JP4822319B2 - Communication robot and attention control system using the same - Google Patents

Description

  The present invention relates to a communication robot and an attention control system using the communication robot, and more particularly, for example, a communication robot that controls human attention by performing communication with a human using at least one of body motion and voice. Related to the attention control system.

An example of this type of conventional communication robot is disclosed in Patent Document 1. According to this patent document 1, the communication robot observes the status of the exhibition hall, the status of the instructors and visitors from the viewpoint of the robot body itself, and the ID number and XY coordinates and video data of the observed infrared tag, Time information or the like is added to the interaction data such as voice data and tactile data, and transmitted to the data acquisition server. Further, the robot body presents communication behavior (guidance, recommendation, etc.) according to the interaction data to the person in the environment. For example, the robot body performs a pointing operation toward a certain exhibit and makes a recommendation such as saying “You should see the exhibit”. That is, it is possible to control (guide) the attention of the conversation partner based on the history of the behavior of the conversation partner.
JP 2005-131713 A

  In this background art, when there is only one conversation partner, the attention can be controlled. Therefore, when there are a large number of conversation partners, attention is individually controlled for each person, which takes a lot of time. That is, it cannot be said that appropriate communication behavior (attention control) is performed. In such a case, the communication partner should be considered as one group and perform communication behavior.

  Therefore, a main object of the present invention is to provide a novel communication robot and an attention control system using the communication robot.

  Another object of the present invention is to provide a communication robot and an attention control system using the same that can execute appropriate attention control according to the number of people.

The invention according to claim 1 is a communication robot that controls human attention by performing communication behavior with a human using at least one of physical movement and voice. This communication robot includes a number detection means for detecting the number of human beings in the surrounding area, a group attention control means for controlling the attention of a predetermined number of human beings in the surrounding area, and the attention of a human being less than the predetermined number existing in the surrounding area. Personal attention control means for individually controlling the group attention control means or the group attention control means based on the detection result of the number detection means . It is determined by the group existence judging means for judging whether or not all human beings are within the first predetermined angle ahead, and the group existence judging means is that the person to be controlled exists outside the first predetermined angle ahead. A first communication action execution means for executing a first communication action for moving all persons to be controlled within the first predetermined angle; When it is determined by the presence determination means that all the persons to be controlled are present within the first predetermined angle ahead, the direction of the line of sight of the person to be controlled and the position of the eyes of the person to be controlled are Whether or not all of the control target humans are looking at themselves by judging whether or not the angle formed by the straight line connecting with their own position is equal to or less than the second predetermined angle. Group attention determination means for determining the second communication behavior, and when the group attention determination means determines that there is a control target person who does not look at himself / herself, the second communication action causes all control target persons to pay attention to themselves A second communication action executing means for executing

According to the first aspect of the present invention, this communication robot (12: reference numeral corresponding to the embodiment; the same applies hereinafter) acts to communicate with a human by using at least one of body movement and voice. To control. The number of persons detecting means (76, S11) detects the number of persons existing around the person. The communication robot (12) includes group attention control means (76, S15) and individual attention control means (76, S19), and selects either one based on the detection result of the number of persons detection means (76, S11). Run it. The group attention control means (76, S15) controls the attention of a predetermined number or more of people around as one group. Further, the personal attention control means (76, S19) individually controls the attentions of less than a predetermined number of people present in the surroundings. For example, when the group attention control means (76, S15) is executed, the communication robot (12) behaves so as to talk to all the humans present around while looking over all the humans (the whole). On the other hand, when the personal attention control means (76, S19) is executed, the communication robot (12) behaves so as to talk individually while looking at the person to be controlled. The group attention control means (76, S15) is a group presence determination means (76, S33), a first communication action execution means (76, S35, S37, S39, S41), a group attention determination means, and a second communication action execution means. (76, S49, S51, S53, S55). The group presence determination means (76, S33) determines whether or not all the persons to be controlled existing around are present within the first predetermined angle ahead. The first communication action execution means (76, S35-S41) is determined when the group existence determination means (76, S33) determines that the person to be controlled exists outside the first predetermined angle ahead, that is, the control object. If any one of the humans does not exist within the first predetermined angle in front of himself / herself, the first communication action is performed to move all the persons to be controlled within the first predetermined angle. For example, the communication robot (12) calls on a group (all persons to be controlled) to gather in front of itself while looking around. The group attention determination unit (76, S47) is configured such that when all the persons to be controlled are present within the first predetermined angle in front of the group presence determination unit (S33), all the persons to be controlled are Judge whether or not you are looking. Here, in the horizontal plane, whether or not the angle formed by the line-of-sight direction of the control target human and the straight line connecting the position of the human eye of the control target and the own position is equal to or less than the second predetermined angle is determined. In other words, it is determined whether or not all the persons to be controlled are paying attention to the communication robot (12). The second communication action execution means (76, S49-S55) is determined by the group attention determination means (76, S47) that there is a person to be controlled who is not looking at the person, that is, the control object. If any one of the humans is not paying attention to itself, the second communication action is executed to make all the controlled humans pay attention to themselves. For example, the communication robot (12) calls on the group to pay attention to itself while looking around.

According to the first aspect of the present invention, different attention control is executed depending on the number of humans present in the surrounding area, so that appropriate attention control can be executed.
Further, if any one person does not exist within the first predetermined angle in front of himself / herself, a communication action is performed to move all persons to be controlled within the first predetermined angle. Can be moved forward.
Furthermore, when any one of them is not paying attention to himself / herself, a communication action that causes all persons to be controlled to pay attention to himself / herself is executed, so that a group of a predetermined number or more can be noted by himself / herself.

The invention of claim 2 is dependent on claim 1 , and the group attention determination means is independent of the determination result of the group presence determination means when the first communication action is executed by the first communication action execution means for the first predetermined number of times. , It is determined whether all the persons to be controlled are looking at themselves.

In the invention of claim 2 , the group attention determining means (76, S47) is executed when the first communication action is executed for the first predetermined number of times by the first communication action executing means (76, S35-S39) ("YES" in S45). "), Regardless of the determination result of the group existence determination means (76, S33), it is determined whether or not all the persons to be controlled are looking at themselves. In other words, if the person to be controlled does not follow the guidance of the communication robot (12) by the first communication behavior, the first communication is semipermanently repeated by ignoring the person who does not follow the guidance. It has been avoided.

According to the invention of claim 2 , since the same communication behavior is avoided semi-permanently, appropriate communication behavior can be executed.

The invention of claim 3 is dependent on claim 1 or 2 , and the group attention control means determines that when the group attention determination means determines that all persons to be controlled are looking at itself, the control object Collective distance determining means for determining whether or not the distances to all humans are within a certain range, and a third method for moving all control target human beings within a certain range based on the determination result of the collective distance determining means It further includes third communication action execution means for executing the communication action.

In the invention of claim 3 , the group attention control means (76, S15) includes the group distance determination means (76, S61, S75) and the third communication execution means (76, S63, S65, S67, S69, S77, S79, S81, S83). The collective distance determining means (76, S61, S75) is determined when it is determined by the collective attention determining means (76, S47) that all the persons to be controlled are looking at themselves , that is, all of the controlled objects. When a human is paying attention to himself / herself, it is determined whether or not the distance between all the control target humans is within a certain range. The third communication action execution means (76, S63-S69, S77-S83) moves all persons to be controlled within a certain range based on the determination result of the collective distance determination means (76, S61, S75). 3 Perform communication behavior. For example, if any one person is too far from or too close to the communication robot (12), he / she calls all the people to be controlled to approach himself / herself while looking around the surroundings. Invite them to move away from themselves.

According to the invention of claim 3 , if any one person does not exist within a certain range, the communication action for moving all the persons to be controlled within the certain range is executed. Can be moved within a certain range.

The invention of claim 4 is dependent on claim 3 , and the group distance determination means is independent of the determination result of the group attention determination means when the second communication action is executed a second predetermined number of times by the second communication action execution means. Then, it is determined whether or not the distances between all persons to be controlled are within a certain range.

In the invention of claim 4 , the collective distance determining means (76, S61, S75) is executed when the second communication action is executed a second predetermined number of times by the second communication action executing means (76, S49-S55) (in S59). “YES”), regardless of the determination result of the group attention determination means (76, S47), it is determined whether or not the distances to all persons to be controlled are within a certain range. In other words, if the person to be controlled does not follow the guidance of the communication robot (12) by the second communication action, the second communication is semipermanently repeated by ignoring the person who does not follow the guidance. It has been avoided.

According to the invention of claim 4, as in the invention of claim 2 , an appropriate communication action can be executed.

The invention of claim 5 is dependent on claim 3 , and the group attention control means is configured to issue a warning for all human beings to be controlled when the third communication action is executed a third predetermined number of times by the third communication action executing means. End control.

In the invention of claim 5 , the group attention control means (76, S15) is executed when the third communication action is executed a third predetermined number of times by the third communication action executing means (76, S63-S69, S77-S83) ( In S87, “YES”), the control of attention for all the persons to be controlled is terminated.

In the invention of claim 5, as in the invention of claim 2 , an appropriate communication action can be executed.

The invention of claim 6 is dependent on claim 1, and the personal attention control means is a personal presence determination means for determining whether or not a human being present is within a third predetermined angle ahead, and a personal presence determination. When the means determines that the person to be controlled does not exist within the third predetermined angle ahead, the fourth communication action executing means for executing the fourth communication action for moving the person to be controlled within the third predetermined angle. including.

In the invention of claim 6 , the personal attention control means (76, S19) includes a personal presence determination means (76, S103) and a fourth communication action execution means (76, S105, S107). The individual presence determination means (76, S103) determines whether or not a person existing in the vicinity exists within a third predetermined angle ahead. That is, it is determined whether or not the person to be controlled is present within the third predetermined angle in front of him / her. Fourth Communication action executing means (76, S105, S107), when the controlled object by personal presence determining means (76, S103) humans the absence within a third predetermined angle in front is determined, the control target A fourth communication action that moves the person within a third predetermined angle is executed. For example, the communication robot (12) calls on the person to be controlled to move in front of the communication robot (12).

According to the invention of claim 6 , when the person to be controlled does not exist within the third predetermined angle in front of itself, the communication action for moving the person to be controlled within the third predetermined angle is executed. The person to be controlled can be moved in front of himself / herself.

The invention of claim 7 is according to claim 6, personal care control means, when the controlled object by personal presence determination means humans to be present within a third predetermined angle in front is determined, in the horizontal plane, the By determining whether or not the angle formed by the line-of-sight direction of the control target human and the straight line connecting the position of the control target human eye and the own position is equal to or smaller than a fourth predetermined angle, the control target human Individual attention determination means for determining whether or not he / she is looking at himself / herself, and when it is determined by the personal attention determination means that the person being controlled is not looking at himself / herself, It further includes fifth communication action execution means for executing the fifth communication action to be noticed.

In the invention of claim 7 , the personal attention control means (76, S19) further includes a personal attention determination means (76, S113) and a fifth communication action execution means (76, S115, S117). The personal attention determination means (76, S113) determines that the person to be controlled exists within the third predetermined angle ahead by the personal presence determination means (76, S103) . By determining whether or not the angle formed by the human gaze direction and the straight line connecting the position of the controlling human eye and its own position is equal to or smaller than a fourth predetermined angle, the control target human is looking at him. Judge whether or not. That is, it is determined whether or not the person to be controlled is paying attention to itself. The fifth communication action execution means (76, S115, S117), when the individual attention determination means (76, S113) determines that the person to be controlled is not looking at the person, controls the person to be controlled. Execute the fifth communication action that draws attention to itself. For example, the communication robot (12) calls on the person to be controlled to look at him / herself.

According to the invention of claim 7, when a person of the controlled object is not focused on itself, so to perform the communication behavior to attention human of the control object to itself, attention human of the control object to itself Can be made.

The invention according to claim 8 is dependent on claim 7 , and the individual attention determination means is independent of the determination result of the individual presence determination means when the fourth communication action is executed a fourth predetermined number of times by the fourth communication action execution means. Then, it is determined whether or not the person to be controlled is looking at himself / herself.

In the invention of claim 8 , the individual attention determining means (76, S113) is executed when the fourth communication action is executed a fourth predetermined number of times by the fourth communication action executing means (76, S105, S107) ("YES" in S111). "), Regardless of the determination result of the individual presence determination means (S103), it is determined whether or not the person to be controlled is looking at himself / herself.

According to the invention of claim 8, as in the invention of claim 2 , an appropriate communication action can be executed.

The invention of claim 9 is dependent on claim 7 or 8 , and the personal attention control means, when it is determined by the personal attention determination means that the person to be controlled is looking at the person to be controlled, Personal distance determining means for determining whether or not the distance to the distance is within a certain range, and sixth communication action for executing a sixth communication action for moving a person within a certain range based on the determination result of the personal distance determining means Execution means is further included.

In the invention of claim 9 , the personal attention control means (76, S19) further includes a personal distance determination means (76, S123, S133) and a sixth communication action execution means (76, S125, S127, S135, S137). . The personal distance determination means (76, S123, S133) is a distance from the control target person when the individual attention determination means (76, S113) determines that the control target person is looking at the person. Is determined to be within a certain range. That is, it is determined whether the person to be controlled is within a certain range from the position of the communication robot (12). The sixth communication action execution means (76, S125, S127, S135, S137) executes the sixth communication action that moves the person within a certain range based on the determination result of the personal distance determination means (76, S123, S133). To do. For example, if the person to be controlled is too far or too close to the communication robot (12), he / she looks at the person to be controlled and calls to approach himself / herself or slightly away from himself / herself. To do.

According to the invention of claim 9, when a person of the controlled object does not exist in the predetermined range, so executes the communication behavior of moving human of the control object within a certain range, a constant human of the control object Can be moved within range.

The invention of claim 10 is dependent on claim 9 , and the personal distance determination means is independent of the determination result of the individual attention determination means when the fifth communication action is executed by the fifth communication action execution means for the fifth predetermined number of times. Then, it is determined whether or not the distance to the person to be controlled is within a certain range.

In the invention of claim 10 , the personal distance determining means (76, S123, S133) is executed when the fifth communication action is executed a fifth predetermined number of times by the fifth communication action executing means (76, S115, S117) (in S121). “YES”), regardless of the determination result of the individual attention determination means (76, S113), it is determined whether or not the distance to the control target person is within a certain range.

In the invention of claim 10 as well, as in the invention of claim 2 , an appropriate communication action can be executed.

The invention of claim 11 depends on claim 9, personal care control means, when the sixth communication behavior is performed sixth predetermined number of times by the sixth communication action executing means, the control of attention for human control subjects finish.

In the invention of claim 11 , the personal attention control means (76, S19) is executed when the sixth communication action is executed a sixth predetermined number of times by the sixth communication action execution means (76, S125, S127, S135, S137) ( In S141, “YES”), the control of attention for the control target person is terminated.

In the invention of claim 11 as well, as in the invention of claim 2 , an appropriate communication action can be executed.

A twelfth aspect of the present invention is a caution control system that controls human attention using a communication robot that performs communication behavior with a human using at least one of body movement and voice. The attention control system includes a number detection means for detecting the number of people present around the communication robot. The communication robot is provided with group attention control means for controlling the attention of a person of a predetermined number or more existing in the surroundings, and individual attention control means for individually controlling the attention of a human being less than a predetermined number of persons in the surroundings, and the number detection means The group attention control means or the personal attention control means is selectively executed based on the detection result, and the group attention control means determines whether all the persons to be controlled around exist within the first predetermined angle in front. When it is determined by the group presence determination means and the group presence determination means that determine whether or not the control target person exists outside the first predetermined angle in front, all the control target persons are assigned to the first control object. The first communication action execution means for executing the first communication action to be moved within a predetermined angle and the group existence determination means all of the control objects. Is determined to be within the first predetermined angle in front of the person, the line of sight of the control target human eye and the position of the control target human eye and its own position are connected in a horizontal plane. Collective attention for determining whether or not all the persons to be controlled are looking at themselves by determining whether or not the angle formed by the straight line is equal to or smaller than a second predetermined angle for all the persons to be controlled. When the determination means and the group attention determination means determine that there is a person to be controlled who does not look at the person, the second communication action is executed to cause all the persons to be controlled to pay attention to themselves. 2nd communication action execution means is included.

In the invention of claim 14, the attention control system (10) controls human attention using the communication robot (12). The communication robot (12) performs communication behavior with a human by using at least one of body movement and voice. The number of persons detecting means (14, 16, 76, S11) detects the number of persons existing around the communication robot (12). The communication robot (12) includes group attention control means (76, S15) and individual attention control means (76, S19), and one of them is based on the detection result of the number of persons detection means (14, 16, 76, S11). Is selectively executed. The group attention control means (76, S15) controls the attention of a predetermined number or more of people around as one group. Further, the personal attention control means (76, S19) individually controls the attentions of less than a predetermined number of people present in the surroundings. For example, when the group attention control means (76, S15) is executed, the communication robot (12) behaves so as to talk to all the humans present around while looking over all the humans (the whole) to be controlled. On the other hand, when the personal attention control means (76, S19) is executed, the communication robot (12) behaves so as to talk individually while looking at the person to be controlled. The group attention control means (76, S15) is a group presence determination means (76, S33), a first communication action execution means (76, S35, S37, S39, S41), a group attention determination means, and a second communication action execution means. (76, S49, S51, S53, S55). The group presence determination means (76, S33) determines whether or not all the persons to be controlled existing around are present within the first predetermined angle ahead. The first communication action execution means (76, S35-S41) is determined when the group existence determination means (76, S33) determines that the person to be controlled exists outside the first predetermined angle ahead, that is, the control object. If any one of the humans does not exist within the first predetermined angle in front of himself / herself, the first communication action is performed to move all the persons to be controlled within the first predetermined angle. For example, the communication robot (12) calls on a group (all persons to be controlled) to gather in front of itself while looking around. The group attention determination unit (76, S47) is configured such that when all the persons to be controlled are present within the first predetermined angle in front of the group presence determination unit (S33), all the persons to be controlled are Judge whether or not you are looking. Here, in the horizontal plane, whether or not the angle formed by the line-of-sight direction of the control target human and the straight line connecting the position of the human eye of the control target and the own position is equal to or less than the second predetermined angle is determined. In other words, it is determined whether or not all the persons to be controlled are paying attention to the communication robot (12). The second communication action execution means (76, S49-S55) is determined by the group attention determination means (76, S47) that there is a person to be controlled who is not looking at the person, that is, the control object. If any one of the humans is not paying attention to itself, the second communication action is executed to make all the controlled humans pay attention to themselves. For example, the communication robot (12) calls on the group to pay attention to itself while looking around.

Also in the twelfth aspect of the invention, similar to the first aspect of the invention, appropriate attention control can be executed.

  According to the present invention, different attention control is selectively executed depending on the number of humans present in the surrounding area, so that appropriate attention control can be executed.

  The above object, 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.

  Referring to FIG. 1, an attention control system (hereinafter simply referred to as “system”) 10 of this embodiment includes a communication robot (hereinafter simply referred to as “robot”) 12. The robot 12 can take a body motion or action (hereinafter sometimes referred to as “communication action”) such as gestures with a human. However, the communication behavior may include a conversation (utterance) between the robot 12 and a human.

  The system 10 includes a general-purpose computer 14 such as a PC or a workstation, and the computer 14 is communicably connected to the robot 12 via a network such as a wireless LAN (not shown). However, as will be described later, since the coordinate signal is only transmitted from the computer 14 to the robot 12, the signal may be directly transmitted without going through the network. In such a case, the computer 14 can transmit the coordinate signal by short-range radio such as Bluetooth (registered trademark).

  In addition, the system 10 includes a floor sensor 16 that is connected to the computer 14. Although not shown, the floor sensor (floor pressure sensor) 16 includes a large number of detection elements (pressure-sensitive sensors), and the large number of detection elements are embedded (laid down) on the floor of a room or venue to which the system 10 is applied. ). In this embodiment, the floor sensor 16 outputs a signal (detection signal) based on the pressure to the computer 14 when the robot 12 or a person is present in a room or a venue. The computer 14 detects a two-dimensional coordinate based on the detection signal, and transmits a signal (coordinate signal) of the detected two-dimensional coordinate to the robot 12. From this coordinate signal, the robot 12 can know whether or not a human is present around the robot, and can further know the number of people and the distance from each human if a human is present.

  Note that the robot 12 stores map data (two-dimensional data) such as a venue to which the system 10 is applied in an internal memory (memory 80: see FIG. 3). Then, the robot 12 moves in the venue with reference to the map data with reference to the arbitrarily set origin position. However, the coordinate system of map data referred to by the robot 12 and the coordinate system of two-dimensional coordinates calculated by the computer 14 are set to be the same.

  Although detailed description is omitted, in this embodiment, since it is assumed that a human is present around the robot 12, the computer 14 is based on the output from the floor sensor 16. The coordinates about the midpoint of the two legs are calculated as human coordinates. Further, the computer 14 calculates the coordinates about the midpoint of the two wheels 34 (see FIG. 2) as the position coordinates of the robot 12.

  The robot 12 has a human-like body and generates complex body movements necessary for communication using the body. Specifically, referring to FIG. 2, the robot 12 includes a carriage 32, and wheels 34 for autonomously moving the robot 12 are provided on the lower surface of the carriage 32. The wheel 34 is driven by a wheel motor (indicated by reference numeral “36” in FIG. 3 showing the internal configuration of the robot 12), and the carriage 32, that is, the robot 12 can be moved in any direction.

  Although not shown in FIG. 2, a collision sensor (indicated by reference numeral “38” in FIG. 3) is attached to the front surface of the carriage 32, and the collision sensor 38 is connected to a person or other person to the carriage 32. Detect obstacle contact. When contact with an obstacle is detected during the movement of the robot 12, the driving of the wheels 34 is immediately stopped and the movement of the robot 12 is suddenly stopped.

  In this embodiment, the height of the robot 12 is about 100 cm so as not to intimidate people, particularly children. However, this height can be arbitrarily changed.

  A polygonal column sensor mounting panel 40 is provided on the carriage 32, and an ultrasonic distance sensor 42 is mounted on each surface of the sensor mounting panel 40. The ultrasonic distance sensor 42 measures the distance between the mounting panel 40, that is, the person around the robot 12 mainly.

  Further, the body of the robot 12 is mounted on the carriage 32 so that the lower portion thereof is surrounded by the mounting panel 40 described above and stands upright. The body is composed of a lower body 44 and an upper body 46, and the lower body 44 and the upper body 46 are connected by a connecting portion 48. Although not shown, the connecting portion 48 has a built-in lifting mechanism, and the height of the upper body 46, that is, the height of the robot 12 can be changed by using the lifting mechanism. As will be described later, the elevating mechanism is driven by a waist motor (indicated by reference numeral “50” in FIG. 3). The height 100 cm of the robot 12 described above is a value when the upper body 46 is at its lowest position. Therefore, the height of the robot 12 can be 100 cm or more.

  One omnidirectional camera 52 and one microphone 16 are provided in the approximate center of the upper body 46. The omnidirectional camera 52 photographs the surroundings of the robot 12 and is distinguished from an eye camera 54 described later. The microphone 16 captures ambient sounds, particularly human voice.

  Upper arms 58R and 58L are attached to both shoulders of the upper body 46 by shoulder joints 56R and 56L, respectively. The shoulder joints 56R and 56L each have three degrees of freedom. That is, the right shoulder joint 56R can control the angle of the upper arm 58R around each of the X, Y, and Z axes. The Y axis is an axis parallel to the longitudinal direction (or axis) of the upper arm 58R, and the X axis and the Z axis are axes orthogonal to the Y axis from different directions. The left shoulder joint 56L can control the angle of the upper arm 58L around each of the A, B, and C axes. The B axis is an axis parallel to the longitudinal direction (or axis) of the upper arm 58L, and the A axis and the C axis are axes orthogonal to the B axis from different directions.

  Forearms 62R and 62L are attached to the respective distal ends of upper arms 58R and 58L via elbow joints 60R and 60L. The elbow joints 60R and 60L can control the angles of the forearms 62R and 62L around the W axis and the D axis, respectively.

  In the X, Y, Z, W axes and the A, B, C, D axes that control the displacement of the upper arms 58R and 58L and the forearms 62R and 62L (FIG. 2), “0 degree” is the home position. In this home position, the upper arms 58R and 58L and the forearms 62R and 62L are directed downward.

  Although not shown in FIG. 2, a touch sensor (FIG. 3) is provided on the shoulder portion including the shoulder joints 56R and 56L of the upper body 46 and the arm portion including the upper arms 58R and 58L and the forearms 62R and 62L. The touch sensor 64 detects whether or not a person has touched these parts of the robot 12.

  Spheres 66R and 66L corresponding to hands are fixedly attached to the tips of the forearms 62R and 62L, respectively. In place of the spheres 66R and 66L, a “hand” in the shape of a human hand can be used when a finger function is required unlike the robot 12 of this embodiment.

  A head 70 is attached to an upper center of the upper body 46 via a neck joint 68. The neck joint 68 has three degrees of freedom and can be controlled in angle around each of the S, T, and U axes. The S-axis is an axis that goes directly from the neck, and the T-axis and the U-axis are axes that are orthogonal to the S-axis in different directions. The head 70 is provided with a speaker 72 at a position corresponding to a human mouth. The speaker 72 is used for the robot 12 to communicate with a person around it by voice or voice. However, the speaker 72 may be provided in another part of the robot 12, for example, the trunk.

  The head 70 is provided with eyeball portions 74R and 74L at positions corresponding to the eyes. Eyeball portions 74R and 74L include eye cameras 54R and 54L, respectively. The right eyeball portion 74R and the left eyeball portion 74L may be collectively referred to as an eyeball portion 74, and the right eye camera 54R and the left eye camera 54L may be collectively referred to as an eye camera 54. The eye camera 54 captures the video signal by photographing the face of the person approaching the robot 12 and other parts or objects.

  Note that each of the omnidirectional camera 52 and the eye camera 54 described above may be a camera using a solid-state imaging device such as a CCD or a CMOS.

  For example, the eye camera 54 is fixed in the eyeball part 74, and the eyeball part 74 is attached to a predetermined position in the head 70 via an eyeball support part (not shown). The eyeball support unit has two degrees of freedom and can be controlled in angle around each of the α axis and the β axis. The α axis and the β axis are axes set with respect to the head 70, the α axis is an axis in a direction toward the top of the head 70, the β axis is orthogonal to the α axis and the front side of the head 70 It is an axis in a direction orthogonal to the direction in which (face) faces. In this embodiment, when the head 70 is at the home position, the α axis is set to be parallel to the S axis and the β axis is set to be parallel to the U axis. In such a head 70, when the eyeball support portion is rotated around each of the α axis and the β axis, the tip (front) side of the eyeball portion 74 or the eye camera 54 is displaced, and the camera axis, that is, the line-of-sight direction is changed. Moved.

  In the α axis and β axis that control the displacement of the eye camera 54, “0 degree” is the home position. At this home position, the camera axis of the eye camera 54 is the head 70 as shown in FIG. The direction of the front side (face) is directed, and the line of sight is in the normal viewing state.

  FIG. 3 is a block diagram showing the internal configuration of the robot 12. As shown in FIG. 3, the robot 12 includes a microcomputer or a CPU 76 for overall control. The CPU 76 is connected to a memory 80, a motor control board 82, a sensor input / output board 84, and a voice through a bus 78. An input / output board 86 is connected.

  Although not shown, the memory 80 includes a ROM, an HDD, a RAM, and the like, and the control program and data for the robot 12 are stored in the ROM or the HDD in advance. The CPU 76 executes processing according to this program. Specifically, a plurality of programs (referred to as action modules) for controlling the body movement of the robot 12 are stored. For example, the body motions indicated by the behavior module include “handshake”, “cuckling”, “many years”, and so on. When the body motion indicated by the behavior module is “handshake”, when the behavior module is executed, the robot 12 presents the right hand forward, for example. Further, when the body motion indicated by the behavior module is “cuddle”, when the behavior module is executed, the robot 12 presents both hands forward, for example. Further, when the body motion indicated by the behavior module is “many years”, when the behavior module is executed, the robot 12 raises and lowers both hands several times (for example, twice), for example. The RAM can be used as a working memory as well as a temporary storage memory.

  The motor control board 82 is composed of, for example, a DSP (Digital Signal Processor) and controls a motor for driving body parts such as the right arm, the left arm, the head, and the eyes. That is, the motor control board 82 receives control data from the CPU 76, and controls the angles of the three motors for controlling the X, Y, and Z axes of the right shoulder joint 56R and the axis W of the right elbow joint 60R. The rotation angle of a total of four motors including one motor (collectively shown as “right arm motor” in FIG. 3) 88 is adjusted. The motor control board 82 includes a total of four motors including three motors that control the angles of the A, B, and C axes of the left shoulder joint 56L and one motor that controls the angle of the D axis of the left elbow joint 60L. The rotation angle of the motor (collectively shown as “left arm motor” in FIG. 3) 90 is adjusted. The motor control board 82 also adjusts the rotation angle of three motors 92 (collectively shown as “head motors” in FIG. 3) that control the angles of the S, T, and U axes of the neck joint 68. To do. The motor control board 82 also controls the waist motor 50 and the two motors 36 that drive the wheels 34 (collectively shown as “wheel motors” in FIG. 3). Further, the motor control board 82 adjusts the rotation angle of two motors 94 (collectively shown as “right eyeball motor” in FIG. 3) that control the angles of the α axis and β axis of the right eyeball portion 74R. In addition, the rotation angles of two motors 96 that collectively control the angles of the α axis and β axis of the left eyeball portion 74L (collectively shown as “left eyeball motor” in FIG. 3) 96 are adjusted.

  The above-described motors of this embodiment are stepping motors or pulse motors for simplifying the control except for the wheel motors 36, but may be direct-current motors as with the wheel motors 36.

  Similarly, the sensor input / output board 84 is also constituted by a DSP, and takes in signals from each sensor and camera and gives them to the CPU 76. That is, data relating to the reflection time from each of the ultrasonic distance sensors 42 is input to the CPU 76 through the sensor input / output board 84. The video signal from the omnidirectional camera 52 is input to the CPU 76 after being subjected to predetermined processing by the sensor input / output board 84 as necessary. Similarly, the video signal from the eye camera 54 is also supplied to the CPU 76. Further, a signal from the touch sensor 64 is given to the CPU 76 via the sensor input / output board 84.

  Synthetic voice data is given to the speaker 72 from the CPU 76 via the voice input / output board 86, and accordingly, voice or voice according to the data is outputted from the speaker 72. Further, the voice input from the microphone 24 is taken into the CPU 76 via the voice input / output board 86.

  Further, a communication LAN board 98 is connected to the CPU 76 through the bus 78. Similarly, the communication LAN board 98 is also configured by a DSP, and sends the transmission data given from the CPU 76 to the wireless communication apparatus 100 and causes the wireless communication apparatus 100 to transmit the transmission data. The communication LAN board 98 receives data via the wireless communication device 100 and provides the received data to the CPU 76.

  For example, the robot 12 provides a service such as explaining an exhibit at a certain venue or providing route guidance for a certain venue. FIG. 4 shows a state in which the robot 12 explains a certain exhibit OB to a plurality of people (here, three people A, B, and C).

  In the robot 12 that provides such a service, attention is individually controlled (hereinafter referred to as “individual attention control”) for a small number of persons (for example, about 1 to 2 persons), and a large number of persons ( For example, for three or more people, a large number of people are considered as one group, and the attention of the group is controlled (hereinafter referred to as “group attention control”), and attention is paid to the exhibit OB and the robot 12. Let Thus, since attention control according to the number of people is executed, natural attention control is possible. This is because, for example, when only personal attention control is performed, attention is individually controlled even for 30 persons, and it takes a lot of time for attention control. Also, for example, when only group attention control is performed, even if there is only one person, the attention is controlled as one group, which may give a sense of incongruity to the person whose attention is controlled, It is also because there is a risk of not being able to feel.

  The attention control of the robot 12 will be described with reference to FIGS. However, in FIGS. 5 to 7, the robot 12 (R) and the human (H) are schematically shown as isosceles triangles, and the direction from the bottom to the vertex vertically is the front direction of the robot 12 and the human (line-of-sight direction). ). The vertex of the isosceles triangle is the position of the viewpoint (eye), and the center (center of gravity) of the isosceles triangle is the position of the robot 12 or human.

First, the robot 12 determines whether or not a human is present within a radius Rm (for example, 6 m) around itself. Specifically, when the two-dimensional coordinates of the robot 12 transmitted from the computer 14 are (x _R , y _R ) and the two-dimensional coordinates of the human being transmitted from the computer 14 are (x _H , y _H ), It is determined whether or not there is a person within the radius Rm according to Equation 1. However, since the robot 12 itself moves according to the map data, the two-dimensional coordinates updated (managed) by itself may be used as the two-dimensional coordinates of the robot 12.

[Equation 1]
^{_{(X R -x H) 2 +}} (y R -y H) 2 ≦ R 2
Here, when a human is present within the radius Rm, the robot 12 selectively executes individual attention control or group attention control according to the number of persons. In this embodiment, as described above, personal attention control is executed if there are fewer than three persons (1 to 2 persons), and group attention control is executed if there are three or more persons. However, the number of persons (threshold value) for selecting the personal attention control and the group attention control should not be limited to three people, and if it is two or more, it is arbitrary according to the service provided using the robot 12 Can be set to If no human is present, it is determined again whether or not a human is present within the radius Rm after a predetermined time (for example, 2 to 3 minutes) has elapsed.

  As shown in FIG. 5A, when there are three persons around the robot 12 and within the radius Rm, the group attention control is executed. When the group attention control is started, first, it is determined whether or not all the persons to be controlled for attention (control target) exist in front of themselves. In this embodiment, the robot 12 has a human face within a first predetermined angle Degf (for example, 60 degrees) in the right direction and the left direction with reference to a state in which the robot 12 is facing the front (0 degrees). It is determined that the person is in front of him.

  Specifically, it is determined whether or not the angle θF formed between the straight line calculated according to Equation 2 and a straight line based on the front direction of the robot 12 is 60 degrees or less. That is, it is determined whether or not Expression 3 is satisfied. However, in this embodiment, with reference to the front direction of the robot 12, the signs of the first predetermined angle DegF and the angle θF are positive for the right front and negative for the left front.

[Equation 2]
_{Y = (x R -x H)} / (y R -y H) × X
[Equation 3]
θF ≦ DegF
Here, when any one of the control objects does not exist within the first predetermined angle DegF, a communication action for moving all the persons to be controlled within the first predetermined angle DegF in front of itself is performed. Execute.

  For example, look at the person at the left end of the front, spread your hands, say "Everyone gather in front of me", look at the person at the right end of the front, and then turn to the front. Specifically, the CPU 76 controls the head motor 92 to rotate the neck joint 68 about the S axis by an angle θLeftMax. Hereinafter, when the direction of the robot 12 is changed, that is, when the neck is moved, the same processing is executed. As a result, the robot 12 looks at the person existing at the front left end. Here, as shown in FIG. 5A, the angle θLeftMax is a straight line connecting the position coordinates of the robot 12 and the position coordinates of the human being existing at the left end in front of the robot 12 with the front direction of the robot 12 as a reference. It is an angle to make. However, the person existing at the front left end is a person existing within the radius Rm. Next, the CPU 76 drives and controls the right arm motor 88 and the left arm motor 90 to rotate the shoulder joint 56R and the shoulder joint 56L. At the same time or substantially the same time, the CPU 76 reproduces the synthesized voice corresponding to “Everyone gather in front of me” and outputs it from the speaker 72. Thereafter, the robot 12 speaks in the same manner. As a result, the robot 12 spreads its hands and speaks, “Everyone gather in front of me.” Then, the CPU 76 sets the neck angle to θRightMax and sets the neck angle to 0 degrees. Thereby, the robot 12 turns to the front after seeing the person who exists in the front right end. Here, as shown in FIG. 5A, the angle θRightMax is a straight line connecting the position coordinates of the robot 12 and the position coordinates of the human being present at the right end in front of the robot 12 with the front direction of the robot 12 as a reference. It is an angle to make. However, the person existing at the front right end is a person existing within the radius Rm.

  Note that the above-described communication behavior for moving all persons to be controlled to move forward is merely an example, and should not be limited to this. As another example, you may make it look over the left end from the right end, and you may make it say "Everyone gather here."

  When all the persons to be controlled exist (move) within the first predetermined angle DegF in front of the robot 12, the robot 12 determines whether all the persons to be controlled are looking at themselves. In this embodiment, as shown in FIG. 6 (A), the angle θL formed by the human eye direction and the direction of the straight line connecting the position of the human eye and the position of the robot is a second predetermined angle (this embodiment). Then, if it is ± 10 degrees or less, it is determined that the person is looking at himself (robot 12). However, if the angle θL is equal to or greater than the second predetermined angle, it is determined that the person is not looking at himself / herself.

  Here, if any one of them determines that he / she is not looking at himself / herself (robot 12), a communication action is executed that causes all persons to be controlled to pay attention to himself / herself. For example, the robot 12 looks at the person at the left end in front, spreads his hands, speaks, “Look at me, everyone,” sees the person at the right end in front, and then turns to the front.

  Note that the above-described communication behavior that causes all persons to be controlled to pay attention to themselves is merely an example, and should not be limited to this. As another example, the left end may be looked at from the right end, or “everyone look at this” may be spoken.

  When all the persons to be controlled pay attention to the robot 12, the robot 12 determines whether all the persons are present at an appropriate distance. This is because when the robot 12 explains (provides) a service to a plurality of humans, if the human is too far away from the robot 12, it is difficult to hear the voice of the robot 12. This is because there is a risk that inconveniences such as the hand of the robot 12 hitting a human being will occur if the distance is too close.

  Therefore, the robot 12 is within a range in which the distance d to each person is determined by the minimum distance DistMin (for example, 0.5 m) and the maximum distance DistMax (for example, 3 m) as shown in FIG. Judgment is made whether there is. Specifically, the distance d between the robot 12 and each person is calculated according to Equation 4, and it is determined whether each calculated distance d satisfies Equation 5.

[Equation 4]
d = √ {(x _R −x _H ) ² + (y _R −y _H ) ² }
[Equation 5]
DistMin ≦ d ≦ DistMax
For example, if any one of them does not satisfy the condition indicated by the middle side and the right side of Formula 5, the robot 12 performs a communication action that brings all the persons to be controlled closer to itself. Specifically, the robot 12 looks at the person at the left end in front, spreads both hands, speaks, “Everyone should be a little closer,” sees the person at the right end in front, and then turns to the front.

  Note that the above-described communication behavior that brings all persons to be controlled closer to themselves is merely an example, and should not be limited to this. As another example, the left end may be looked over from the right end, and “the person behind should be put forward” may be spoken.

  On the other hand, if any one of them does not satisfy the condition indicated by the left side and the middle side of Formula 5, the robot 12 executes a communication action that causes all the persons to be controlled to be separated from themselves. Specifically, the robot 12 sees the person at the left end in the front, spreads both hands, speaks “Everyone is a little further away”, looks at the person at the right end in the front, and then turns to the front.

  Note that the above-described communication behavior that causes all persons to be controlled to move away from themselves is merely an example, and should not be limited to this. As another example, the left end may be looked over from the right end, and “the previous person should lower a little” may be spoken.

  Note that, as described above, in group attention control, it is assumed that all humans to be controlled move in front of themselves, pay attention to themselves, or move within a certain distance from themselves. explained. However, there are naturally cases where all the persons to be controlled do not follow the guidance of the robot 12. In such a case, it may not be appropriate to repeat the same communication action many times. Therefore, in this embodiment, when the same communication action is executed a predetermined number of times, not all humans to be controlled are present in front of the robot 12, attention is not paid to the robot 12, or the distance to the robot 12 is constant. Even if it is not within the range, the communication action is not executed. For example, there are 10 humans to be controlled, and 8 of them have moved in front of themselves, but even if a communication action for moving forward is performed a predetermined number of times (for example, 3 times), the other two people When the robot 12 does not move in front of the robot 12, the communication action for moving the robot 12 forward is not executed, and it is determined whether or not all the persons to be controlled are paying attention to themselves. The same applies to other communication actions in means attention control. In such a case, a person who has moved according to the guidance (communication behavior) of the robot 12 may be a person to be controlled thereafter.

  Moreover, the robot 12 performs personal attention control when one or two persons exist within the radius Rm. Since the personal attention control is almost the same as the group attention control, it will be briefly described below. However, even if there are a plurality of attention control targets (here, two people), the attention control is executed individually. to differ greatly. In this individual attention control, since the attention control is executed individually, the robot 12 performs communication behavior by looking at the person currently performing the attention control. Specifically, as shown in FIG. 7, the robot 12 calculates an angle θHDeg formed by a straight line connecting its own position and the position of the person to be controlled with the front direction as a reference, and the neck is tilted by this angle θHDeg. It moves and looks at the person.

  For example, when the person to be controlled does not exist within the first predetermined angle DegF in front of himself / herself, a communication action for moving the person within the first predetermined angle DegF in front of himself / herself is executed. For example, the angle of the neck is set to θHDeg, and the hand is directed to the angle θHDeg and “Hey, come in front of me” is spoken. That is, the CPU 76 drives and controls the head motor 92 to rotate the neck joint 68 about the S axis by an angle θHDeg. Next, the CPU 76 drives and controls the right arm motor 88 or the left arm motor 90 to rotate the shoulder joint 56R or the shoulder joint 56L. At the same time or substantially the same time, the CPU 76 reproduces the synthesized voice corresponding to “Hey, come to me” and outputs it from the speaker 72. The same applies hereinafter.

  In this way, a communication action is performed in which the robot 12 turns to the person, makes a voice while pointing, and moves the person in front of himself / herself. However, this is merely an example and should not be limited. As another example, the user may be invited after pointing his hand toward θHDeg. Also, you may be allowed to speak with a name such as “Mr. OO, come in front of me”. In such a case, for example, it is necessary to make each person wear (carry) a wireless tag (frequency tag, IC tag, etc.) and read information on the wireless tag on the robot 12 side so that an individual can be identified. There is. The same applies hereinafter.

  In addition, when the person to be controlled exists (moves) within the first predetermined angle DegF ahead of himself / herself but does not look at himself / herself (not paying attention to himself / herself), the robot 12 Execute communication behaviors that make you pay attention to yourself. For example, the angle of the neck is set to θHDeg, and the hand is turned to the angle θHDeg, and “Hey, look at me” is spoken. That is, the robot 12 looks at the person to be controlled, utters a voice while pointing at the person, and prompts the user to pay attention.

  Note that the above-described communication behavior that causes the control target person to pay attention to himself / herself is merely an example, and should not be limited to this. As another example, after pointing the hand to the angle θHDeg, the user may be allowed to point at his / her face or speak using the name “Look at me,” .

  Then, when the person to be controlled is within the first predetermined angle DegF in front of himself / herself, paying attention to himself / herself, the robot 12 calculates the distance d to the person. If the calculated distance d does not satisfy Equation 5, a communication action for moving to an appropriate distance for explaining the service is executed. Specifically, when the distance d between the robot 12 and the human does not satisfy the condition indicated by the middle side and the right side of Formula 5, the robot 12 sets the neck angle to θHDeg and sets the hand to θHDeg. He says, “Hey, get a little closer”. In other words, the person is urged to look at the person to be controlled, scream while pointing, and approach the person. However, this is merely an example and should not be limited. As another example, a hand may be invited after turning to the angle θHDegn, or “Mr. OO, approach a little more” may be used to speak.

  On the other hand, when the distance d between the robot 12 and the human does not satisfy the condition indicated by the left side and the middle side of Equation 5, the robot 12 sets the neck angle to θHDeg and points the hand to θHDeg, “Hey, get a little further away.” In other words, the person who is to be controlled is urged to make a voice while pointing and pointing away from him. However, this is merely an example and should not be limited. As another example, after the hand is turned to the angle θHDeg, the hand may be raised a little, or “Mr. OO, a little further away” may be used to speak.

  Even in the case of personal attention control, the person to be controlled always moves in front of the robot 12 according to the guidance of the robot 12, pays attention to the robot 12, and moves so that the distance from the robot 12 is within a certain range. I explained in the premise. However, as described above, as in the case of group attention control, when the same communication action is executed a predetermined number of times, even if the control target person does not follow the guidance of the robot 12, the communication action Execution is terminated.

  As described above, different attention control processes are executed in accordance with the number of persons who are objects of attention control. When the attention is controlled, a description of the service provided by the system 10 (robot 12) is executed. For example, there are various explanations of services such as explanation of a certain exhibit or explanation of a certain play equipment. In addition, the communication behavior regarding the description of the service may be different depending on the number of people to be explained, may be the same, or may be changed depending on the content of the service.

  FIG. 8 is a flowchart showing the overall processing of the CPU 76 shown in FIG. Referring to FIG. 8, when starting the entire process, CPU 76 determines whether or not there is a stop command from the operator in step S1. For example, the stop command can be input remotely using the computer 14, and can also be input by providing a run / stop button on the robot 12 and operating it. If “YES” in the step S1, that is, if there is a stop command by the operator, the entire process is ended as it is. On the other hand, if “NO” in the step S1, that is, if there is no stop command by the operator, it is determined whether or not there is a human in the surrounding in a step S3. Specifically, it is determined whether or not a person is present around the computer 14 based on whether coordinate data other than the coordinate data for the robot 12 has been input.

  If “YES” in the step S3, that is, if there is a human in the surroundings, a caution control and service providing process (see FIG. 9) described later is executed in a step S5, and the process returns to the step S1. On the other hand, if “NO” in the step S3, that is, if there is no human being around, a waiting action is executed in a step S7, and the process returns to the step S1. For example, in step S7, the CPU 76 controls the head motor 92 to rotate the neck joint 68 around the S axis. As a result, the robot 12 can be operated so as to look around by swinging its neck left and right.

  FIG. 9 is a flowchart showing the attention control and service provision processing in step S5 shown in FIG. As shown in FIG. 9, when the CPU 76 starts the attention control and service providing process, the CPU 76 detects the number of humans present in the surrounding area in step S <b> 11. Here, the number of coordinate signals input from the computer 14 is counted, and the number obtained by subtracting 1 from the count value is determined (detected) as the number of humans. That is, the number of robots 12 is eliminated. In the subsequent step S13, it is determined whether or not there are N (for example, three) or more people within the radius Rm (for example, 6 m) of the robot 12. Here, the robot 12 uses the position coordinates indicated by its own coordinate signal and the human coordinate signal to determine whether the distance between itself and the human satisfies Equation 1, and there are three humans who satisfy Equation 1. It is judged whether or not it exists.

  If “YES” in the step S13, that is, if there are three or more persons within a radius of 6 m, a group attention control process (see FIG. 10 and FIG. 11) described later is executed in a step S15. In S17, the communication action for explaining the service is executed, and the attention control and the service providing process are returned.

  On the other hand, if “NO” in the step S13, that is, if one or two persons exist within a radius of 6 m, a personal attention control process (see FIGS. 12 and 13) described later is executed in a step S19. In step S21, it is determined whether or not attention is controlled for all the control target persons existing around. If “NO” in the step S21, that is, if the cautions about all the persons to be controlled existing in the vicinity are not controlled, the attention of the next person (the person who has not yet controlled the caution) should be controlled. Return to step S19. Although detailed description is omitted, for example, the robot 12 executes the personal attention control process in the order from the closest to the human. On the other hand, if “YES” is determined in the step S21, that is, if attention is controlled for all the persons to be controlled present in the surrounding area, the communication action for explaining the service is executed in the step S23, and the attention control and service are performed. Returns the provision process.

  10 to 13 are flowcharts showing the group attention control process in step S15 shown in FIG. Referring to FIG. 10, when starting the group attention control process, CPU 76 initializes variables a, b, c, d (a, b, c, d = 0) in step S31. That is, the number of executions of a communication action a that collects all persons to be controlled in the forward direction a, the number of executions of communication action b that causes all persons to be controlled to pay attention to itself, and the distance d between all persons to be controlled are less than DistMax. The number of executions c of the communication action to be performed and the number of executions d of the communication action to set the distance d to all humans to be controlled to be DistMin or less are set to “0”.

  In a succeeding step S33, it is determined whether or not all persons to be controlled exist within the first predetermined angle DegF ahead. That is, it is determined whether or not the angle θF calculated according to Equation 2 satisfies Equation 3 for all humans to be controlled. However, “all human beings to be controlled” mentioned here means humans whose distance from the robot 12 is determined to be within Rm. The same applies to the group attention control process. However, as described above, the robot 12 performs a communication action to guide a person to be controlled, but a person who does not respond may be excluded from the control target.

  If “YES” in the step S33, that is, if all the persons to be controlled exist within the first predetermined angle DegF ahead, the process proceeds to a step S47 shown in FIG. 11 as it is. However, if “NO” in the step S33, that is, if any one person is not present within the first predetermined angle DegF in the front, the communication action of collecting (moving) all the persons to be controlled in the front is performed. Execute. Specifically, in step S35, the neck angle is set to θLeftMax. Next, in step S37, open both hands and say "Everyone gather in front of me". Subsequently, in step S39, the neck angle is set to θRightMax, and then in step S41, the neck angle is set to 0 degrees. In this way, by the processing of step S35 to step S41, looking over all the human beings to gather in front of themselves, overlooking the human being present at the right end from the human being present at the leftmost front, After that, a communication action such as facing forward is performed.

  In step S43, the execution number a of the communication action for moving all persons to be controlled forward is incremented (a = a + 1). In step S45, the execution number a is equal to or greater than the predetermined number M1 (for example, 3). It is determined whether or not. That is, it is determined whether or not the robot 12 has executed communication behavior for moving all control target persons forward (three times or more). If “NO” in the step S45, that is, if the execution count a is 2 or less, the process returns to the step S33 as it is. On the other hand, if “YES” in the step S45, that is, if the number of executions a is 3 or more, the step S47 is performed regardless of whether or not all the persons to be controlled exist within the first predetermined angle DegF ahead. Proceed to

  In step S47 shown in FIG. 11, it is determined whether all the persons to be controlled are looking at themselves. That is, it is determined whether or not the absolute value of the calculated angle θL is equal to or smaller than the second predetermined angle DegL (10 degrees) for all humans to be controlled. If “YES” in the step S47, that is, if all humans are looking at themselves (watching themselves), the process proceeds to a step S61 shown in FIG. 12 as it is. However, if “NO” in step S47, that is, if any one person is not looking at himself (not paying attention to himself), a communication action is executed that causes all persons to be controlled to pay attention to himself / herself. To do.

  Specifically, in step S49, the neck angle is set to θLeftMax, and in step S51, both hands are spread out and “everyone look at me” is spoken. In step S53, the neck angle is set to θRightMax. In step S55, the neck angle is set to 0 degree. In other words, the process from step S49 to step S55 overlooks the person at the right end from the person at the left end in front of the person while spreading his hands and calling out to all the persons to be controlled looking at himself. Then, the communication action of facing forward is executed.

  Then, in step S57, the execution number b of the communication action that causes all persons to be controlled to pay attention to itself is incremented (b = b + 1). In a succeeding step S59, it is determined whether or not the number of executions b is a predetermined number M2 (for example, 3) or more. That is, it is determined whether or not the robot 12 has executed a communication action that causes all persons to be controlled to pay attention to itself three times (or more). If “NO” in the step S59, that is, if the execution count b is 2 or less, the process returns to the step S47 as it is. On the other hand, if “YES” in the step S59, that is, if the execution count b is 3 or more, the process proceeds to a step S61 regardless of whether or not all the persons to be controlled pay attention to themselves.

  As shown in FIG. 12, in step S <b> 61, it is determined whether or not the distance d to all the persons to be controlled is DistMax (for example, 3 m) or less. That is, it is determined whether or not the distance d calculated using Equation 4 satisfies the inequalities (conditions) indicated by the middle side and the right side of Equation 5 for all humans to be controlled. If “YES” in the step S61, that is, if the distances to all the persons to be controlled are 3 m or less, the process directly proceeds to a step S75 shown in FIG. On the other hand, if “NO” in the step S61, that is, if any one of the distances d to the robot 12 exceeds 3 m, the communication action to make the distances d to all the persons to be controlled 3 m or less. Execute.

  Specifically, in step S63, the neck angle is set to θLeftMax, and in step S65, both hands are spread out, saying “Everyone should be a little closer”, and in step S67, the neck angle is set to θRightMax. In step S69, the neck angle is set to 0 degree. That is, by the processing of step S63 to step S69, looking out to the human being at the left end from the human being at the left end in front, looking over all the human beings with their hands wide open and approaching themselves, Communication behavior such as facing is executed.

  Then, in step S71, the number of executions c of the communication action for setting the distance d to all control target humans to 3 m or less is incremented (c = c + 1). In the next step S73, it is determined whether or not the number of executions c is a predetermined number M3 (for example, 3) or more. That is, it is determined whether or not the robot 12 has executed (or more) three times (or more) a communication action that sets the distance d to all the control target humans to 3 m or less. If “NO” in the step S73, that is, if the execution count c is 2 or less, the process returns to the step S61. On the other hand, if “YES” in the step S73, that is, if the execution count c is 3 or more, the process proceeds to a step S75 regardless of whether or not the distance d to all the persons to be controlled is 3 m or less.

  In step S75 shown in FIG. 13, it is determined whether or not the distance d to all the control target humans is DistMin (for example, 0.5 m) or more. That is, it is determined whether or not the distance d calculated according to Equation 4 satisfies the inequalities (conditions) indicated by the left side and the middle side of Equation 5 for all humans to be controlled. If “YES” in the step S61, that is, if the distance d to all the persons to be controlled is 0.5 m or more, all the persons to be controlled exist in front of themselves, pay attention to themselves, and are constant. The group attention control process is determined to be determined to exist within the range.

  However, if “NO” in the step S75, that is, if the distance d to any human being is less than 0.5 m, the communication action for setting the distance d to all human beings to be controlled to 0.5 m or more is performed. Execute. Specifically, in step S77, the neck angle is set to θLeftMax, in step S79, both hands are spread out and "everyone is a little further away", and in step S81, the neck angle is set to θRightMax. In step S83, the neck angle is set to 0 degree. That is, by the processing of step S77 to step S83, looking out to the human being at the left end from the human being at the left end in the front, spreading all hands and calling out to all human beings away from themselves, Communication behavior such as facing is executed.

  Then, in step S85, it is determined whether or not the number of executions d of the communication action that sets the distance d to all control target humans to 0.5 m or more is a predetermined number M4 (for example, 3) or more. In other words, it is determined whether or not the robot 12 has executed the communication action for making the distance d with all the control target humans d 0.5 m or more three times (or more). If “NO” in the step S87, that is, if the execution count d is 2 or less, the process returns to the step S75. On the other hand, if “YES” in the step S87, that is, if the number of executions d is 3 or more, the group attention control is performed regardless of whether or not the distance d to all human beings to be controlled is 0.5 m or more. Return processing.

  14 to 16 are flowcharts showing the personal attention control process in step S19 shown in FIG. However, in the personal attention control process, a process similar to the process included in the group attention control process will be briefly described. Referring to FIG. 14, when starting the personal attention control process, CPU 76 initializes variables e, f, g, h (e, f, g, h = 0) in step S101. That is, the execution number e of the communication action that moves the person in front of the person, the execution number f of the communication action that directs the person's attention to the person, the execution number g of the communication action that brings the person closer to the person, and the self The execution number h of the communication action for keeping the person a little away from is set to “0”.

  In the subsequent step S103, it is determined whether or not there is a person to be controlled (hereinafter referred to as “the person”) within the first predetermined angle DegF ahead. If “YES” in the step S103, that is, if the person exists within the first predetermined angle DegF ahead, the process proceeds to a step S113 shown in FIG. 15 as it is.

  However, if “NO” in the step S103, that is, if the person is not present within the first predetermined angle DegF ahead, the neck angle is set to θHDeg in a step S105, and the hand is moved in a step S107. Say “Hey, come in front of me” toward the angle θHDeg. In this way, a communication action is performed in which the robot 12 turns to the person, makes a voice while pointing, and moves the person in front of himself / herself.

  In step S109, the execution number e of the communication action for moving the person in front of itself is incremented (e = e + 1). In a succeeding step S111, it is determined whether or not the number of executions e is a predetermined number N1 (for example, 3) or more. That is, it is determined whether or not the robot 12 has executed the communication action for moving the person in front of itself three times (or more). If “NO” in the step S111, that is, if the execution count e is 2 or less, the process returns to the step S103. On the other hand, if “YES” in the step S111, that is, if the execution count e is 3 or more, the process proceeds to the step S113 regardless of whether or not the person exists in front of the user.

  As shown in FIG. 15, in step S113, it is determined whether or not the person is looking at the person. If “YES” in the step S113, that is, if the person is looking at himself (ie paying attention to himself), the process proceeds to a step S123 as it is. On the other hand, if “NO” in the step S113, that is, if the person is not looking at the person (not paying attention to the person), a communication action for directing the person's attention to the person is executed. Specifically, in step S115, the neck angle is set to θHDeg, and in step S117, the hand is directed to the angle θHDeg and “Hey, look at me” is spoken. In this way, the communication action is performed in which the robot 12 turns to the person, calls out while pointing, and causes the person to pay attention to the person.

  Then, in step S119, the number of executions f of the communication action for directing the person's attention to himself is incremented (f = f + 1). In a succeeding step S121, it is determined whether or not the number of executions f is a predetermined number N2 (for example, 3) or more. In other words, it is determined whether or not the robot 12 has executed the communication action for directing the attention of the person to itself three times (or more). If “NO” in the step S121, that is, if the execution frequency f is 2 or less, the process returns to the step S113 as it is. On the other hand, if “YES” in the step S121, that is, if the execution frequency f is 3 or more, the process proceeds to a step S123 regardless of whether or not the person is paying attention to himself / herself.

  In step S123, it is determined whether the distance d to the person is equal to or less than DistMax (for example, 3 m). If “YES” in the step S123, that is, if the distance d to the person is 3 m or less, the process proceeds to a step S133 shown in FIG. 16 as it is. However, if “NO” in the step S123, that is, if the distance d with the person exceeds 3 m, a communication action is performed to bring the person closer to the person. Specifically, in step S125, the neck angle is set to θHDeg, and in step S127, the hand is directed to θHDeg and “Hey, a little closer” is spoken. In this way, the communication action is performed in which the robot 12 turns to the person and makes a voice while pointing at the person to approach the person.

  In step S129, the number of executions g of the communication action that brings the person closer to itself is incremented (g = g + 1). In subsequent step S131, it is determined whether or not the number of executions g is a predetermined number N3 (for example, 3) or more. That is, it is determined whether or not the robot 12 has executed the communication action that brings the person closer to itself three times (or more). If “NO” in the step S131, that is, if the execution count g is 2 or less, the process returns to the step S123. On the other hand, if “YES” in the step S131, that is, if the execution count g is 3 or more, the process proceeds to a step S133 even if the distance d to the person exceeds 3 m.

  As shown in FIG. 16, in step S133, it is determined whether or not the distance d to the person is DistMin (for example, 0.5 m) or more. If “YES” in the step S133, that is, if the distance d to the person is 0.5 m or more, it is determined that the person exists in front of him, pays attention to himself and is within a certain range. Return the personal attention control process.

  On the other hand, if “NO” in the step S133, that is, if the distance d to the person is less than 0.5 m, a communication action for moving the person a little away from the person is executed. Specifically, in step S135, the neck angle is set to θHDeg, and in step S137, the hand is directed to the angle θHDeg and “Hey, say a little further away”. In this way, the communication action is performed so that the robot 12 turns to the person, makes a voice while pointing, and moves away from the robot 12.

  In step S139, the communication action execution count h for keeping the person a little away from him is incremented (h = h + 1). In subsequent step S141, it is determined whether or not the number of executions h is a predetermined number N4 (for example, 3) or more. That is, it is determined whether or not the robot 12 has executed the communication action for moving the person a little away from himself / herself three times (or more). If “NO” in the step S141, that is, if the execution count h is 2 or less, the process returns to the step S133. On the other hand, if “YES” in the step S141, that is, if the execution count h is 3 or more, the personal attention control process is returned even if the distance d to the person is less than 0.5 m.

  According to this embodiment, since attention control is selectively executed according to the number of persons to be controlled, appropriate attention control is possible. Therefore, the robot can naturally dissolve into human society.

  In this embodiment, a floor sensor is provided to detect the presence and position of a person, a coordinate signal is obtained by a computer based on the output of the floor sensor, and the coordinate signal is given from the computer to the robot. However, if the robot is provided with an omnidirectional camera, it is possible to execute the caution control by the robot alone without using the floor sensor and the computer. In such a case, by analyzing the image of the omnidirectional camera, it is possible to determine the number of humans existing around the robot and whether or not it exists within a predetermined angle in front. Further, in such a case, the distance to the human being existing around can be detected based on the output of the ultrasonic distance sensor (42).

  In this embodiment, a floor sensor is provided to detect the presence and position of a person, but should not be limited to this. For example, instead of a floor sensor, a ceiling camera may be provided and an image of the ceiling camera may be analyzed. In such a case, it is possible to know the direction of the human (whether the robot is facing). Alternatively, a wireless tag may be attached to a human and a reader of the wireless tag may be equipped on the robot. In such a case, the computer included in the system can be omitted.

  Further, in this embodiment, it is determined whether or not a human is looking at the robot by analyzing the image of the eye camera. However, if an infrared LED that irradiates infrared rays in the direction of the human line of sight is attached to the human and the robot is equipped with an infrared camera, whether the human is looking at the robot depending on whether infrared light is detected. It can also be judged.

  Furthermore, in this embodiment, the angles and distances when a robot having a height of about 100 cm is used are exemplified. However, these numerical values can be changed as appropriate.

  Further, in this embodiment, in the attention control, in order to avoid an infinite loop, the same communication action is executed a predetermined number of times, even when the control target person does not follow the guidance of the robot 12. I tried to ignore it. However, if the service provided by the robot 12 is an important matter such as a confidential matter, and if the person to be controlled should follow the guidance (instructions or commands) of the robot 12, all humans As long as the guidance is not followed, the same communication behavior may be repeated. In such a case, in the group attention control process shown in FIGS. 10 to 13, steps S31, S43, S45, S57, S59, S71, S73, S83, and S85 are deleted, and the individuals shown in FIGS. In the attention control process, steps S109, S111, S119, S121, S129, S131, S139, and S141 may be deleted. However, only some communication actions may be repeatedly executed. For example, until the control target person pays attention to the robot 12, a communication action for causing the control target person to pay attention to the robot 12 is repeatedly executed, but other communication actions are executed a predetermined number of times. Is also possible.

  Further, in this embodiment, the predetermined number of times M1 to M4 and N1 to N2 are all the same number, but the group attention control and the personal attention control may be different times, and are appropriately determined according to the service to be provided. You may make it set, and also you may make it set to each different frequency | count.

FIG. 1 is a block diagram showing an example of the attention control system of the present invention. FIG. 2 is an illustrative view for explaining the appearance of the robot shown in FIG. 1 embodiment. FIG. 3 is an illustrative view showing an electrical configuration of the robot shown in FIGS. 1 and 2. FIG. 4 is an illustrative view showing an example of application of the system. FIG. 5 is an illustrative view for explaining a method in which the robot executes group attention control. FIG. 6 is an illustrative view for explaining a method in which the robot executes group attention control. FIG. 7 is an illustrative view for explaining a method in which the robot executes personal attention control. FIG. 8 is a flowchart showing the overall processing of the CPU shown in FIG. FIG. 9 is a flowchart showing the attention control and service provision processing of the CPU shown in FIG. FIG. 10 is a flowchart showing a part of the group attention control process of the CPU shown in FIG. FIG. 11 is another part of the group attention control process of the CPU shown in FIG. 3, and is a flowchart subsequent to FIG. FIG. 12 is another part of the group attention control process of the CPU shown in FIG. 3, and is a flowchart subsequent to FIG. FIG. 13 is still another part of the group attention control process of the CPU shown in FIG. 3, and is a flowchart subsequent to FIG. FIG. 14 is a flowchart showing a part of the personal attention control process of the CPU shown in FIG. 15 is another part of the personal attention control process of the CPU shown in FIG. 3, and is a flowchart subsequent to FIG. FIG. 16 is another part of the personal attention control process of the CPU shown in FIG. 3, and is a flowchart subsequent to FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Attention control system 12 ... Communication robot 14 ... Computer 16 ... Floor sensor 38 ... Collision sensor 42 ... Ultrasonic distance sensor 52 ... Omnidirectional camera 54 ... Eye camera 64 ... Touch sensor 76 ... CPU
DESCRIPTION OF SYMBOLS 80 ... Memory 82 ... Motor control board 84 ... Sensor input / output board 86 ... Voice input / output board 88-96 ... Motor 98 ... Communication LAN board 100 ... Wireless communication apparatus

Claims (12)

A communication robot that controls human attention by communicating with humans using at least one of body movement and voice,
Number detection means for detecting the number of human beings around,
A group attention control means for controlling the attention of more than a predetermined number of persons around, and an individual attention control means for individually controlling the attention of persons less than the number of persons around
Selectively executing group attention control means or individual attention control means based on the detection result of the number of persons detection means ,
The group attention control means includes
Group existence determination means for determining whether or not all human beings to be controlled exist within a first predetermined angle ahead;
When the group presence determination means determines that the person to be controlled exists outside the first predetermined angle ahead, the first communication moves all the persons to be controlled within the first predetermined angle. A first communication action execution means for executing an action;
When it is determined by the group presence determination means that all the persons to be controlled are present within the first predetermined angle in front, the human eye direction of the target to be controlled and the human being to be controlled in the horizontal plane Determining whether or not the angle formed by the straight line connecting the position of the eye and the position of the eye is equal to or smaller than a second predetermined angle, so that all the persons to be controlled have their own Group attention determination means for determining whether or not
When the group attention determination unit determines that there is a person to be controlled who is not looking at the second person, the second communication that executes the second communication action that causes all the persons to be controlled to pay attention to itself Communication robot including action execution means . When the first communication action is executed for the first predetermined number of times by the first communication action executing means, the group attention determining means is configured to determine that all human beings to be controlled are independent of the determination result of the group presence determining means. It determines whether looking towards its own claim 1, wherein the communication robot. The group attention control means, when the group attention determination means determines that all the persons to be controlled are looking at themselves, the distance from all the persons to be controlled is within a certain range. Group distance determining means for determining whether or not there is, and third communication action for executing a third communication action for moving all the control target persons within the predetermined range based on the determination result of the group distance determining means further comprising, according to claim 1 or 2 communication robot execution means. When the second communication action is executed a second predetermined number of times by the second communication action executing means, the group distance determining means is connected to all the control target human beings regardless of the determination result of the group attention determining means. The communication robot according to claim 3 , wherein it is determined whether or not the distance is within a certain range. The population Note control means, when the third communication behavior is performed a third predetermined number of times by the third communication action executing means ends the control of attention for all human the controlled object, according to claim 3 or 4. The communication robot according to 4 . Said personal care control means, the human said controlled object by personal presence determining means, and the personal presence determining means human control subjects to determine whether there within third predetermined angle of forward existing around And a fourth communication action executing means for executing a fourth communication action for moving the person to be controlled within the third predetermined angle when it is determined that it does not exist within the third predetermined angle ahead. Item 1. The communication robot according to item 1. The personal attention control means, when it is determined by the personal presence determination means that the person to be controlled is present within the third predetermined angle ahead, in the horizontal plane, the line-of-sight direction of the person to be controlled, Whether or not the person being controlled is looking at himself / herself by determining whether or not the angle formed by the straight line connecting the position of the person's eye and the position of the person being controlled is a fourth predetermined angle or less . And a fifth communication action that causes the person to be controlled to pay attention to himself / herself when the person to be controlled is judged not to look at the person by the person's attention determination means . The communication robot according to claim 6 , further comprising fifth communication action execution means for executing. When the fourth communication action is executed by the fourth communication action executing means for a fourth predetermined number of times, the individual attention determining means determines whether the person to be controlled is his / her own regardless of the determination result of the individual presence determining means. The communication robot according to claim 7 , wherein it is determined whether or not the person is looking. The personal attention control means determines whether the distance to the control target person is within a certain range when the personal attention determination means determines that the control target person is looking at the person. And a sixth communication action executing means for executing a sixth communication action for moving the person to be controlled within the predetermined range based on a determination result of the personal distance determination means. The communication robot according to claim 7 or 8 . When the fifth communication action is executed by the fifth communication action execution means for a fifth predetermined number of times, the personal distance determination means is a distance from the control target person regardless of the determination result of the individual attention determination means. The communication robot according to claim 9 , wherein it is determined whether or not is within a certain range. It said personal care control means, when said sixth communication behavior is performed sixth predetermined number of times by said sixth communication action executing means ends the control of attention for human the control target, communication according to claim 9, wherein robot. An attention control system that controls human attention using a communication robot that performs communication with humans using at least one of body movement and voice,
Comprising number-of-people detection means for detecting the number of humans present around the communication robot;
The communication robot is
A group attention control means for controlling the attention of more than a predetermined number of persons around, and an individual attention control means for individually controlling the attention of persons less than the number of persons around
Selectively executing group attention control means or individual attention control means based on the detection result of the number of persons detection means ,
The group attention control means includes
Group existence determination means for determining whether or not all human beings to be controlled exist within a first predetermined angle ahead;
When the group presence determination means determines that the person to be controlled exists outside the first predetermined angle ahead, the first communication moves all the persons to be controlled within the first predetermined angle. A first communication action execution means for executing an action;
When it is determined by the group presence determination means that all the persons to be controlled are present within the first predetermined angle in front, the human eye direction of the target to be controlled and the human being to be controlled in the horizontal plane Determining whether or not the angle formed by the straight line connecting the position of the eye and the position of the eye is equal to or smaller than a second predetermined angle, so that all the persons to be controlled have their own Group attention determination means for determining whether or not
When the group attention determination unit determines that there is a person to be controlled who is not looking at the second person, the second communication that executes the second communication action that causes all the persons to be controlled to pay attention to itself Attention control system including action execution means .

Images