JP2003285286A - Robot - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To prevent a robot from growing before a user learns a function with usage the user needs to learn. <P>SOLUTION: An acquisition degree indicating the degree of the user learning a function is determined by an acquisition evaluation section. A growth evaluation section 213 evaluates experience in use of the user, and the degree of the growth of the robot is determined based on the evaluated experience and the acquisition degree. A scenario execution section 200 and an operation control section 202 control the robot based on the degree of the growth evaluated by the section 213. <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, and more particularly to a robot device that grows according to a user's experience of using the robot device.

[0002]

2. Description of the Related Art Conventionally, this type of robot apparatus is used, for example, at home, and changes or grows in a simulated manner according to the degree of involvement of the user, and makes the user feel the change or growth to be attached. It is used to hold you.

An example of a conventional robot device will be described with reference to FIGS. 8 and 9.

As shown in FIG. 8, the external appearance of a conventional robot apparatus is composed of a head unit 204, a body unit and a wheel unit 205.

The head unit 204 has a head button 100.
, Voice recognition microphone 101, and two CCD cameras 1
02 and a plurality of LEDs 103, and the head unit 2
A neck 108 for rotating 04 vertically and horizontally is connected to the body unit.

The body unit is a microphone 1 for detecting the direction of a sound source.
04, the speaker 105, the ultrasonic sensor 106,
And a power switch 110.

The wheel unit 205 includes the proximity sensor 10
7 and wheels 109.

The head button 100 is an electric switch,
It can detect whether the switch is on or off,
Further, it is possible to handle different inputs depending on how long the head button 100 is pressed.

The voice recognition microphone 101 is a directional microphone and is suitable for voice recognition in which the directional characteristic is maximized when the user speaks directly at the face of the robot.

The two CCD cameras 102 are stereo cameras installed in a pre-calibrated state such that the distance between the two cameras and the axes of the two cameras are aligned, and the neck 108 is directed downward. Used for input for detecting obstacles on the floor surface and for input for detecting and identifying a person with the neck 108 facing upward. .

The plurality of LEDs 103 are embedded in parts corresponding to eyes, ears, mouth, and cheeks, respectively, and inform the user of the role of emotional expression of the robot and the state of robot sensing such as sound detection and person detection. Have a role and.

The sound source direction detecting microphone 104 has a total of three microphones attached to the left and right sides and the front side of the collar portion.
It is used to estimate the direction of a sound source by measuring the time difference between arriving sounds.

The speaker 105 outputs a synthesized voice, a recorded voice, a sound effect, music and the like.

The ultrasonic sensor 106 has a short distance (eg,
There is a sensor for measuring a distance to an object at a distance of up to about 50 cm and a sensor for measuring a distance to an object at a medium distance (for example, up to about 120 cm). The sensor for medium distance is attached to the front of the central part of the robot.
This ultrasonic sensor 106 is used together with obstacle detection using the CCD camera 102, and is used to detect and avoid obstacles when the robot moves.

The power switch 110 is used to turn on / off the power of the robot.

The proximity sensor 107 is used to detect steps such as stairs and prevent falling from the stairs.

The wheels 109 are attached to the left and right sides of the lower part of the body, one wheel 109 capable of independently providing a rotational angular velocity, and one caster is attached to the rear of the body.

The control system applied to the conventional robot apparatus shown in FIG. 8 has a scenario execution unit 900 as shown in FIG.
A scenario DB unit 901, an operation control unit 902, a dialogue selection unit 210, a dialogue DB unit 211, a parameter storage unit 904, and a growth determination unit 903.

The LED 203 and the head unit 2 in FIG.
04 actuator 204A, wheel unit 205
The actuator 205A, various sensors 206, microphone 207, speaker 208, and camera 209 are controlled by the operation control unit 902.

Here, the LED 203 is the LED 10 of FIG.
3, the actuator 204A is an actuator for moving the neck 108 of FIG. 8, and the actuator 205A is shown in FIG.
An actuator for moving the wheel 109 of the vehicle, various sensors 206 are the head button 100 and the ultrasonic sensor 10 of FIG.
6, each sensor of the proximity sensor 107, the microphone 20
7 is the voice recognition microphone 101, the sound source direction detection microphone 104 in FIG. 8, and the speaker 208 is the speaker 10 in FIG.
5. The camera 209 is the CCD camera 102 shown in FIG.

The parameter storage unit 904 stores growth parameters indicating the degree of growth of the robot apparatus (parameter values are, for example, 1, 2, and 3) and emotion parameters indicating the degree of emotion of the robot apparatus. ing.

The serif DB section 211 stores the growth parameter value and emotion parameter value for each serif category name (hereinafter, referred to as serif type) that represents the serif utterance situation when the serif is classified according to the situation. Based on that, the corresponding line is stored. The serif type is, for example, a "serious greeting" that is used when a robot device greets a person, such as "Good morning" and "Good morning". It represents the category name "morning greeting".

In the scenario DB section 901, "move",
It stores various scenarios that indicate actions such as “search for a person” and “greeting”. Each scenario has a scenario corresponding to the parameter value of the growth parameter. There are three types of “search for people” scenarios corresponding to the parameter values of the growth parameter. For example, when the parameter value of the growth parameter is 1,
If you can't detect a person without moving your neck, always run the "Find person" scenario for a certain period of time, but when the parameter value of the growth parameter is 3, you sometimes shake your neck from side to side If there is a mechanism (not described) that the robot imitates emotions, for example, if the emotional state is good, a long time “Find person” scenario is used. Although it is operated, the scenario is described so that the “search for person” scenario is operated only for a short time when the emotional state is bad. In this way, as the growth parameters go up, the user feels that the robotic device has emotions, but on the other hand, it does not detect a person while moving his / her neck. Since the execution time of the "search for" scenario is not constant, the user may exit the "search for person" scenario and execute another scenario at an unexpected timing.

Each scenario in the dialogue DB section 211 includes a description of the lighting control processing of the LED 203, a description of the operation control processing of the actuator 204A of the head unit 204, and a description of the actuator 205A of the wheel unit 205. Description of motion control process and speaker 2
08 description of voice output control processing and operation control unit 90
2 is the measurement result of the various sensors 206 sent from the sensor 2 and the description of the process when there is a sensor event input issued as the analysis result of the internal state of the robot, and the voice recognition which is the voice recognition result of the voice input through the microphone 207. Regarding a description of processing when an event is input, an image recognition obtained by analyzing an image input through the camera 209, a description of processing when an event is input, and transition to the next scenario (state) Description and are described.

The growth determination unit 903 determines the growth stage of the robot apparatus based on the experience of the robot such as the elapsed time after the robot apparatus is first started, the total startup time, and the number of interactions with the user. Growth parameters predetermined according to stages (parameter values are, for example, 1, 2,
3 kinds of 3. ) Is set in the parameter storage unit 904.

The scenario execution unit 900 selects one scenario from various scenarios that are stored in the scenario DB unit 901 and indicate operations such as “move”, “search for a person”, and “greeting”. The commands described in 1. are sequentially transmitted to the operation control unit 902,
02 performs processing corresponding to various events indicating the occurrence of operation results and the occurrence of detection results. When the command described in the selected scenario has a serif type, the scenario execution unit 900 sends this command to the serif selection unit 210, receives the serif from the serif selection unit 210, and includes this serif in the command to be uttered. It is sent to the operation control unit 902.

The dialogue selection unit 210 is a scenario execution unit 9
00, the specific dialogue is selected from the dialogue DB unit 211 based on the dialogue type described in the command received, the growth parameter and the emotional parameter stored in the parameter storage unit 904, and the dialogue is transmitted to the scenario execution unit 900. . When the serif type is "morning greeting," select "Good morning" or "Good morning."

The operation control unit 902 is a scenario execution unit 90.
A process of interpreting and executing a command given from 0, an analysis process of an input from various sensors 206, a voice signal from the microphone 207, and an image signal from the camera 209, and the process result is executed as a scenario in the form of an event. The process of transmitting to the unit 900 is performed. At this time, the scenario execution unit 90
When the command given from 0 is a command to speak a speech, the operation control unit 902 generates a speech signal corresponding to this speech by the speech synthesis function, and outputs the generated speech signal from the speaker 208.

Here, the operation of the robot apparatus when, for example, a situation of searching for a person is reached will be described.

When the robot apparatus is in a situation of searching for a person, the scenario execution unit 900 reads from the scenario DB unit 901 the “search for a person” scenario corresponding to the parameter value of the growth parameter in the “search for a person” scenario. Run. By this execution, the robot device notifies the user that he is searching for a person, and the camera 209
Search for people while performing image recognition processing on the input image from. Here, in order to notify the user that he is searching for a person, the scenario execution unit 900 "searches for a person",
Dialogues such as "Who is there?" And "Where is Mr. A?" Are sent to the operation control unit 902, the operation control unit 902 generates an audio signal, and the speaker 208 outputs this line. In order to search for a person while performing image recognition processing on the input image from the camera 209, the scenario execution unit 900 uses
The operation control unit 902 is instructed to “search for a person while performing image recognition processing on the input image from the camera 209”, and the operation control unit 902 searches for a person while performing image recognition processing on the input image from the camera 209.

At this time, if the user is not familiar with the person detecting function of the robot apparatus, it takes time for the robot apparatus to find the user.

The reason for this will be described.

At present, there are already devices having a person detecting function by image recognition, but in reality, they cannot exhibit desirable performance in a general environment where a home robot device is used. Therefore, when using a device having a person detection function by image recognition, by devising the installation position of the camera 209 or the like, a limited environment capable of sufficiently exhibiting the expected performance is created, It is necessary to use it. In addition, depending on the content of the image recognition processing, there are many cases where the user is requested to devise an operation that helps the person detection by the image recognition device. An example of requesting this user to devise a motion that helps in person detection is when motion information is used in the person detection process. It's not working, it needs to move a little. The image recognition technology adopted in this robot apparatus also requires such restrictions on the usage environment conditions and the user to devise a usage method. However, in order to move with a household robot that moves,
It is difficult to improve the environmental conditions by devising the installation position of the camera 209, and it is necessary for the user to understand the usable environmental conditions to some extent.

Therefore, if the user is not familiar with the person detecting function of the robot apparatus for the above reason,
It takes time for the robotic device to find the user.

If the user is unfamiliar with this person detection function and the user's experience with the robot apparatus advances, the growth determination unit 903 increases the growth parameter value, and the robot apparatus changes and grows.

This occurs not only in the person detecting function, but also in a function such as a voice recognition function which requires the user to learn how to use the robot in order to master it. As for the voice recognition function, at present, the level at which humans perform voice recognition in a conversation between humans and the level of voice recognition by a robot are far from each other. In the voice recognition in the current robot, the user has a distance of, for example, 80 cm from the robot microphone (the optimum distance for the robot to recognize the voice) and an appropriate voice volume (the sound pressure level is not saturated inside the robot). , And the level is not too low), and it is necessary to speak not with spoken words such as "Well, please give me a message", but with words centered on words such as "Message" and "Act on message". . Therefore, unless the user knows how to use such a voice recognition function, the user cannot make the robot recognize the voice unless the user makes a trial and error call.

[0037]

In the above-mentioned conventional robot apparatus, the experience of the user's robot apparatus such as the elapsed time since the robot apparatus was first started, the total startup time, the number of interactions with the user, etc., increases. , The growth determination unit increases the parameter value of the growth parameter,
The robot device changes and grows, the scenario execution unit executes the scenario according to this growth parameter value, and the robot device operates according to this growth, so for the functions that the user needs to learn how to use. And if the robotic device grows before the user learns this function, the user will not be able to use this function more and more, so the user will have a bad impression on the robot and thus the robotic device. There is a problem that getting tired of is encouraged.

The object of the present invention is to eliminate the above-mentioned drawbacks of the prior art, so that for a function that the user needs to learn how to use, the robot apparatus grows before the user learns this function. The purpose is to provide a robot device that does not exist.

[0039]

A first robot apparatus of the present invention is a robot apparatus having a plurality of functions and growing according to a user's experience of using the robot apparatus. A first mastering degree judging means for judging a first mastering degree showing a degree; the user's experience of use for judging the user's use experience; and the first mastery degree judging means for judging the use experience. A growth degree determination unit that determines the degree of growth of the robot apparatus based on the degree of learning, and a robot apparatus control unit that controls the robot apparatus based on the degree of growth determined by the growth degree determination unit. It is equipped with.

Further, the first learning degree judging means of the first robot apparatus of the present invention performs a test for confirming the degree of learning of the function for the user on a plurality of functions of the own robot apparatus. The first learning level is determined according to the test result.

Further, the test in the first learning degree judging means of the first robot apparatus of the present invention receives a response from the user with respect to the display content displayed on the display means connected to the own robot apparatus. I try to do it.

Further, the first learning degree judging means of the first robot apparatus of the present invention is adapted to judge the first learning degree based on the use history of the user's own robot apparatus.

Further, the first learning degree judging means of the first robot apparatus of the present invention is the number of successful action results of the robot apparatus corresponding to the function to be learned by the user,
The usage history including the number of unsuccessful times and the average time until an action result is obtained is totaled for a predetermined period and indicates whether or not the user has learned the function based on a predetermined standard. I try to judge the degree of acquisition.

The second robot apparatus of the present invention is a robot apparatus having a plurality of functions and growing according to a user's experience of using the robot apparatus, and shows the degree of learning of the function by the user for each function. Second learning degree judging means for judging a second learning degree, and a function use for teaching the user the teaching contents according to the second learning degree of the function judged by the second learning degree judging means. Method explanation means,
It is configured with.

Further, the second learning degree judging means of the second robot apparatus of the present invention performs a test for confirming the degree of learning of the function with respect to the user for each function, and according to the test result, the above-mentioned The second degree of learning is determined for each function.

Further, the test in the second learning degree judging means of the second robot apparatus of the present invention receives a response from the user with respect to the display content displayed on the display means connected to the own robot apparatus. I try to do it.

Further, the function use method explanation means of the second robot apparatus of the present invention is the teaching content according to the second learning degree of the plurality of teaching contents in the function to be learned by the user. Is displayed on the display means connected to the robot device itself, and the user is instructed by receiving a response from this display by the user.

[0048]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is a diagram showing an example of the external appearance of the robot apparatus of the present invention.

In this figure, an AV terminal 111, an AV cable 112, a monitor 113 and a mouse 114 are added to FIG. 8 showing the appearance of a conventional robot apparatus. The same numbers as those used in FIG. 8 have the same functions.

FIG. 2 is a block diagram showing the first embodiment of the robot apparatus according to the present invention.

In this figure, a monitor 216, a mouse 217 and a storage medium 215 are added to FIG. 9 showing a control system of a conventional robot apparatus. The monitor 216 and the mouse 217 are the same as the monitor 113 and the mouse 114 shown in FIG. These are used when explaining the function of the robot apparatus to the user and when performing a test to confirm the degree of learning of this function.

Further, the scenario DB section 201,
The scenario execution unit 200 is different from the growth determination unit 213, the operation control unit 202, and the parameter storage unit 212, and a user learning degree determination unit is added.

In the scenario DB unit 201, a "functional lesson" scenario 201A is added to the scenario DB unit 901 of FIG. In the "functional lesson" scenario 201A, a scenario such as a test for confirming the function explanation to the user and the degree of learning of the function is described.

In the scenario execution section 200, the execution operation of the "functional lesson" scenario 201A is added to the execution operation of the scenario execution section 900 of FIG.

The parameter storage unit 212 stores growth parameters (parameter values are, for example, 1, 2, and 3 shown in FIG. 9) indicating the degree of growth of the robot apparatus.
seed. ) And an emotion parameter (not shown) indicating the degree of emotion of the robot apparatus, and a learned flag indicating whether or not the user has learned the function of the robot apparatus is stored for each function of the robot apparatus. Further, each of these functions has a plurality of items to be learned, and a plurality of sub-clear flags indicating whether or not the items to be learned are learned are stored for each of these functions. For example,
Regarding the image recognition function, the items that users should learn are
The user needs to bring his face within the viewing angle of the robot camera 209. Optimally, the face is 80 cm from the robot camera 209. The user needs to move his face a little. Don't tilt your face too much. People cannot be detected well in backlit conditions or in dark environments. The accuracy of person identification by image recognition cannot be improved unless face registration is performed to some extent. There are six sub-clear flags.

The learned flag and the sub-clear flag are all reset when the robot apparatus is purchased and the power switch 110 is turned on for the first time, and the user receives the function lesson prepared for each function. If the user later answers the question to confirm the degree of mastery of the function of the robot device, and if the user answers correctly to the item with this function, the sub-clear flag of this item is set and this function is set. When the setting rate of the plurality of sub-clear flags (second degree of learning: indicating, for example, the proportion of flags set among the plurality of sub-clear flags) is equal to or more than a predetermined value, the function has been learned. Set the flag.

The growth determination unit 213 performs a process of updating the growth parameter in the parameter storage unit 212 when the power switch 110 of the robot apparatus is turned on. At this time, the set rate of the learned flag in the parameter storage unit 212 (first
Degree of learning: Indicates, for example, the ratio of flags set among a plurality of learned flags. ) And the user's experience of using the robot apparatus, the growth parameter is set in the parameter storage unit 212.

The user learning level determination unit 214 sets the sub clear flag in the parameter storage unit 212 or sets the sub clear flag in the parameter storage unit 212 according to an instruction from the scenario execution unit 200 (second learning level). When is greater than or equal to a predetermined value, the mastered flag of the function corresponding to this sub-clear flag is set.

The same numbers as those used in FIG. 9 have the same functions.

Next, the operation of the robot apparatus (FIG. 2) of the present embodiment will be described in detail with reference to FIGS. 3, 4, 5 and 6.

FIG. 3 is a diagram showing an example of states of the robot apparatus shown in FIG. 2 and transitions between the states.

FIG. 4 is a flowchart showing an example of processing performed in the function lesson state.

FIG. 5 is a diagram showing an example of display of teaching contents of a function performed in the function lesson state.

FIG. 6 is a diagram showing an example of a display of test contents for confirming the degree of learning of the function of the user.

In FIG. 1, description will be made with reference to FIG.

When the power switch 110 of the robot apparatus is turned on by the user, the robot apparatus transits to the state 300 immediately after activation, and the scenario execution unit 200 reads the scenario “immediately after activation” from the scenario DB unit 201 and executes it. , "Starting is completed" is sent to the operation control unit 202, and the motor of the neck 108 and the wheel 10 are sent.
9 to operate the servo with the motor, the growth determination unit 21
Various types of initialization processing such as causing the 3 to update the growth parameters are performed.

The operation control unit 202 includes the scenario execution unit 20.
From 0, the line "starting is completed" is received, a voice signal is generated, and this "starting is completed" is output from the speaker 208 to notify the user that the starting is completed.

The scenario execution unit 200 sends a servo control start command to the operation control unit 202 in order to operate the servo between the motor of the neck 108 and the motor of the wheel 109, and the operation control unit 202 receives the command. The actuators 204A and 205A start servo control.

The scenario execution unit 200 includes the growth determination unit 21.
In order to make 3 perform the growth parameter update processing, the growth determination unit 213 is instructed to execute the growth parameter update processing, and the growth determination unit 213 causes the growth determination unit 213 to set the learned flag set rate in the parameter storage unit 212 (first (Learning degree), the set rate that was examined, and the elapsed time since the startup for the first time,
Based on the total start-up time, the experience of using the robot such as the number of interactions with the user, the growth stage of the robot apparatus is determined, and the growth parameter predetermined according to this growth stage is set in the parameter storage unit 212. Growth determination unit 2
13 always counts the elapsed time after starting for the first time, the total starting time, the number of times the head button 100 is pressed,
The number of times of strokes with the head, the number of times of detecting a person, and the like, the number of times of interaction with the user are received from the scenario execution unit 200 and calculated each time.

The robot apparatus has, for example, three growth stages, which are represented by growth parameters. The lowest growth stage has a growth parameter of 1, the next growth stage has a growth parameter of 2, and the highest growth stage has
The growth parameter is 3. The condition for the growth parameter 3 is that the elapsed time after the first activation is, for example, 14 days or more, the total activation time is, for example, 30 hours or more, and the number of times the head button 100 has been pressed and the number of times the head has been stroked is recognized by voice. Satisfies that the total of the number of words and the number of detected people is 1000 or more, and that the user can learn all the functions that the user should learn (set rate (first learning level) is 100%) It is to be.

Whether or not the user has learned the function to be learned is checked by whether or not the learned flag in the parameter storage section 212 corresponding to the function to be learned is set. Also, the set rate is calculated by the parameter storage unit 21.
It is decided by looking at the set states of a plurality of learned flags corresponding to the plurality of functions in 2 to be learned.

The condition for the growth parameter 2 is such that the condition for the growth parameter 3 is not satisfied, the elapsed time after the first activation is, for example, 7 days or more, the total activation time is, for example, 15 hours or more, and the head button is pressed. By satisfying that the total of the number of times 100 is pressed, the number of strokes of the head, the number of speech-recognized words, and the number of detected people is 500 or more and the set rate (first learning level) is 50% or more. is there. The growth parameter 1 is set when the growth parameters 2 and 3 are not satisfied.

When the processing of the “immediately after starting” scenario is completed, the robot apparatus moves from the immediately after starting state 300 to the moving state 3
01, the scenario execution unit 200 reads the “movement” scenario from the scenario DB unit 201, executes the scenario, sends a command to the operation control unit 202, and moves to the robot apparatus so-called a walk that is autonomously moving. To perform.

When the robot apparatus walks for a certain period of time, the state transits to the resting state 302, and the scenario execution unit 200 reads the "resting" scenario from the scenario DB unit 201 and executes it, and stops the robot apparatus to make it quiet.

This resting state 302 is a state in which the robot apparatus is resting as an effect, and after resting for a certain period of time, it transits to the moving state 301, and the scenario executing section 200
The “move” scenario is read from the scenario DB unit 201 and executed.

When the robot apparatus is in the moving state 301 or the resting state 302, if there is any action from the user, for example, if the user calls the robot apparatus "Oh," this call is issued by the microphone 207.
When the time when the picked-up sound exceeds the sound pressure equal to or higher than a predetermined threshold for a certain time or longer, the operation control unit 202 transmits a sound source detection event to the scenario execution unit 200, and the robot device Transitions to the search for person state 310.

When the user strokes the robot device (head button 100) while the robot device is in the moving state 301 or the resting state 302, the operation control unit 202 detects ON / OFF of the head button 100. Send the event that the head button 100 has been stroked to the scenario execution unit 200,
The robot apparatus transits to the greeting state 311.

When the robot apparatus transits to the state 310 for searching for a person, the scenario execution unit 200 reads the scenario “search for person” from the scenario DB unit 201 and executes it, and the robot apparatus informs the user that he is searching for a person. A person is searched for while notifying and while performing image recognition processing on the input image from the camera 209.

The scenario execution unit 200 notifies the user that he or she is looking for a person, "searching for a person", "is there anyone?", "Where is Mr. A?"
And the like to the operation control unit 202, and the operation control unit 20
2 generates an audio signal and outputs this line from the speaker 208.

The scenario executing unit 200 searches for a person while performing image recognition processing on the input image from the camera 209.
The scenario execution unit 200 instructs the operation control unit 202 to “search for a person while performing image recognition processing on the input image from the camera”, and the operation control unit 202 performs image recognition processing on the input image from the camera 209. Search for people.

In the state 310 for searching for a person, when the image recognition processing succeeds in detecting a person, that is, when the robot apparatus finds a user, a person detection event is transmitted from the operation control section 202 to the scenario execution section 200, and the robot apparatus is detected. Makes a transition to the greeting state 311.

When the robot device transits to the greeting state 311, the scenario execution unit 200 reads the "greeting" scenario from the scenario DB unit 201 and executes it, and the robot device greets the user and speaks with the user. Notify that the interaction has started. That is, the scenario execution unit 200 sends the lines such as “Good morning”, “Good afternoon”, and “Good evening” to the operation control unit 202 according to the time zone determined by the internal clock, and causes the operation control unit 202 to generate a voice signal. This dialog is output from the speaker 208, a dialog such as “Let's talk” is sent to the operation control unit 202, and the operation control unit 202 generates a voice signal to output the dialog from the speaker 208.

When the scenario execution unit 200 finishes executing the "greeting" scenario, the robot apparatus transits to the function lesson state 312, and the scenario execution unit 200 reads the "function lesson" scenario 201A from the scenario DB unit 201 and executes it. To do.

As an example of the processing performed in the function lesson state 312, a function lesson of the person detecting function by image recognition will be described with reference to the flowchart of FIG. 4 and the screen images of FIGS. 5 and 6.

When the scenario execution unit 200 executes the "functional lesson" scenario 201A, step S400
At, the user learning degree determination unit 214 is inquired whether or not the function to be learned remains. The user learning degree determination unit 214 includes a parameter storage unit 212.
Check the learned flag of and check whether the user has learned all the functions to be learned by the setting status of the learned flag. When there is one or more unlearned functions, the method of using the function with the highest priority, in other words, the function name that should be remembered first is described in step S401 and subsequent steps. When the user has learned all the functions, the process ends without doing anything, and the robot apparatus transits to the interactive state 313.

At step S401, the AV cable 112 determines whether the screen output is possible by the AV cable 112 of the robot apparatus.
Whether the scenario execution unit 2 is connected to the terminal 111 or not
00 inquires of the operation control unit 202 to investigate.
As a result of the examination, screen output is possible (AV cable 112 is AV
If it is connected to the terminal 111), step S
Proceed to 404. If screen output is not possible, the process proceeds to step S402.

In step S402, a utterance of a content requesting the user to make the screen output possible (for example, the scenario executing unit 200 inserts an "AV cable,
Please connect to a monitor TV "to the operation control unit 202, and the operation control unit 202 causes the speaker to output this line. ), And it progresses to step S403.

In step S403, the scenario execution unit 2
00 waits for a predetermined time for an event (described as a screen output enable event) issued when the operation control unit 202 transits to the screen output enable state. Operation control unit 202
Is detected by the sensor 206 from the state where the AV cable 112 is not connected to the AV terminal 111.
2 detects a change to the state of being connected to the AV terminal 111, and issues a screen output enable event. If there is a screen outputable event within the predetermined time, step S40
If there is no screen outputable event within the predetermined time, the process ends and the robot apparatus transits to the interactive state 313.

In step S404, first, the scenario execution unit 200 determines that the monitor 2 connected to the robot apparatus has
16 is displayed an explanation screen of a function that has not been learned.
For example, when the unlearned function is the “person detection function by image recognition”, and when the setting rate (second learning degree) of the sub-clear flag of this function is “0”, for example, FIG.
The explanation screen as shown in FIG.

Items to be displayed on the sentence explanation section 500 of the explanation screen will be described.

For example, the user is required to bring his / her face within the viewing angle of the camera 209 of the robot for the item to learn the "person detection function by image recognition".
Optimally, the face is 80 cm from the robot camera 209. The user needs to move his face a little. Don't tilt your face too much. People cannot be detected well in backlit conditions or in dark environments. The accuracy of person identification by image recognition cannot be improved unless face registration is performed to some extent. There are six
0 causes the user learning degree determination unit 214 to check the set status of the sub-clear flag of the “person detection function by image recognition”, and the set rate (second
When the set rate is, for example, “0”, the three users with the smallest numbers must bring their faces within the viewing angle of the camera 209 of the robot.
Optimally, the face is 80 cm from the robot camera 209. The user needs to move his face a little. 3 items are displayed on the explanation screen. And
Next, in the function lesson that is performed when the robot apparatus is started, among the items for which this function has not been learned, three small numbers are displayed on the explanation screen. At this time, the number of items to be displayed on the explanation screen may be increased or decreased, or the items to be displayed on the explanation screen may be selected depending on the value of the set rate of the sub-clear flag.

The scenario execution unit 200 displays an explanation screen of how to use the "person detection function by image recognition" stored in advance in the storage medium 215 in order to display the explanation screen as shown in FIG. 5 on the monitor 216. The operation control unit 202 is instructed to display the above items, and the operation control unit 202 retrieves from the storage medium 215 an explanation screen of how to use the “person detection function by image recognition” together with the items and monitor 216. To display.

In step S404, next, the scenario execution section 200 asks the user to press the video playback button 501 after the user has read and understood the items of the sentence explanation section 500 displayed on the monitor 216 (monitor 2).
A mouse 217 connected to the mouse 16 is used to click a video playback area, etc.) and the method of use will be described using video images. In other words, when the scenario execution unit 200 receives a video playback button ON event from the operation control unit 202, the scenario execution unit 200 operates to display a video image of how to use this "person detection function by image recognition" stored in the storage medium 215 in advance. Instructing the control unit 202, the operation control unit 202
A video image of how to use the “person detection function by image recognition” is extracted from the storage medium 215 and displayed on the monitor 216. In this video image, important points for making good use of a person's skillful use of functions will be explained by moving pictures while displaying captions (captions) at the bottom of the screen. When this explanation ends, the explanation screen of FIG.
Display in 6.

In step S404, finally, the scenario execution unit 200 asks the user to press the test button 502 (eg, click the test area with the mouse 217 connected to the monitor 216), and the "image" shown in FIG. 6 is displayed. A question screen of the confirmation test of “person detection function by recognition” is displayed on the monitor 216, and it is tested (checked) whether or not the user has learned how to use the “person detection function by image recognition”. (The question screen of this confirmation test corresponds to the item of the sentence explanation section 500 shown in FIG. 5.) That is, when the scenario execution section 200 receives the test button ON event from the operation control section 202, it is stored in advance. It corresponds to one item in the items of the sentence explanation part 500 shown in FIG. 5 among the question screens of the plurality of confirmation tests corresponding to the number of items of “person detection function by image recognition” stored in the medium 215. The operation control unit 202 is instructed to specify a question screen and display this question screen.
Is the scenario execution unit 2 stored in the storage medium 215.
00, the question screen of the confirmation test of the “person detection function by image recognition” designated from 00 is taken out and displayed on the monitor 216.

When the user answers the displayed question by voice, the operation control section 202 generates an answer event which is the answer content, and the scenario executing section 200 receives this answer event and responds to this question. It is determined whether or not the answer is correct, and the operation control unit 202 displays the sentence explanation unit 500 shown in FIG.
A question screen corresponding to the next item among the items in the above is displayed, and similarly, a response event for this question is received from the operation control unit 202, and whether or not the received response event is the correct answer to this question is displayed. to decide.

When all the problems corresponding to the plurality of items to be learned prepared in advance for the "person detecting function by image recognition" are completed, the process proceeds to step S405.

In step S405, the scenario execution unit 2
00 indicates that when the user's answer to the question given in step S404 has a correct answer, it is assumed that the user has learned the item of the function corresponding to this correct question, and the user learns to set the sub-clear flag corresponding to this item. Instructing the degree determining unit 214, the user learning degree determining unit 214 sets the instructed sub clear flag. The scenario execution unit 200 performs this with respect to the user's answers to all the questions set in step S404, and if even one of the user's answers is correct, step S406.
Proceed to. When all the answers of the user are incorrect, the process ends, and the robot apparatus transits to the dialogue state 313.

In step S406, the scenario execution unit 2
00 is used by the user learning degree determination unit 214 to determine whether or not the user has learned how to use the function to be learned.
Instruct. Upon receipt of this instruction, the user learning level determination unit 214 checks the setting status of each of the plurality of subclear flags corresponding to the designated function, and determines the setting rate (second learning level) of the subclear flag of this function, When the set rate is equal to or higher than the predetermined set rate, it is determined that the user has learned this function, the learned flag corresponding to this function is set, and the process ends. "Function lesson" scenario 20
When the execution of 1A is completed, the robot apparatus enters the conversation state 31.
Transition to 3.

When the robot apparatus transits to the dialogue state 313, the scenario execution unit 200 reads the "dialogue" scenario from the scenario DB unit 201 and executes it to hear the presence or absence of a request from the user and realize the requested content. Or

For example, a dialogue such as "Are you not requesting anything?" Is sent to the operation control unit 202, the operation control unit 202 generates a voice signal, and this speech is output from the speaker 208. However, if the user receives a message from the user saying "tell me a message" from the microphone 207 and recognizes this line, the user receives a message using the microphone 207, and this message is sent to the message source user name and message destination user name. Is stored in a storage medium 215 such as an internal HD (not shown).

When it is obtained from the voice recognition result that the user has input a voice such as “Bye-bye” or “Good night” that prompts the end of the dialogue when the robot apparatus is in the dialogue state 313, A dialogue end event is transmitted from the operation control unit 202 to the scenario execution unit 200, and the non-personal action state 30 (moving state 301 or resting state 3
02).

FIG. 7 is a block diagram showing a second embodiment of the robot apparatus of the present invention.

In this figure, a user use history storage section is added to FIG. 2 showing the first embodiment of the present invention.

The same number as that used in FIG. 2 has the same function.

The user use history storage unit 700 stores a use history including the number of times of success and non-success of the action result of the robot apparatus corresponding to the function to be learned by the user, and the average time until the action result is obtained. is doing.

That is, for example, 2002/02/1
5: First activation: 100 times of voice recognition: Number of voice recognition rejects = 38 times: Number of voice recognition non-rejects = 62
No .; 2002/02/15: First activation: average time until human detection = 3400 [ms], 2002/02/1
5: Second activation: 50 times of voice recognition: 40 times of voice recognition rejects: 10 times of voice recognition non-rejections; 10 times;
2002/02/15: Second activation: Data such as average time until person detection = 3000 [ms] is stored for about one week in the past from the current time. For example, this data is stored in the user use history storage unit 700 each time the scenario execution unit 702 performs voice recognition or image recognition to detect a person.

In addition to the operation in the first embodiment, the user learning degree determination unit 701 receives the usage history stored in the user usage history storage unit 700 according to an instruction from the scenario execution unit 702, for example, the current time. Then, the voice recognition reject rate for the past week and the average time from person detection to person detection for the past week are calculated. If the voice recognition reject rate is, for example, 30% or less, the parameter storage unit 21
The learned flag corresponding to the voice recognition function of 2 is set, and the time from the average person detection to the person detection is, for example, 2
If it is 500 ms or less, the learned flag corresponding to the person detection function is set.

The operation of the user learning degree judging unit 701 for checking the usage history stored in the user usage history storage unit 700 and setting the learning completed flag is performed, for example, in the state 300 immediately after the robot apparatus is started or in the first state. In the present embodiment, the scenario execution unit 200 executes it when instructing the user learning degree judging unit 214 to judge whether or not the user has learned how to use the function to be learned.

The scenario execution unit 702 is generated by adding a user use history storage unit to FIG. 2 showing the first embodiment, in addition to the operation in the first embodiment.
The above operation is added.

[0111]

As described above, according to the robot apparatus of the present invention, the first learning degree judging means judges the first learning degree indicating the degree of learning of the function of the user to judge the growth degree. The means determines the use experience of the user, and the degree of growth of the robot apparatus is determined based on the determined use experience and the first degree of learning determined by the first degree-of-acquisition determination means, and the robot apparatus control means determines In order to control the robot apparatus based on the degree of growth determined by the growth degree determining unit, the first degree of learning determined by the first learning degree determining unit is used, and the growth degree determining unit determines Since the degree of growth is determined, the robot device does not grow before the user learns this function for the function that the user needs to learn how to use.

Further, according to the robot apparatus of the present invention, the second learning degree judging means judges the second learning degree indicating the degree of learning of the function of the user for each function, and the function using method explaining means. In order to teach the user the teaching content according to the second learning degree of the function judged by the second learning degree judging means, the user is taught how to use the function by the teaching content according to the learning degree. Even difficult-to-understand functions can be learned easily step by step.

[Brief description of drawings]

FIG. 1 is a diagram showing an example of an external appearance of a robot apparatus of the present invention.

FIG. 2 is a block diagram showing a first embodiment of a robot apparatus according to the present invention.

3 is a diagram showing an example of states of the robot apparatus shown in FIG. 2 and transitions between the states.

FIG. 4 is a flowchart showing an example of processing performed in a function lesson state.

FIG. 5 is a diagram showing an example of display of teaching contents of a function performed in a function lesson state.

FIG. 6 is a diagram showing an example of display of test contents for confirming a user's degree of learning of functions.

FIG. 7 is a block diagram showing a second embodiment of the robot apparatus according to the present invention.

FIG. 8 is a diagram showing an appearance of a conventional robot device.

9 is a control system applied to the conventional robot apparatus shown in FIG.

[Explanation of symbols]

100 head button 101 Microphone for voice recognition 102 CCD camera 103 LED 104 Microphone for sound source direction detection 105 speakers 106 Ultrasonic sensor 107 Proximity sensor 108 neck 109 wheels 110 power switch 111 AV terminal 112 AV cable 113 monitor 114 mice 200 Scenario Execution Unit 201 Scenario DB 201A "Function lesson" scenario 202 operation control unit 203 LED 204 head unit 204A actuator 205 Wheel unit 205A actuator 206 sensor 207 microphone 208 speakers 209 camera 210 Dialogue selection section 211 Dialogue DB 212 Parameter storage 213 Growth determination unit 214 User Acquisition Determining Section 215 storage medium 216 monitor 217 mouse 30 Non-personal behavior 31 Interpersonal behavior 300 Immediately after startup 301 Moving state 302 Resting state 303 Termination processing status State to find 310 people 311 Greeting state 312 Functional lesson status 313 Dialogue state 500 Text explanation section 501 video play button 502 Test button 600 Confirmation Test Questions 700 user usage history storage 701 User learning degree determination unit 702 Scenario execution unit 900 scenario execution unit 901 Scenario DB section 902 operation control unit 903 Growth determination unit 904 Parameter storage

   ─────────────────────────────────────────────────── ─── Continued front page    F-term (reference) 2C150 CA01 CA02 CA04 DA06 DA24                       DA25 DA26 DA27 DA28 DF03                       DF04 DF06 DF33 DG02 DG12                       DG13 DG14 DG15 EB01 ED10                       ED42 ED47 ED52 EF07 EF09                       EF16 EF17 EF22 EF23 EF28                       EF29 EF33 EF36                 3C007 AS36 CS08 KS36 KS39 KT01                       WA16 WC00 WC01 WC03

Claims (10)

[Claims] 1. A robot apparatus having a plurality of functions, which grows according to a user's experience of using the robot apparatus, wherein a first learning degree indicating a degree of learning of the function by the user is determined. A degree of learning determination means, determining the use experience of the user, and determining the degree of growth of the robot apparatus based on the determined use experience and the first degree of learning determined by the first degree of learning determination means. A robot apparatus comprising: a growth degree determining means for determining; and a robot apparatus control means for controlling the robot apparatus itself based on the growth degree determined by the growth degree determining means. 2. The first learning degree judging means performs a test for confirming a degree of learning of a function for a user on a plurality of functions of the robot apparatus itself, and according to a result of the test, the first learning degree judging means. The robot apparatus according to claim 1, wherein the learning degree of 1 is determined. 3. The robot apparatus according to claim 2, wherein the test is performed by receiving a response from the user with respect to a display content displayed on a display unit connected to the own robot apparatus. 4. The robot apparatus according to claim 1, wherein the first learning degree determining unit determines the first learning degree based on a usage history of the user's own robot apparatus. 5. The use of the first learning degree determining means including the number of successes, the number of non-successes of action results of the robot apparatus corresponding to the function to be learned by the user, and the average time until the action results are obtained. The robot according to claim 1, wherein the history is aggregated for a predetermined period, and the first degree of learning indicating whether or not the user has learned the function is determined based on a predetermined standard. apparatus. 6. The usage experience is the elapsed time since the robot apparatus was first started, the total startup time, and the number of times the robot apparatus has captured information on actions performed by the user on the robot apparatus. 6. The robot apparatus according to claim 1, including the number of times of the interaction between the user and the robot apparatus shown. 7. In a robot apparatus having a plurality of functions, which grows according to a user's experience of using the robot apparatus, a second degree of learning indicating the degree of the user's learning of the function is determined for each function. A second learning degree judging means; and a function usage method explaining means for teaching the user the teaching content according to the second learning degree of the function judged by the second learning degree judging means. A robot device characterized by the above. 8. The second degree-of-learning determination means performs a test for the user to confirm the degree of learning of the function for each function, and determines the second degree-of-learning for each function according to the test result. The robot apparatus according to claim 7, wherein the robot apparatus determines. 9. The robot apparatus according to claim 8, wherein the test is performed by receiving a response from the user with respect to a display content displayed on a display means connected to the robot apparatus itself. 10. The function use method explanation means is a display means in which the teaching content corresponding to the second learning degree of the plurality of teaching contents in the function to be learned by the user is connected to the robot apparatus. 10. The robot apparatus according to claim 7, 8 or 9, wherein the robot device is instructed to the user by receiving the response from the user.