JP2003305674A - Robot device, robot control method, recording medium and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To realize a pet robot capable of actively executing autonomous action immediately after starting. <P>SOLUTION: Figure 14 shows the actual operation image of contents by the pet robot 1 for realizing the ideal change of a user's degree of interest, that is, the pet robot 1 is put in a Wake Up mode where rather large contents including contents corresponding to the time and date and season are continuously manifested for a prescribed time after starting, then put in a Vivid mode where rather large contents are autonomously manifested for a subsequent prescribed time, and then put in a first to a third Break modes where rather small contents are manifested for a prescribed time each. The first to third Break modes and Vivid mode are periodically repeated as shown. This constitution can be applied to a pet robot for entertainment, for instance. <P>COPYRIGHT: (C)2004,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a robot device, a robot control method, a recording medium, and a program, and, for example, a robot device and a robot control method for autonomously determining selection of contents to be expressed and expression frequency. , A recording medium, and a program.

[0002]

2. Description of the Related Art In recent years, for example, pet pet robots for entertainment have been realized which autonomously perform various actions in accordance with the surrounding environment and the internal state of the pet.

Some pet robots have a function of recognizing a user's voice by voice and acting according to the recognition result, in addition to the above-mentioned function of autonomously acting.

[0004]

By the way, when the pet robot behaves autonomously, many resources are used for determining autonomous behavior and for motion control, and the motion of an actuator provided at a joint or the like. Since the sound or the like becomes noise, the recognition rate of the voice is lowered, and it is not possible to promptly operate in response to the user's utterance.

Therefore, does the conventional pet robot having the function of autonomously acting and the voice recognition function allow the reduction of the recognition rate of the voice recognition by giving priority to the function of autonomously acting (that is, autonomously? Character that prioritizes the function to act on), or suppresses the function that acts autonomously to improve the recognition rate of speech recognition (that is, character that prioritizes speech recognition). There is.

[0006] A user sometimes feels that he / she is ignorant of a pet robot having a personality in which the function of autonomously acting is prioritized. In addition, a pet robot having a personality in which voice recognition is prioritized may feel that it is “not interesting because it does not move much”.

Therefore, there is a demand for a pet robot that appropriately transitions between a state in which the function of autonomous behavior is prioritized and a state in which voice recognition is prioritized, but there is no such pet robot in the past. There were challenges.

Further, in the conventional pet robot having the function of autonomously acting, the autonomous behavior is scarce in the period immediately after the activation, and thereafter the autonomous behavior gradually becomes active (the movement becomes large, the frequency becomes large). Therefore, there is a problem that the user's interest in the pet robot is diminished during the period when the autonomous behavior after activation is scarce.

The present invention has been made in view of such a situation, and an object thereof is to realize a pet robot capable of actively executing an autonomous action immediately after starting.

[0010]

A robot apparatus according to the present invention comprises a selection means for selecting one content from a plurality of preset contents, and an expression means for expressing the content selected by the selection means. Wherein the selecting means selects a large content in a predetermined period after starting, and the expressing means expresses the content selected by the selecting means at a high frequency in the predetermined period after starting. To do.

[0011] The selecting means may select content corresponding to at least one of season, date, and time.

[0012] The selecting means can select the content corresponding to at least one of the emotion and the desire to be set during the period from the end of the previous time to the start of the present time. .

The expression means adjusts the expression frequency of the content in response to at least one of the emotion and desire set during the period from the end of the previous time to the start of the present time. be able to.

The robot apparatus according to the present invention may further include voice recognition means for recognizing the user's utterance, and detection means for detecting the user's contact.

The selection means may select the content in accordance with at least one of the frequency of voice recognition by the voice recognition means and the frequency of contact of the user by the detection means.

The expression means may include notifying means for notifying the user that the voice recognition has been performed by the voice recognition means and the contact of the user has been detected by the detection means.

The voice recognition means can also recognize a scale.

The selecting means may select a predetermined content when a predetermined scale is recognized by the voice recognition means.

The robot apparatus according to the present invention may further include an adding means for adding the content that can be expressed when the predetermined scale is recognized by the voice recognizing means.

The robot apparatus according to the present invention may further include output means for outputting a scale as a response corresponding to the recognized scale when the predetermined scale is recognized by the voice recognition means.

The robot apparatus of the present invention comprises an acquisition means for acquiring an image signal, a detection means for detecting a moving body based on the image signal acquired by the acquisition means, and an acquisition means corresponding to the detection result of the detection means. And a storage unit for storing the image signal acquired by.

The robot control method of the present invention includes a selection step of selecting one content from a plurality of preset contents, and an expression step of expressing the content selected in the processing of the selection step. The process of the selection step selects a large content in a predetermined period after the start, and the process of the expression step expresses the content selected in the process of the selection step at a high frequency in the predetermined period after the start. Is characterized by.

The program of the recording medium of the present invention includes a selection step of selecting one content from a plurality of preset contents, and an expression step of expressing the content selected in the processing of the selection step. ,
The process of the selection step selects a large content in a predetermined period after the start, and the process of the expression step expresses the content selected in the process of the selection step at a high frequency in the predetermined period after the start. Is characterized by.

The program of the present invention causes a computer to execute a selection step of selecting one content from a plurality of preset contents and an expression step of expressing the content selected in the processing of the selection step. , The processing of the selection step selects a large content in a predetermined period after activation, and the processing of the expression step selects the content selected in the processing of the selection step,
It is characterized in that it is frequently expressed in a predetermined period after activation.

In the robot apparatus, the robot control method, and the program of the present invention, one content is selected from among a plurality of preset contents, and the selected content is expressed. In the selection process, a large content is selected in a predetermined period after activation, and in the expression process, the selected content is expressed with high frequency in a predetermined period after activation.

[0026]

1 is a perspective view showing an example of the external configuration of a pet robot 1 to which the present invention is applied.

For example, the pet robot 1 has a four-legged bear shape, and the leg units 3A, 3B, 3C, 3D are connected to the front, rear, left, and right of the body unit 2, respectively, and the body is The head unit 4 and the tail unit 5 are connected to the front end and the rear end of the sub unit 2, respectively.

FIG. 2 is a block diagram showing an example of the internal configuration of the pet robot 1 of FIG. The body unit 2 includes a controller 1 that controls the entire pet robot 1.
0, a battery 11 for supplying electric power to each part of the pet robot 1, a battery sensor 12, and a heat sensor 13.
The internal sensor 14 and the like are stored. This controller 10 basically has a CPU (Central Processi).
ng Unit) 10A, a memory 10B in which a program for the CPU 10A to control each unit is stored, and a clock 10C indicating the current date and time, the elapsed time after activation, and the like.

As shown in FIG. 2, the head unit 4 includes
Microphone 1 corresponding to an "auditory organ like an ear" that senses sound as a sensor that senses an external stimulus
5. CCD (Charge Coupled Device) and CMOS (Complementary
Metal Oxide Semiconductor) A camera 16 which is composed of an image sensor or the like and corresponds to a “visual organ like an eye” that acquires an external image signal, and a “skin like a skin” that senses pressure or the like caused by contact with a user. Tactile organ "
The touch sensors 17 corresponding to are provided at predetermined positions. Further, in the head unit 4, a position detection sensor 18 that measures a distance to an object, and a speaker 19 that corresponds to a "speech-like organ" of the pet robot 1 that outputs a predetermined scale are provided at predetermined positions. It is installed in.

Joint portions of the leg units 3A to 3D, connecting portions of the leg units 3A to 3D and the body unit 2, connecting portions of the head unit 4 and the body unit 2, and a tail unit 5 An actuator is installed at a connecting portion between the body unit 2 and the body unit 2. The actuator operates each unit based on an instruction from the controller 10.

In the example of FIG. 2, the leg unit 3A is
Is the actuator 3AA₁Through 3AA_KProvided with legs
The unit 3B includes an actuator 3BA₁Through 3B
A_KIs provided. Also, in the leg unit 3C,
Actuator 3CA₁To 3 CA_KIs installed on the leg
Actuator 3DA for knit 3D₁Through 3DA _KBut
It is provided. Furthermore, the head unit 4 is
Player 4A₁Through 4A_LIs provided and the tail uni
The actuator 5A₁And 5A ₂Is that
It is provided.

Hereinafter, actuators 3AA _{1 to} 3DA _K provided on the leg units 3A to 3D and actuators 4A ₁ to 4 provided on the head unit 4 will be described.
When it is not necessary to individually distinguish A _L and the actuators 5A ₁ and 5A ₂ provided in the tail unit 5, the actuators 3A may be collectively referred to as appropriate.
A _{1 to} 5 A ₂ .

Further, the leg units 3A to 3D include
In addition to the actuators, the switches 3AB to 3DB are installed at places corresponding to the soles of the feet of the pet robot 1. Then, when the pet robot 1 walks, the switches 3AB to 3DB are pressed, and a signal indicating that is input to the controller 10.

The microphone 15 installed in the head unit 4 collects ambient voice (sound) including the user's utterance and outputs the obtained voice signal to the controller 10.
The camera 16 images the surrounding situation and outputs the obtained image signal to the controller 10. Touch sensor 17
Is provided on the upper part of the head unit 4, for example,
The pressure received by a physical action such as “stroking” or “striking” from the user is detected, and the detection result is output to the controller 10 as a pressure detection signal. The position detection sensor 18 outputs, for example, infrared rays and outputs the detection result of the timing at which the reflected light is received to the controller 10.

The controller 10 is the microphone 1
5, based on the audio signal, the image signal, the pressure detection signal, etc. provided from the camera 16, the touch sensor 17, and the position detection sensor 18, the surrounding conditions and the command from the user,
Whether or not there is an action from the user is determined, and based on the result of the determination, the pet robot 1 determines the action to be performed next. Then, the controller 10 drives the necessary actuator based on the determination, thereby swinging the head unit 4 vertically and horizontally, moving the tail unit 5, and each of the leg units 3A to 3D. To drive the pet robot 1 to walk. The entire series of operations of the pet robot 1 as described above will also be described as content hereinafter.

In addition, the controller 10 performs processing such as turning on, off, or blinking an LED (not shown) provided on the head unit 4 of the pet robot 1 or the like.

FIG. 3 is a block diagram showing a functional configuration example of the controller 10 of FIG. The functions shown in FIG. 3 are realized by the CPU 10A executing the control program stored in the memory 10B.

The controller 10 basically includes a sensor input processing section 31 for detecting various signals from sensors (microphone 15 to position detection sensor 18 and switches 3AB to 3DB) for detecting an external stimulus, and a sensor input. Based on the information and the like detected by the processing unit 31,
The pet robot 1 is composed of an information processing unit 32 that operates.

The angle detection section 41 constituting the sensor input processing section 31 is based on the information notified from each of the actuators 3AA _{1 to} 5A ₂ when the motor provided in each of the actuators 3AA _{1 to} 5A ₂ is driven. Then, the angle is detected. The angle information detected by the angle detection unit 41 is the action management unit 62 of the information processing unit 32,
And is output to the sound data generation unit 66.

The volume detecting section 42 detects the volume based on the signal supplied from the microphone 15, and outputs the detected volume information to the behavior management section 62 and the sound data generating section 66.

The voice recognition unit 43 performs voice recognition on the voice signal supplied from the microphone 15. For example, the voice recognition unit 43 uses, as the voice recognition information, a command such as “let's talk”, “walk”, “prone”, “follow the ball” and the like as the voice recognition result. The unit 61, the behavior management unit 62, and the sound data generation unit 66 are notified.

The image recognition unit 44 performs image recognition using the image signal supplied from the camera 16. For example, when the image recognition unit 44 detects "a red round object" or "a plane perpendicular to the ground and having a predetermined height or more" as a result of the processing, "there is a ball"",
The image recognition result such as "there is a wall" is used as the image recognition information.
The instinct / emotion management unit 61, the behavior management unit 62, and the sound data generation unit 66 are notified.

The pressure detection unit 45 processes the pressure detection signal supplied from the touch sensor 17. For example, as a result of the processing, the pressure detection unit 45 is equal to or higher than a predetermined threshold value, and
When a short-time pressure is detected, it is recognized as "struck (exhausted)", and when a long-term pressure that is less than a predetermined threshold value is detected, "stroked (praised)" is detected. , ”And notifies the instinct / emotion management unit 61, the behavior management unit 62, and the sound data generation unit 66 of the recognition result as state recognition information.

The position detecting section 46 measures the distance to a predetermined object based on the signal supplied from the position detecting sensor 18, and notifies the action managing section 62 and the sound data generating section 66 of the distance information. To do. For example, the position detector 46
Detects the distance to the hand and the distance to the ball recognized by the image recognition unit 44 when the user's hand or the like is extended in front of the eyes.

The switch input detection unit 47 is based on the signals supplied from the switches 3AB to 3DB provided in the portion corresponding to the sole of the foot of the pet robot 1, for example, when the pet robot 1 is walking. The instinct / emotion management unit 61 and the behavior management unit 62 are notified of the walking timing and the fact that the sole of the foot is touched by the user.

On the other hand, the instinct / emotion management unit 61 constituting the information processing unit 32 manages the instinct and emotion of the pet robot 1, and expresses the parameter and the emotion indicating the instinct of the pet robot 1 at a predetermined timing. The parameters are output to the behavior management unit 62 and the sound data generation unit 66.

A parameter representing the instinct of the pet robot 1 and a parameter instinct representing the emotion will be described with reference to FIG. As shown in FIG. 4, the instinct / emotion management unit 61 stores and manages an emotion model 81 expressing the emotion of the pet robot 1 and an instinct model 82 expressing the instinct.

The emotion model 81 includes, for example, "joy", "sadness", "anger", "surprise", "fear",
The emotional state (degree) such as “disgust” is represented by emotion parameters in a predetermined range (for example, 0 to 100), and outputs from the voice recognition unit 43, the image recognition unit 44, and the pressure detection unit 45. The value is changed based on the passage of time.

In this example, the emotion model 81 is
Emotional unit 81A expressing "joy", "Sadness"
An emotional unit 81B that represents, an emotional unit 81C that represents "anger", an emotional unit 81D that represents "surprise",
The emotion unit 81E representing "fear" and the emotion unit 81F representing "dislike" are included.

The instinct model 82 is, for example, “appetite”,
The states (degrees) of instinct desires such as “sleep desire” and “exercise desire” are represented by instinct parameters in a predetermined range, and output from the voice recognition unit 43, the image recognition unit 44, the pressure detection unit 45, and the like. The value is changed based on the elapsed time or the like. Further, the instinct model 82 enhances the parameter indicating “exercise desire” based on the behavior history, or “appetite” based on the remaining amount (voltage) of the battery 11.
Increase the parameter that represents.

In this example, the instinct model 82 is
An instinct unit 82A representing "motility", an instinct unit 82B representing "love", an instinct unit 82C representing "appetite", an instinct unit 82D representing "curiosity",
And an instinct unit 82E representing "sleep desire".

The instinct / emotion management unit 61 has such emotion units 81A to 81F and instinct units 82A to 8F.
By changing the parameters of 2E, the emotion and instinct of the pet robot 1 are expressed and the change is modeled.

Further, the parameters of the emotion units 81A to 81F and the instinct units 82A to 82E are changed not only by the input from the outside but also by the mutual influence of the respective units as shown by the arrows in the figure. To be done.

For example, an emotion unit 81A expressing "joy" and an emotion unit 81B expressing "sadness".
Instinct / emotion management unit 61 is "joyful" when the user compliments each other due to their mutual inhibition.
The emotion unit 81B expressing "sadness" is increased while increasing the parameter of the emotion unit 81A expressing
Change the emotion to be expressed, for example, by reducing the parameter of.

Further, the parameters of not only the units forming the emotion model 81 and the units forming the instinct model 82 but also the parameters of the respective units are changed over both models.

For example, as shown in the figure, the instinct model 82
Instinct unit 82B that expresses "love desire" and "appetite"
The parameters of the emotion unit 81B expressing "sadness" and the emotion unit 81C expressing "anger" of the emotion model 81 are changed according to the change of the parameter of the instinct unit 82C expressing ".

Specifically, when the parameter of the instinct unit 82C representing "appetite" becomes large, the emotion unit 81B expressing "sadness" of the emotion model 81,
The parameter of the emotion unit 81C expressing “anger” becomes large.

The emotion parameters or the instinct parameters managed by the instinct / emotion management unit 61 in this manner are, for example, measured in a predetermined cycle, as will be described later, and the behavior management unit 62 and the sound data generation are performed. It is output to the unit 66.

More specifically, not only the emotion model 81 and the instinct model 82, but also a growth model is prepared in the instinct / emotion management unit 61, and each unit of the emotion model 81 and the instinct model 82 is changed depending on the growth stage. The parameters are changed. In this growth model, for example, growth states (degrees) such as “childhood”, “adolescence”, “mature”, “old age” are represented by values in a predetermined range, and the speech recognition unit 43, The value is changed based on the output from the image recognition unit 44, the pressure detection unit 45, and the like, the elapsed time, and the like.

The instinct / emotion management unit 61 is supplied with recognition information from the voice recognition unit 43, the image recognition unit 44, the pressure detection unit 45, and the like, and the behavior management unit 62 notifies the pet robot 1 of the pet robot 1. Current or past behavior, specifically, behavior information indicating the content of the behavior such as "walking for a long time" is supplied. Then, the instinct / emotion management unit 61 generates different internal information according to the action of the pet robot 1 indicated by the action information even when the same recognition information or the like is given.

For example, when the pet robot 1 greets the user and the user pats his / her head, the instinct / emotion management section provides the behavior information that the user greeted the user and the recognition information that the user patted the head. 61 is supplied. At this time, in the instinct / emotion management unit 61, the value of the emotion unit 81A representing “joy” is increased.

Returning to the explanation of FIG. The behavior management unit 62 determines the next behavior based on the information supplied from the voice recognition unit 43, the image recognition unit 44, and the like, the parameters supplied from the instinct / emotion management unit 61, and the elapsed time. Then, the command instructing the execution of the determined action is output to the posture transition management unit 63. Further, the behavior management unit 62 outputs a command instructing the sound synthesis to the voice synthesis unit 65 when the pet robot 1 speaks or when the sound corresponding to a predetermined motion is output from the speaker 19.

Next, the first to eighth characteristic actions of the pet robot 1 will be described.

As a first characteristic action, the pet robot 1 is adapted to execute contents corresponding to a date (season).

FIG. 5 shows the mode transition of the pet robot 1. That is, the pet robot 1 is
Transition to Wake Up (wake up) mode, depending on the value of exercise desire 82A (Exe) 82A at that time, Vivid (move around) mode, Break (break) mode, or a predetermined period from the end of the last time ( For example, when more than 5 days have passed, the mode is changed to the Love mode.

The Vivid mode is a state in which the autonomous action is prioritized over the voice recognition function, and the pet robot 1
Actively runs autonomous content. In Vivid mode, if a predetermined voice ("Let's talk", "Noisy", "Quietly", "Play with sound", etc.) is recognized, it will switch to Talk A mode. . Also, in the Vivid mode, the pet robot 1
Is fatigued (when the desire to exercise 82A or the desire to love 82B decreases), the mode is changed to the break mode.

In the Talk A mode, the voice recognition function has priority over autonomous actions. In Break mode, content with relatively small movement is executed.

FIG. 6 shows details of the Wake Up mode. The pet robot 1 reproduces the contents of the seasonal event, which is the first feature, after the power is turned on, the prelude reproduction, and the birth art reproduction. By thus continuously expressing the content, the cheerful feeling of the pet robot 1 is produced. After this, the content of "bowing",
After playing the "look around and look around" content, the content of the exciting course or the content of the requested course is executed.

FIG. 7 shows an example of contents corresponding to a seasonal event. For example, the start date is January 1 to 1
If it is the 7th of the month, the content of the event such as "rice cake with" and "octopus fried" suitable for the New Year is executed. Further, for example, when the startup date is from July 21st to August 31st, content of events such as "watermelon splitting" and "bon festival" suitable for summer vacation is executed. The correspondence table shown in FIG. 7 is stored in, for example, the memory 10B. In addition,
Not only the content corresponding to the date (season) but also the content corresponding to the time may be prepared.

FIG. 8 is a flowchart for explaining the first feature of the pet robot 1, that is, the process for executing different contents corresponding to the date (season), that is, the date / season corresponding process.

In step S1, the controller 10
Determines whether the present time is at the time of startup, at the time of starting operation, or at the time of displaying content, and waits until it is determined as either one. When it is determined that the present time is the start-up time, the operation start time, or the content appearance time, the process proceeds to step S2. In step S2, the controller 1
0 refers to the built-in clock 10C and acquires the current date and time. In step S3, the controller 10 selects the content corresponding to the date and time acquired in step S2 by referring to the correspondence table as shown in FIG. In step S4, the controller 10 expresses the content selected in step S4. This is the end of the description of the date / season correspondence process.

As a second characteristic action, the pet robot 1 has a voice recognition function suppressed so that only a predetermined word can be recognized while giving priority to autonomous action (Vivi in FIG. 5).
d mode) and a state (Talk A mode in FIG. 5) in which the accuracy (recognition rate) of the voice recognition function is prioritized over the autonomous action, and the two states are transitioned according to a predetermined condition. . It should be noted that the pet robot 1 turns on or off the LED provided on the head unit 4 or the like in order to notify the user whether the state is such that the autonomous action is prioritized or the voice recognition function is prioritized. It is designed to blink.

FIG. 9 shows conditions for transitioning between a state in which the autonomous action is prioritized and a state in which the voice recognition function is prioritized.

In the state where the autonomous behavior is prioritized, in addition to walking, larger contents (using the whole body, moving at high speed, emitting a large volume, and producing many colors) are expressed. In addition, the frequency of occurrence of those contents is increased.

When a predetermined word that is difficult to be erroneously recognized (such as "Let's talk") is obtained as a result of voice recognition in a state where the autonomous action is prioritized, the voice recognition function is transited to the state where it is prioritized. There is. Not only when a predetermined voice is recognized, but also when, for example, a predetermined sensor detects a predetermined signal, the state in which the autonomous action is prioritized may be changed to the state in which the voice recognition function is prioritized. Good.

When the voice recognition function is prioritized, a predetermined LED is emitted to indicate that the voice recognition function is prioritized. Alternatively, the pet robot 1 may have a predetermined posture (for example, a sitting posture) to indicate that the voice recognition function is prioritized.

When the voice recognition function is prioritized,
Autonomous behaviors are suppressed, and small content (for example, cramming the neck, stooping, etc.) (using only a part of the whole body, moving slowly, producing silence or small sounds, producing monochromatic color) is expressed. It Also, the frequency of occurrence of those contents is reduced.

When the utterance instructing the operation is recognized by the user while the voice recognition function is prioritized, the content corresponding to the utterance is executed.

In the state where the voice recognition function is prioritized, when there is no communication with the user (speaking from the user, contact, etc.) for a predetermined time (for example, 300 seconds), the autonomous action is returned to the prioritized state. It is done like this.

As a third characteristic action, the pet robot 1 executes a predetermined content when it recognizes a predetermined scale broadcast in a predetermined television program, for example. Further, the pet robot 1 is configured to add operable content when recognizing a predetermined scale.

FIG. 10 shows a predetermined scale that is broadcast in a television program or the like, and contents that are executed in correspondence with the predetermined scale. For example, when a scale (sound 6) is broadcast and the pet robot 1 recognizes the scale, the content indicating "easy greeting" is executed. Further, for example, when a scale (sound 23) is broadcast and the pet robot 1 recognizes the scale, the content of "dance" is executed.

FIG. 11 shows a predetermined scale broadcasted in a television program or the like, and contents added to the contents operable in correspondence therewith. For example, when the scale (sound 12 or 13) is broadcast and the pet robot 1 recognizes the scale, the content indicating “weightlifting” can be executed thereafter. Further, for example, when the musical scales (sounds 26 to 28) are broadcast and the pet robot 1 recognizes the musical scales, the content indicating “gymnastics (twisting the body)” can be executed thereafter.

When the user's utterance "Media motion check" is recognized in a state where priority is given to autonomous behavior (Vivid mode), it is possible to operate corresponding to a predetermined scale broadcast in a television program or the like. The contents are played continuously.

As a fourth characteristic action, the pet robot 1 has the highest content expression rate at each startup, and thereafter the content expression rate changes periodically. In addition, the pet robot 1 starts up this time for a predetermined period (for example, 5 days) from the end of the previous time.
If the time has passed, the Wake Up mode does not change as usual, but it first changes to the Love mode that expresses content that is unpleasant to the user, and then changes to the Wake Up mode. There is. Furthermore, the pet robot 1 is configured to transition to the Love mode when the frequency of being accepted by the user is high.

FIG. 12 is an estimation of changes in the degree of interest of the user with respect to the pet robot 1. In the figure, the horizontal axis represents the passage of time, and the vertical axis represents the level of interest of the user. Further, a wavy line indicates a change in the user's interest in the conventional robot, and a solid line indicates a change in the user's interest in the target pet robot 1.

In the case of the conventional robot, since the operation after starting is poor, the interest of the user is rapidly lowered, and the power is often turned off as it is. Therefore, in the case of the pet robot 1, the pet robot 1 is activated by activating the operation after activation to attract the user's attention, and then periodically operating the pet robot 1 to appropriately attract the user's attention. Make sure that the time that you have

FIG. 13 shows an ideal operation image of contents by the pet robot 1 for realizing the ideal change in the degree of interest of the user shown in FIG.
In the figure, the horizontal axis represents the passage of time and the vertical axis represents the size of the content. That is, the size of the content is
The change is made according to the change in the degree of interest of the ideal user shown in FIG.

Here, the size of the content means the operation speed (the amount of angle moved in a unit time), the number of actuators moved at the same time (the number of actuators operating with respect to the total number of actuators), the operation angle (movement in one operation). Angle), posture (walking posture, standing posture, sitting posture, prone posture, supine posture, etc.), volume (volume to be output corresponding to one action, sound length), light emission amount (one time Number of LEDs that emit light in response to movement, color type), line-of-sight direction (upward, downward), operating time (time required for one operation),
And the expression rate (the number of contents expressed per unit time).

FIG. 14 shows an actual operation image of contents by the pet robot 1 for realizing the ideal change in the degree of interest of the user shown in FIG. That is, the pet robot 1 is set to the Wake Up mode in which a large content including the content corresponding to the date and time and the season is continuously expressed for a predetermined time (for example, 5 minutes) after being activated, and then for a predetermined time (for example, 4 minutes). For a minute), it is designed to be in Vivid mode that autonomously expresses large contents. After that, the first to third Break modes in which small contents are expressed are set for a predetermined time (for example, 3 minutes, 1 minute, and 4 minutes each). After that, the first to third Break modes and the Vivid mode are periodically repeated as illustrated.

The first to third Break modes are 5
It is a part of Break modes (first to fifth Break modes) divided into stages, and among the first to fifth Break modes, the first Break mode produces the largest content and the fifth Break mode. Break mode is the smallest and the content is expressed. In the first Break mode, leisure-centered contents (PERFORMANCE, SLEEPY, BABY_SLEEP, etc.) are defined. In the second Break mode, contents centered around leisure arts (PERFORMANCE, etc.) are defined. Third
In Break mode, content that focuses on major skills and appeals (PERFORMANCE, SING_A_SONG, DANCE, EXERCISE, CAL
L_OWNER etc.) is defined. In the 4th Break mode, the content centering on the decline system (EMOTIONAL PERFORMANC
E, ANGRY, etc.) are defined. In the 5th Break mode, the content centered on appeal (PERFORMANCE, SING_
A_SONG, DANCE, CALL_OWNER, etc.) are defined.

FIG. 15 shows an image in which the pet robot 1 transits to the Love mode when the frequency of being accepted by the user is high.

As a fifth characteristic action, when the pet robot 1 detects a contact by the user or recognizes the user's utterance, in order to notify the user of the contact,
After the scale output or LED light emission, a predetermined operation is executed.

FIG. 16 is a flow chart for explaining the fifth feature of the pet robot 1, which is an interactive content expression process. In step S11, the controller 10 determines whether or not the user touches a predetermined sensor, and in step S12, determines whether or not the user's utterance is recognized by voice, and the user touches the predetermined sensor. Alternatively, it waits until it is determined that the voice of the user is recognized. When it is determined that the user has touched a predetermined sensor or has recognized the user's utterance by voice, the process proceeds to step S13.

In step S13, the controller 1
0 refers to the correspondence table prepared in advance to select the content corresponding to the sensor that has detected the contact of the user or the speech that has been speech-recognized.

In step S14, the controller 1
0 causes at least one of the output of a predetermined utterance (scale) and the light emission of the LED to be executed corresponding to the selected content. In step S15, the controller 1
4 controls a predetermined actuator to execute an operation corresponding to the selected content. This is the end of the description of the interactive content expression processing.

As a sixth characteristic action, the pet robot 1 in the Vivid mode in which it autonomously behaves, for example, a motion of shaking its head and looking around, a motion of stopping to think, etc. By doing, he is trying to express his will. Further, when the pet robot 1 detects a moving object in the image of the image signal from the camera 16 in the answering machine in a state of autonomously acting, it stores the image signal (takes a picture). ing.

FIG. 17 is a flow chart for explaining a process for achieving both the autonomous action in Vivid mode and the reaction (for example, moving body tracking) to information constantly input such as an image from a camera. This process
It starts when transitioning to Vivid mode and ends when transitioning to another mode.

In step S21, the controller 1
0 resets the autonomous action timer, which is provided inside itself, for measuring the elapsed time of the autonomous action. In step S22, the controller 10 controls a predetermined actuator to stop the current operation and cause the content of shaking the head to appear. In this way, by expressing the content of the gesture of stillly shaking the head, it is possible to make an expression as if the pet robot 1 is thinking and detecting the surrounding environment.

In step S23, the controller 1
A value of 0 determines whether or not the autonomous action timer has passed a predetermined time. When it is determined that the timer for autonomous action has not elapsed for the predetermined time period, the process proceeds to step S24. In step S24, the controller 10 controls each part to act autonomously. Along with this, the controller 10 turns on the autonomous action flag provided inside itself. The process returns to step S21, and the subsequent processes are repeated. Then, if it is determined in step S23 that the timer for autonomous action has elapsed for the predetermined time, which is determined in advance, the process proceeds to step S25.

In step S25, the controller 1
0 determines whether or not a moving object (hereinafter referred to as a moving body) is detected in the image from the camera 16. If it is determined that a moving object has been detected, the process proceeds to step S26.
Proceed to. In step S26, the controller 10
Determines whether the autonomous action flag is on.
If it is determined that the autonomous action flag is on, the process proceeds to step S27.

In step S27, the controller 1
When 0 is set, the moving body tracking timer that measures the elapsed time of moving body tracking provided inside itself is reset to 0. In step S28, the controller 10 starts moving body tracking. That is, the control of the head unit 4 is started so as to move the neck following the movement of the moving body. In step S29, the controller 10
Sets the autonomous behavior flag to off.

In step S30, the controller 1
0 determines whether or not the moving body is lost. When it is determined that the moving body has not been lost, the process proceeds to step S31. In step S31, the controller 10 determines whether or not the moving object tracking timer has elapsed for a predetermined time that is determined in advance. If it is determined that the moving body tracking timer has not elapsed for the predetermined time, the process returns to step S30.

If it is determined in step S30 that the moving body has been lost, or if it is determined in step S31 that the moving body tracking timer has elapsed by a predetermined time, the process proceeds to step S3.
Go to 2. In step S32, the controller 10
Stops motion tracking. The process is step S
Returning to step 22, the subsequent processing is repeated.

Even if it is determined in step S25 that a moving body is detected, and if it is determined in step S26 that the autonomous action flag is not ON, the process returns to step S22, and the subsequent processes are performed. Repeated.

By the processing as described above, in the Vivid mode, the behavior caused by the internal factor (instinct value etc.) of the pet robot 1 and the external factor (moving object detection etc.) are combined, and the expression stress is further increased. It becomes possible to realize a high pet robot 1.

FIG. 18 is a flow chart for explaining the autonomous search action control process in the Vivid mode. In step S41, the controller 10 controls each part to start a walking motion. In step S42,
The controller 10 determines whether an obstacle or the like has been detected. If it is determined that an obstacle or the like has been detected, the process proceeds to step S43. In step S43, the controller 10 controls each unit to avoid obstacles and the like by changing the direction.

At step S44, the controller 1
0 determines whether the user has walked a predetermined distance (or time) from the start of walking in step S41. If it is not determined that the user has walked the predetermined distance (or time), the process returns to step S42, and the subsequent processes are executed. Thereafter, when it is determined in step S44 that the user has walked a predetermined distance (or time), the process proceeds to step S45. In step S45, the controller 10 controls each part to stop walking. In step S46, the controller 10 responds to the instinctive value (motility desire 82A, etc.) and expresses the intention of the pet robot 1 (shaking, swinging, leisure art, turning,
Select (Take a picture etc.) and execute.

If it is determined in step S42 that an obstacle or the like is not detected, step S43 is skipped.

As described above, according to the autonomous search action control process in the Vivid mode, it is possible to interrupt the content expressing the intention of the pet robot 1 based on the walking motion.

For example, the motion of shaking the head is
It is an expression indicating a state in which the pet robot 1 is thinking and an intention to detect the surrounding environment. Leisure art (such as scratching the body with a foot) is an expression that indicates a willingness to behave voluntarily. The turning is an expression indicating the intention that the action policy has changed. For more information on turning,
This will be described later by controlling FIGS. Photographing is an expression that indicates the intention of setting an object of interest.

Regarding the turning processing, the flowchart of FIG. 19 and FIG. 20 (view of the pet robot 1 viewed from above)
Will be described with reference to. In step S51, the controller 10 determines the turning direction in the stopped state. In step S52, the controller 10
Directs the head unit 4 in the turning direction. That is, the front direction of the head unit 4 is changed from the state shown in FIG. 20A to the state shown in FIG. 20B.

In step S53, the controller 1
0 makes the direction of the body unit 2 coincide with that of the head unit 4 while maintaining the pointing direction of the head unit 4 in the turning direction. That is, the direction of the front of each of the head unit 4 and the body unit is changed from the state shown in FIG. 20B to
The state shown in FIG. 20C is changed to the state shown in FIG. 20D.

As described above, in the turning process, as shown in FIG. 21, the front of the head unit 4 is first oriented in the turning direction, and then the body unit 2 is turned.
Is aligned with the pointing direction of the head unit 4.

As a seventh characteristic action, the pet robot 1 is in the break mode (first to fifth break modes) for executing the content without walking while autonomously acting, until then. The desire to move is changed in accordance with the exercise history, and the type and frequency of leisure arts are changed corresponding to the desire to exercise 82A.

The process of determining the content to be expressed in the break mode will be described with reference to the flowchart of FIG. In step S61, the controller 10 acquires the elapsed time after activation by referring to the clock 10C. In step S62, the controller 10 detects the detection amount of the touch sensor 17 after activation,
And the recognition amount of voice recognition is acquired. In step S63, the controller 10 acquires information indicating the content that has appeared after activation.

At step S64, the controller 1
0 adjusts the instinct value based on each information acquired in steps S61 to S63.

For example, exercise instinct (Exercise) 82A
23, as shown by the curve a in FIG. 23, is adaptively changed to the size and the frequency of occurrence of the content that has been expressed up to that point. That is, when the motivation for exercise 82A is low, small contents are expressed, so that the motivation for exercise 82A is gradually increased.
Moves to vid mode and walks, gradually motivating 8
2A is set to go down. Further, for example, the instinct Affection 82B is changed as shown by the curve ba in FIG.

At step S65, the controller 1
0 means the desire to exercise as shown in FIG. 24, which is prepared in advance.
The Break mode (first to fifth Break modes) is determined based on the matrix table of (Exercise) 82A and Affection 82B. For example, Exercise 82A
When the Affection 82B is High and the Affection 82B is Low, the fourth Break mode is determined. Also, for example, Exercise 82A is Low and Affection
If 82B is high, the fifth Break mode is determined.

The exercise desire (Exercise) 82A and the affection desire (A)
ffection) 82B are both Vhigh, the transition to the Vivid mode is made. Also, Exercise 82A is Vlow
If it is, the sleep mode is entered.

At step S66, the controller 1
0 selects the content defined in the mode determined in step S65. In step S67, the controller 10 expresses the content selected in step S66. This is the end of the description of the process of determining the content to be expressed in the Break mode.

As an eighth characteristic action, the pet robot 1 is adapted to execute communication such as conversation with another pet robot 1 using a scale.

The pet robot 1 starts communication with another pet robot 1 in response to a predetermined operation from the user (for example, touching a touch sensor provided on the tail unit 5). Expresses the indicated command (outputs a predetermined scale). The master of the pet robot 1 that expresses the command indicating the start of this communication will be described below. On the contrary, another pet robot 1 that detects a command indicating the start of communication and follows it will be referred to as a slave hereinafter.

The master selects and executes one of preset scenarios (interview, compatibility check, etc.).

For example, in the interview scenario, the scale or motion corresponding to the conversation shown below is expressed by the master and the slave. Master "Good morning!" Slave "Good morning!" Master "What is your name?" Slave "xxx" (Sorry operation if not registered) Master "Owner name?" Slave "xxx" (Sorry if not registered Operation) Master "What is the generation?" Slave "xxx" Master "Goodbye" Slave "Goodbye"

FIG. 25 is a flow chart for explaining a compatibility check scenario. In step S71,
The master expresses a command to start communication. Corresponding to this, in step S81, the slave expresses a command of communication understanding (outputs a predetermined scale).

In step S72, the master issues a query command. In response to this, in step S82, the slave expresses a reply command based on its own instinct value. Specifically, a scale corresponding to the following conversation is developed by the master and the slave. Master "Good morning!" Slave "Good morning!" Master "Is it fun now?" Slave "YES / NO" Master "Is angry?" Slave "YES / NO" Master "Is sad now?" Slave "YES / NO""Master" Are you tired now? "Slave" YES / NO "

In step S73, the master diagnoses the compatibility based on the reply from the slave. Specifically, if the slave's state (whether it is fun, angry, sad, tired or not) and its own state match two or more items, it is determined that the compatibility is good. , If the slave state and the self state do not match two or more items, it is determined that the compatibility is bad.

[0128] In step S74, when the master determines that the compatibility is good in step S73, the master develops a command for an affection scenario (the master and the slave synchronously express the dance content). On the other hand, when it is determined that the compatibility is not good in step S73, a command for a confrontation scenario (a master and a slave play rock-paper-scissors, a winner wins, a loser expresses sad content) is expressed.

Corresponding to this, in step S83,
The slave develops the content corresponding to the command from the master (dancing or rock-paper-scissors in sync with the master, either happy or sad depending on the win or loss). This completes the description of the compatibility check scenario.

The description of the first to eighth characteristic behaviors of the pet robot 1 has been completed.

The first to eighth characteristic actions described above are not only executed by the animal type robot as shown in FIG. 1, but also, for example, a humanoid robot capable of bipedal walking, It may be executed by a virtual robot or the like that operates in the computer.

In the present specification, the steps for writing the program recorded on the recording medium are not limited to the processing performed in time series according to the order described, but may be performed in parallel even if they are not necessarily processed in time series. Alternatively, it also includes processes that are individually executed.

[0133]

As described above, according to the present invention, it is possible to realize a pet robot capable of actively executing autonomous behavior immediately after starting.

[Brief description of drawings]

FIG. 1 is a perspective view showing an example of the appearance of a pet robot to which the present invention is applied.

FIG. 2 is a block diagram showing an internal configuration example of the pet robot of FIG.

FIG. 3 is a block diagram showing a configuration example of a functional module of a pet robot.

4 is a diagram schematically showing an example of functions of an instinct / emotion management unit in FIG.

FIG. 5 is a diagram showing a mode transition of a pet robot.

FIG. 6 is a diagram showing details of the Wake Up mode of FIG.

FIG. 7 is a diagram showing an example of contents corresponding to a date / season.

FIG. 8 is a flowchart illustrating a date / season handling process by a pet robot.

FIG. 9 is a diagram showing a condition for transitioning between a state in which autonomous behavior is prioritized and a state in which voice recognition function is prioritized.

FIG. 10 is a diagram showing a predetermined scale broadcasted in a television program and the like, and contents executed corresponding to it.

FIG. 11 is a diagram showing a predetermined scale broadcast in a television program and the like, and contents added to contents operable in correspondence therewith.

FIG. 12 is a diagram in which a change in the degree of interest of a user to a pet robot is estimated.

13 is a diagram showing an ideal operation image of content by a pet robot for realizing the change in the degree of interest of the ideal user shown in FIG.

FIG. 14 is a diagram showing an actual operation image of contents by a pet robot for realizing the change in the degree of interest of the ideal user shown in FIG. 12;

FIG. 15 is a diagram schematically showing how the pet robot transitions to the Love mode when the frequency with which the user cares is high.

FIG. 16 is a flowchart illustrating an interactive content expression process performed by a pet robot.

FIG. 17 is a flowchart illustrating a process for achieving both autonomous behavior and reaction to information that is constantly input in the Vivid mode.

FIG. 18 is a flowchart illustrating an autonomous search action control process in Vivid mode.

FIG. 19 is a flowchart illustrating a turning process of a pet robot.

FIG. 20 is an external view of the pet robot that is performing the turning process as seen from above.

FIG. 21 is a diagram showing timing of turning of the head unit 4 and the body unit 2 of the pet robot in the turning process.

FIG. 22 is a flowchart illustrating processing for determining content to be expressed in Break mode.

[Fig. 23] Fig. 23 is a diagram showing that the exercise motivation (Exercise) of the instinct is adaptively changed depending on the size of the content and the frequency of occurrence of the content up to that point.

Figure 24: Exercise 82A and affection desire (Affectio)
n) Break mode corresponding to the matrix with 82B (first
It is a figure which shows thru | or 5th Break mode).

FIG. 25 is a flowchart illustrating a scenario of a compatibility check between a pet robot (master) and another pet robot (slave).

[Explanation of symbols]

31 sensor input processing unit, 32 information processing unit, 41
Angle detection unit, 42 Volume detection unit, 43 Voice recognition unit, 44 Image recognition unit, 45 Pressure detection unit, 46
Position detector, 47 Switch input detector, 61
Instinct / emotion management unit, 62 behavior management unit, 63 posture transition management unit, 64 control unit, 65 voice synthesis unit, 6
6 Sound data generator

   ─────────────────────────────────────────────────── ─── Continued front page    F term (reference) 2C150 CA02 DA05 DA24 DA25 DA26                       DA27 DA28 DF03 DF04 DF06                       DF08 DF33 ED10 ED42 ED47                       ED52 EF03 EF07 EF09 EF16                       EF17 EF22 EF23 EF28 EF29                       EF33 EF36                 3C007 AS36 CS08 KS21 KS31 KS36                       KS39 KT01 MT14 WA04 WA14                       WB19 WB23

Claims (15)

[Claims] 1. A robot apparatus for selectively executing a plurality of preset contents, wherein the selecting unit selects one of the preset contents, and the selecting unit. Expression means for expressing the content selected by, the selection means selects a large content in a predetermined period after activation, the expression means, the content selected by the selection means, A robot device, which is frequently expressed in a predetermined period after activation. 2. The robot apparatus according to claim 1, wherein the selecting unit selects the content corresponding to at least one of a season, a date, and a time. 3. The selection means selects the content in response to at least one of emotion and desire set during a period from the time of the previous termination to the time of the current activation. The robot apparatus according to claim 1. 4. The expression unit adjusts the expression frequency of the content in response to at least one of emotion and desire set during the period from the end of the previous time to the start of the present time. The robot apparatus according to claim 1, wherein: 5. The robot apparatus according to claim 1, further comprising voice recognition means for recognizing a user's utterance, and detection means for detecting a user's contact. 6. The selection unit selects the content according to at least one of the frequency of voice recognition by the voice recognition unit and the frequency of contact of a user by the detection unit. 5. The robot apparatus according to item 5. 7. The expression means includes a notification means for notifying a user that the voice recognition means has performed voice recognition and that the contact of the user has been detected by the detection means. The robot apparatus according to Item 5. 8. The robot apparatus according to claim 5, wherein the voice recognition unit also recognizes a scale. 9. The robot apparatus according to claim 8, wherein the selection unit selects a predetermined content when the predetermined scale is recognized by the voice recognition unit. 10. The robot apparatus according to claim 8, further comprising an addition unit that adds content that can be expressed when a predetermined scale is recognized by the voice recognition unit. 11. The robot according to claim 8, further comprising output means for outputting a scale as a response corresponding to the recognized scale when the voice recognition means recognizes a predetermined scale. apparatus. 12. An acquisition unit for acquiring an image signal, a detection unit for detecting a moving body based on the image signal acquired by the acquisition unit, and an acquisition unit for detecting a detection result of the detection unit. The robot apparatus according to claim 1, further comprising a storage unit that stores the acquired image signal. 13. A robot control method for a robot apparatus for selectively executing a plurality of preset contents, the selecting step of selecting one of the preset contents from the plurality of contents. , Including an expression step of expressing the content selected in the processing of the selection step, the processing of the selection step selects a large content in a predetermined period after activation, the processing of the expression step, A robot control method, wherein the content selected in the process of the selecting step is expressed with high frequency in a predetermined period after activation. 14. A program for a robot apparatus for selectively executing a plurality of preset contents, the selecting step of selecting one of the preset contents from the plurality of contents. And, including an expression step of expressing the content selected in the processing of the selection step, the processing of the selection step selects a large content in a predetermined period after activation, the processing of the expression step, A recording medium on which a computer-readable program is recorded, wherein the content selected in the process of the selecting step is expressed with high frequency in a predetermined period after activation. 15. A selection step of selecting one of the preset contents from among the preset preset contents in a computer for a robot device that selectively executes preset contents. The expression step of expressing the content selected in the processing of the selecting step is executed, the processing of the selecting step selects a large content in a predetermined period after activation, and the processing of the expressing step is A program, characterized in that the content selected in the process of the selecting step is expressed with high frequency in a predetermined period after starting.