JP2002113680A - Robot device and teaching method for its operation - Google Patents

Abstract

PROBLEM TO BE SOLVED: To teach any motion to a robot device without using a compiling apparatus, etc. SOLUTION: The robot device measures the data fed externally at the teaching timing using a measuring means and stores various pieces of the acquired measuring data in a memory means (for example, built-in memory) as the time series data (for example, motion data, acoustic data, light emission data, etc.). The robot device controls the drive of a display means such as actuator, speaker, LEDs, etc., on the basis of the measuring data stored in the form of time series data.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a robot device that displays various operations and a method of teaching the operation of such a robot device.

[0002]

2. Description of the Related Art In recent years, there has been provided a robot device whose external shape is formed by imitating an animal such as a dog. The robot apparatus includes an expression unit that expresses a movement, a sound, a facial expression, and the like, and operates such an expression unit in accordance with external information, an internal state (e.g., an emotional state), and the like. By doing so, the gestures like animals are exposed.

[0003] Here, a leg is cited as a means for expressing motion, and a microphone is cited as a means for expressing voice.
As a means for expressing the facial expression of the eyes, an LED (Light Emit
tingDiode). Such an expression means operates based on reproduction data (control data).

[0004]

By the way, in the conventional robot apparatus, reproduction data (eg, motion data, acoustic data, light emission) used for expressing means (legs, microphones, LEDs, etc.) of motion, sound, light emission, etc. Are prepared in advance by the designer of the robot apparatus. For example,
The robot device is provided with a target value calculated by a control formula or the like, or created reproduction data in advance, and based on such reproduction data stored in advance in a storage area inside the robot device at the time of design. Was expressing the action. If the robot device operates on the basis of such constant reproduction data, the robot device can only repeat the operation of a predetermined constant pattern, and lacks entertainment.

[0005] Apart from this method, for example, motion data, sound data or light emission data edited on an editor using an editing device such as a personal computer is transferred to a robot device using communication means, storage medium means and the like. A technique that can customize a reproduction pattern (or operation pattern) has also been proposed. However, this method requires a device for editing data (for example, a personal computer) in addition to the robot device, so that it costs money and furthermore, it takes time and effort for the user to learn the data editing technology. Further, the presence of a medium called an editing device between the user and the robot device has a disadvantage that the affinity between the user and the robot device is lost.

Accordingly, the present invention has been made in view of the above-mentioned circumstances, and a robot apparatus and an operation teaching method of a robot apparatus capable of teaching an arbitrary operation without using an editing device or the like. The purpose is to provide.

[0007]

According to the present invention, there is provided a robot apparatus provided with an expression unit for solving the above-mentioned problems.
This is a robot device that changes the driving state of the expression unit based on external information and / or the internal state. The robot device includes a measuring unit that measures teaching data input from outside at a teaching timing, a storage unit that stores the teaching data acquired by the measuring unit, and a control unit that controls driving of the expression unit. It has. Then, the control means controls the driving of the expression means based on the teaching data stored in the storage means.

[0008] The robot device having such a configuration is as follows.
The control means controls the drive of the expression means based on the teaching data input externally.

According to another aspect of the present invention, there is provided a method for teaching operation of a robot apparatus, comprising: a display unit for changing a driving state of the display unit based on external information and / or an internal state. This is an operation teaching method of the robot apparatus for teaching the driving of the expression means to the robot apparatus to be operated. In the method of teaching operation of the robot device, the robot device measures teaching data input from the outside at the teaching timing, measures and stores the teaching data in the storage unit, and based on the teaching data stored in the storage unit. The robot device controls the driving of the expression means.

[0010] According to the operation teaching method of the robot device, the robot device controls the driving of the expression means based on the teaching data input from the outside.

[0011]

Embodiments of the present invention will be described below in detail with reference to the drawings. This embodiment is an autonomous robot apparatus that autonomously acts according to a surrounding environment (external factors) and an internal state (internal factors).

In the embodiment, first, the configuration of the robot apparatus will be described, and thereafter, a portion to which the present invention is applied in the robot apparatus will be described in detail.

(1) Configuration of Robot Apparatus According to the Present Embodiment As shown in FIG. 1, a so-called pet robot having a shape imitating a "dog" is provided, and leg units 3A, 3A, 3B, 3C, and 3D are connected, and a head unit 4 and a tail unit 5 are connected to the front end and the rear end of the body unit 2, respectively.

As shown in FIG. 2, a CPU (Central Processing Unit) 10 and a DRA
M (Dynamic Random Access Memory) 11, Flash ROM (Read 0nly Memory) 12, PC (Personal Co.)
A controller 16 formed by interconnecting a card interface circuit 13 and a signal processing circuit 14 via an internal bus 15 and a battery 17 as a power source of the robot apparatus 1 are housed therein. . The body unit 2 also houses an angular velocity sensor 18 and an acceleration sensor 19 for detecting the acceleration of the direction and movement of the robot device 1.

The head unit 4 includes a CCD (Charge Coupled Device) camera 20 for capturing an image of an external situation, and a pressure applied by a physical action such as “stroke” or “hit” from the user. , A distance sensor 22 for measuring a distance to an object located ahead, a microphone 23 for collecting external sounds, and a speaker for outputting a sound such as a cry 24 and an LED corresponding to the “eye” of the robot device 1
(Light Emitting Diode) (not shown) are arranged at predetermined positions.

Further, the joints of the leg units 3A to 3D, the leg units 3A to 3D, and the trunk unit 2
Each coupling portion of the head unit 4 and body unit connecting portion 2, and the tail unit actuator 25 _1, respectively, etc. The consolidated portion of the tail 5A of freedom minutes 5
To 25 _n and potentiometers 26 _{1 to} 26 _n are provided. For example, each of the actuators 25 _{1 to} 25 _n has a servomotor. By driving the servo motor, the leg units 3A to 3D are controlled, and transition to a target posture or operation is made.

The angular velocity sensor 18, the acceleration sensor 19, the touch sensor 21, the distance sensor 22, the microphone 23, the speaker 24, and each of the potentiometers 26 ₁ to 26 ₁ .
Various sensors such as 26 _n and the LEDs and the actuators 25 _{1 to} 25 _n are respectively connected to the corresponding hubs 27 ₁ to 27 2.
The CCD camera 20 and the battery 17 are directly connected to the signal processing circuit 14 via the signal processing circuit 14 of the control unit 16 via 7 _n .

The signal processing circuit 14 sequentially takes in the sensor data, image data, and audio data supplied from each of the above-mentioned sensors, and sequentially stores them at predetermined positions in the DRAM 11 via the internal bus 15. In addition, the signal processing circuit 14 sequentially takes in remaining battery power data indicating the remaining battery power supplied from the battery 17 and stores the data at a predetermined position in the DRAM 11.

The sensor data, image data, voice data, and remaining battery data stored in the DRAM 11 in this manner are thereafter transmitted to the robot apparatus 1 by the CPU 10.
It is used when controlling the operation of.

In practice, when the power of the robot apparatus 1 is turned on, the CPU 10 executes the control program stored in the memory card 28 or the flash ROM 12 inserted in the PC card slot (not shown) of the body unit 2 into a P program.
The data is read out via the C card interface circuit 13 or directly and stored in the DRAM 11.

The CPU 10 then determines its own status (internal status) based on the sensor data, image data, audio data and remaining battery data sequentially stored in the DRAM 11 from the signal processing circuit 14 as described above. It determines the surrounding situation (external information) and the presence / absence of instructions and actions from the user (external information).

Further, the CPU 10 determines a subsequent action based on the determination result and the control program stored in the DRAM 11, and drives the necessary actuators 25 _{1 to} 25 _n based on the determination result.
The head unit 4 can be swung up and down, left and right, the tail 5A of the tail unit 5 can be moved, and each of the leg units 3A to 3A.
D is driven to perform an action such as walking.

At this time, the CPU 10 generates audio data as necessary, and supplies the generated audio data to the speaker 24 as an audio signal via the signal processing circuit 14, thereby outputting an audio based on the audio signal to the outside. LE above
D is turned on, off or blinked.

In this way, the robot device 1 can autonomously behave in accordance with the situation of itself and the surroundings, and instructions and actions from the user.

(2) Software Configuration of Control Program Here, the software configuration of the above-described control program in the robot apparatus 1 is as shown in FIG. In FIG. 3, a device driver layer 30 is located at the lowest layer of the control program, and includes a plurality of device drivers.
It comprises a device driver set 31 composed of drivers. In this case, each device driver
An object that is permitted to directly access hardware used in a normal computer, such as a CCD camera 20 (FIG. 2) and a timer, and performs processing in response to an interrupt from the corresponding hardware.

The robotic server object 32 is located at the lowermost layer of the device driver layer 30 and includes, for example, the various sensors and actuators 2 described above.
A virtual robot 33 comprising a software group that provides a 5 _to 253 interface for accessing hardware such as _n, a bus word manager 34 made of a software suite for managing the power supply switching, the other various device A device driver manager 35, which is a software group for managing drivers, and a robot device 1
And a designed robot 36 which is a software group for managing the mechanism.

The manager object 37 includes an object manager 38 and a service manager 39.
It is composed of Object Manager 38
Is a software group that manages activation and termination of each software group included in the robotic server object 32, the middleware layer 40, and the application layer 41, and includes a service manager 39.
Are a group of software for managing the connection of each object based on the connection information between the objects described in the connection file stored in the memory card 28 (FIG. 2).

The middleware layer 40 is located on the upper layer of the robotic server object 32, and is composed of a group of software for providing basic functions of the robot apparatus 1 such as image processing and sound processing. I have. Further, the application layer 41 is located above the middleware layer 40, and
It is composed of a software group for determining an action of the robot apparatus 1 based on a processing result processed by each software group constituting the layer 40.

FIG. 4 shows a specific software configuration of the middleware layer 40 and the application layer 41, respectively.

As shown in FIG. 4, the middle wear layer 40 includes noise detection, temperature detection, brightness detection, scale recognition, distance detection, attitude detection, touch sensor,
Each signal processing module 50 for motion detection and color recognition
58 and input semantics converter module 5
9 and an output semantics converter module 68 and signal processing modules 61 to 67 for attitude management, tracking, motion reproduction, walking, fallback recovery, LED lighting and sound reproduction. And a recognition system 69.

Each of the signal processing modules 50 to 50 of the recognition system 60
Numeral 58 fetches corresponding data among the sensor data, image data, and audio data read from the DRAM 11 (FIG. 2) by the virtual robot 33 of the robotic server object 32, and performs predetermined processing based on the data. Is given to the input semantics converter module 59. Here, for example, the virtual robot 33 is configured as a part that exchanges or converts signals according to a predetermined communication protocol.

The input semantics converter module 59 detects "noisy", "hot", "bright", "ball detected", and "fallover" based on the processing results given from each of the signal processing modules 50 to 58. Self and surrounding conditions such as `` has been stroked '', `` stroked '', `` hitted '', `` he heard the domes '', `` detected a moving object '' or `` detected an obstacle '', and the user , And outputs the recognition result to the application layer 41 (FIG. 2).

As shown in FIG. 5, the application layer 41 includes five modules: a behavior model library 70, a behavior switching module 71, a learning module 72, an emotion model 73, and an instinct model 74.

As shown in FIG. 6, the behavior model library 70 includes "when the remaining battery power is low", "returns from the fall", "when avoiding obstacles", and "when expressing emotions". , And independent action models 70 ₁ to 70 _n are respectively provided corresponding to several preselected condition items such as “when a ball is detected”.

The behavior models 70 ₁ to 70 _1
n is stored in the emotion model 73 as described later as necessary when the recognition result is given from the input semantics converter module 59 or when a certain time has elapsed since the last recognition result was given. The subsequent actions are determined with reference to the parameter values of the corresponding emotions and the corresponding parameter values of the desire held in the instinct model 74, and the determination result is output to the action switching module 71.

In this embodiment, each of the behavior models 70 ₁ to 70 _n uses one node (state) NODE _{0 to} NO as shown in FIG. 7 as a method for determining the next behavior.
Or transitions from DE _n to any other node NODE ₀ ~NODE _n the transition probability P ₁ to P _n which is set respectively arc ARC ₁ ~ARC _n1 that connects to each node NODE ₀ ~NODE _n An algorithm called a finite stochastic automaton that determines stochastically on the basis is used.

More specifically, each of the behavior models 70 ₁ to 70 _n is
Each respectively in correspondence to the node NODE ₀ ~NODE _n to form a self-behavior model 70 ₁ to 70 _n, and a state transition table 80 as shown in FIG. 8 for each of these nodes NODE ₀ ~NODE _n.

In the state transition table 80, the node NO
Input events (recognition results) as transition conditions in DE _{0 to} NODE _n are listed in order of priority in the row of “input event name”, and further conditions for the transition conditions are described in the rows of “data name” and “data range”. It is described in the corresponding column.

Therefore, in the node NODE ₁₀₀ represented by the state transition table 80 in FIG.
L) "is given, the" size (SIZ) "of the ball given together with the recognition result is given.
E) is in the range of “0 to 1000”, or when a recognition result of “obstacle detected (OBSTACLE)” is given, the “distance (DISTANCE)” to the obstacle given together with the recognition result is given. )) Is in the range of “0 to 100”, which is a condition for transitioning to another node.

In the node NODE ₁₀₀ , even when no recognition result is input, the behavior models 70 ₁ to 70 ₁
70 _n of the parameter values of each emotion and each desire held in the emotion model 73 and the instinct model 74 that are periodically referred to, respectively.
If any of the parameter values of “OY”, “SURPRISE”, or “Sadness” is in the range of “50 to 100”, it is possible to transition to another node.

In the state transition table 80, "other nodes"
In the column of "Transition destination node" in the column of
Node NODE of₀~ NODE_nNode that can transition from
Names are listed, as well as the “input event name”,
Data value and data range.
Other nodes NODE that can transition when the conditions are met ₀
~ NODE_nThe transition probability to
Rate is described in the corresponding section of the column,
NODE₀~ NODE_nLine to be output when transitioning to
Movement is "output line" in the column of "transition probability to other nodes".
Line ". In addition, "Transition to other nodes
The sum of the probabilities of each row in the “Transfer probability” column is 100 [%].
Has become.

Therefore, in the node NODE ₁₀₀ represented by the state transition table 80 in FIG. 8, for example, “ball is detected (BALL)”, and the “SIZE” of the ball is in the range of “0 to 1000”. Is given, the probability of “30 [%]” and “node N
ODE ₁₂₀ (node 120) "
The action of “TION1” is output.

Each of the behavior models 70 ₁ to 70 _n corresponds to a node NOD described as such a state transition table 80.
E ₀ to NODE _n are connected to each other, and the input semantics converter module 59
For example, when a recognition result is given from the user, the next action is determined stochastically by using the state transition table of the corresponding nodes NODE ₀ to NODE _n , and the determined result is changed to the action switching module 7.
1 is output.

The action switching module 71 shown in FIG.
Each behavior model 70 ₁ to 70 _{n of the} behavior model library 70
Among the actions which are output from, select an action that is output from a predetermined higher priority behavior model 70 ₁ to 70 _n, the command to the effect that execute the action (hereinafter, referred to as an action command )) Middleware
The output is sent to the output semantics converter module 68 of the layer 40. Incidentally, in this embodiment, is denoted behavioral models 70 ₁ more to 70 _n priority lower is set higher in FIG.

The action switching module 71 outputs the output semantics converter module 68 after the action is completed.
The completion of the action is notified to the learning module 72, the emotion model 73, and the instinct model 74 based on the action completion information given by the user.

On the other hand, the learning module 72 inputs, from among the recognition results given from the input semantics converter module 59, the recognition results of the teachings received from the user, such as "hit" and "stroke". I do.

Then, based on the recognition result and the notification from the action switching module 71, the learning module 72 lowers the probability of occurrence of the action when "beaten (scolded)" and "strokes ( praised obtained) "sometimes to increase the expression probability of that action, behavior model 70 _1-7 corresponding in behavioral model library 70
Change the corresponding transition probability of 0 _n .

On the other hand, the emotion model 73 indicates “joy (jo
y) "," sadness "," anger ",
For a total of six emotions, “surprise”, “disgust”, and “fear”, a parameter indicating the strength of the emotion is stored for each emotion. Then, the emotion model 73 converts the parameter values of each of these emotions into a specific recognition result such as “hit” and “stroke” given from the input semantics converter module 59 and the elapsed time and action switching module 71. Updates periodically based on the notification from.

Specifically, the emotion model 73 is determined based on the recognition result given from the input semantics converter module 59, the behavior of the robot device 1 at that time, the elapsed time since the last update, and the like. The amount of change of the emotion at that time calculated by the arithmetic expression is expressed by △ E
[T], E [t] of the current parameter value of the emotion, the coefficient representing the sensitivity of the emotion as k _e, (1) the parameter value of the emotion in a next period by equation E [t +
1] is calculated, and the current parameter value E of the emotion is calculated.
The parameter value of the emotion is updated by replacing it with [t]. The emotion model 73 updates the parameter values of all emotions in the same manner.

[0050]

(Equation 1)

The degree to which each recognition result and the notification from the output semantics converter module 68 affect the variation ΔE [t] of the parameter value of each emotion is determined in advance. Is the amount of change in the parameter value of the emotion of “anger” △ E
[T] is greatly affected, and the recognition result such as “stroke” is the variation amount of the parameter value of the emotion of “joy” 喜 び E
[T] is greatly affected.

Here, the notification from the output semantics converter module 68 is so-called action feedback information (action completion information), information on the appearance result of the action, and the emotion model 73 also uses such information. Change emotions. This is, for example, a behavior such as "barking" that lowers the emotional level of anger. Note that the notification from the output semantics converter module 68 is also input to the above-described learning module 72, and the learning module 72 changes the corresponding transition probabilities of the behavior models 70 ₁ to 70 _n based on the notification.

The feedback of the action result may be made by the output of the action switching modulator 71 (the action to which the emotion is added).

On the other hand, the instinct model 74 is “exercise greed (exer
cise) "," affection "," appetite "
e) ”and“ curiosity ”4
For each of the desires, a parameter indicating the strength of the desire is stored for each of the desires. And instinct model 7
4 periodically updates these desire parameter values based on the recognition result given from the input semantics converter module 59, the elapsed time, the notification from the action switching module 71, and the like.

More specifically, the instinct model 74 determines, based on the recognition result, the elapsed time, the notification from the output semantics converter module 68, and the like, for “exercise desire”, “affection desire”, and “curiosity”. The change amount of the desire at that time calculated by the arithmetic expression is ΔI [k],
I [k] the current parameter value of the desire, as the coefficient k _i which represents the sensitivity of the desire, the parameter value of the desire in a next period with a predetermined period (2) I [k +
1] is calculated, and the calculation result is replaced with the current parameter value I [k] of the desire to update the parameter value of the desire. Similarly, the instinct model 74 updates the parameter values of each desire except “appetite”.

[0056]

(Equation 2)

The degree to which the recognition result and the notification from the output semantics converter module 68 affect the variation ΔI [k] of the parameter value of each desire is determined in advance. For example, the output semantics converter 68 The notification from the module 68 has a large effect on the variation ΔI [k] of the parameter value of “fatigue”.

In the present embodiment, the parameter values of each emotion and each desire (instinct) are regulated so as to fluctuate in the range of 0 to 100, and the coefficient k
The values of _e and k _i are also individually set for each emotion and each desire.

On the other hand, as shown in FIG. 4, the output semantics converter module 68 of the middleware layer 40 provides “forward” and “pleasure” provided from the action switching module 71 of the application layer 41 as described above. , "Sound" or "tracking (follow the ball)" is given to the corresponding signal processing modules 61 to 67 of the output system 69.

The signal processing modules 61 to 6
7, when an action command is given, the action command
Actuator to perform the action based on
TA25₁~ 25_n(Fig. 2)
Audio data of sound output from the speaker 24 (FIG. 2);
Alternatively, drive data to be given to the “eye” LED is generated, and
These data into the robotic server object 32
Virtual robot 33 and signal processing circuit 14 (FIG.
2) corresponding actuators 25 in sequence ₁~ 25_n
Alternatively, the data is sequentially transmitted to the speaker 24 or the LED.

In this way, the robot apparatus 1 can perform autonomous actions according to its own (internal) and surrounding (external) conditions and instructions and actions from the user based on the control program. It has been made possible.

(3) Teaching an Operation to a Robot Apparatus (Form to which the Present Invention is Applied) By applying the present invention, a robot apparatus teaches data such as movement, sound, and light emission by a user. It is configured so that they can be directly input, measured, recorded, converted and reproduced at the appropriate timing. As a result, the user can come into contact with the robot device as if teaching a trick to a pet, and a robot system with high entertainment properties is realized.

The robot apparatus 1 for realizing such an operation (movement, sound, light emission, etc.) includes the leg units 3A to 3A.
A 3D (specifically, an actuator), a speaker 24, and a not-shown LED or other expression means are provided to provide external information (for example, surrounding conditions) and / or internal conditions (for example, internal conditions). The driving state of the above-mentioned expression means is changed based on this. The robot apparatus 1 stores a measuring unit that measures teaching data (for example, motion data, acoustic data, light emission data, and the like) input from outside at the teaching timing, and stores the teaching data acquired by the measuring unit. Storage means (for example, internal memory, etc.)
And C as control means for controlling the driving of the above-described expression means.
A PU 10 is provided, and the CPU 10 controls the driving of the above-mentioned expression means based on the above-mentioned teaching data stored in the above-mentioned storage means. Here, for example, the above-described measuring unit is realized by the module (object) of the middleware layer 40 shown in FIG.

FIG. 9 shows a specific teaching form (measurement of teaching data, (A) in FIG. 9) and a representation form of a taught operation (reproduction of teaching data, (B) in FIG. 9). Is shown.
Robot device 1 includes, as expression unit as described above, the speaker 24 is a sound output means, LED (not shown) is a light emitting device, and comprises an actuator 25 ₁ to 25 _n and the like, to these expression means The teaching will be described.

At the time of teaching, as shown in FIG. 9A, the user 200 imitates the sound of a dog such as "Wow, Wow- !!" while giving motion to each of the front legs 3A and 3B. And take the teaching action. On the robot device 1 side, data is measured by a portion corresponding to each expression means in accordance with the teaching action of the user. For example, the robot apparatus 1 uses the potentiometer 26 as the movement teaching.
_The motion data is measured in _{1 to} 26 _n , and the sound data is measured by the microphone 23 as sound input means as a sound teaching. Further, the robot apparatus 1 measures the brightness of the surroundings (for example, the brightness of the illumination) while the user is teaching as such as the light emission data in the CCD camera 20 as the image input means. For example,
The robot apparatus 1 stores the measurement data, which is the teaching data acquired in the teaching as described above, in a storage unit such as an internal memory.

For example, such measurement in each part is realized by the module (object) of the middleware layer 40 as described above. In teaching movement, displacement data obtained by displacing the leg units 3A to 3D (specifically, actuators), which are movable parts at the teaching timing, by applying external force is measured as teaching data by the measuring unit. . That is, the data of the potentiometer for measuring the displacement state of the leg is measured.

After the teaching, the robot apparatus 1 displays the action taught based on the measured data. For example, as shown in FIG.
When sound and light emission are taught at the same time, that is, when motion data, sound data, and light emission data are measured at the same time, each part of the expression means is driven synchronously after teaching. That is, after teaching, the robot apparatus 1 drives the actuator based on the motion data stored in the storage means to drive the front leg 3 as shown in FIG.
A and 3B are moved, and “Wow, Wow-
! ! "", And further causes an LED (not shown) to emit light based on the emission data stored in the storage means.

The robot apparatus 1 is thus taught to the expression means, and can reproduce the taught contents and the like by driving the expression means. The robot apparatus 1 measures data (movement data, sound data, light emission data, etc.) for operating the expression means, and controls various expression means based on the measurement data as the teaching data to teach. The operation that was performed is expressed,
For example, FIG. 10 shows a format of such measurement data stored as time-series data in a storage unit such as a memory.

In the example shown in FIG. 10, L points (L-order) of measurement points (for example, measurement points by L potentiometers) for all the joints of the four legs, and M for the input sound.
Measurement points (M-order) (for example, measurement points by M microphones) and N (N-th) measurement points (for example, measurement points by N cameras) are prepared for the input image. Shows the format of the teaching data when teaching is performed between the teaching start time and the teaching end time. In the example shown in FIG. 10, L-dimensional motion data (joint 1 measurement value to joint L measurement value), M-dimensional motion data (sound 1 measurement value to sound M measurement value), and N-dimensional light emission data (light emission 1 measurement value) (Value to measured light emission N) is measured from the teaching start time to the teaching end time and stored as the time series length of T.

For example, (L +
The (M + N) -dimensional data form is obtained by stimulating the contact sensor of the robot apparatus 1 at time 1 by the user.
The data is obtained by the time when the robot apparatus 1 starts measuring data and before the user gives the stimulus for ending at the time T.

The robot apparatus 1 stores measurement data in such a form, and the robot apparatus 1 operates various expression means based on the measurement data thus stored. Thus, the robot device 1
Any operation taught by the user can be reproduced. As a result, a robot system with high entertainment properties is realized.

The procedure for teaching the operation will be described in detail with reference to FIGS. The teaching procedure of the operation shown in FIGS. 11 to 13 is a teaching procedure for teaching the operation at the time of joy, and the procedure shown in FIGS. 11 to 13 is a procedure for teaching the operation at the time of joy by different procedures. Is shown. First, the teaching procedure shown in FIG. 11 will be described.

As shown in FIG. 11, the robot device 1
As shown in step S1, usually, the user is acting in the autonomous mode. That is, the robot apparatus 1 changes the level of various models such as an emotion model according to the input of information from the outside and the internal state, and operates according to the level.

Then, the teaching of the operation is started at a predetermined timing. For example, there is a voice input such as "joy motion",
The teaching of the operation is started with the fact that the emotional state has become a predetermined state as a trigger. For example, the robot device 1 performs a predetermined operation when the emotion level of “joy” reaches a predetermined level. This allows the user to know that teaching is possible.

In step S2, the robot device 1 determines whether the joy motion has been registered (taught). If the joy motion has not been registered, the robot device 1 proceeds to step S3.
If registered, the process proceeds to step S4. For example, whether or not registration has been performed is determined by determining the state of a flag of a data storage area in which “joy motion” is registered.

In step S3, the robot apparatus 1 switches to a so-called teaching mode and reproduces an action indicating that teaching is enabled. That is, the robot apparatus 1 prepares in advance a so-called “teach movement” action (hereinafter referred to as a teaching permission action).
To play. For example, as a teaching permission action, the robot apparatus 1 removes servos of both front legs in a sitting posture and weakens both front legs. When the robot apparatus 1 reproduces the teaching permission action, the user can know the teaching mode (that the teaching is enabled).

In this example, the teaching permission action is such that both front legs are weakened in the sitting posture, but the teaching permission action is not limited to this. That is, for example, the robot apparatus 1 is configured such that the posture of the robot apparatus and the sensors that can be taught when the robot apparatus 1 is taught according to the emotional state (state of the emotion level) and the content of the voice input are different. So that the posture is appropriate for That is, the robot apparatus 1 assumes an attitude in which an emotional state or a desired sensor can be used for teaching.

On the other hand, in step S4 when the joy motion has been registered, the robot device 1 reproduces the registered joy motion based on the data stored in the storage area of the storage means.

Then, if there is a reaction from the user for re-registering the motion, the robot apparatus 1
Proceeding to step S3, the teaching permission action is reproduced.
For example, the reaction for re-registration is that the head of the robot device 1 is hit,
Detects that the head has been hit, and reproduces the teaching permission action in step S3. Also,
If there is no such reaction for re-registration from the user, the robot apparatus 1 returns to the autonomous mode in step S1 without shifting to the teaching mode.

During the playback of the teaching permission action or within a predetermined time after the playback, the teaching by the user is started. For example, if the contact sensor on the leg detects contact,
The robot device 1 starts teaching motion. For example, the robot apparatus 1 includes, as a leg contact sensor, a sensor that detects that a so-called meat ball on the sole of the foot is pressed (hereinafter, referred to as a meat ball sensor). When it is detected that the ball has been pressed, data measurement is started.

Thus, in step S5, the robot apparatus 1 teaches the motion during the period in which the meat ball is being pressed. That is, at this time, the motion data is measured in the robot device 1 as described with reference to FIG. The measured motion data has a format as shown in FIG. 10 and is stored as time-series data in the storage area for joy and motion.
The robot apparatus 1 records, in a storage area, measurement data obtained during a period in which the meat ball is pressed, with the time when the meat ball is pressed as the teaching start time and the time when the meat ball is released as the teaching end time. I do. Then, for example, at this time, a flag indicating information on whether or not the information is registered is set.

On the other hand, in step S3, the robot apparatus 1 reproduces the teaching permission action, and when there is no teaching from the user within a predetermined time, that is, the meat ball sensor can detect that the meat ball has been pressed. If not, the process returns to the autonomous mode in step S1.

When the teaching of the motion in step S5 is completed, the robot device 1 reproduces the motion registered in step S5 in step S6. That is, a desired leg (specifically, an actuator) as an expression means based on the motion data stored in the storage area of the joy motion in the storage means
Drive. By playing back such registered motion, the user can confirm the motion taught by the user (hereinafter referred to as “taught motion”). Note that, for example, the robot apparatus 1 detects the end of the motion teaching when the meat ball is no longer pressed within a predetermined time or when the meat ball is pressed and a predetermined time has elapsed, and proceeds to step S7.

When the reproduction of the teaching motion is completed in step S7, the robot apparatus 1 performs a process for registering a voice command as a trigger for reproducing the teaching motion in the autonomous mode. For example, the robot apparatus 1 reproduces an action for prompting (permitting) input of a motion name. For example, the robot apparatus 1 reproduces a so-called “Tell me a word?” Action (hereinafter referred to as a motion name input permission action) prepared in advance. For example, the motion name input permission action includes a motion in which the robot apparatus 1 puts the front leg on the ear.

The robot apparatus 1 reproduces the motion name input permission action, and then waits for the user to say something in step S8. At this time, the robot device 1 plays a predetermined action when waiting for an utterance from the user. For example, the robot device 1 reproduces a so-called “standby” action prepared in advance. For example, as the “standby” action, the robot apparatus 1 uses the eye (LE)
Blinking D) or outputting a sound such as "Pirori".

Then, the robot device 1 stores the word spoken by the user as a motion name as a motion trigger, and returns to the autonomous mode in step S1. Specifically, in step S9, the motion name is registered in the robot apparatus 1 in association with the registered motion. For example, from speech utterance to end of speech is registered as a motion name. It is also possible to limit the motion name, for example, to limit the registration time. For example, a motion name is registered with a maximum registration time of 2 seconds. And the robot device 1
Plays the registered motion name in step S10, and returns to the autonomous mode in step S1.

On the other hand, if there is no voice input from the user within the predetermined time (for example, if there is no voice input for 10 seconds), the process proceeds from step S8 to step S11, and an action indicating the end of the motion name registration is reproduced. For example, the robot apparatus 1 reproduces a so-called “end” action prepared in advance. Then, the robot device 1 returns to the autonomous mode in step S1.

When the motion and the trigger motion are registered as described above, the robot apparatus 1 recognizes the registered motion name (registered name) or changes the emotional state to a predetermined state in the autonomous mode. If the motion is already registered at step S4,
In, the motion is reproduced. Then, when receiving a stimulus from the user during the motion reproduction, the robot device 1 deletes the registered motion data from the storage area and registers a new motion.

Next, a procedure for teaching the operation shown in FIG. 12 will be described. In the teaching procedure of the operation shown in FIG. 11, the motion name is registered after the motion is registered. In the operation teaching shown in FIG. 12, the motion and the motion name are registered at the same time. This will be described with reference to FIG.

The robot apparatus 1 is acting in the autonomous mode in step S1, as in the case shown in FIG. And the robot apparatus 1
The instruction of the operation is started when there is a voice input such as “joyful motion” or when the emotional state of joy has reached a predetermined state.

Then, the robot apparatus 1 operates as shown in FIG.
As in the case shown in (1), in step S3, the mode is switched to the teaching mode, and an action indicating that teaching is enabled is reproduced. That is, the robot apparatus 1 reproduces a so-called “teach movement” action (teaching permission action) prepared in advance.

Thus, the teaching by the user is started during the playback of the teaching permission action or within a predetermined time after the playback. For example, the robot device 1 starts measuring data at the timing when the meat ball is pressed.

The robot apparatus 1 teaches a motion during the period in which the meat ball is being pressed in step S51, as in the case shown in FIG. Then, at the time of teaching the motion, a motion name is also input. At this time, in the robot device 1, this motion name is stored in the storage unit in association with the teaching motion. Note that the motion name may be input at the same time as the motion, or may be input within a predetermined time after the motion is registered.

On the other hand, as in the case shown in FIG. 11, the robot apparatus 1 reproduces the teaching permission action in step S3, and if there is no teaching from the user within the predetermined time, that is, within the predetermined time, If the paws have not been pressed, the process returns to the autonomous mode in step S1.

After the teaching of the motion and the input of the motion name in step S51 are completed, the robot apparatus 1 determines the motion and the motion name registered in step S5 in step S6, as in the case shown in FIG. Play at the same time. After ending the reproduction of the registered motion and motion name, the robot device 1 returns to the autonomous mode in step S1.

When the motion and the motion name are registered as described above, the robot apparatus 1 determines whether or not the motion has been registered when the emotional state changes to a predetermined state in the autonomous mode. , The motion and the motion name are reproduced. When the robot apparatus 1 receives a stimulus from the user during reproduction (for example, when the output of the touch sensor of the head changes), the robot apparatus 1 deletes the registered motion data from the storage area, and outputs a new teaching motion. Register.

In this example, although the motion name is not used as a trigger of the motion, the robot 1 can reproduce the motion and the motion name using the motion name as a trigger.

Next, the teaching procedure of the operation shown in FIG. 13 will be described. In the teaching of the operation shown in FIGS. 11 and 12, the motion and the motion name are registered in the same sequence. In the teaching of the operation shown in FIG.
This shows a case where a motion name is registered in another sequence. This will be described with reference to FIG.

The robot apparatus 1 is acting in the autonomous mode in step S1, as in the case shown in FIG. And the robot apparatus 1
The instruction of the operation is started when there is a voice input such as “joyful motion” or when the emotional state of joy has reached a predetermined state.

Then, the robot apparatus 1 uses the above-described FIG.
As in the case shown in (1), in step S2, it is determined whether the joy motion has been registered (taught). If the joy motion is not registered, the robot device 1 proceeds to step S3, and if registered, proceeds to step S41.

Then, the robot apparatus 1 operates as shown in FIG.
As in the case shown in (1), in step S3, the mode is switched to the teaching mode, and an action indicating that teaching is enabled is reproduced. That is, the robot apparatus 1 reproduces a so-called “teach movement” action (teaching permission action) prepared in advance.

On the other hand, in step S41 when the joy motion has been registered, the robot device 1 reproduces the registered joy motion and motion name based on the data stored in the storage area of the storage means.

The robot apparatus 1 performs a reaction for re-registering the motion from the user (for example,
If yes, the process proceeds to step S3, where the teaching permission action is reproduced.

Thus, the teaching by the user is started during the playback of the teaching permission action or within a predetermined time after the playback. As in the case shown in FIG. 11, the robot device 1 teaches the motion during the period in which the meat ball is pressed in step S5.

On the other hand, as in the case shown in FIG. 11, the robot apparatus 1 reproduces the teaching permission action in step S3, and if there is no teaching from the user within a predetermined time, that is, the meat ball sensor If it cannot be detected that the button has been pressed, the process returns to the autonomous mode in step S1.

When the teaching of the motion in step S5 is completed, the robot apparatus 1 reproduces the motion registered in step S5 in step S6, as in the case shown in FIG. When the reproduction of the registered motion is completed, the robot device 1 proceeds to step S
1 to return to the autonomous mode.

When the motion is registered as described above, the robot apparatus 1 recognizes the motion name registered in another sequence in the autonomous mode or changes the emotional state to a predetermined state in the autonomous mode. If the corresponding motion has been registered, in step S41,
Play the motion and the motion name. And
When receiving a stimulus from the user during the reproduction, the robot apparatus 1 deletes the registered motion data from the storage area and registers a new teaching motion.

The teaching procedure of various operations has been described above with reference to FIGS. 14 and 15 show the outline of the flow of the teaching procedure. FIG.
The flow of the teaching procedure shown in FIG. 15 is for registering a motion and a motion name at different timings, and the flow of the teaching procedure shown in FIG. 15 is for registering a motion and a motion name at the same time. First, FIG.
4, a procedure for teaching a motion and a motion name at different timings will be described.

As shown in FIG. 14, the robot device 1
In step S21, the user is notified that movement may be taught. In this case, for example, the robot apparatus 1 reproduces the “tell me the movement” action. As described above, the timing (trigger) for notifying that the movement may be taught may be, for example, that there is a voice input such as “joy motion” or that the emotional state of joy of the robot apparatus 1 becomes a predetermined state. It is assumed that it has become. Then, the robot device 1 cuts the gain of the neck and both front legs. As a result, the posture in which both front legs are weakened as the teaching permission action of the robot apparatus 1 is reproduced, and a motion teaching waiting state is entered in step S22.

Then, the robot apparatus 1 starts recording a motion (specifically, motion data) in step S23 by pressing the paws, and when the user releases the paws, the motion (concrete) is performed. Specifically, the recording of the motion data) ends. Then, the robot device 1
In step S24, the registered motion is reproduced. After ending the reproduction of the registered motion, the robot device 1 asks the user whether or not the robot device 1 is sufficient in step S25. For example, the robot apparatus 1 reproduces an action prepared in advance to ask whether the registered motion is satisfactory. The robot apparatus 1 proceeds to step S26 when the user decides that this is all right, and returns to step S21 when the user decides that this is not possible, and starts the processing for registering the motion again.

In step S26, the robot device 1 asks the user for the motion name. For example, the robot apparatus 1 reproduces the action of putting the front leg on the ear as the motion name input permission action. And the robot device 1
Outputs a sound such as blinking the eyes (LED) or “pirori” as a holding action.

In the robot apparatus 1, when there is a voice input during this standby action, the process proceeds to step S.
At 27, the input voice is recorded. Then, when the recording (recording) time has elapsed for a predetermined time, in step S28, the robot apparatus 1 reproduces the recorded voice, and asks whether or not the motion name is satisfactory. If the motion name is determined to be good, the robot device 1 proceeds to step S29. If the motion name is determined to be good, the robot device 1 returns to step S26 and starts the process of prompting the input of the motion name again.

In step S29, the robot device 1 reproduces the end action and returns to the autonomous mode. According to the teaching procedure as described above, the motion and the motion name are taught at different timings, and they can be reproduced.

Next, a procedure for simultaneously teaching a motion and a motion name will be described with reference to FIG.

As shown in FIG. 15, the robot device 1
In step S31, the user is notified that movement may be taught. In this case, for example, the robot apparatus 1 reproduces the “tell me the movement” action. As described above, the timing (trigger) for notifying that the movement may be taught may be, for example, that there is a voice input such as “joy motion” or that the emotional state of joy of the robot apparatus 1 becomes a predetermined state. It is assumed that it has become. Then, the robot device 1 cuts the gain of the neck and both front legs. As a result, the posture in which both front legs are weakened as the teaching permission action of the robot apparatus 1 is reproduced, and in step S32, a state of waiting for the teaching of the motion and the motion name is entered.

Then, the robot apparatus 1 starts recording the motion and the motion name (specifically, the motion data and the sound data) in step S33 when the paws are pressed, and the user releases the paws. When
The recording of the motion and the motion name (specifically, the motion data and the sound data) ends. Then, in step S34, the robot device 1 reproduces the registered motion and motion name. Robot device 1
After ending the reproduction of the registered motion, in step S35, the robot apparatus 1 asks the user whether or not this is all right. For example, the robot apparatus 1 reproduces an action prepared in advance to ask whether the registered motion is satisfactory. Robot device 1
If the user decides that this is the case, step S36
Then, the action of the end is reproduced, and if the user cannot do so, the process returns to step S31, and the processing for registering the motion is started again.

According to the above-described teaching procedure, the motion and the motion name are taught simultaneously.

By configuring the robot apparatus 1 as described above, the robot apparatus 1 measures data input from the potentiometer, the microphone 23 and the CCD camera 20, stores the data in the storage means, and measures the data. By controlling the leg unit (specifically, the actuator), the speaker 24, and the not-shown LED or other expression means based on the data, the expression means is driven in accordance with the acquired measurement data. , Without using editing equipment, etc.
Any action can be taught. This allows the user to contact the robot device 1 as if teaching a trick to a pet, and a robot system with high entertainment properties is realized.

In the above embodiment, the object to be taught is described as a motion, but the present invention is not limited to this. That is, for example, the object to be taught may be a sound, an image, or the like. Further, in the above-described embodiment, a case has been described in which a registered predetermined operation (movement in the above example) is reproduced using sound as a trigger, but the present invention is not limited to this. For example, the robot apparatus 1 can also reproduce a registered motion by using a predetermined image or a predetermined motion as a trigger. For example, thereby, the robot apparatus 1 can register the sound and the image in association with each other. in this case,
When a predetermined light emission level is input, the robot apparatus 1 outputs a taught sound.

For teaching an image, for example, the robot apparatus 1 registers light emission data corresponding to a case where an image captured by the CCD camera 20 can be recognized as a predetermined pattern based on pattern matching. To do. Alternatively, as shown in FIG. 16, the captured image in the image feature space is based on the image feature space including the R, G, and B features of the captured image and the luminescence data feature space including the features of the luminescence data. The emission data can also be obtained on the emission data feature space mapped from. Thereby, the robot apparatus 1 performs an eye (LED) based on the emission data corresponding to the input image at the time of reproduction.
Will be driven.

Further, in the above-described embodiment, when an object is taught, that object is reproduced. For example, when a voice is taught, the robot device 1 outputs the voice again as a voice. However, the present invention is not limited to this.
Can be converted into a motion action even if a voice instruction is given, and the motion action corresponding to the voice input can be reproduced. This will be described with reference to FIG.

As shown in FIG. 17, when audio data is input as time-series data, this audio data ((A) in FIG. 17) is replaced with motion data ((B) in FIG. 17).
Convert to This example shows a case where M-dimensional acoustic data having a time sequence length T is converted to one-dimensional motion data having a time sequence length T. For example, such a conversion is realized by a conversion formula J (t) as shown in the formula (3).

[0123]

(Equation 3)

Here, S_min and S_max are the measurable ranges of the acoustic measurement value S (t) at time t, and J_min and J_max are the joint target values J (t) to be reproduced at time t.
Are the minimum and maximum possible values of the motion data in the operable range.

By such data conversion, the robot apparatus 1 can express an action different from that taught.

Similarly, when the robot apparatus 1 is taught by movement, the robot apparatus 1 can convert the instruction into a light-emitting operation. This will be described with reference to FIG.

For converting the motion data to the light emission data, for example, an absolute value space of the joint angle as shown in FIG. 18A and a feature space of the light emission data as shown in FIG. 18B are used. I do.

The absolute value space of the joint angle shown in FIG. 18A indicates, for example, the absolute value of the angle of the first joint | J ₁
And | J ₂ | indicating the absolute value of the angle of the second joint. For example, the first joint is the first joint of the right front leg,
The second joint is the first joint of the left front leg, and the absolute value of the angle is the absolute value of the value detected by the potentiometer that detects the angles of the first and second joints. Also, in this data space, | j ₁ | max indicates the maximum value of the angle that the first joint can take, and | j ₂ | max indicates the maximum value of the angle that the second joint can take.

The characteristic space of the light emission data shown in FIG. 18B is, for example, a space constituted by the light emission data of the LEDs, and is an LE indicating the light emission data of the first color.
And D _1, consisting of LED ₂ Metropolitan showing the light emission data for the second color. In this data space, of led ₁ _max indicates the maximum value of the light emission data for the first color, of led ₂ _max indicates the maximum value of the light emission data for the second color. For example, each light emission data is a PWM signal. Using the above data space, conversion can be performed as follows. Further, for example, the first color is red and the second color is blue.

For example, when movement is taught and | j ₁ | and | j ₂ | are input as absolute values of the angles of the first and second joints as shown in FIG. FIG.
As shown in the middle (B), the data is converted into LED ₁ and LED ₂ as red light emission data of the LED and blue light emission data of the LED.

For example, the conversion formula of led ₁ and led ₂ is (4)
It becomes as shown in Formula and Formula (5).

[0132]

(Equation 4)

[0133]

(Equation 5)

By the above data conversion, the robot apparatus 1 can convert a certain movement into a purple light emission operation by the LED.

[0135] In this example, the case where acoustic data used as measurement data (teaching data) is converted into motion data is described, but the present invention is not limited to this. Conversions different from this combination can also be made. That is, for example, when the light emission data is taught, the robot apparatus 1 converts the light emission data into acoustic data and outputs a sound corresponding to the light emission data.

FIGS. 19 to 21 show a specific configuration of the above-mentioned so-called meat ball sensor used for setting the timing of taking in the teaching data. The meat ball sensor 7 is provided in each of the leg units 3A to 3D. The meat ball sensor 7 will be described using the leg unit 3A of the left front leg as an example.

As shown in FIGS. 19 and 20, the leg unit 3A has a crotch portion 3AA having one end attached to a side surface of the body unit 2 and a shin portion attached to the other end of the crotch portion 3AA. 3AB. Here, crotch 3
AA is attached to the torso unit 2 so as to be driven by an actuator, and the shin part 3AB is attached to the crotch part 3AA so as to be driven by the actuator.

At the other end of the shin part 3AB, an upper part 3AC is provided. In the upper part 3AC,
A hemispherical meat ball sensor 7 serving as a touch sensor for detecting a ground contact is disposed, and the toe portion is provided with, for example, three claws 3AD.

The meat ball sensor 7 disposed on the sole surface of the instep 3AC has a semicircle made of rubber material such as NBR as shown in FIG. A plurality of protrusions 7A provided on the inner surface of the shell-shaped grounding portion 7A
One end of a cylindrical first push-up member (hereinafter, referred to as a flange member) 7B having one end in a flange shape is fixed to the central projection 7AB of A to 7AC.

At the same time, the meat ball sensor 7 is
A second push-up member (hereinafter, referred to as a semi-circular shell member) having a semi-circular shell shape smaller than the ground contact portion 7A in which a hole is formed in the center of the inner surface of A through each of the protrusions 7AA to 7AC. ) 7C
Is connected to the hole so as to penetrate the flange member 7B, and the flange member 7B has another end formed in a groove 7DA formed in the center of one end of the cylindrical slider 7D.
Are formed so as to be slidably connected along.

The pawl sensor 7 is provided with a grounding portion 7A.
Is perpendicular to the road surface from the center, the protrusion 7AB of the grounding portion 7A pushes up the slider 7D by the center of the flange member 7B and the semicircular shell member 7C, and the other end of the slider 7D is connected to the switch 7E. By contact, the grounding of the meat ball sensor 7 is detected.

The meat ball sensor 7 is connected to the grounding portion 7.
When A comes into contact with the road surface or the like obliquely, the protrusion 7AA or 7AC of the ground contact portion 7A pushes up the semicircular shell member 7C, so that the semicircular shell member 7C moves the slider 7D along the side surface of the flange member 7B. When the other end of the slider 7D comes into contact with the switch 7E in the same manner as when the grounding portion 7A vertically contacts the road surface or the like from the center as described above, the grounding of the meat ball sensor 7 is detected. It has been made.

As described above, in the meat ball sensor 7, regardless of the contact angle between the ground contact portion 7A and the road surface, the slider 7D
It is possible to uniformly detect whether or not the grounding section 7A is grounded on the road surface by determining whether or not the other end of the grounding section contacts the switch 7E.

As described above, in the robot device 1, the meat ball sensors 7 for detecting whether or not the robot is in contact with the ground are provided in each of the leg units 3A to 3D. The robot device 1 detects the user's pressing by such a meat ball sensor 7, detects the teaching start time, that is, starts the data measurement, and further detects the teaching end time, that is, measures the data. To end.

[0145]

According to the robot apparatus of the present invention, a measuring means for measuring teaching data inputted from outside at a teaching timing, a storage means for storing the teaching data acquired by the measuring means, and a displaying means And control means for controlling the driving of the expression means based on the teaching data stored in the storage means, whereby the control means controls the driving of the expression means based on the teaching data obtained by the measurement means. The means can control the driving of the expression means. Thus, since the robot device drives the expression unit in accordance with the teaching data input from the outside, it is possible to teach an arbitrary operation without using an editing device or the like.

In the method for teaching operation of a robot apparatus according to the present invention, the robot apparatus measures teaching data input from the outside at the teaching timing, measures and stores the teaching data in the storage means, and stores the teaching data in the storage means. The robot device controls the driving of the expression device based on the stored teaching data, so that the robot device can control the driving of the expression device based on the acquired teaching data. Accordingly, since the robot device drives the expression unit in accordance with the teaching data input from the outside, it is possible to teach an arbitrary operation without using an editing device or the like.

[Brief description of the drawings]

FIG. 1 is a perspective view illustrating an external configuration of a robot device according to an embodiment of the present invention.

FIG. 2 is a block diagram showing a circuit configuration of the robot device described above.

FIG. 3 is a block diagram illustrating a software configuration of the robot device described above.

FIG. 4 is a block diagram showing a configuration of a middleware layer in a software configuration of the robot device described above.

FIG. 5 is a block diagram showing a configuration of an application layer in the software configuration of the robot device described above.

FIG. 6 is a block diagram showing a configuration of the behavior model library of the application layer.

FIG. 7 is a diagram used to explain a finite probability automaton that is information for determining an action of the robot apparatus.

FIG. 8 is a diagram showing a state transition table prepared for each node of the finite probability automaton.

FIG. 9 is a diagram showing a specific example of teaching and reproduction of the teaching content.

FIG. 10 is a diagram showing a format of teaching data.

FIG. 11 is a diagram showing a teaching procedure for teaching a motion and a motion name at different timings.

FIG. 12 is a diagram showing a teaching procedure for simultaneously teaching a motion and a motion name.

FIG. 13 is a diagram showing a teaching procedure for teaching a motion when a motion name is taught by another sequence.

FIG. 14 is a diagram showing a teaching procedure flow for teaching a motion and a motion name at different timings.

FIG. 15 is a diagram showing a teaching procedure flow for teaching a motion and a motion name at the same time.

FIG. 16 is a diagram used for explanation for obtaining light emission data from an image.

FIG. 17 is a diagram illustrating a specific example of a case where teaching data is converted;

FIG. 18 is a diagram used for describing conversion of a taught motion into light emission data.

FIG. 19 is a side view showing an external configuration of a leg unit and a meat ball sensor.

FIG. 20 is a front view showing an external configuration of a leg unit and a meat ball sensor.

FIG. 21 is a cross-sectional view showing an external configuration of a leg unit and a meat ball sensor.

[Explanation of symbols]

1 robot unit, 3A, 3B, 3C, 3D leg unit, 10 CPU, 23 microphone, 24 speaker,
25 _{1 to} 25 _n actuator, 26 _{1 to} 26 _n potentiometer

Claims (13)

[Claims] 1. A robot apparatus comprising an expression means for changing a driving state of the expression means based on external information and / or an internal state, wherein measurement for measuring teaching data inputted from outside at a teaching timing. Means, storage means for storing the teaching data obtained by the measuring means, and control means for controlling the driving of the display means, wherein the control means comprises the teaching data stored in the storage means. A robot device that controls the driving of the above-mentioned expression means on the basis of (1). 2. The robot apparatus according to claim 1, wherein said display means is at least one of a movable part, a sound output means, and a light emitting means. 3. The expression means is a movable part. The measurement means measures displacement data obtained by displacing the movable part by applying an external force at a teaching timing as the teaching data. 2. The robot apparatus according to claim 1, wherein driving of the movable section is controlled based on the displacement data. 4. A sound input means, wherein the measuring means measures sound data inputted from the sound input means at the teaching timing as the teaching data, and the control means based on the sound data. 2. The robot apparatus according to claim 1, wherein the driving of the sound output means as the expression means is controlled. 5. An image input means, wherein said measuring means measures image data input from said image input means at said teaching timing as said teaching data, and said control means based on said image data. 2. The robot apparatus according to claim 1, wherein the driving of the light emitting means as the displaying means is controlled. 6. The teaching data stored in the storage means is converted into teaching data which is drive data of another attribute, and the control means controls the display means based on the converted teaching data. The robot device according to claim 1, wherein the driving is controlled. 7. The expression means is a plurality of types of expression units, wherein the measurement means measures a plurality of types of teaching data input from outside at the time of teaching, and the storage means The plurality of types of teaching data are stored in association with each other, and the control means drives the plurality of types of expression units based on the plurality of types of associated teaching data. The robot device according to 1. 8. The robot apparatus according to claim 7, wherein the control means drives the plurality of types of expression units in synchronization based on the plurality of types of teaching data associated with each other. 9. The robot according to claim 1, wherein the measuring means measures the teaching data as time-series data, and the storage means stores the teaching data as time-series data. apparatus. 10. The measurement means controls a measurement period of teaching data, and the storage means stores time-series data obtained during the measurement period. The robot device as described. 11. The robot according to claim 1, wherein the posture can be freely changed based on the external information and / or the internal state, and when teaching, the robot is changed to a predetermined posture that can be taught. apparatus. 12. The robot apparatus according to claim 1, wherein the internal state is at least one of an instinct state, an emotion state, a learning state, and a growth state. 13. A method for teaching operation of a robot device which includes a displaying device and which teaches driving of the displaying device to a robot device which changes a driving state of the displaying device based on external information and / or an internal state. The robot device measures teaching data input from outside at the teaching timing, measures and stores the teaching data in the storage means, and based on the teaching data stored in the storage means,
An operation teaching method for a robot device, wherein the robot device controls the driving of the expression means.