162: each skeleton drive actuator 11 for causing the robot 101 to execute a predetermined motion
0 operation data is given. According to the type of the operation, FIG.
Many types of data are prepared as shown in, for example, in addition to motion data related to the emotional expression motion of the robot, such as "joy", "disappointment", "anger", "pride", "sadness", Other motion data includes, for example, data of a motion to dance to music. (8) Voice data 163: data of a robot voice (message, singing voice, etc.) output from the speaker 115 in accordance with the above-described robot operation. FIG. 7 shows the contents. (9) Word waveform data 164: includes waveform data of various words, and serves as reference data for identifying the type of word detected by the word detection microphone 108.

As shown in FIG. 8, the RAM 152 has the following programs or data storage sections. (1) Audience image data storage unit 165: CCD sensor 120
Stores the image data of the audience to be detected. (2) Reaction sound waveform data storage unit 166: Stores the waveform data of the reaction sound of the audience detected by the reaction sound detection microphone 105. (3) Word waveform data storage 167: Word detection microphone 10
8 stores the waveform data of the word to be detected. (4) Robot operation control program storage section 168: Stores a robot operation control program 154. (5) Operation data storage unit 169: Stores operation data used in the robot operation control program 154. It has storage areas R1 to R16 for individually storing data selected from the operation data 162 in FIG. (6) Voice data storage unit 170: stores voice data used in the robot operation control program 154. It has storage areas M1 to M16 for individually storing audio data selected from the audio data in FIG.

Hereinafter, the operation and the flow of processing of the robot system 100 will be described with reference to flowcharts. First,
In FIG. 9, a process of deciding the contents of an operation to be performed by the robot 101 with the activation of a robot operation control program (hereinafter, referred to as an operation control program) 154 (FIG. 1) and storing the operation data 162 for that in the RAM 152. Is performed (S1 to S15). The operation data 16
The outline of the flow of the operation of the robot 101 based on 2 is as follows. That is, after appearing on the stage (S16 in FIG. 10), the robot 101 visually detects the number of spectators by the CCD sensor 120 and performs an operation according to the detection result (S17 to S26). next. Sing a song while dancing to the music (FIG. 11, S27 to S29), detect the audience's reaction sound after the song is completed, and perform an operation according to the detected content (FIG. 1).
1 and FIG. 12, S30 to S49). Finally, the word content issued by one of the spectators is identified, and an operation is performed in accordance with the identification result (FIG. 13, S50 to S60).

The motion of the robot 101 along the above flow reflects a relatively obedient personality pattern (hereinafter, referred to as an obedient operation pattern), for example, when the applause comes, the joy is straightforward, and when the boo comes, the user gets angry. Conversely, one of the motion patterns (hereinafter referred to as rebellious motion patterns) that reflects a rebellious or blunt personality, such as taking an angry or sullen attitude for applause and rejoicing for booing, (S1 ~ S3).

When the obedient operation pattern is selected, the storage areas R1 to R9 of the operation data storage section 169 are selected.
Operation data 201 to 209 (FIG. 6) are stored in (FIG. 8) (S4). Further, the storage areas M1 to M9 of the voice data storage unit 170 store the robot 1 corresponding to the operation data.
Voice data 501 to 509 indicating the content of the message 01
(FIG. 7) is stored (S5). When the rebellion operation pattern is selected, the operation data 301 to R1 to R9 are stored.
309 stores audio data 601 to 609 in M1 to M9, respectively (S6, S7). In the present embodiment, one of the above two operation patterns is determined based on the remainder when the generated random number F1 is divided by 2 (hereinafter, simply referred to as “based on the value of the random number F1”). Although it is automatically selected, for example, the input unit 12 shown in FIG.
The user may manually select a desired item by performing an input for selection using the number 1.

Next, based on the identification result of words uttered by the audience, operation data 401 to 403 for causing the robot 101 to perform an operation are stored in storage areas R13 to R15, and corresponding audio data 701 to 703 are stored. Storage area M
13 to M15. Also, the robot 101
Is stored in the storage area R16 (S8, S9). As shown in FIG. 7, the singing voice data of the robot 101 includes a version (704) recording a singing voice of a professional singer and a version (705) recording a slightly poor singing voice of an amateur. There are three types of tone correction versions (706), any one of which is selected based on the value of the random number F2 and stored in the storage area M16 (S10 to S1).
Five). In this way, after the singing of the robot 101 is completed, the audience can be expected to react differently depending on the type of singing voice, and the effectiveness of making the operation pattern of the robot 101 different according to the audience's reaction sound is enhanced. Will be done.

Subsequently, the flow proceeds to FIG. 10, and in S16, the robot 101 is caused to perform an operation to appear on the stage 250 (FIG. 3 and the like). Then, the detection output of the CCD sensor is read in S17, and it is determined whether the number of spectators exceeds a predetermined value N based on the output (S17, S18). Here, if the entire audience seat 251 is uniformly colored with clear and dark colors, the image of the audience 252 by the CCD sensor 120 may be darker than the background audience seat 251 as shown in FIG. Can be determined based on whether or not the audience is bright, and it is possible to detect how much the audience is present from the area ratio of the image of the audience 252 to the area of the image detection visual field 120a.

Returning to FIG. 10, when the number of spectators is N or more, the data is stored based on the operation data and voice data stored in the storage units R1, R2, M1, and M2 (S19 to S22). Based on the operation data and audio data stored in the sections R3, R4, M3, M4 (S23 to S26), different operations and audio outputs are performed respectively. For example, taking the case where the obedience operation pattern is selected as an example, if the number of spectators is N or more, the robot 101 spreads both arms while saying "Wow,
Great customer. I'll do my best today. "And then pick up the microphone vigorously and say," Then, today's first kiku. " On the other hand, if the value is N or less, the robot 101 looks down and takes a disappointed pose, utters "Now, that's all for today. I'm lonely if there is no customer." Just pick up the microphone and start singing reluctantly.

On the other hand, if the rebellious motion pattern is selected, if the number of spectators is N or more, a pose in which the right hand is placed on the waist and the user is inclined and poses, saying, "There are many. "I guess." And then slowly picked up the microphone and said, "Ginger. Also, if it is less than N, take a guts pose and say, "Is this the way it is. It's fine. I'm more cheerful if there are few customers." Say, "Okay, that's the first song. I'll sing today." In the following description, description will be given on behalf of a case where the obedient operation pattern is selected.

Next, the process proceeds to S27 in FIG.
The process of singing along with the karaoke music while performing with the microphone is performed (S27 to S29). When the song ends in S29, the robot 101 sets the reaction sound detection microphone 10
The reaction sound of the audience detected by 5 is “applause”, “laughing”,
A different operation is performed depending on which of the “boos” and whether the volume is equal to or higher than the predetermined value Q (FIG. 12, S39 to S49). Here, as the operation data, three each of five types of operation data and voice data stored in the storage areas R5 to R9 and M5 to M9 (FIG. 8) are selected based on the value of the random number F3. Transferred to storage areas R10-R12 and M10-M12 (S30-S12)
38).

The selection method is, for example, in the case of an obedient operation pattern, the above-mentioned five types of operation data are arranged in order from the top in FIG.
6: "Have a small life", 207: "Rip your right hand on your waist", 208: "Walk down and wobbly", and 20
9 "The crouching of the face with both hands" means that the upper one has a greater degree of joy, and the lower one has a greater degree of sadness or discouragement. If the remainder obtained by dividing the random number F3 by 3 is 0, the upper three 205
When ２０７207 is 1, the middle three 206２０８208
, And in the case of 2, the lower three 207 to 209 are selected. Similar selections are made for the audio data 505 to 509.

Then, in S41 of FIG. 12, the type of the reaction sound is determined. If a "clapping" with a sound volume equal to or higher than Q is detected, the operation based on the data stored in the storage areas R10 and M10 and the sound output are executed (S43, S4).
Four). In addition, when “applause” having a volume lower than Q is detected, “laughing” is detected regardless of the volume, and “booing” having a volume lower than Q is detected, R11
The operation based on the data stored in M11 and the audio output are executed (S45, S46). Then, when a "boo" having a volume of Q or more is detected, the operation based on the data stored in R12 and M12 and the audio output are executed (S48 to S49).

For example, in FIG. 6 and FIG. 7, when the upper three of the motion data 205 to 209 and the voice data 505 to 509 are selected, the robot 101 Performs a great joy of saying, "Well, I may be a pro." Well done. "
And perform a little joyful action. On the other hand, even when a loud boo with a volume of Q or more occurs, the right hand is put on the waist, and "Well, this is what it is." Such an operation pattern of the robot 101 can be seen as reflecting a relatively cheerful state in which the mood is enhanced when compared to a human.

However, if the operation data 205 to 209
When the lower three of the voice data 505 to 509 are selected, the robot 101 puts his hand on the waist even if a great applause occurs, and utters “Well, this kind of thing”, so much joy. Do not perform the operation of And when the applause is small, she shows a muffled attitude, muttering, "Just. Today's customer is stingy." Furthermore, when a big boo occurs, the robot 101 squats with his hands covering his face and says, "I sang hard, but not much.
Ein. " Such an operation pattern of the robot 101 can be seen as reflecting a state in which the mood is lowered when compared to a human.
Therefore, the process of selecting the motion data and the voice data in S30 to S38 can be regarded as a process of setting the mood state of the robot 101 in other words.

FIG. 14 shows the flow of processing in the reaction sound discrimination program 155. The reaction sound detection microphone 105 detects a request signal (S39 in FIG. 12) from the operation control program 154. Read the measured waveform output and calculate the volume Q from the amplitude (D1 to D
3). Then, the measured waveform is converted to each of the standard waveform data 159 to 1.
61 (D4), and the judgment results 1 to 3 (“applause”,
"Laughter" and "Boo" are transmitted to the operation control program 154 along with the volume Q (D5 to D1).
1).

Subsequently, the processing of the operation control program 154 proceeds to S50 in FIG. Here, a situation in which one of the spectators selects a word from a predetermined word list, and uses the word to speak to the word detection microphone 108 (FIG. 1) about the impression of the robot 101 singing. Think. First, the processing in the word identification program 156 is described. In response to a request signal (S50 in FIG. 13) from the operation control program 154, the word detection microphone 108
Reads the waveform output of the word detected by the computer and calculates the volume Q from the amplitude (C1 to C3). And the measured waveform is stored in ROM
153 is compared with the word waveform data 164 stored in
(C4), a word corresponding to the measured waveform is identified. Then, the following processing is performed according to the identification result. -When the identified word is "Onchi" or "Hetaxo": the identification result number is set to 1. -When the identified word is "refund" or "return": the identification result number is set to 2. -When the identified word is "bravo" or "genius": the identification result number is 3. Then, the identification results 1 to 3 are transmitted to the operation control program 154 along with the volume Q (C5 to C11).

In the operation control program 154, FIG.
In S51, the identification result of the word and the volume Q are received, and in S52, for the operation data stored in the storage areas R13 to R15, parameter values for determining the drive amount of the skeleton drive actuator 110 for executing the operation, and By changing the output level of the speaker 115, the magnitude of the operation of the robot 101 and the output level of the message are adjusted. This adjustment is performed so that the operation and the voice output increase as the volume Q of the identified word increases. Then, when the received identification result is 1, that is, when the word is “hetaxo” or the like, the robot 101 “try again.”
(Steps S54, S55).
When the identification result is 2, that is, when the word is "pay money" or the like, an operation of uttering "Chikshaw. Remember." And scratching the head is performed (S56, S57). Further, when the identification result is 3, that is, when the word is "bravo" or the like, the hands are put on the waist and the chest is distorted, and the operation of laughing at "Wah-ha-ha." (S58, S59).

[Brief description of the drawings]

FIG. 1 is a block diagram showing the overall configuration of a robot system according to the present invention.

FIG. 2 is a schematic diagram of a robot skeleton.

FIG. 3 is a schematic side view showing an arrangement state of a reaction sound detection microphone.

FIG. 4 is a schematic side view showing an arrangement state of an image sensor.

FIG. 5 is a schematic diagram showing an image of a spectator by an image sensor.

FIG. 6 is an explanatory diagram of a configuration of operation data.

FIG. 7 is a diagram illustrating the configuration of audio data.

FIG. 8 is an explanatory diagram showing the contents of a RAM.

FIG. 9 is a flowchart showing the flow of a robot operation control program.

FIG. 10 is a flowchart following FIG. 9A.

FIG. 11 is a flowchart following FIG. 10B.

FIG. 12 is a flowchart following C in FIG. 11;

FIG. 13 is a flowchart following D in FIG. 12;

FIG. 14 is a flowchart showing the flow of processing by a reaction sound determination program.

FIG. 15 is a flowchart showing the flow of processing by the word identification program.

[Explanation of symbols]

 REFERENCE SIGNS LIST 100 robot system 101 robot 102 robot controller 105 reaction sound detection microphone (audience information detection means) 108 word detection microphone (audience information detection means) 120 two-dimensional CCD sensor (audience information detection means) 151 CPU 153 ROM (drive data storage means) ) 252 audience

Claims (8)

(57) [Claims] 1. A spectator information detecting means for detecting specific spectator information comprising at least one of sound information and visual information from a spectator, and any one of a plurality of operations predetermined in correspondence with the spectator information. A robot operation unit that performs the operation for the audience, an operation data storage unit that stores operation data corresponding to the plurality of operations, a data selection unit that selects an arbitrary one of the stored operation data, A robot control unit that controls the robot operation unit based on the selected operation data; and a robot control unit that is provided in the spectator information detection unit, and generates a waveform of the sound information.
Waveform detection means for detecting, and waveform data storage means for storing waveform data of a plurality of sound information
And a waveform of the sound information detected by the waveform detecting means.
And the waveform data stored in the waveform data storage means.
Sound information that determines the type of the sound information by collation
Discriminating means and a set of motion data corresponding to each of the discriminated sound information
The operation data storage means to be stored and the correspondence between the sound information and the operation data are compliant.
Correspondence that gives an obedient behavior pattern that reflects personality,
Rebellious behavioral patterns that reflect a rebellious or humble personality
Correspondence storage means for storing a correspondence giving a turn
And a correspondence that selects one of the stored correspondences
Selection means, wherein the data selection means is selected by the correspondence selection means.
Based on the selected correspondence, the determined sound information
Select the corresponding operation data and select the selected pair.
Depending on the response, the character of the robot may be
A robot system that responds in various ways based on audience information, characterized by switching between opponents . 2. The robot system according to claim 1, wherein said data selection means includes a random number generation means, and said operation data is automatically selected based on a random number generated by said random number generation means. 3. The correspondence selecting means includes a random number generating means.
Based on the random number generated by the random number generating means,
Claims that automatically select the correspondence
Item 3. The robot system according to item 1 or 2. 4. The volume of the sound information included in the audience information
A volume detecting means for detecting, The robot control means detects the sound information detected by the sound information detection means.
Operation data corresponding to the selected sound information
Unit, and based on the read operation data
Controlling the robot operation section by using
Based on the volume detected by the detection means, the robot
2. The method according to claim 1, wherein a magnitude of the operation by the operation unit is changed.
4. The robot system according to any one of claims 3 to 3. 5. The robot control means according to claim 1, wherein
The higher the volume, the greater the
5. The robot system according to claim 4, wherein the operation is increased.
Stem. 6. The spectator information detecting means includes:
And at least applause, roar, laugh,
It is said to detect two or more of voice and boo
A robot system according to any one of claims 1 to 5.
M 7. The spectator information detecting means includes:
To detect one or more words pronounced by the audience
Word detection unit and word identification to identify the detected word
The robot according to any one of claims 1 to 6, including means.
System. 8. The motion data may include joy, discouragement, sadness.
Data corresponding to at least one action of anger
The robot system according to any one of claims 1 to 7, comprising:
Stem.