JP2003136451A - Robot device and control method thereof - Google Patents

Abstract

PROBLEM TO BE SOLVED: To control action of a robot device by combining its memory and emotion. SOLUTION: In the robot device 1, with a specified emotion model, for performing an action in response to the change of the emotion model, controlling memory contents in accordance with emotion information for indicating a change state of the emotion model enables action control of the robot device 1 by combining its memory and emotion. Thus, the robot device 1 capable of autonomously performing improved natural action can be realized.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a robot apparatus and its control method, and is suitable for application to, for example, a pet robot.

[0002]

2. Description of the Related Art In recent years, the applicant of the present invention has proposed and developed a four-legged walking type pet robot that behaves according to a command from a user and the surrounding environment. Such a pet robot has a shape similar to a dog or cat raised in a general household, and is adapted to act autonomously in response to a command from a user and a surrounding environment.

[0003]

By the way, in such a pet robot, for the purpose of giving the pet robot an emotion, for example, from various emotion parameters indicating the intensity of emotion such as "joy" and "sadness", The emotion model is provided, and the level of each emotional parameter is changed according to the user's action or the surrounding environment, thereby performing an action according to the change of each emotional parameter.

As described above, the pet robot executes various actions such as selecting an action according to the change of each emotional parameter. When controlling the action of the pet robot, the past action is performed. It is considered that if it is possible to control by combining memory and emotion, it is possible to realize advanced behavior that is closer to that of a real pet.

Further, in such a pet robot, as a method of managing the data stored in the memory, for example, when the number of data stored in the memory reaches the storable upper limit value, the data is stored in the oldest. However, the method of deleting new data and the data with the least number of accesses and adding new data is not necessarily appropriate for the emotional robot.

The present invention has been made in consideration of the above points, and an object thereof is to propose a robot apparatus and a control method thereof that autonomously perform a more natural motion than ever before.

[0007]

In order to solve the above problems, the present invention shows a change state of an emotion model in a robot apparatus having a predetermined emotion model and performing an action according to the change of the emotion model. A storage means for managing the stored contents based on emotion information is provided. As a result, it is possible to control the operation of the robot device by combining memory and emotion.

[0008]

BEST MODE FOR CARRYING OUT THE INVENTION An embodiment of the present invention will be described in detail below with reference to the drawings.

(1) Structure of Pet Robot In FIG. 1, reference numeral 1 indicates a pet robot as a whole,
The leg units 3 are provided on the front, rear, left and right of the body unit 2, respectively.
A to 3D are connected, and the head unit 4 and the tail unit 5 are connected to the front end and the rear end of the body unit 2, respectively.

As shown in FIG. 2, the body unit 2 includes a CPU (Central Processing Unit) 10 and a DRA.
M (Dynamic Random Access Memory) 11, Flash ROM (Read Only Memory) 12, PC (Personal Com)
puter) A control unit 16 formed by connecting the card interface circuit 13 and the signal processing circuit 14 to each other via an internal bus 15 and a battery 17 as a power source of the pet robot 1 are housed. . Further, the body unit 2 includes an angular velocity sensor 18 for detecting the direction of the pet robot 1 and the acceleration of movement.
An acceleration sensor 19 and the like are also stored.

Further, the head unit 4 detects a CCD (Charge Coupled Device) camera 20 for picking up an image of an external situation, and a pressure applied by a physical action such as "stroking" or "striking" from a user. A touch sensor 21 for moving, a distance sensor 22 for measuring a distance to an object located in front, a microphone 23 for collecting an external sound, and a speaker 24 for outputting a voice such as a cry. LEDs (Light Emitting Diodes) (not shown) corresponding to the “eyes” of the pet robot 1 are arranged at predetermined positions.

Further, the joints of the leg units 3A to 3D, the leg units 3A to 3D and the body unit 2 are connected.
Each of the connecting portions of the head unit 4 and the body unit 2, the connecting portion of the tail 5A of the tail unit 5, and the like have actuators 25 ₁ having a number of degrees of freedom.
.About.25 _n and potentiometers 26 _{1 to} 26 _n are provided.

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

At this time, the signal processing circuit 14 sequentially takes in the sensor data, the image data and the audio data supplied from the above-mentioned respective sensors, and these are respectively taken in the internal bus 15.
It is sequentially stored in a predetermined position in the DRAM 11 via. Further, the signal processing circuit 14 also sequentially takes in the battery remaining amount data representing the remaining battery amount supplied from the battery 17, and stores it in a predetermined position in the DRAM 11.

The sensor data, the image data, the audio data, and the battery remaining amount data thus stored in the DRAM 11 are used when the CPU 10 subsequently controls the operation of the pet robot 1.

In practice, the CPU 10 executes the control program stored in the memory card 28 or the flash ROM 12 loaded in the PC card slot (not shown) of the body unit 2 at the initial stage when the power of the pet robot 1 is turned on by the PC card interface. It is read out via the circuit 13 or directly and stored in the DRAM 11.

After that, the CPU 10 receives the sensor data, the image data, the audio data, and the battery remaining amount data, which are sequentially stored in the DRAM 11 from the signal processing circuit 14 as described above, based on the self and surrounding conditions and the user. Judging whether or not there are instructions and how to work.

Further, the CPU 10 determines this determination result and D
By determining the subsequent action based on the control program stored in the RAM 11 and driving 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 3
Cause D to drive and walk.

Further, at this time, the CPU 10 generates voice data as required and gives the voice data to the speaker 24 through the signal processing circuit 14 to output the voice based on the voice signal to the outside. LED mentioned above
Is turned on, turned off, or blinks.

In this way, the pet robot 1 can act autonomously according to its own and surrounding conditions, and instructions and actions from the user.

(2) Processing of the control unit 16 Next, the control unit 16 in the pet robot 1
The specific processing of will be described.

When the processing contents of the control unit 16 are functionally classified, as shown in FIG. 3, the environment recognition unit 30 for recognizing the external environment and the emotion parameter values based on the recognition result of the environment recognition unit 30 are obtained. The emotion generation unit 31 that determines the state of emotions by changing it, the storage unit 32 that stores the recognition result of the environment recognition unit 30 and the emotion parameter value provided from the emotion generation unit 31 in combination, and the environment recognition unit 3
The recognition result of 0, the storage content of the storage unit 32, and the emotion generation unit 31
Can be classified into an action selection unit 33 that selects an action based on the emotion parameter value given by

The control unit 16 includes a CCD camera 20.
The image data given by the above and the voice data given by the microphone 23 are input to the environment recognition unit 30. The environment recognition unit 30 performs color recognition, shape recognition, motion recognition, and face recognition data processing on the input image data, and performs voice recognition data processing on voice data,
The recognition result information S1 is sent to the emotion generation unit 31, the storage unit 32, and the action selection unit 33.

The emotion generating unit 31 has a total of 6 "joy", "sadness", "fear", "anger""surprise", and "disgust".
For each emotion, a parameter indicating the strength of the emotion is held for each emotion. And the emotion generation unit 31
The parameter value of each of these emotions is set to the environment recognition unit 3 respectively.
"Struck" given as recognition result information S1 from 0
And a specific recognition result such as “stroked” and the elapsed time and the like are sequentially updated.

Specifically, the emotion generator 31 determines the degree to which the recognition result obtained based on the recognition result information S1 acts on the emotion (preset) and the degree of suppression and stimulation received from other emotions. And the change amount of the emotion calculated by a predetermined arithmetic expression based on the elapsed time, etc.
E [t], the current parameter value of the emotion is E [t],
The coefficient representing the rate of changing the emotion in accordance with the recognition result and the like is set to ke

[0026]

[Equation 1]

Using, the parameter value E [t + 1] of the emotion in the next cycle is calculated.

Then, the emotion generating section 31 updates the parameter value of the emotion by replacing the result of this calculation with the current parameter value E [t] of the emotion. Note that which emotional parameter value is updated for each recognition result is predetermined, and when a recognition result such as “struck” is given, the emotional parameter value of “anger” increases and When the parameter of the emotion of "joy" is lowered and the recognition result "struck" is given, the parameter value of the emotion of "joy" is increased and the parameter value of emotion of "sadness" is reduced.

Similarly to this, the emotion generating section 31
With respect to four independent desires of "exercise desire", "love desire", "appetite" and "curiosity", a parameter representing the strength of the desire is held for each of these desires. Then, the emotion generation unit 31 sequentially updates the parameter values of these desires based on the recognition result from the environment recognition unit 30, the elapsed time, and the like.

Specifically, the emotion generating section 31
As for “love desire” and “curiosity”, the fluctuation amount of the desire calculated by a predetermined arithmetic expression based on the elapsed time and the recognition result is ΔI [k], and the current parameter value of the desire is I [ k], a coefficient representing the sensitivity of the desire is ki,

[0031]

[Equation 2]

The parameter value I [k + 1] of the desire in the next cycle is calculated by using, and the parameter value of the desire is updated by replacing the calculation result with the current parameter value I [k] of the desire. To do. It should be noted that which desire parameter value to change with respect to the recognition result or the like is predetermined.

In this embodiment, the parameter values of each emotion and each desire are regulated so as to vary in the range of 0 to 100, and the coefficients ke and ki are also regulated.
The value of is also set individually for each emotion and each desire.

As described above, the emotion generator 31 is
Based on the recognition result information S1 supplied from the environment recognition unit 30, there are six kinds of emotion parameters indicating the degree of each of "sadness", "fear", "anger", "surprise", and "disgust". The value of each emotion parameter is, for example, 0 to 1.
It is designed such that it can be changed in the range of up to 00.

For example, when the pet robot 1 has a personality of "red ball", the emotion generating section 31
When the recognition result information S1 supplied from the environment recognition unit 30 indicates a “red ball”, the emotion parameter of “joy” is increased among the six types of emotion parameters.

Therefore, the emotion generator 31 recognizes the recognition result information S.
The value of each emotional parameter changed according to 1 is sent to the storage unit 32 and the action selection unit 33 as emotional parameter information S2.

The storage unit 32 stores the recognition result information S1 supplied from the environment recognition unit 30 and the emotion parameter information S2 supplied from the emotion generation unit 31 in association with each other, and the recognition result based on the emotion parameter information S2. Management of stored contents such as registration and deletion of the information S1 is performed. Then, the storage unit 32 sends the stored contents as the stored information S3 to the action selection unit 33 as necessary.

The action selection unit 33 includes the emotion parameter information S2 supplied from the emotion generation unit 31, the stored information S3 supplied from the storage unit 32, the action model stored in advance in the storage unit 32, and the environment. The next action is selected and determined based on the recognition result information S1 supplied from the recognition unit 30, and the determination result is sent to each of the actuators 251 to 25n as the action determination information S4.

Then, the pet robot 1 executes the next action selected by driving and controlling the actuators 25 _{1 to} 25 _n based on the action determination information S4.

In this case, the action selection unit 33 determines the next action by using one node (state) NODE0 to the same or any other node NOD as shown in FIG.
Whether each node NODE0-EDE-NODEn is changed
An algorithm called a probabilistic automaton is used which is determined stochastically based on the transition probabilities P0 to Pn set for the arcs ARC0 to ARCn connecting the NODEn.

More specifically, a state transition table 40 as shown in FIG. 5 for each node NODE0 to NODEn is stored in the storage unit 32 as an action model, and the action selection unit 33 makes this state transition. The next action is determined based on the table 40.

Here, in the state transition table 40, the input events (recognition results of the environment recognition unit 30) which are transition conditions in the nodes NODE0 to NODEn are listed in order of priority in the row of "input event". Further conditions are described in the corresponding columns of the "data name" and "data range" rows.

Therefore, in the node NODE100 defined in the state transition table 40 of FIG. 5, "ball is detected (BAL
L) ”, the" size (SIZ) of the ball given together with the recognition result is given.
"E)" is in the range of 0 to 1000 (0,1000), and when the recognition result of "obstacle detection (OBSTACE)" is given, even the obstacle given together with the recognition result. The “distance” of “is in the range of 0 to 1000 (0,1000)” is a condition for transition to the self or another node.

Further, in this node NODE100, even if there is no input of the recognition result, "joy (JOY)" among the parameter values of each emotion and each desire of the emotion generation unit 31 which the action selection unit 33 refers to periodically. , "Surprise (SUPR
The emotional parameter value of either "ISE" or "SODESS" ranges from "50 to 100 (50,10
0) ”, it can transit to itself or another node.

Further, in the state transition table 40, in the column of "transition destination node" in the column of "transition probability to another node", the node names that can transit from the nodes NODE0 to NODEn are listed, and "input event name" , "Data value" and "data range", if all the conditions described in each line are met, the node NODE0 to NOD
The transition probability to En is described in the row of the nodes NODE0 to NODEn in the "Transition probability to another node" column, and the action or action output at this time is described in the "output action" line. Note that the sum of the transition probabilities of each row in the "Transition Probability to Other Node" column is 100 [%].

Therefore, in the node NODE100 of this example,
For example, if a "ball is detected (BALL)" and the "size" of the ball is "0 to 1000 (0,10
00) ", the recognition result is given,
With a probability of "30 [%]", "node NODE 120 (node 12
0) ”, at which time the action or motion of“ ACTION 1 ”is output.

The behavior model is the node NODE0 to NODEn described as such a state transition table 40.
Are configured so that they are connected together.

Thus, the action selection unit 33 is the environment recognition unit 3
When the recognition result information S1 is given from 0, or when a certain time has passed since the last action was expressed, the corresponding nodes NODE0 to NODEn of the action models stored in the storage unit 32 are stored. The next action or action (action or action described in the row of “output action”) is stochastically determined using the state transition table 40, and the determination result is output to each actuator 251 to 25n as action determination information S4. To do.

Here, the management of the stored contents using the emotion parameters in the storage unit 32 will be described. Storage unit 3
As shown in FIG. 6, 2 corresponds to the storage item indicated by the recognition result information S1 supplied from the environment recognition unit 30 and the value of each emotion parameter indicated by the emotion parameter information S2 supplied from the emotion generation unit 31. It is attached and stored, and the memory content is forgotten (that is, deleted) is managed using the emotion parameter value as an evaluation criterion.

That is, when a new storage item is supplied as the recognition result information S1 from the environment recognition unit 30, the storage unit 32 is a target of forgetting (deleting) of the storage items stored in the storage unit 32. The evaluation value, which is the reference when selecting a memory item, for all memory items,

[0051]

[Equation 3]

It is calculated and stored by. The evaluation value indicates the degree of impression of the storage item stored in the storage unit 32.

The storage unit 32 is supplied with a new storage item as the recognition result information S1 from the environment recognition unit 30 and the emotion parameter information S2 from the emotion generation unit 31.
When the current value of each emotion parameter is supplied, the storage item having the smallest evaluation value is deleted from the stored storage items, and a new storage item is stored in association with the emotion parameter value.

For example, as shown in FIG. 6, the storage capacity of the storage unit 32 is three items, and the storage items are "red ball", "blue ball", and "yellow ball".
Are associated with emotion parameter values, respectively, and are stored in the storage unit 32.
It is stored in.

In this state, the storage unit 32 stores "seven-colored balls" as the recognition result information S1 from the environment recognition unit 30.
When the current emotion parameter values are supplied as emotion parameter information S2 from the emotion generation unit 31, the memory item “red ball” among the memory items stored in the storage unit 32 is Delete and register "seven color balls" as a memory item.

When the storage unit 32 manages forgetting (deleting) the stored contents with the passage of time, the forgetting rate is determined based on the current emotional parameter value, and the forgetting management is performed using the forgetting rate. The case will be described.

The storage unit 32 calculates the forgetting rate, which becomes a reference when stochastically forgetting (deleting) a stored item at regular time intervals,

[0058]

[Equation 4]

It is calculated by As a result, the pet robot 1 tends to easily forget the past memory when the value of the emotional parameter “surprise” is large among the six types of emotional parameters.

That is, the storage unit 32 calculates the forgetting rate by the above equation (3) at regular time intervals. For example, when the forgetting rate becomes equal to or more than a predetermined value, the memory having the smallest evaluation value is stored. Delete the item.

Thus, the action selection unit 33 is the environment recognition unit 3
When it is determined that the recognition result information S1 supplied from 0 is stored as a storage item in the storage unit 32,
The emotional parameter information at the time of storage, which is stored in association with the memory item, the current emotional parameter information S2 supplied from the emotion generation unit 31, and the recognition result information S1.
And the next action based on the action model.

On the other hand, in the action selection section 33, the recognition result information S1 supplied from the environment recognition section 30 is stored in the storage section 32.
If it is determined that the next action is not stored as a storage item, the next action is determined based on the current emotion parameter information S2 supplied from the emotion generation unit 31, the recognition result information S1, and the action model.

(3) Operations and Effects According to the Present Embodiment In the above configuration, the pet robot 1 manages the stored contents by using the emotion parameters generated by the emotion generation unit 31 to store the memory and emotions. The motions of the pet robot 1 can be controlled in combination with each other, and thus various motions can be generated, and continuous motion changes can be generated over a long period of time.

Further, the storage contents are managed by using the emotion parameters generated by the emotion generation unit 31, so that the storage unit 32 having a certain storage capacity is managed by a method suitable for the operation of the pet robot 1. You can

According to the above configuration, the memory content is managed by using the emotion parameter generated by the emotion generating unit 31, and the operation of the pet robot 1 can be controlled by combining the memory and emotion. Therefore, it is possible to realize the pet robot 1 that autonomously performs a more natural motion.

(4) Other Embodiments In the above-mentioned embodiments, the case where the evaluation value is calculated and stored by the above-mentioned equation (3) is described, but the present invention is not limited to this. The evaluation value is

[0067]

[Equation 5]

It may be calculated and stored by At this time, for example, when the storage item as shown in FIG. 6 is stored in the storage unit 32, the storage unit 32
When the “seven-colored ball” is supplied from the environment recognition unit 30 as the recognition result information S1, the storage item “yellow ball” is deleted from the storage items stored in the storage unit 32, and the “seven-colored ball” is deleted. "Ball" is registered as a memory item.

Further, in the above-described embodiment, the case where the emotion generation unit 31 is applied as the emotion model has been described, but the present invention is not limited to this, and the emotion parameters that indicate a plurality of types of emotion strength are used. Various other emotion models that generate emotion information by changing the emotion parameters may be applied.

In the above embodiment, the case where the storage unit 32 is applied as the storage means has been described.
The present invention is not limited to this, and various other storage means for managing the storage content based on the emotion information indicating the change state of the emotion model may be applied.

Further, in the above-mentioned embodiment, the case where the present invention is applied to the pet robot 1 has been described, but the present invention is not limited to this, and has a predetermined emotion model,
The present invention may be applied to various other robot devices that perform operations according to changes in the emotion model.

[0072]

As described above, according to the present invention, a robot apparatus having a predetermined emotion model and performing an action according to the change of the emotion model is based on the emotion information indicating the change state of the emotion model. By managing the stored contents,
It is possible to control the operation of the robot apparatus by combining memory and emotion, and thus it is possible to realize a robot apparatus that autonomously performs a more natural operation.

[Brief description of drawings]

FIG. 1 is a schematic diagram showing an embodiment of a pet robot according to the present invention.

FIG. 2 is a block diagram showing a circuit configuration of a pet robot.

FIG. 3 is a block diagram showing a configuration of a control unit.

FIG. 4 is a schematic diagram used to explain a probability automaton.

FIG. 5 is a schematic diagram for explaining a state transition table.

FIG. 6 is a schematic diagram for explaining memory management in which a memory item and an emotional parameter are combined.

[Explanation of symbols]

1 ... Pet robot, 2 ... Body unit, 3 ...
Leg unit, 4 head unit, 5 tail unit, 10 CPU, 11 DRAM, 12 flash ROM, 14 signal processing circuit, 16 control unit, 20 CCD camera, 21 ... Touch sensor, 22 ... Distance sensor, 23 ... Microphone, 2
4 ... Speaker, 25 ... Actuator, 26 ... Potentiometer, 27 ... Hub, 30 ... Environment recognition unit,
31 ... emotion generating unit, 32 ... storage unit, 33 ... action selecting unit.

Continued front page    (72) Inventor Rika Hasegawa             Sony 6-735 Kitashinagawa, Shinagawa-ku, Tokyo             Within the corporation (72) Inventor Gen Endo             Sony 6-735 Kitashinagawa, Shinagawa-ku, Tokyo             Within the corporation (72) Inventor Shinichi Kariya             Sony 6-735 Kitashinagawa, Shinagawa-ku, Tokyo             Within the corporation F-term (reference) 2C150 CA02 DA05 DA24 DA26 DA27                       DA28 DF03 DF04 DF33 ED42                       ED47 ED52 EF07 EF16 EF17                       EF23 EF29 EF33 EF36                 3C007 AS36 CS08 HS09 KS12 KS21                       KS24 KS31 KS36 KS39 KT01                       KT04 KX02 MT14 WA04 WA14                       WB25 WC13

Claims (8)

[Claims] 1. A robot apparatus having a predetermined emotion model and performing an action in accordance with a change in the emotion model, comprising storage means for managing stored contents based on emotion information indicating a change state of the emotion model. A robot device characterized by the ability to get. 2. The storage means, when sequentially storing each storage element constituting the storage content,
The robot device according to claim 1, wherein the emotion information is stored in association with the storage element, and the storage element is managed based on the stored emotion information. 3. The robot apparatus according to claim 1, wherein the storage means manages each storage element forming the storage content based on the current emotion information. 4. The emotion model comprises emotion parameters indicating a plurality of types of emotion strength,
The robot apparatus according to claim 1, wherein the emotion information is generated by changing each of the emotion parameters. 5. A control method of a robot apparatus having a predetermined emotion model and performing an action according to a change of the emotion model, managing stored contents based on emotion information indicating a change state of the emotion model. And a method for controlling a robot apparatus. 6. When sequentially storing each storage element constituting the storage content, the emotion information is stored in association with the storage element, and the storage element is managed based on the stored emotion information. The control method of the robot apparatus according to claim 5, wherein. 7. The control method for a robot apparatus according to claim 5, wherein each storage element constituting the storage content is managed based on the current emotion information. 8. The emotion model comprises emotion parameters indicating a plurality of types of emotion strength,
The control method for a robot apparatus according to claim 5, wherein the emotion information is generated by changing each of the emotion parameters.