JP2020037141A - Robot, robot control program, and robot control method - Google Patents

Abstract

To execute a natural reaction operation to a human of a communication object.SOLUTION: A system 10 includes an android robot 12. The robot refers to human data on positions of each head and hand of one or a plurality of humans acquired on the basis of the output of a distance image sensor 18, determines whether or not the human is in a fixed range, and further determines whether or not the human in the fixed range and in a visual field is trying to touch the robot's face. In response to the fact that the human is trying to touch the robot's face, the robot executes a reaction operation according to a degree of affection of the human.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a robot, a robot control program, and a robot control method, and more particularly to, for example, a robot having a human-like appearance, a robot control program, and a robot control method.

  An example of a conventional robot of this type is disclosed in Patent Document 1. The android control system disclosed in Patent Document 1 has an android which is a humanoid robot having a shape very similar to a human, and when the human approaches the android and stops in front of the android, the android is given to the human. Say hello or introduce yourself. At this time, the control device of the android detects that the person has stopped near the android based on the output of the environment sensor (floor sensor).

  When a floor sensor is not used, the control device detects that a human or an object touches or collides with an android when a tactile sensor or a collision sensor responds. Also, when a sound of a certain level or more is input to the microphone, it is detected that a human is approaching or talking to the android.

JP 2012-111038 A

  In the android control system of Patent Document 1 described above, since a floor sensor is used as an environment sensor, it is determined based on the distance between the standing position of the person and the arrangement position of the android that the person has approached the android. If you try to touch the android with a part that is not in contact with the floor (for example, your hand), it cannot be detected.

  However, even if it is not possible to detect that a human is trying to touch the android using the floor sensor, the control device still sends a human or object to the android when the tactile sensor or collision sensor responds. Touch and collision can be detected.

  However, in this case, since the android reacts after being touched by a communication target such as a human, it differs from the reaction of the human when the human tries to contact another person, and the Will feel uncomfortable.

  Androids greet and introduce themselves to humans, but they also have the disadvantage of introducing themselves to the same person over and over. In other words, the same operation as that of the first meeting is repeated for a person who has met many times.

  Therefore, a main object of the present invention is to provide a novel robot, a robot control program, and a robot control method.

  Further, another object of the present invention is to provide a robot, a robot control program, and a robot control method that can execute a natural reaction operation on a human to be communicated.

  A first invention is a robot having an appearance resembling a human being, wherein a preference storage means for storing preference data on the preference of another person, and a part belonging to the other person present around the robot and belonging to the robot. A first approach determining means for determining whether the robot has approached within a first predetermined distance of the robot; and a first approach determining means for determining that a part belonging to another has approached within a first predetermined distance of the robot. The robot includes an action execution unit that executes a reaction operation corresponding to the degree of favor of the other person stored in the favor degree storage unit to the other person.

  A second invention is according to the first invention, and further includes calculation means for calculating a shape of another person present around the robot and a position of a part belonging to the other person.

  A third invention is according to the first or second invention, and the action execution means executes the first reaction operation when the degree of favor is equal to or more than a predetermined value or the second reaction operation in which the degree of favor is less than a predetermined value. .

  A fourth invention is according to the third invention, further comprising a second approach determining means for determining whether a part belonging to another person has approached within a second predetermined distance longer than the first predetermined distance, and The means executes a first reaction operation when the first approach determination means determines that a part belonging to another person has approached within a first distance of the robot if the degree of favorableness is equal to or more than a predetermined value, If the degree of favor is less than the predetermined value, the second reaction operation is executed when the second approach determining means determines that the part belonging to another person has approached within the predetermined distance of the robot.

  A fifth invention is according to any one of the first to fourth inventions, wherein the degree of favor of another person is changed according to the frequency of a communication action with the other person.

  A sixth aspect of the present invention is a robot control program for a robot having a likeness storage means for storing likeness data on the likeness of another person, the robot having a similar appearance to a human being. An approach judging step of judging whether or not a part belonging to another person present in the robot has approached within a predetermined distance of the robot; and when it is judged in the approach judging step that a part belonging to another person has approached within a predetermined distance of the robot. A robot control program for causing the other person to execute an action execution step of executing a reaction operation corresponding to the degree of favor of the other person stored in the favor degree storage means.

  A seventh invention is a robot control method for a robot having a likeness storage means for storing likeness data on the likeness of another person, the robot having a similar appearance to a human being. (B) determining whether a part belonging to another person has approached within a predetermined distance of the robot; and (b) determining in step (a) that a part belonging to another person has approached within a predetermined distance of the robot. And a step of executing a reaction operation on the other person according to the degree of favor of the other person stored in the favor degree storage means.

  An eighth invention is an agent control program for an agent which is executed by a computer provided with a likeness storage means for storing likeness data about the likeness of another agent, and which exists in a virtual space and has a human-like appearance. An approach judging step for judging whether a part belonging to another agent present around the agent has approached within a predetermined distance of the agent, and a part belonging to another agent in the approach judging step. When it is determined that the agent has approached within a predetermined distance of the agent, an action execution step of executing a reaction operation corresponding to the degree of favorableness of the other agent stored in the favorable degree storage means to the other agent is performed. Is an agent control program.

  A ninth invention is an agent control method for controlling an agent, which exists in a virtual space and has an appearance similar to a human, by a computer having a favorable degree storage means for storing favorable degree data on the favorable degree of other agents. (A) a step of determining whether a part belonging to another agent existing around the agent has approached within a predetermined distance of the agent; and (b) a part belonging to another agent in step (a). An agent including, when it is determined that the agent has approached within a predetermined distance of the agent, performing a reaction operation on the other agent according to the degree of favorableness of the other agent stored in the favorable degree storage means. It is a control method.

  ADVANTAGE OF THE INVENTION According to this invention, a natural reaction operation | movement can be performed with respect to the communication target person.

  The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description of embodiments with reference to the drawings.

FIG. 1 is a diagram showing a system according to an embodiment of the present invention. FIG. 2A is a diagram for explaining an actuator for moving the eyelids and eyeballs of the android robot shown in FIG. 1, and FIG. 2B is a diagram showing an actuator for moving the forehead, eyebrows and mouth angle of the android robot shown in FIG. FIG. 2C is a diagram for explaining an actuator that moves the lips of the android robot shown in FIG. 1. FIG. 3 is a diagram for explaining an actuator that moves the head, shoulders, and waist of the android robot shown in FIG. FIG. 4 is a block diagram showing an electrical configuration of the android robot of FIG. FIG. 5 is a diagram for explaining a method of measuring a first distance at which a human reacts to contact with another person. FIG. 6 is a diagram showing an example of a memory map of the RAM shown in FIG. FIG. 7 is a flowchart showing a robot control process of the CPU shown in FIG. FIG. 8 is a diagram showing an example of a memory map of the RAM according to the second embodiment. FIG. 9 is a flowchart showing a part of the robot control process of the CPU of the second embodiment. FIG. 10 is a flowchart showing another part of the robot control process of the CPU of the second embodiment, which is subsequent to FIG. FIG. 11 is a flowchart showing a process of a reaction operation with a high degree of favor of the CPU of the second embodiment. FIG. 12 is a flowchart showing a process of a low-favorable reaction operation of the CPU of the second embodiment.

<First embodiment>
Referring to FIG. 1, an android robot control system (hereinafter, may be simply referred to as “system”) 10 of the first embodiment includes an android robot (hereinafter, simply referred to as “robot”) 12. The robot 12 is a humanoid robot having a shape (appearance, etc.) very similar to a human (see FIGS. 2 (A), (B), (C), and FIG. 3), and an operation (swing, behavior) very similar to a human Utterance).

  The robot 12 is connected to a computer 16 via a network 14 such as the Internet or a telephone communication line. The computer 16 is a general-purpose computer such as a PC or a server, and a plurality of distance image sensors 18 are connected to the computer 16.

  The range image sensor 18 emits light such as infrared light or laser, and captures light (reflected light) reflected from an object by an optical sensor such as a CCD (Charge Coupled Device) sensor. The distance image sensor 18 measures the actual time to the object by measuring the time until the light returns for each pixel. Further, the distance image sensor 18 can measure the shape of the object (for example, a human gesture). Therefore, based on the output of the distance image sensor 18, the position of a person and the position of a predetermined part (head and hand) of the person can be detected. However, a three-dimensional coordinate system is set in advance in the place or environment where the robot 12 is arranged, and the three-dimensional coordinates of the position of a human and the position of a predetermined part of the human are detected using the predetermined position as the origin. can do. However, in the first embodiment, since the position of the human is the position of the foot of the human, the component in the height direction is ignored. This is the same for the position of the robot 12.

  As the distance image sensor 18 of the first embodiment, a product called Xtion (registered trademark) made by ASUS (registered trademark) is employed. In another example, the distance image sensor 18 uses a Kinect (registered trademark) sensor made by Microsoft (registered trademark), a three-dimensional distance image sensor D-IMager (registered trademark) made by Panasonic (registered trademark), or the like. It is also possible. This type of sensor is sometimes referred to as a three-dimensional distance measurement sensor, a 3D scanner, or the like.

  In addition, as the distance image sensor 18, an omnidirectional laser range finder such as LiDAR (for example, imaging unit LiDAR (HDL-32e) (trade name) manufactured by Velodine), a stereo camera, or the like can be used.

  The distance image signal from each of the plurality of distance image sensors 18 is input to the computer 16, and the computer 16 stores the distance image signal as digital data in a memory (for example, an HDD or a RAM). The computer 16 calculates the position of each of one or a plurality of persons (in this first embodiment, the position of the person, the three-dimensional position of the head 26 and the hand) obtained by processing the distance image data stored in the memory. Data about the position (hereinafter, referred to as “human data”) is transmitted to the robot 12.

  Although omitted in FIG. 1, an external control terminal may be provided so as to be able to communicate with the robot 12 via the network 14. The external control terminal is a computer for remotely operating the robot 12. For example, in a case where the robot 12 communicates with a human, when an event that cannot be handled by the robot 12 occurs, an administrator or the like controls the robot 12 using an external control terminal and responds to an event that the robot 12 cannot handle. . An administrator or the like talks with a human through the robot 12 or transmits a command to the robot 12 to execute a communication action.

  2A, 2B, 2C, and 3 show an example of the appearance and configuration of the robot 12 in FIG. Specifically, FIG. 2A is a diagram for explaining the actuators A1, A2, A3, A4, and A5 for moving the eyelids (28a, 28b) and the eyeball of the robot 12 shown in FIG. FIG. 2B is a diagram for explaining the actuators A6, A7, A8, A9 for moving the forehead, eyebrows and mouth angle 30 of the robot 12 shown in FIG. 1, and FIG. 2C is a diagram showing the lips of the robot 12 shown in FIG. It is a figure for explaining actuator A10, A11, and A13 to move. FIG. 3 is a view for explaining actuators A14, A15, A16, A17, A18, and A19 for moving the head 26, the shoulder 32, and the waist 34 of the robot 12 shown in FIG. Hereinafter, the appearance and configuration of the robot 12 will be briefly described with reference to FIGS. 2A to 2C and FIG.

  Note that the robot 12 shown in FIGS. 2A to 2C and FIG. 3 is an example, and any Android robot having another appearance and configuration can be used. Further, the robot 12 does not need to be limited to an android robot, and any other robot having an appearance similar to a human can be used. As an example, a communication robot capable of communicating with a human or other robot to be communicated by physical movement or / and voice can be used. Specifically, Robobie (registered trademark), which is an example of a communication robot developed by the applicant, can be used. Unlike a human, this Roboby is configured to be movable by wheels, but has a head, a torso, and both arms, and has an appearance similar to a human.

  The robot 12 includes a body 24 and a head 26 provided on the body 24. An upper eyelid 28a and a lower eyelid 28b are formed above and below an eye (eyeball) on the head 26, and the eyes are opened and closed by controlling the vertical movement of the upper eyelid 28a and the lower eyelid 28b. Operation becomes possible. Lips are further formed on the head 26, and both ends of the lips form a corner 30. The mouth angle 30 can also be moved up and down similarly.

  The upper end (below the head) of the torso portion 24 is a shoulder 32, and the middle of the torso portion 24 is a waist 34. The shoulder 32 can be moved up and down, the waist 34 can be twisted (rotated) left and right, and can bend forward and backward.

  In the first embodiment, each of the actuators described below for moving the above-described portions of the robot 12 is a stepping motor driven by pulse power, and the rotation amount of the stepping motor is determined by the number of pulses. The number of pulses is given as a command value. In each of the target parts, an initial value is given to the actuator in a normal state, and when the target part is displaced, a command value of a pulse number according to the direction and magnitude is given to the corresponding actuator. In the first embodiment, each actuator is operated with a command value of "0-255", and any value of "0-255" is given as an initial value.

  The actuator A1 is an actuator for controlling the vertical movement of the upper eyelid 28a. The actuators A2, A3 and A4 are actuators for moving the eyeball left, right, up and down. The actuator A5 is an actuator that controls the vertical movement of the lower eyelid 28b. Therefore, the eyes are opened and closed by the actuators A1 and A5.

  The actuator A6 is an actuator for moving the forehead, and the actuator A7 is an actuator for moving the forehead.

  The actuator A8 is an actuator for raising the corner angle 30. The actuator A9 is an actuator for moving the tongue up and down. The actuator A10 is an actuator for expanding the lips left and right, and the actuator A11 is an actuator for protruding the lips forward.

  The actuator A13 is an actuator for protruding and pulling a jaw. The mouth is opened and closed by the actuator 13.

  The actuator A14 is an actuator for tilting the head 26 right and left, the actuator A15 is an actuator for lowering the head 26, and the actuator A16 is an actuator for rotating the head left and right. .

  The actuator A17 is an actuator for moving the shoulder 32 up and down. The actuator A18 is an actuator for bending the hip 34 forward or backward, and the actuator A19 is an actuator for rotating (twisting) the hip 34 right and left.

  As shown in FIG. 4, the robot 12 includes a processor (CPU in the first embodiment) 50 that controls the entire operation of the robot 12. The CPU 50 is connected to the communication module 56 via the bus 52, and thus, the CPU 50 is communicably connected to the network 14, that is, the computer 16 via the communication module 56 by wire or wirelessly.

  The CPU 50 can also access the RAM 54 through the bus 52, and gives a command value to the actuator control circuit 58 through the bus 52 in accordance with the programs and data (see FIG. 6) stored in the RAM 54 to control the operation of each of the actuators A1-An. Control.

  The RAM 54 is used as a buffer area and a work area of the CPU 50. However, an HDD can be used instead of the RAM 54. The actuator control circuit 58 drives each of the actuators A1 to An by generating pulse power of a number corresponding to the command value given from the CPU 50 and supplying the pulse power to the corresponding stepping motor.

  However, as the actuator, any actuator such as an actuator using a servomotor and a fluid actuator can be used other than the one using such a stepping motor.

  The sensor I / F (interface) 62 is connected to the CPU 50 via the bus 52, and receives respective outputs from the tactile sensor 64 and the eye camera 66.

  The tactile sensor 64 or the skin sensor is, for example, a touch sensor and forms a part of the tactile sensation of the robot 12. That is, the tactile sensor 64 is used to detect whether or not a human or another object has touched the robot 12. The output (detection data) from the tactile sensor 64 is provided to the CPU 50 via the sensor I / F 60. Therefore, the CPU 50 can detect that a human or another object touches the robot 12 (and the strength thereof).

  The eye camera 66 is an image sensor and forms a part of the vision of the robot 12. That is, the eye camera 66 is used to detect a video or image viewed from the eyes of the robot 12. In the first embodiment, data (image data) corresponding to a captured image (moving image or still image) of the eye camera 66 is provided to the CPU 50 via the sensor I / F 60. The CPU 50 stores the image data in the RAM 54 or transmits the image data to an external computer (for example, an external control terminal) via the communication module 56 and the network 14 (FIG. 1).

  Further, the speaker 68 and the microphone 70 are connected to the input / output I / F 62. The speaker 68 outputs a sound when the robot 12 speaks. The microphone 70 is a sound sensor and forms a part of the hearing of the robot 12. The microphone 70 has directivity, and is mainly used for detecting a voice of a human being who is to communicate with the robot 12 (communication).

  The system 10 having such a configuration is applied to a certain company, a certain event venue, or the like, and the robot 12 acts as a substitute for a human. For example, the robot 12 functions as a reception at a company or an event venue. The robot 12 performs a communication action (or action) such as talking with a human or guiding a human in response to a talk from a human. At this time, the robot 12 not only emits a voice, but also moves at least one of the head 26, the shoulder 32, and the waist 34.

  Although a detailed description is omitted, when a communication action is performed, the mouth is opened and closed when a voice is emitted, and the facial expression is changed by moving the forehead, eyebrows, and mouth angle 30. Such movements of the mouth, forehead, eyebrows, mouth corner 30 and the like are also included in the communication behavior. Hereinafter, the same applies to the case where a communication action is performed.

  For example, when talking with a human, the robot 12 may be able to hear his or her voice simply by listening or agreeing (e.g., "yes") while striking a neck so as to hit each other. Shaking (nodding) or shaking or tilting the head while giving a voice when disagreement (eg, “No”). When spoken by a human, the robot 12 greets, introduces itself, and listens to requirements. In the case of greeting, while issued a "good morning" or "Hello", to bow, in other words, tilted forward a little upper body.

  Further, when guiding the route, the robot 12 moves the head 26 while uttering the voice of the route, turns the head to look in the traveling direction according to the route, moves the shoulder 32, and reaches in the traveling direction. (Points). However, in the first embodiment, the line of sight of the robot 12 is a vertical bisector of a line connecting the centers of the left and right eyes of the robot 12 and means a straight line extending in front of the face.

  As described above, a communication action for talking with a human or providing a predetermined service such as a route guide (hereinafter, referred to as a “normal action” with respect to a “reaction action” described later) is a human communication target. Is executed after performing a reaction operation in response to (talking to) the robot 12. However, when a human talks (interrogates) the robot 12, the human needs to approach the robot 12 to a certain distance (for example, 60 to 70 cm). This is because the robot 12 detects human voice and correctly recognizes the detected voice.

  Further, the robot 12 performs a communication action (return action) executed in response to a predetermined input (or stimulus). The predetermined input is an input of various sensors provided in the robot 12. Specifically, the predetermined input is based on the output of the distance image sensor 18 and indicates that an object or a person exists within a certain range (for example, within a circle having a radius of 60 to 70 cm centered on the position of the robot 12). That was detected. However, based on not only the distance but also the image captured by the eye camera 66, it can be further known that there is an object or a person in front of the robot 12. The predetermined input is that the tactile sensor 64 detects that the robot 12 has collided with or touched an object or a person. Further, the predetermined input is that the microphone 70 has detected a sound having a volume higher than a certain level.

  In the first embodiment, the reaction operation is as follows. The robot 12 is configured such that a human approaches the robot 12, the human is within (or is present in) the field of view of the robot 12, and a predetermined part (the first In the embodiment, when a “hand” attempts to touch a predetermined part (for example, “face”) of the robot 12, a communication action (action) performed by noticing the touch, a human approaches the robot 12, When the human is not in the field of view of the robot 12 and touches the robot 12, this means an operation performed by noticing that the human has touched or an operation performed in response to a human talking to the robot 12. .

  Further, in the first embodiment, as a reaction operation, the robot 12 does not talk to the robot 12 but sees a human face trying to touch the face (head 26) of the robot 12 itself (communication action). Be executed. Therefore, the robot 12 that is focused on something and has not noticed the approaching person can operate so as to react to notice that the person has tried to touch the face of the robot 12.

  Specifically, the CPU 50 detects an output (human data) from the computer 16 and determines whether or not a human is within a certain range based on the robot 12. The robot 12 previously stores the coordinates of the position where the robot 12 is located, and can calculate the distance to the human from the coordinates and the coordinates of the human position included in the human data. If the calculated distance is shorter than the length that defines the certain range, it is determined that the human is within the certain range based on the robot 12, and if the calculated distance is equal to or longer than the length that defines the certain range, It is determined that the human is not within a certain range based on the robot 12.

  When a human is within a certain range based on the robot 12, the CPU 50 determines whether or not the human is within the field of view of the robot 12. That is, when the current face direction of the robot 12 is set as the reference direction (that is, the direction of the line of sight), the CPU 50 determines whether or not a person who is within the above-described certain range is within the viewing angle of the robot 12. I do.

  However, the viewing angle of the robot 12 is set to be about 200 degrees in the horizontal direction (however, 100 degrees for each of the left and right sides based on the line of sight) in accordance with the viewing angle of a general human, The vertical direction is set to about 125 degrees (however, based on the line of sight, the downward direction is 75 degrees and the upward direction is 50 degrees). However, in the first embodiment, since it is only determined whether or not a human is present in the direction in which the robot 12 is looking, the vertical direction is ignored.

  The robot 12 calculates a vector (line-of-sight vector) having a magnitude of 1 in the direction in which its line of sight is directed (excluding the vertical component), and calculates a vector from the position of the robot 12 to the position of the human. It is determined whether the angle formed by the two vectors is within 100 degrees. If the angle formed by the two vectors is within 100 degrees, it is determined that the human is in the field of view of the robot 12. On the other hand, when the angle formed by the two vectors exceeds 100 degrees, it is determined that the human is outside the visual field of the robot 12.

  In this embodiment, the viewing angle is fixedly set, but may be set variably. For example, the viewing angle may be reduced as a person approaches the robot 12.

  When a human is in the field of view of the robot 12, the CPU 50 determines whether or not the human hand is within a predetermined distance (first distance: for example, 20 cm) around the face of the robot 12. Specifically, in the first embodiment, it is determined whether or not the distance between the human hand and the surface of the head 26 of the robot 12 is within a predetermined distance. If the human hand is within 20 cm of the periphery of the robot 12 face, it is determined that the human is about to touch the robot 12 face. On the other hand, if the human hand is separated by more than 20 cm around the face of the robot 12, it is not determined that the human is about to touch the face of the robot 12.

  Although a detailed description will be omitted, when there are a plurality of persons within the above-described certain range, it is determined whether or not each person is within the field of view of the robot 12. Further, when a plurality of humans are within the field of view of the robot 12, it is determined whether or not the hand closest to the robot 12 is within a first distance around the face of the robot 12. However, when a plurality of humans are in the field of view of the robot 12, it may be determined whether or not any of the human hands is within a first distance around the face of the robot 12.

  In the first embodiment, as described above, when it is determined that a human is about to touch the face of the robot 12, the robot 12 causes the robot 12 to change its face to the human face as a reactive action. Turn to. Based on the human data transmitted from the computer 16, the three-dimensional position of the human face is detected, and at least one of the actuators A 14, A 15 and A 16 is controlled so that the line of sight of the robot 12 passes through the three-dimensional position, The direction of the head 26 of the robot 12 is changed.

  However, in the first embodiment, when a human is not in the field of view of the robot 12 (or does not exist), the robot 12 performs a slight reaction operation when touching any part by the human, Turn your face toward the person. However, the slight reaction operation means an operation of noticing that a touch has been made, and more specifically, an operation of slightly tilting the upper body backward so as to be surprised. That is, when touched by a human, the CPU 50 slightly tilts the upper body of the robot 12 in the same direction as the direction in which the touched hand extends (in the first embodiment, a two-dimensional direction, that is, a horizontal direction) (for example, 3 degrees). The actuator A18 or A19 is controlled so as to incline by about 5 to 10 degrees with respect to the height direction in the dimensional space.

  Although a detailed description is omitted, when a human talks (questions) to the robot 12, a “greeting” operation or a “reply” operation is executed as a reaction operation. Although a detailed description is omitted, in the operation of "greeting", robot 12, after the speech as "Hello", to bow. In the operation of “reply”, the robot 12 looks at a human after speaking “yes”.

  As described above, in the first embodiment, the first distance is set to 20 cm. The numerical value of the first distance is a numerical value determined by performing an experiment.

  In order to verify how far humans respond to contact with others, we conducted data collection experiments with other subjects who did not know each other. Specifically, as shown in FIG. 5, first, in a situation where the subject who is the evaluator T1 is sitting in a chair and looking at the front, the subject who becomes the contactor T2 slowly approaches his / her hand to the face of the evaluator T1. Then, data collection was performed in which the evaluator T1 measures the distance by pressing a button at a distance where the evaluator T1 does not want the hand to be closer. Two distance image sensors 18 (Kinect V2 was used in the experiment) were used for distance measurement. Further, as shown in FIG. 5, nine standing positions (0 to 8) of the contact person T2 are prepared, and a task of having the hand approach the face of the evaluator T1 at various angles from each standing position is performed. Repeated. Taking into account the gender of the contactor T2 and the evaluator T1, 10 pairs in each of the four combinations (40 pairs in total; male evaluator / female contactor, female evaluator / male contactor, male evaluator / male evaluator) , Female evaluator / female evaluator), and distance data before contact were collected about 12,000 times.

  Analysis of the collected data and the like indicated that at an average distance of about 20 cm, the evaluator T1 felt that he did not want any more hands. In addition, no significant effect due to the gender of the contactor T2 and the evaluator T1 was observed, and no significant effect due to the angle of approaching the hand was observed. In this way, the first distance for determining whether the robot 12 performs the reaction operation has been determined.

  In addition, as described above, in the normal operation and the reaction operation, the robot 12 performs a bodily operation such as a predetermined swing and behavior or / and an utterance operation. Therefore, in the first embodiment, the control information for executing the communication action such as the normal action and the reaction action is the control data for driving and controlling the actuators (A1 to A11, A13 to A19) and / or the utterance. It contains the voice data of the synthesized voice for the content, and is stored corresponding to the name (command name) given to each communication action. However, the physical motion includes a natural motion (unconscious motion). Blinking and breathing are typical examples of unconscious movements. In addition to such physiological actions, unconscious actions include actions due to human habits. For example, the operation due to the habit corresponds to, for example, an operation of touching hair, an operation of touching a face, an operation of biting a nail, and the like. The control information also includes control data for expressing mouth movements and facial expressions, in addition to body movements.

  Although omitted in FIG. 4, control information on the communication behavior is stored in a non-volatile memory such as an HDD, read from the HDD as needed, and written into the RAM 54.

  FIG. 6 is a diagram showing an example of the memory map 300 of the RAM 54 shown in FIG. As shown in FIG. 6, the RAM 54 includes a program storage area 302 and a data storage area 304.

  The program storage area 302 stores a communication program 302a, a distance detection program 302b, an operation control program 302c, and an audio processing program 302d.

  The communication program 302a is a program for communicating with another robot or computer (for example, the computer 16). The distance detection program 302b is a program for detecting or acquiring data on the distance to one or more persons (hereinafter, referred to as “distance data”) based on the human data transmitted from the computer 16. .

  The motion control program 302c is a program for controlling the motion of the robot 12, and includes a head control program 3020, a lip motion control program 3022, an expression control program 3024, an upper body (shoulder) control program 3026, and a lower body (waist) control. And a program 3028.

  The head control program 3020 is a program for controlling the actuators A14 to A16 shown in FIG. 3 so that the head 26 (FIG. 2) of the robot 12 is adapted to a normal operation or a reaction operation.

  The lip operation control program 3022 controls, for example, the actuators A10 to A11 shown in FIG. 2C so that when the robot 12 utters from the speaker 68, the lip shape conforms to the uttered voice (synthesized voice). Program.

  The expression control program 3024 controls the actuators A1 to A11 and A13 shown in FIGS. 2A to 2C to express the expression of the eyes and / or mouth of the robot 12 in accordance with the normal operation or the reaction operation. It is a program for controlling.

  The upper body (shoulder) control program 3026 is a program for controlling the actuator A17 shown in FIG. 3 so as to perform the operation of the upper body (shoulder) 32 of the robot 12 in accordance with the normal operation or the reaction operation.

  The lower body (waist) control program 3028 is a program for controlling the actuators A18 and A19 shown in FIG. 3 in order to operate the lower body (waist) 34 of the robot 12 in accordance with the normal operation or the reaction operation.

  The speech processing program 302d includes a speech recognition program and a speech synthesis program. The voice recognition program is a program for allowing the CPU 50 to recognize the contents of a human speaking to the robot 12 input through the microphone 70. The CPU 50 includes, for example, DP matching and a Hidden Markov Model (HMM). Thus, the speech content of the human utterance is recognized. The CPU 50 outputs a voice synthesized according to the voice synthesis data to the speaker 68 by executing the voice synthesis program.

  Although not shown, another program for controlling the robot 12 is stored in the program storage area 302.

  Various data are stored in the data storage area 304 of the RAM 54. The audio data 304a is audio data input from the microphone 70, and is temporarily stored. The dictionary data 304b is data such as a dictionary necessary for voice recognition. The distance data 304c is distance data detected according to the distance detection program 302b, and is temporarily stored. However, when a plurality of people exist around the robot 12, distance data for each person is detected.

  Although not shown, the data storage area 304 stores other data such as control information for executing a communication action necessary for controlling the robot 12, and also includes a timer and a register necessary for the operation of the CPU 50. , A flag, and the like.

  FIG. 7 is a flowchart showing an example of the robot control process of the CPU 50 shown in FIG. 4 in the first embodiment. As shown in FIG. 7, when starting the robot control process, the CPU 50 sets the direction of the face of the robot 12 to the initial direction in step S1. In the first embodiment, the initial direction is the direction in which the face of the robot 12 faces the front, and the command values of the actuators A14, A15, and A16 are set to all the initial values.

  In the next step S3, the process waits for a fixed time (for example, several seconds to ten and several seconds). In the first embodiment, the robot 12 is operated to look at one point, thereby expressing that the robot 12 is concentrated on something. For example, the eyelids (28a and 28b) are actuated to close their mouth, stare slightly downward at the material on the desk, and blink. That is, the CPU 50 controls the actuators A1 and A5, controls the actuator A13, and controls the actuator A15.

  Subsequently, in step S5, it is determined whether or not the human is within a certain range (for example, a circle of 60 to 70 cm centering on the position of the robot 12). Here, the CPU 50 receives the human data from the computer 16, calculates the distance to the human based on the received human data, and determines whether the human is within a certain range.

  If “NO” in the step S5, that is, if the person is not within the predetermined range, the process returns to the step S1. On the other hand, if “YES” in the step S5, that is, if the human is within a certain range, it is determined whether or not the human is in the visual field of the robot 12 in a step S7. Here, the CPU 50 determines whether or not a human is within the viewing angle of the robot 12 based on the human data.

  If “YES” in the step S7, that is, if the human is within the visual field of the robot 12, it is determined in a step S9 whether the human hand is within the first distance around the face of the robot 12. Here, the CPU 50 determines whether the human hand is located within a first distance from the face (head 26) of the robot 12 based on the human data. That is, it is determined whether or not a human is about to touch the face of the robot 12.

  If “NO” in the step S9, that is, if the human hand is not within the first distance around the face of the robot 12, the process returns to the step S1. On the other hand, if “YES” in the step S9, that is, if the human hand is within the first distance around the face of the robot 12, the face of the robot 12 is turned toward the human face in a step S11. The process proceeds to step S19. In this step S11, the CPU 50 acquires the three-dimensional position of the human face from the human data, and operates the head 26 so that the line of sight passes through the three-dimensional position.

  Therefore, the robot 12 is operated so as to detect that a human is about to touch the face of the robot 12 and look at the human face. For example, when a human approaches another human and tries to touch the face of the other human, the robot 12 can cause the robot 12 to perform the same operation as the operation performed by the other human. That is, since the robot 12 performs a natural reaction operation, it is possible to prevent a person who tries to touch the face of the robot 12 from feeling uncomfortable as much as possible.

  If “NO” in the step S7, that is, if the human is not in the visual field of the robot 12, it is determined whether or not the human hand touches the robot 12 in a step S13. Here, the CPU 50 indicates that the three-dimensional position of the human hand acquired from the human data is the position of the surface of the head 26, the body, or the hand (including the arm) of the robot 12, and the detection data of the tactile sensor 64 is touched. Judge whether to show that

  If “NO” in the step S13, that is, if the human hand is not touching the robot 12, the process returns to the step S3. On the other hand, if “YES” in the step S13, that is, if a human hand touches the robot 12, a slight reaction operation is executed in a step S15. In step S15, an operation of noticing that the user has been touched is executed. For example, when the robot 12 is touched by a human, the robot 12 moves its upper body so as to release or avoid the touched state.

  In a succeeding step S17, the face of the robot 12 is turned to a human face, and the process proceeds to a step S19. Note that the processing in step S17 is the same as the processing in step S11, and a duplicate description will be omitted.

  In the step S19, it is determined whether or not to end. That is, the CPU 50 determines whether or not an end instruction has been given by the user. If “NO” in the step S19, that is, if not to end, the process returns to the step S1. On the other hand, if “YES” in the step S19, that is, if it is to be ended, the control processing is ended.

  Although not shown in FIG. 7, but not shown, as described above, when a person who is within a certain range talks to the robot 12, the robot 12 performs a reaction operation and then performs a normal operation.

  According to the first embodiment, when the human hand tries to touch the robot face without talking to the robot, the direction of the head is controlled so that the robot looks at the human face. Therefore, it is possible to provide a robot that performs a reaction operation closer to that of a human. Therefore, it is possible to prevent a person who tries to touch the robot from feeling uncomfortable as much as possible.

  In the first embodiment, the case where the human hand tries to touch the face of the robot has been described. However, the present invention is not limited to this. For example, when a human has an object in his hand, it may be determined whether the object in his hand tries to touch the face of the robot. Further, the specific part of the robot 12 does not need to be limited to the face, and it may be determined whether or not a human tries to touch another part of the robot (such as a hand or a shoulder). However, when it is determined whether or not an attempt is made to touch another part, the first distance according to the other part is determined by performing the above-described experiment.

<Second embodiment>
The system 10 according to the second embodiment is the same as the system 10 according to the first embodiment except that the robot 12 performs a reaction operation according to parameters set for each person. The description of the overlapping points will be omitted or briefly described.

  In the second embodiment, when a human approaches a certain range in a state where the robot 12 is performing an unconscious operation such as looking around, instead of being concentrated on something, the robot 12 will Look at the face towards you. Thereafter, the robot 12 performs a different reaction operation according to the degree of human preference.

  In the second embodiment, for each person who communicates with the robot 12, the degree of favorableness (or intimacy) when viewed from the robot 12 is set and updated, and when a reaction operation is performed, the reaction operation is performed. A reaction operation according to the degree of favor is performed with reference to the degree of favor of humans. As an example, the degree of favor is determined by a number from 0 to 3, and the greater the number, the higher the degree of favor. Before a human communicates with the robot 12, the degree of favor is 0, and a communication action is performed on the human in accordance with the number of times of communication with the human and / or the length of time (cumulative time), that is, on the human. The degree of favor is increased according to the frequency with which the request is made. In addition, the degree of favor is reduced when the non-communication time exceeds a predetermined length (for example, several months).

  In the second embodiment, since it is necessary to individually identify a person, an IC tag storing identification information unique to the person is attached, and the robot 12 transmits the identification information from the IC tag attached to the communication target person. Is read to individually identify humans. Therefore, the robot 12 further includes an IC tag reader.

  Further, in the second embodiment, when the degree of favorableness is 2 or more, a reaction operation having a high degree of favorableness is performed, and when the degree of favorableness is less than 2, a reaction operation having a low degree of favorableness is performed. In the second embodiment, when a human is within a certain range and is within the visual field of the robot 12, the face of the robot 12 is turned toward the human face. This operation can also be called a reaction operation, but the operation of turning the face of the robot 12 toward a human face within a certain range is executed regardless of the degree of favor.

  In addition, as a method of executing a communication action (action) according to the intimacy level and changing the intimacy level, a method of Japanese Patent Application Laid-Open No. 2011-681, which was filed by the applicant first and has already been published, is adopted. Can also.

  Updating the degree of friendship (intimacy) is not an essential content of the present invention, and a detailed description thereof will be omitted in this specification.

  After the face of the robot 12 is turned toward the human face, different reaction actions are executed according to the degree of favor. In the reaction operation with a high degree of favor, when the human hand is within the first distance around the face of the robot 12, a reaction operation expressing high friendship is executed. In the second embodiment, a smiling action is executed as a reaction action expressing high favor, and "What do you want?" In the operation of smiling, the actuator A8 is controlled so as to slightly raise the mouth angle 30.

  In the reaction operation with a low degree of favor, if the human hand is within a second distance longer than the first distance around the face of the robot 12, a reaction operation expressing low or no favor is executed. You. In the second embodiment, a slight slewing motion is executed as a reaction operation expressing low or no favor, and when a human hand is within a first distance around the face of the robot 12, the reaction is performed. As an action, "What is it for?" In the slight slewing operation, the actuator A18 is controlled so that the upper body is tilted backward by about 5 to 10 degrees.

  Furthermore, in the reaction operation with a low degree of favor, when a human hand touches the robot 12, the robot 12 performs an unpleasant operation. As the disliked motion, the motion of tilting the upper body greatly in the opposite direction of the human being is executed, and "Please stop" is issued. In the operation of tilting the upper body greatly, the actuator A18 or the actuators A18 and A19 are controlled so that the upper body is tilted by about 20 to 30 degrees in the opposite direction of the human.

  In addition, even when the person is within a certain range, if the person is not within the field of view of the robot 12, a slight reaction operation is performed as in the first embodiment, but in the second embodiment, A reaction operation according to the degree of favor is performed. When the degree of favorableness is high, a smiling action is executed as a reaction action expressing the fact, and "What do you want?" On the other hand, when the degree of favorableness is low, as a reaction operation expressing this, a motion of tilting the upper body in the opposite direction of the human is executed, and "Please stop" is issued.

  Therefore, in the second embodiment, the favorableness degree determination program 302e is further stored in the program storage area 302. The favorableness determination program 302e is a program for determining whether the favorableness of a human to whom the robot 12 performs a reaction operation is equal to or greater than a predetermined value. In the second embodiment, the operation control program 302c executes a process according to the degree of favor (in the second embodiment, a reaction operation process with a high degree of favor or a reaction operation process with a low degree of favor).

  In the data storage area 304, data (favoring degree data) 304d on the degree of favorableness of a human to whom the robot 12 performs a reaction operation is stored. For example, the favorableness data 304 d of the human to be reacted by the robot 12 is acquired from a database provided inside the robot 12 or on the network 14. In addition, in response to the robot 12 performing the communication behavior with the human, the human preference data 304d is updated. For example, when performing a normal action with a human, the time from the start of the communication action to the end of the communication action is measured as the communication time, added to the accumulated time, and the number of times of communication Is added once. However, this is only an example and does not need to be limited. For example, the end of the communication behavior is when a human has left (leave a certain range).

  FIGS. 9 and 10 are flowcharts showing an example of the robot control process of the CPU 50 in the second embodiment. Hereinafter, the robot control processing of the second embodiment will be described, but the same processing as that described in the first embodiment will be briefly described. Although illustration is omitted, as in the first embodiment, a normal operation is also performed after the reaction operation is performed in response to a speech from a human.

  As shown in FIG. 9, when starting the robot control process, the CPU 50 sets the face direction of the robot 12 to the initial direction in step S31. In the next step S33, the process stands by for a fixed time. In the second embodiment, the eyelids (28a and 28b) are operated so that the robot 12 blinks, and the head 26 is rotated left and right so that the robot 12 is swirling. That is, the CPU 50 controls the actuators A1 and A5 and controls the actuator A16.

  Subsequently, in a step S35, it is determined whether or not the human is within a certain range. If “NO” in the step S35, the process returns to the step S31. On the other hand, if “YES” in the step S35, it is determined in a step S37 whether or not a person within a certain range is within the visual field of the robot 12.

  If “NO” in the step S37, the process proceeds to a step S47 shown in FIG. On the other hand, if “YES” in the step S37, in a step S39, the favorable degree of the human being within the fixed range and within the visual field of the robot 12 is equal to or more than a predetermined value (2 in the second embodiment). Determine whether or not. However, when there are a plurality of persons within a certain range and within the visual field of the robot 12, the person at the position closest to the robot 12 is selected as the target of the reaction operation.

  If “YES” in the step S39, that is, if the favorable degree is equal to or more than the predetermined value, in a step S41, a process of a reaction operation with a high favorable degree described later (see FIG. 11) is executed, and the process proceeds to the step S45. . On the other hand, if “NO” in the step S39, that is, if the favor degree is less than the predetermined value, in a step S43, the processing of the low favor reaction operation (see FIG. 12) described later is executed, and the step S45 is performed. Proceed to.

  In step S45, it is determined whether to end the robot control process. If “NO” in the step S45, the process returns to the step S31. On the other hand, if “YES” in the step S45, the robot control process ends.

  As described above, if “NO” in the step S37, as shown in FIG. 10, it is determined whether or not the human hand touches the robot 12 in a step S47. If “NO” in the step S47, the process returns to the step S33 shown in FIG. On the other hand, if “YES” in the step S47, a slight reaction operation is executed in a step S49, and in a step S51, the face of the robot 12 is turned to the human face.

  In a next step S53, it is determined whether or not the degree of favor is equal to or more than a predetermined value. If "YES" in the step S53, a smiling operation is executed in a step S55, and in a step S57, "What do you need?" Is spoken, and the process proceeds to the step S45 shown in FIG.

  On the other hand, if “NO” in the step S53, an operation of inclining the upper body in a direction opposite to the human is executed in a step S59, and “stop please” is uttered in a step S61, and the process proceeds to a step S45.

  FIG. 11 is a flowchart showing the processing of the reaction operation with a high degree of favor in step S41 of FIG. Hereinafter, the processing of the reaction operation with a high degree of favor will be described, but the processing already described will be briefly described. As shown in FIG. 11, when the CPU 50 starts the reaction operation with a high degree of favor, the CPU 50 turns the face of the robot 12 toward a human in step S71. In a next step S73, it is determined whether or not the human hand is within a first distance around the face of the robot 12.

  If “NO” in the step S73, the process returns to the step S71. On the other hand, if “YES” in the step S73, a smiling operation is executed in a step 75, and “Say something?” Is uttered in a step S77, and the robot control process shown in FIGS. 9 and 10 is performed. Return to

FIG. 12 is a flowchart showing the processing of the reaction operation of low favor in step S43 of FIG. Hereinafter, the processing of the reaction operation with a low degree of favor will be described, but the processing already described will be briefly described. As shown in FIG. 12, when the low-favorable-degree reaction operation is started, the CPU 50 turns the face of the robot 12 toward a human in step S91. In a next step S93, it is determined whether or not the human hand is within a second distance around the face of the robot 12.

  If “NO” in the step S93, that is, if the human hand is not within the second distance around the face of the robot 12, the process returns to the step S91. On the other hand, if “YES” in the step S93, that is, if the human hand is within the second distance around the face of the robot 12, a slight slashing operation is executed in a step S95.

  Subsequently, in a step S97, it is determined whether or not the human hand is within the first distance around the face of the robot 12. If “NO” in the step S97, the process proceeds to a step S101. On the other hand, if “YES” in the step S97, in a step 99, “What is it for?” Is uttered, and the process proceeds to the step S101.

  In step S101, it is determined whether a human hand has touched the robot 12. If “NO” in the step S101, the process returns to the robot control process shown in FIGS. On the other hand, if “YES” in the step S101, an operation of tilting the upper body in a direction opposite to a human is executed in a step S103, and “stop please” is uttered in a step S105, and then, the process returns to the robot control process. .

  Normally, the human and the human hand gradually approach the robot 12, and the scan time in steps S <b> 91 to S <b> 93 is about 1/60 second in a low-favorable reaction operation. When it is determined that the human hand is within the second distance around the face of the robot 12, it is considered that the human hand is hardly within the first distance around the face of the robot 12. That is, in step S93, it is determined whether the human hand is longer than the first distance around the face of the robot 12 and is within the second distance.

  According to the second embodiment, not only the reaction operation is performed in response to the human hand approaching the face of the robot, but also the content of the reaction operation is changed in accordance with the degree of preference of the human. It is possible to cause the robot to perform the same reaction operation as a human having. A reaction closer to human beings can be realized.

  In the second embodiment, the degree of favor (or intimacy) is used as a parameter, and different reaction actions are performed according to the value of this parameter. However, the parameter need not be limited to the degree of favor. . For example, the age of the robot may be set, and a different reaction operation may be performed depending on whether the age of the person who performs the reaction operation is higher than, equal to, or lower than the age of the robot. Alternatively, the gender of the robot may be set, and a different reaction operation may be performed depending on whether the gender of the person who performs the reaction operation is the same as or different from the gender of the robot. The reaction operation may be determined using a parameter that considers these in a complex manner.

  Further, the reaction operation shown in each of the above embodiments is merely an example, and should not be limited. It can be set or changed as appropriate in consideration of the environment or place where the robot 12 is actually applied, the actual role given to the robot 12, and the like.

  Further, in each of the above-described embodiments, the communication behavior of the robot between the robot and the human, which exists in the real space, has been described, but is not limited thereto. When two agents (character objects) having a human-like appearance (shape) are arranged in a virtual space, a part (a hand or a part corresponding to a hand) belonging to the other agent is set to a predetermined position of one agent. When an attempt is made to touch a part (a face or a part corresponding to a face), one of the agents is caused to execute a reaction operation, or the other agent is caused to execute a reaction operation according to the degree of favorableness of the other agent. You may do so. In such a case, a processor of a general-purpose computer draws an agent in a virtual space, executes a program as described in each of the above embodiments, and controls the agent.

  Further, in each of the above-described embodiments, the position of the human, the position of the human hand and the face of the human are detected by detecting the distance to the target and the shape of the target using the image distance sensor. However, it need not be limited to this. Since the robot 12 includes the eye camera 66, the robot 12 is used as a stereo camera, and detects the position of a human approaching from the front direction of the robot 12, the position of the human hand and the face of the human based on the images captured by the left and right cameras. You may do so.

  Furthermore, in each of the above-described embodiments, it is determined whether the human hand is within a predetermined distance (first distance or second distance) around the face of the robot 12, and the reaction operation is performed. However, it need not be limited to this. A reaction operation may be performed by estimating from a moving speed of a human and, after a few seconds, determining whether or not the human hand is within a predetermined distance around the face of the robot 12.

  Further, the specific numerical values shown in the above-described embodiments are merely examples, and need not be limited, and can be appropriately changed according to the actual product, the environment to which the product is applied, and the like.

  Furthermore, in the robot control processing shown in the above-described embodiment, the order in which the steps are processed may be changed as long as the same result is obtained.

DESCRIPTION OF SYMBOLS 10 ... System 12 ... Android robot 16 ... Computer 18 ... Image distance sensor 26 ... Head 28a ... Upper eyelid 28b ... Lower eyelid 30 ... Mouth angle 32 ... Shoulder 34 ... Waist 50 ... CPU
54… RAM
56: communication module 64: tactile sensor 66: eye camera 68: speaker 70: microphone

Claims (9)

A robot having a human-like appearance,
Liking storage means for storing liking data about liking of others;
First approach determining means for determining whether a part belonging to the other person present around the robot has approached within a first predetermined distance of the robot;
When it is determined by the first approach determining means that the part belonging to the other person has approached within the first predetermined distance of the robot, the similarity degree of the other person stored in the similarity degree storing means is determined. A robot comprising an action execution unit that executes a corresponding reaction operation on the other person.   The robot according to claim 1, further comprising a calculation unit configured to calculate a shape of the other person present around the robot and a position of a part belonging to the other person.   The robot according to claim 1, wherein the action execution unit executes a first reaction operation when the degree of favor is equal to or more than a predetermined value or a second reaction operation when the degree of favor is less than the predetermined value. A second approach determination unit configured to determine whether a part belonging to the other person has approached within a second predetermined distance longer than the first predetermined distance,
The action execution means is configured to determine whether the part belonging to the other person has approached the first distance of the robot by the first approach determination means if the degree of favor is equal to or greater than the predetermined value. Executing the first reaction operation, and if the degree of favor is less than the predetermined value, the second approach determining means determines that the part belonging to the other person has approached the second predetermined distance of the robot. The robot according to claim 3, wherein the second reaction operation is performed when the operation is performed.   The robot according to any one of claims 1 to 4, wherein the degree of favor of the other person is changed according to a frequency of a communication action with the other person. A robot control program for a robot having a likeness storage means for storing likeness data about the like of another person, the robot having an appearance similar to a human,
In the processor of the robot,
An approach determining step of determining whether a part belonging to another person present around the robot has approached within a predetermined distance of the robot,
When it is determined in the approach determination step that the part belonging to the other person has approached the predetermined distance of the robot, a reaction operation according to the other person's favorable degree stored in the favorable degree storage means is performed. A robot control program that causes the other person to execute an action execution step to be executed. A robot control method for a robot having a likeness storage means for storing likeness data about another's like, and having a human-like appearance,
(A) determining whether a part belonging to another person present around the robot has approached within a predetermined distance of the robot;
(B) when it is determined in step (a) that the part belonging to the other person has approached within the predetermined distance of the robot, according to the other person's favorable degree stored in the favorable degree storage means; Performing a reaction operation on the other person. An agent control program for an agent that is executed by a computer including a preference storage unit that stores preference data about the preference of another agent, which is present in a virtual space and has an appearance similar to a human,
To the processor of the computer,
An approach determining step of determining whether a part belonging to another agent present around the agent has approached within a predetermined distance of the agent,
When it is determined in the approach determination step that the part belonging to the other agent has approached within the predetermined distance of the agent, a reaction according to the degree of favorableness of the other agent stored in the favorable degree storage means An agent control program for executing an action execution step of executing an action on the other agent. An agent control method that controls an agent that exists in a virtual space and has an appearance similar to a human by a computer including a preference storage unit that stores preference data about the preference of other agents,
(A) determining whether a part belonging to another agent present around the agent has approached within a predetermined distance of the agent;
(B) when it is determined in step (a) that the part belonging to the other agent has approached the predetermined distance of the agent, the similarity of the other agent stored in the similarity storage means; An agent control method including a step of executing a reaction operation according to the above-mentioned other agent on the other agent.

Images