JP2012161851A - Robot system and space formation recognizing device used in the same - Google Patents

Abstract

PROBLEM TO BE SOLVED: To make a robot naturally start a dialogue with a human body, and to progress smooth communication by making the robot perform a salutation speed after a space formation in which the robot and the human body are brought into dialogue participation states is generated.SOLUTION: This robot system 100 includes the robot 10 and a motion capture system 12. In the robot system 100, the space formation between the robot 10 and the human body is analyzed by using positions of the robot 10 and the human beings, the orientation of the body and a direction of a view, and the dialogue participation states of the robot 10 and the human body are recognized. Then, after the robot 10 and the human body are brought into the dialogue participation states by an effect that the robot 10 takes proper motion according to the recognized dialogue participation states, the robot 10 performs the salutation speech to the human body.

Description

  The present invention relates to a robot system and a space formation recognition apparatus used therefor, and more particularly to a robot system including a robot that performs communication with a person using at least speech and a space formation recognition apparatus used therefor.

  In recent years, robots (communication robots) that provide various services such as exhibition guidance and customer attraction using speech and body movements have been developed. Here, when a robot provides services such as exhibition guidance and customer attraction, how to cause interaction (communication) with a person is important. If the robot is a novelty, it may start interaction from a person, but considering that the novelty of the robot will fade in the near future, work from the robot side to start the interaction Because it is thought that it is necessary to do.

  In other words, in order to perform communication with people more smoothly and provide services more efficiently, the function that the robot speaks to people at the appropriate timing and position, that is, the function that starts conversation with the person naturally. It is thought that it is important to acquire.

  For example, Patent Document 1 discloses an example of a conventional conversation robot. The conversation robot of Patent Document 1 detects the front direction of a person's face or body, moves to the front direction of the detected person's face or body, and then talks to the person by looking at the person's eyes.

On the other hand, Non-Patent Document 1 discloses that a specific space formation called an F formation is maintained when people interact with each other. Non-Patent Document 2 discloses that the idea about the spatial formation of Non-Patent Document 1 is used for interaction between a human and a robot.
JP 2004-34274 A [G05D 1/2] Kendon, A., 1990, Spatial Organization in Social Encounters: the F-formation System, in Conducting Interaction: Patterns of Behavior in Focused Encounters, A. Kendon ed., Cambridge University Press, pp. 209-238. Kuzuoka, H., Suzuki, Y., Yamashita, J. and Yamazaki, K., 2010, Reconfiguring Spatial Formation Arrangement by Robot Body Orientation, ACM / IEEE Int. Conf. On Human-Robot Interaction (HRI2010), pp. 285 -292.

  In the technique of Patent Document 1, the conversation is started after moving in front of a person. Talking while looking at the person's eyes directly in front of the person may increase intimacy, but the timing and position of speaking to the person is not always appropriate when moving in front of the person. For example, whenever a person talks with each other, it is not always the case that the conversation is started after moving to the front of the other party. Therefore, the behavior of the robot as in the technique of Patent Document 1 is unnatural. End up. That is, there are various situations in which the robot talks to a person. For example, if there is a situation where the robot approaches from the front direction of the person and talks, the situation may approach from the lateral direction or the rear direction. In addition, if there is a situation that is simply for the purpose of dialogue with a person, there are situations in which the product must be explained to the person or the person must be guided close to the product. The technique of Patent Document 1 cannot appropriately cope with such various situations.

  In the techniques of Non-Patent Documents 1 and 2, it is assumed that people or people and a robot have already started interaction. In other words, it is not clarified at what timing and position the robot should speak to a person and start a conversation in a variety of situations.

  Therefore, a main object of the present invention is to provide a novel robot system and a space formation recognition apparatus used therefor.

  Another object of the present invention is to provide a robot system and a spatial formation recognition device used therefor that can naturally start a dialogue with a person.

  The present invention employs the following configuration in order to solve the above problems. Note that reference numerals in parentheses and supplementary explanations indicate correspondence with embodiments described later in order to help understanding of the present invention, and do not limit the present invention.

  A first invention is a robot system including a robot that performs communication with a person using at least an utterance, and detecting means for detecting arrangement information of a person and a robot including a position, a body direction, and a gaze direction , A determination means for analyzing a spatial formation between the person and the robot based on the arrangement information detected by the detection means, and determining a dialog participation state of the person and the robot, and at least one of the person and the robot is not in the dialog participation state by the determination means When it is determined that both the person and the robot are in the dialog participation state, the space formation adjusting means for controlling the operation of the robot so that both the person and the robot are in the dialog participation state, and the determination means are determined that both the person and the robot are in the dialog participation state. The robot system includes a greeting execution means for causing the robot to execute a greeting utterance to a person.

  In the first invention, the robot system (100) includes a robot (10) that performs communication with a person using at least speech. The robot talks to the person himself / herself in the environment where the robot is arranged and causes interaction with the person. The detection means (12, 62, 66, 84, 86, S1) detects arrangement information of the person and the robot, for example, the position, the body direction, and the line-of-sight direction. The determination means (62, 66, S3) determines the dialogue participation state of the person and the robot by analyzing the space formation (spatial arrangement relationship) based on the arrangement information of the person and the robot. Here, the dialogue participation state refers to a state (mental agreement state) implicitly agreed to participation in the dialogue, for example, a line-of-sight area (gz) defined in advance for a person and himself, front view It is estimated (recognized) based on the spatial formation represented by using the region (bz), the visual field region (sz), and the visual field (fv). The space formation adjusting means (26, 54, 62, 66, 82, S5-17) controls the operation of the robot according to the dialogue participation state of the person and the robot, and the space where both the person and the robot are in the dialogue participation state. Form a formation. Greeting execution means (54,62,66, S19) is, when both of human and robot has become interactive participation state (both participating state), to perform a greeting speech such as "Hello" or "May I help you?" The robot .

  According to the first invention, since the greeting utterance is executed after generating the spatial formation in which both parties are in the dialogue participation state, the dialogue with the person can be started naturally and smooth communication can be achieved.

  The second invention is dependent on the first invention, and the determination means is configured such that when both the human head and the robot head are in a space formation in a state where they enter the line-of-sight area of the opponent, It is determined that the user is in a dialog participation state.

  In the second invention, the judging means (62, 66, S3) has the human head in the line-of-sight region (gz) of the robot (10) and the robot head (52) in the human line-of-sight region. When the space form of the state is reached, that is, when the line of sight of the person and the robot is within a predetermined distance, it is determined that both are in a participating state. As a result, it is possible to appropriately recognize the both-participation state.

  The third invention is dependent on the first or second invention, and the determination means is in a state where both the person and the robot participate in the dialogue when both the person and the robot enter a space formation state in which the person enters the front area of the opponent. It is judged that.

  In the third invention, when the determination means (62, 66, S3) has a space shape in which a person enters the front area (bz) of the robot (10) and the robot enters the front area of the person, It is determined that both parties are participating. As a result, it is possible to appropriately recognize the both-participation state.

  The fourth invention is dependent on any one of the first to third inventions, and the determination means is not in a state where the head of the person and the head of the robot are both in the line-of-sight area of the opponent, but in the front area of the person. When the robot enters, a space formation is formed in which the person does not enter the front area of the robot and the person enters the field of view of the robot, it is determined that only the person is in the conversation participation state.

  In the fourth invention, the determination means (62, 66, S3) is not in a state in which the line of sight of the person and the robot (10) is within a predetermined distance, but the robot enters the front area (bz) of the person and the front of the robot. When a space is formed in a state where no person enters the area and a person enters the field of view (fv) of the robot, it is determined that only the person is in the conversation participation state. This makes it possible to appropriately recognize that only a person is in a dialog participation state.

  The fifth invention is dependent on any one of the first to fourth inventions, and the determination means is not in a state where both the human head and the robot head enter the partner's line-of-sight region, but in the front region of the robot. When a space is formed such that a person enters, a robot does not enter the person's front area, and a robot enters the person's visual field area, it is determined that only the robot is in the conversation participation state.

  In the fifth invention, the determination means (62, 66, S3) is not in a state in which the line of sight of the person and the robot (10) are aligned within a predetermined distance, and the person enters the front area (bz) of the robot. When a space is formed in a state where the robot does not enter the region and the robot enters the human visual field region (sz), it is determined that only the robot is in the dialog participation state. This makes it possible to appropriately recognize that only the robot is in the dialog participation state.

  The sixth invention is dependent on any one of the first to fifth inventions, and the spatial formation adjusting means adjusts the main movement of the spatial formation when it is determined by the determination means that neither the person nor the robot is in the dialogue participation state. It includes a main adjustment means for causing the robot to execute the movement.

  In the sixth invention, the space formation adjusting means (26, 54, 62, 66, 82, S5-17) includes main movement adjusting means (26, 62, 66, 82, S5, S7). When the determination means (62, 66, S3) determines that both the person and the robot (10) are not participating in the dialogue, that is, both are not participating, the main movement adjustment means moves the robot into a space-form main movement adjustment movement. Is executed. For example, in the main movement adjustment movement of the space formation, a point (or arrangement state) where a person enters the front area (fz) of the robot and the robot enters the human field of view (fv) is set as the movement target position. Move the robot.

  According to the sixth aspect of the invention, at least a space formation in which the robot is in a dialog participation state is secured.

  The seventh invention is dependent on the sixth invention, and when there is an object to be explained, the main adjustment means selects a point where the object can be easily explained as a movement target position of the robot.

  In the seventh invention, the main motion adjusting means (26, 62, 66, 82, S5, S7), when there is an object to be explained, sets a point where the object can be easily explained as the movement target position of the robot (10). Set as. For example, in order to satisfy the condition that a point where a person enters the front area (fz) of the robot and the robot enters the field of view (fv) of the person is set as a movement target position, The movement target position is set so as to form a spatial formation that falls within both fields of view (fv) of the person.

  According to the seventh aspect, since the point where the object can be easily explained is selected as the movement target position of the robot, the robot can avoid the adjustment of the position and the body orientation after starting the dialogue as much as possible. , More natural and smooth interaction with people.

  The eighth invention is dependent on any one of the first to seventh inventions, and the spatial formation adjusting means performs the passive adjustment movement of the spatial formation when the determination means determines that only the person is in the dialogue participation state. Passive adjustment means to be executed by the robot is included.

  In the eighth invention, the spatial formation adjusting means (26, 54, 62, 66, 82, S5-17) includes passive adjusting means (26, 62, 66, 82, S9, S11). The passive adjustment means causes the robot (10) to execute a spatial adjustment passive adjustment movement when it is determined by the determination means (62, 66, S3) that only a person is in the dialog participation state. For example, in the passive adjustment movement of the spatial formation, the robot is also brought into a dialog participation state by adjusting the body direction so that a person enters the front area (fz) of the robot.

  According to the eighth invention, when a person tries to work on the robot, the person can be shown that the robot is interested in the person. Can be prevented.

  A ninth invention is dependent on any one of the first to eighth inventions, and the spatial formation adjusting means executes a warning utterance to the robot when it is judged by the judging means that only the robot is in the dialogue participation state. Including an alerting execution means.

  In the ninth invention, the space formation adjusting means (26, 54, 62, 66, 82, S5-17) includes alerting executing means (54, 62, 66, S13, S15). The alerting execution means causes the robot to execute an alerting utterance such as “I am sorry” when it is determined by the determining means (62, 66, S3) that only the robot (10) is in the dialog participation state. This alerting utterance allows the person to adjust the position, body orientation, etc., so that the participation state can be realized.

  According to the ninth aspect of the invention, it is possible to flexibly cope with a situation in which the robot cannot go around the front area of the person because the space in front of the person is narrow, and more natural and smooth interaction is performed with the person. it can.

  The tenth invention is dependent on any one of the first to ninth inventions, and when the determination means determines that both the person and the robot are in the dialog participation state, the space form is suitable for the dialog. It further includes dialog formation adjusting means for controlling the operation of the robot.

  In a tenth aspect of the present invention, a dialogue shape adjusting means (26, 62, 66, 82, S21) is further provided. The dialogue formation adjustment means causes the robot (10) to perform adjustment movement to a more appropriate place for dialogue. For example, the robot is moved to an area where the distance from the person is 1.1 to 1.5 m while maintaining a space formation in which both sides are participating.

  According to the tenth aspect, the subsequent dialogue with the person can be executed more comfortably, and a more natural and smooth interaction can be executed with the person.

  An eleventh aspect of the present invention is a spatial formation recognition apparatus used for motion control of a robot that performs communication with a person using at least an utterance, the arrangement of the person and the robot including a position, a body direction, and a line-of-sight direction A space formation recognition device comprising: detection means for detecting information; and a determination means for analyzing a spatial formation of a person and a robot based on arrangement information detected by the detection means and determining a dialog participation state of the person and the robot is there.

  In the eleventh aspect of the invention, the space formation recognizing device (10, 62, 66) is used for controlling the operation of the robot (10) that performs communication with a person using at least speech, and the detecting means (12, 62). , 66, 84, 86, S1) and determination means (62, 66, S3). The detection means (12, 62, 66, 84, 86, S1) detects arrangement information of the person and the robot, for example, the position, the body direction, and the line-of-sight direction. The determination means (62, 66, S3) determines the dialogue participation state of the person and the robot by analyzing the space formation (spatial arrangement relationship) based on the arrangement information of the person and the robot. Here, the dialogue participation state refers to a state (mental agreement state) implicitly agreed to participation in the dialogue, for example, a line-of-sight area (gz) defined in advance for a person and himself, front view It is estimated (recognized) based on the spatial formation represented by using the region (bz), the visual field region (sz), and the visual field (fv).

  According to the eleventh aspect, since the conversation participation state of the person and the robot can be determined, it is possible to realize a robot that can naturally start a conversation with a person by controlling the operation of the robot in accordance with the determination result.

  According to the present invention, since the greeting speech is executed after generating the spatial formation in which both parties are in the dialogue participation state, the dialogue with the person can be started naturally, and smooth communication can be achieved.

  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.

It is an illustration figure which shows the structure of the robot system of one Example of this invention. It is an illustration figure which shows a mode that the external appearance of the robot of FIG. 1 was seen from the front. It is a block diagram which shows the electric constitution of the robot of FIG. It is an illustration figure which shows an example of a definition of a gaze area | region. It is an illustration figure which shows an example of the definition of a front area | region. It is an illustration figure which shows an example of a visual line area | region and a definition of a visual line. It is an illustration figure which shows an example of the space formation which will be in a both-participation state. It is an illustration figure which shows another example of the space formation which will be in a both-participation state. It is an illustration figure which shows an example of the space formation which only a person will be in a participating state. It is an illustration figure which shows an example of the space formation which only a robot will be in a participating state. It is an illustration figure which shows an example of the target position of the main adjustment movement when there is no target object. It is an illustration figure which shows an example of the target position of the main adjustment movement when there exists a target object. It is an illustration figure which shows an example of the target position of passive adjustment movement. It is an illustration figure which shows an example of the target position of the adjustment movement of a dialog formation. It is a flowchart which shows an example of the whole process which CPU of FIG. 3 performs.

  Referring to FIG. 1, a robot system 100 according to an embodiment of the present invention includes a robot 10 and a motion capture system 12 that are communicably connected. The robot 10 is an interaction-oriented robot (communication robot) that performs communication actions with people using speech, gestures, and the like, and is arranged in various environments such as stores and event venues. Then, in the arranged environment, the user talks to the person himself / herself to cause interaction with the person, and provides various services such as exhibition guide, customer attraction and entertainment. In the robot system 100, as will be described in detail later, the robot 10 can naturally start a conversation with a person (interactive person) by appropriately adjusting the space formation between the robot 10 and the person.

  FIG. 2 is a front view showing the appearance of the robot 10. The hardware configuration of the robot 10 will be described with reference to FIG.

  The robot 10 includes a carriage 20, and two wheels 22 and one slave wheel 24 that autonomously move the robot 10 are provided on the lower surface of the carriage 20. The two wheels 22 are independently driven by a wheel motor 26 (see FIG. 3), and can move the robot 10 in any direction, front, back, left, and right. The slave wheel 24 is an auxiliary wheel that assists the wheel 22. Thus, the robot 10 can move freely within the environment in which it is placed. However, the movement mechanism of the robot 10 is not limited to the wheel type, and a known movement mechanism can be appropriately employed. For example, a biped walking type movement mechanism can also be employed.

  The robot 10 stores map data of an environment to which the robot system 100 is applied in an internal memory (memory 66: see FIG. 3). Then, the robot 10 moves in the environment with reference to the map data with reference to the arbitrarily set origin position. At this time, the coordinate system of the map data referred to by the robot 10 and the coordinate system of the coordinates calculated by the computer 14 of the motion capture system 12 are set to be the same.

  A cylindrical sensor mounting panel 28 is provided on the carriage 20, and an infrared distance sensor 30 is mounted on the sensor mounting panel 28. The infrared distance sensor 30 measures the distance between the robot 10 and a surrounding object (such as a person or an obstacle).

  Further, the body 32 is provided on the sensor mounting panel 28 so as to stand upright. The above-described infrared distance sensor 30 is further provided on the front center upper portion of the body 32 (a position corresponding to the chest). This measures the distance to the person mainly in front of the robot 10. The body 32 is provided with one omnidirectional camera 34. The omnidirectional camera 34 is provided, for example, on a support column 36 extending from substantially the center of the upper end on the back side. The omnidirectional camera 34 captures the surroundings of the robot 10 and is distinguished from an eye camera 60 described later. As this omnidirectional camera 34, for example, a camera using a solid-state imaging device such as a CCD or a CMOS can be adopted. In addition, the installation positions of the infrared distance sensor 30 and the omnidirectional camera 34 are not limited to the portions, and can be changed as appropriate.

  Upper arms 40R and 40L are provided by shoulder joints 38R and 38L, respectively, at upper end portions (positions corresponding to shoulders) on both side surfaces of the body 32. Although illustration is omitted, each of the shoulder joints 38R and 38L has three orthogonal degrees of freedom. That is, the shoulder joint 38R can control the angle of the upper arm 40R around each of the three orthogonal axes. A certain axis (yaw axis) of the shoulder joint 38R is an axis parallel to the longitudinal direction of the upper arm 40R, and the other two axes (pitch axis and roll axis) are axes orthogonal to each other from different directions. Similarly, the shoulder joint 38L can control the angle of the upper arm 40L around each of the three orthogonal axes. A certain axis (yaw axis) of the shoulder joint 38L is an axis parallel to the longitudinal direction of the upper arm 40L, and the other two axes (pitch axis and roll axis) are axes orthogonal to each other from different directions.

  Further, forearms 44R and 44L are provided at the tips of the upper arms 40R and 40L via elbow joints 42R and 42L, respectively. Although illustration is omitted, each of the elbow joints 42R and 42L has one degree of freedom, and the angle of the forearms 44R and 44L can be controlled around the axis (pitch axis).

  Spheres 46R and 46L corresponding to hands are fixedly provided at the tips of the forearms 44R and 44L, respectively. However, if a finger or palm function is required, a “hand” in the shape of a human hand can be used.

  Although illustration is omitted, a contact sensor (FIG. 3) is provided on each of the front surface of the carriage 20, a portion corresponding to the shoulder including the shoulder joints 38R and 38L, the upper arms 40R and 40L, the forearms 44R and 44L, and the spheres 46R and 46L. Is comprehensively shown as a contact sensor 48.). The contact sensor 48 on the front surface of the carriage 20 detects contact of a person or another obstacle to the carriage 20. Therefore, if there is contact with an obstacle while the robot 10 is moving, it can be detected, and the driving of the wheel 22 can be immediately stopped to suddenly stop the movement of the robot 10. The other contact sensors 48 mainly detect whether or not a person has touched each part of the robot 10. The installation position of the contact sensor 48 is not limited to these, and may be provided at an appropriate position (chest, abdomen, side, back, waist, etc.).

  A neck joint 50 is provided at the upper center of the body 32 (a position corresponding to the neck), and a head 52 is further provided thereon. Although illustration is omitted, the neck joint 50 has a degree of freedom of three axes, and the angle can be controlled around each of the three axes. A certain axis (yaw axis) is an axis directed directly above (vertically upward) of the robot 10, and the other two axes (pitch axis and roll axis) are axes orthogonal to each other in different directions.

  The head 52 is provided with a speaker 54 at a position corresponding to the mouth. The speaker 54 is used for the robot 10 to communicate with people around it by voice or sound. Further, microphones 56R and 56L are provided at positions corresponding to the ears. Hereinafter, the microphone 56R corresponding to the right ear and the microphone 56L corresponding to the left ear may be collectively referred to as “microphone 56”. The microphone 56 captures ambient sounds, particularly a voice of a person who is a target of communication. Further, eyeball portions 58R and 58L are provided at positions corresponding to the eyes. Eyeball portions 58R and 58L include eye cameras 60R and 60L, respectively. Hereinafter, the right eyeball portion 58R and the left eyeball portion 58L may be collectively referred to as “eyeball portion 58”, and the right eye camera 60R and the left eye camera 60L are collectively referred to as “eye camera 60”. Sometimes.

  The eye camera 60 captures a human face approaching the robot 10, other parts or objects, and captures a corresponding video signal. As the eye camera 60, a camera similar to the omnidirectional camera 34 described above can be used. For example, the eye camera 60 is fixed in the eyeball part 58, and the eyeball part 58 is attached to a predetermined position in the head 52 via an eyeball support part (not shown). Although illustration is omitted, the eyeball support portion has two degrees of freedom, and the angle can be controlled around each of these axes. For example, one of the two axes is an axis (yaw axis) in a direction toward the top of the head 52, and the other is orthogonal to one axis and the direction in which the front side (face) of the head 52 faces. It is an axis (pitch axis) in the direction to be. By rotating the eyeball support portion around each of these two axes, the tip (front) side of the eyeball portion 58 or the eye camera 60 is displaced, and the camera axis, that is, the line-of-sight direction is moved. The installation positions of the speaker 54, the microphone 56, and the eye camera 60 described above are not limited to these, and may be provided at appropriate positions.

  The robot 10 is designed to be slightly smaller than an adult so as not to give intimidation to a person (especially a child), and has a height of 120 cm and a radius of 50 cm. is there.

  FIG. 3 is a block diagram showing an electrical configuration of the robot 10. As shown in FIG. 3, the robot 10 includes a CPU 62 that controls the whole. The CPU 62 is also called a microcomputer or a processor, and is connected to the memory 66, the motor control board 68, the sensor input / output board 70, the audio input / output board 72, and the like via the bus 64.

  Although not shown, the memory 66 includes a ROM, an HDD, and a RAM. A control program for the robot 10 is stored in advance in the ROM and HDD. For example, an action control program for executing a communication action with a person, a communication program for transmitting / receiving necessary information to / from an external computer (motion capture system 12), data from the motion capture system 12, etc. A determination program for analyzing a space formation between the person and himself based on the person and his / her own conversation participation state, a space formation adjustment program for forming a predetermined space formation, and the like. In addition, in the ROM or HDD, voice or voice data (voice synthesis data) to be generated when each action is executed, angle data for presenting a predetermined gesture, map data of the environment, and explanation Data such as data relating to the product (object) is also stored as appropriate. The RAM is used as a work memory or a buffer memory.

  The motor control board 68 is configured by, for example, a DSP, and controls driving of motors of the axes such as the arms, the neck joint 50, and the eyeball unit 58. That is, the motor control board 68 receives two control data from the CPU 62 and controls two motors for controlling the respective angles of the two axes of the right eyeball portion 58R (collectively, “right eyeball motor” in FIG. 3) 74. Control the rotation angle. Similarly, the motor control board 68 receives control data from the CPU 62, and controls two angles of the two axes of the left eyeball part 58L (in FIG. 3, collectively referred to as “left eyeball motor”). The rotation angle of 76 is controlled.

  The motor control board 68 receives control data from the CPU 62, and includes three motors for controlling the angles of the three orthogonal axes of the right shoulder joint 38R and one motor for controlling the angle of the right elbow joint 42R. The rotation angles of a total of four motors 78 (collectively referred to as “right arm motor” in FIG. 3) 78 are adjusted. Similarly, the motor control board 68 receives control data from the CPU 62 and includes three motors for controlling the angles of the three orthogonal axes of the left shoulder joint 38L and one motor for controlling the angle of the left elbow joint 42L. The rotation angles of a total of four motors (collectively referred to as “left arm motor” in FIG. 3) 80 are adjusted.

  Furthermore, the motor control board 68 receives the control data from the CPU 62 and controls three motors for controlling the angles of the three orthogonal axes of the neck joint 50 (in FIG. 3, collectively referred to as “head motors”). The rotation angle of 82 is controlled. Furthermore, the motor control board 68 receives control data from the CPU 62 and controls the rotation angle of two motors 26 (hereinafter collectively referred to as “wheel motors”) 26 that drive the wheels 22.

  In this embodiment, stepping motors or pulse motors are used for the motors other than the wheel motor 26 in order to simplify the control. However, as with the wheel motor 26, a DC motor may be used.

  Similarly, the sensor input / output board 70 is also configured by a DSP, and takes in signals from each sensor and gives them to the CPU 62. That is, data relating to the reflection time from each of the infrared distance sensors 30 is input to the CPU 62 through the sensor input / output board 70. The video signal from the omnidirectional camera 34 is input to the CPU 62 after being subjected to predetermined processing by the sensor input / output board 70 as necessary. Similarly, the video signal from the eye camera 60 is also input to the CPU 62. Further, signals from the plurality of contact sensors 48 described above are given to the CPU 62 via the sensor input / output board 70.

  Similarly, the voice input / output board 72 is also configured by a DSP, and a voice or voice according to voice synthesis data provided from the CPU 62 is output from the speaker 54. Also, the voice input from the microphone 56 is taken into the CPU 62 via the voice input / output board 56.

  The CPU 62 is connected to the communication LAN board 84 via the bus 64. The communication LAN board 84 is constituted by a DSP, gives transmission data sent from the CPU 62 to the wireless communication device 86, and transmits the transmission data from the wireless communication device 86 to an external computer via a network such as a wireless LAN. . The communication LAN board 84 receives data via the wireless communication device 86 and gives the received data to the CPU 62. That is, the communication LAN board 84 and the wireless communication device 86 allow the robot 10 to perform wireless communication with an external computer or the like.

  Returning to FIG. 1, the motion capture system 12 is used to detect the position of the robot 10 and a person, the direction of the body, the direction of the line of sight, etc., and a plurality of cameras installed in the environment with a general-purpose computer 14 such as a PC. (Infrared camera) 16. Although not shown, a plurality of infrared reflection markers are attached to the robot 10 and the person. In this embodiment, a total of 23 infrared reflection markers are attached to appropriate positions such as a head, a trunk, and an arm for each of the robot 10 and a person. An infrared reflective marker is also attached to an object (such as a product) that the robot 10 should explain (introduce) to a person. As the motion capture system 12, a known motion capture system can be applied. For example, an optical motion capture system manufactured by VICON can be used.

  The computer 14 of the motion capture system 12 acquires image data from the camera 16 at, for example, 60 Hz (60 frames per second), and performs image processing on the image data so that each infrared reflection marker in all image data at the time of measurement is obtained. Are extracted. Then, the computer 14 calculates the three-dimensional position of each infrared reflection marker in the real space based on the two-dimensional position of each infrared reflection marker in the image data, whereby the robot 10 and the position (coordinates) of the person, the body The direction and the direction of the face (line of sight) are calculated. Then, the computer 14 transmits arrangement information such as the calculated position data (coordinate data) of the robot 10 and the person, body direction data, and line-of-sight direction data to the robot 10 in response to a request from the robot 10 (CPU 62).

  Note that the position, body direction, and line-of-sight direction of the robot 10 can be grasped without necessarily using the motion capture system 12. For example, the position, body direction, and line-of-sight direction of the robot 10 can also be obtained by calculation from the rotation angles of the wheel motor 26 and the head motor 66 described above. However, in the embodiment, the motion capture 12 is used in order to reduce the real-time calculation amount of the CPU 62.

  In such a robot system 100, the robot 10 works on the person himself / herself in the environment in which the robot 10 is arranged to cause interaction with the person, and provides various services such as exhibition guidance, customer attraction and entertainment. Here, in order for the robot 10 to provide a service more efficiently, it is important that the robot 10 acquire a function of talking to a person at an appropriate timing and position, that is, a function of starting a conversation with a person naturally. .

  The inventors of the present invention have carefully observed how people start to interact with each other. As a result, they have found that they form a specific spatial formation (that is, a spatial arrangement relationship) and then start the conversation. Therefore, in this embodiment, the robot system 100 (robot 10) that can naturally start a conversation with a person is realized by modeling it and causing the robot 10 to execute it.

  Specifically, when the present inventors observed a situation where a store clerk talks to a customer, which is considered to be widely used when the robot 10 provides a service, the following four points were confirmed. (1) When a customer notices the presence of a store clerk (when two people are in line of sight), the store clerk greets when the customer approaches a predetermined distance (for example, 2.5 m), and then A little closer (for example, up to 1.5m) when talking. However, the predetermined distance at this time depends on the situation and environment. (2) A store clerk approaching from the front of the customer (in the range of 120 ° centered on the front direction) greets when approaching a distance of about 2 m and approaches 1.5 m or less when talking thereafter. (3) The store clerk approaching from outside the front of the customer moves so as to be within the customer's field of view (a range of 270 ° centered on the front direction) and approaches a distance of about 1.5 m. When the customer does not notice the approach of the store clerk, he / she greets the customer with a word such as “I'm sorry” and makes the customer aware of his / her presence. (4) When it is necessary to explain the next plan to the store clerk, for example, to guide the customer to the place of the product, and the customer is not aware of the store clerk, Say hello in a place where you can easily take the next action.

  From the above observations, whenever a person greets each other and starts a dialogue, by forming a specific spatial formation, both parties recognize the existence of the other party, that is, implicit in participating in the dialogue It can be seen that a state of mutual agreement (mental consent state) is formed for both sides. In this embodiment, this mental consent state is named “dialog participation state”. From the observation results, it can also be seen that the spatial formation for starting the conversation is not necessarily the same as the spatial formation for the conversation. In other words, in order for the robot 10 to naturally start a conversation with a person, it is important to first make both the robot 10 and the person into a conversation participation state, that is, form a space formation in which both of them are in a conversation participation state. Yes, it can be said that it is necessary to adjust the space formation suitable for dialogue depending on the situation.

  Therefore, in this embodiment, when the robot 10 works on its own to start a dialogue (interaction) with a person, first, the space formation between the robot 10 and the person is analyzed, and the dialogue participation state of the robot 10 and the person. Is recognized (estimated). Then, after the robot 10 takes an appropriate action according to the recognized dialog participation state, both the robot 10 and the person enter the dialog participation state, and then the robot 10 greets and speaks to the person. I am doing so. This will be specifically described below.

  In order to recognize the dialogue participation state based on the spatial formation, the line-of-sight region gz, the front region fz, the visual field region sz, and the visual field fv are defined as follows.

  As shown in FIG. 4, the line-of-sight area gz is a conical area extending from the center of the head (face) toward the face front direction with the line-of-sight direction gd as the central axis, and the apex angle θ is 30 °. It is assumed that the distance from the apex to the bottom surface is 2.5 m. As shown in FIG. 5, the front area fz is a fan-shaped area having a range of 120 ° centering on the front direction bd of the body and having a distance of 2 m or less from the center of the body. Furthermore, as shown in FIG. 6, the visual field region sz is a region having a range of 270 ° centered on the front direction bd of the body and a distance from the center of the body within 1.5 m. The field of view fv is a range of 270 ° centered on the front direction bd of the body and has no distance limitation from the center of the body.

  Then, when the next predetermined space condition is satisfied, it is determined that the user is in the dialog participation state.

  (1) As shown in FIG. 7, when the human head (face) enters the line-of-sight area gz of the robot 10 and the head 52 of the robot 10 enters the line-of-sight area gz of the robot 10 That is, when the robot 10 and the person are in a state where their eyes are aligned within a predetermined distance, it is determined that both the robot 10 and the person are in a dialog participation state (both participation state). (2) As shown in FIG. 8, in a state where the robot 10 and the person are not aligned, the person enters the front area fz of the robot 10 and the robot 10 enters the person's front area fz. When this happens, it is determined that both the robot 10 and the person are in a dialog participation state. (3) As shown in FIG. 9, the robot 10 enters the front area fz of the person, the person does not enter the front area fz of the robot 10, and the robot 10 When the space formation is such that a person enters the field of view fv, it is determined that only the person is in the dialog participation state (only the person is in the participation state). (4) As shown in FIG. 10, in a state where the line of sight between the robot 10 and the person does not match, the person enters the front area fz of the robot 10, the robot 10 does not enter the person's front area fz, and the field of view of the person When the space formation is such that the robot 10 enters the area sz, it is determined that only the robot 10 is in the dialogue participation state (the robot only participation state). (5) In the case of a space formation that does not satisfy the above-described space conditions 1-4, it is determined that both the robot 10 and the person are not in the dialogue participation state (both are in a non-participation state).

  The specific numerical values (threshold values) that define each area are values determined based on the results of observing communication between people, but these optimum values vary depending on the environment in which the robot 10 is placed, the conversation partner, and the like. Since it is a numerical value to be used, it may be changed as necessary. For example, in a wide place with a good view, the distance that defines the line-of-sight area gz may be set to be larger than 2.5 m, and when the height of the robot 10 or the person of the conversation partner is high, You may make it take the distance setting of an area | region large. In addition, whether or not the user has entered a certain area may be determined by whether or not the center of the body (or head) has entered the area. You may judge by having entered into the area.

  When the dialogue participation state of the robot 10 and the person is recognized, the action (motion) of the robot 10 is determined according to the recognition result. That is, the robot 10 performs an action to form a predetermined space formation (that is, a space formation for starting a conversation) that is in a participation state.

  Specifically, when it is determined that both are in a non-participating state, the robot 10 performs a proactive adjustment of spatial formation. In the space movement main adjustment movement, the robot 10 sets a point (or arrangement state) where a person enters the front area fz of the robot 10 and the robot 10 enters the person's visual field area fv as a movement target position. Moving.

  At this time, if the robot 10 does not have the next plan, that is, if the purpose is simply to interact with a person, the point that is the shortest distance from its own position is set as the movement target position, as shown in FIG. Selected. However, as can be seen from FIG. 11, when the robot 10 approaches from the direction of the person's front area fz, the robot 10 enters the person's front area fz. Just enter. Further, when approaching from the direction of the person's line-of-sight area gz, the robot 10 only needs to enter the person's line-of-sight area gz because both enter the state when entering the person's line-of-sight region gz.

  On the other hand, when the robot 10 has the next plan, for example, when it is necessary to explain the product or to guide a person to the place of the product, the main movement adjustment movement of the space formation is an aspect in consideration of the next action. It is said. For example, when there is an object to be described, the condition that a person enters the front area fz of the robot 10 and the point where the robot 10 enters the person's visual field area fv is set as the movement target position. Further, a point where the object can be easily explained is selected as the movement target position. Specifically, as shown in FIG. 12, the movement target position is set so that the object has a spatial formation that falls within the field of view fv of both the robot 10 and the person.

  However, if the person moves or changes the direction of the body or the line of sight during the execution of the main adjustment movement of the space formation, the robot 10 becomes a participatory state or only the person enters the state. Ends the main movement adjustment movement of the space formation, and moves to the next action according to the dialogue participation state of the robot 10 and the person. As a result of the main movement adjustment movement of the space formation as described above, at least a space formation in which the robot 10 is in a dialog participation state is secured.

  When it is determined that only a person is participating, the robot 10 performs a reactive adjustment of spatial formation. As shown in FIG. 13, in the passive adjustment movement of the space formation, the robot 10 is also in a dialog participation state by adjusting the body direction so that a person enters the front area fz of the robot 10. At this time, the line-of-sight direction may be adjusted so that the human head (face) enters the line-of-sight area gz of the robot 10. In addition, the space formation in which only people are in the conversation participation state is the situation that occurs when a person moves or changes the body direction or line of sight during the main movement adjustment movement of the space formation, that is, from the person's side. Since it is assumed that the robot 10 is going to work, the adjustment movement (details will be described later) to a more appropriate place for the dialogue may be performed simultaneously in the passive adjustment movement of the space formation. This space formation passive adjustment movement can indicate to the person that the robot 10 is interested in the person. Therefore, when the person tries to work on the robot 10, the person gives up on the way and the robot gives up. It is possible to prevent the distance from 10.

  When it is determined that only the robot is in the participation state, the robot 10 performs an alert utterance. The space formation in which only the robot 10 is in a dialog participation state is assumed to be a situation in which a person is not aware that the robot 10 has approached. Therefore, the robot 10 causes the person to adjust the direction of the body and the direction of the line of sight by making a cautionary utterance such as “I'm sorry”, and forms a space formation with both participating states. What is important here is that the robot 10 is already in the visual field region sz of the person, and this prevents as much as possible talking that is unexpected for the person. This alerting utterance allows the person to adjust the body direction and line-of-sight direction, so that the space on the front side of the person is narrow and the robot 10 cannot go around the front area fz of the person. It can respond flexibly to the situation.

  Then, when it is determined that both participating state, the robot 10, to run the greeting speech such as "Hello" or "May I help you?" To the people. The bilateral participation state is a state where both the robot 10 and the person implicitly agree to participate in the dialogue. That is, from the human side, the robot 10 is in the state indicated by the robot 10 that it wants to talk with itself (or accept the dialogue with itself) and accepts the dialogue with the robot 10 (or wants to talk with the robot 10). The intention is indicated to the robot 10. Therefore, the greeting utterance of the robot 10 when the two-participants are in the participation state is accepted by the person very naturally, and the robot 10 can start the conversation with the person naturally.

  Further, from the observation result of the dialogue between the above-mentioned people, it has been found that there is a suitable space formation (dialog formation), so in this embodiment, the robot 10 further interacts with the person. Also performs coordinated movements (dialogue-shaped coordinated movements) to more appropriate locations for dialogue. Specifically, as shown in FIG. 14, the distance from the person moves to an area where the distance is 1.1 to 1.5 m while maintaining a space formation in which both players are participating. By this adjustment movement of the dialog formation, the subsequent dialog with the person can be executed more comfortably. The adjustment movement of the dialogue formation may be performed before the next utterance after the greeting utterance of the robot 10 is finished, or may be performed while performing a dialogue with a person.

  Next, the operation of the robot 10 (robot system 100) when starting an interaction with a person will be described using a flowchart. Specifically, the CPU 62 of the robot 10 shown in FIG. 3 executes the entire process according to the flowchart shown in FIG. Referring to FIG. 15, in step S <b> 1, the CPU 62 detects the position of the robot 10 and the person, the body direction, and the line-of-sight direction. That is, arrangement information such as position data, body direction data, and gaze direction data of the robot 10 and the person is acquired from the motion capture system 12 via the wireless communication device 86 and the communication LAN board 84.

  In the next step S3, the dialogue participation state of the robot 10 and the person is recognized from the space formation. That is, by analyzing the spatial formation between the robot 10 and the person based on the arrangement information acquired in step S1, the dialogue participation state of the robot 10 and the person is in the non-participation state, only the person participation state, only the robot participation Recognize (determine) whether the state or both-participation state. For example, when both heads are in a space formation in a state where they enter each other's line-of-sight region gz (when each other's line-of-sight matches), they both enter a space formation in a state where they enter each other's front region fz. Sometimes it is recognized that both are participating. Further, for example, in a state where the lines of sight do not match each other, the robot 10 enters the front area fz of the person, the person does not enter the front area fz of the robot 10, and the person is in the field of view fv of the robot 10. When it becomes, it is judged that only a person is in a participating state. Further, for example, a space in which a person enters the front area fz of the robot 10, the robot 10 does not enter the person's front area fz, and the robot 10 enters the person's visual field area sz in a state where the lines of sight do not match each other. When it becomes a formation, it is determined that only the robot is in a participating state. Further, when neither of the space conditions (spatial formation) in which only the person participates, only the robot participates, or both participates, it is determined that both are not participating. Note that the processes in steps S1 and S3 are repeatedly executed at predetermined time intervals.

  In the next step S5, it is determined whether the dialog participation state of the robot 10 and the person recognized in step S3 are both non-participation states. If “YES” in step S5, that is, if both are in a non-participating state, the process proceeds to step S7. If “NO” in step S5, that is, if both are not in a non-participating state, the process proceeds to step S9. .

  In step S7, the main movement adjustment movement of the space formation is executed. That is, a point (or arrangement state) where a person enters the front area fz of the robot 10 and the robot 10 enters the human visual field area fv is set as a movement target position, and the robot 10 moves to the movement target position. As described above, the control data for controlling the rotation angle of the wheel motor 26 is transmitted to the motor control board 68. At this time, if the robot 10 does not have the next plan, that is, if it is only intended to interact with a person, the point (or arrangement state) that is the shortest distance from its own position is selected as the movement target position. The On the other hand, when the robot 10 has the next plan, for example, when it is necessary to explain the product or guide a person to the place of the product, the product (target) is the field of view of both the robot 10 and the person. A point that forms a space formation entering fv is set as the movement target position. When step S7 ends, the process returns to step S1.

  In step S9, it is determined whether or not the dialog participation state of the robot 10 and the person recognized in step S3 is only a person participation state. If “YES” in the step S9, that is, if only a person is in a participating state, the process proceeds to a step S11. If “NO” in step S9, that is, if only a person is not in a participating state, the process proceeds to a step S13.

  In step S11, the passive adjustment movement of the space formation is executed. That is, control data for controlling the rotation angle of the wheel motor 26 is transmitted to the motor control board 68 so that a person enters the front area fz of the robot 10 to adjust the body direction of the robot 10, Control data for controlling the rotation angle of the head motor 82 is transmitted to the motor control board 68 so that the human head enters the 10 line-of-sight area gz, and the line-of-sight direction of the robot 10 is adjusted. The robot 10 is also in a dialog participation state. At this time, adjustment movement to a more appropriate place for dialogue may be performed at the same time. When step S11 ends, the process returns to step S1.

  In step S13, it is determined whether the dialogue participation state of the robot 10 and the person recognized in step S3 is a participation state of only the robot. If “YES” in the step S13, that is, if only the robot is in a participating state, the process proceeds to a step S15. If “NO” in step S13, that is, if only the robot is not in a participating state, the process proceeds to the step S17.

  In step S15, a warning utterance is executed. That is, voice data for performing a caution utterance such as “I'm sorry” is transmitted to the voice input / output board 72, and a caution utterance is output from the speaker 54. When step S15 ends, the process returns to step S1.

  In step S17, it is determined whether or not the dialog participation state of the robot 10 and the person recognized in step S3 is a both participation state. If “YES” in the step S17, that is, if both are in a participating state, the process proceeds to a step S19. If “NO” in step S17, that is, if not in a both participating state, the process returns to the step S1.

  In step S19, a greeting utterance is executed. In other words, by sending "Hello" and the voice data to perform a greeting speech in accordance with the status of "not Welcome" and the like to the audio input / output board 72, and outputs a warning speech from the speaker 54. At this time, control data for executing a physical action such as bowing may be transmitted to the motor control board 68 in conjunction with the greeting utterance.

  In the following step S21, adjustment movement of the dialog formation is executed. That is, the control data for controlling the rotation angle of the wheel motor 26 is transferred to the motor control board so as to move to a region where the distance to the person is 1.1 to 1.5 m while maintaining the space formation in which both sides are in a participating state. 68. When the space formation for dialogue is established by the processing in step S21, the entire processing is terminated.

  According to this embodiment, the robot 10 executes a greeting utterance after generating a spatial formation in which both the robot 10 and a person are in a dialog participation state. That is, since the greeting utterance closer to the dialogue between humans is executed, the greeting utterance of the robot 10 is accepted by humans very naturally. Therefore, the robot 10 can naturally start a conversation with a person and can smoothly communicate with the person.

  Further, according to this embodiment, when the robot 10 has the next plan, the main movement adjustment movement of the space formation of the robot 10 is set in a mode that considers the next action. That is, when there is an object to be explained, a point where the object can be easily explained is selected as the movement target position of the robot 10. As a result, the robot 10 can avoid adjustments such as the position and body orientation after starting the conversation as much as possible, so that a more natural and smooth interaction can be performed with a person. In particular, if the spatial relationship between the robot 10, the person, and the object is aligned in a straight line, it becomes difficult for the robot 10 to point to the object using a pointing gesture, but this problem can be avoided.

  Further, in this embodiment, when it is determined that only a person is participating in the dialogue, the robot 10 performs a spatial adjustment passive movement. As a result, when a person tries to work on the robot 10, the person can be shown that the robot 10 is interested in the person, so that the person gives up on the way and leaves the robot 10. Can be prevented.

  Further, in this embodiment, when it is determined that only the robot 10 is in the dialog participation state, the robot 10 performs a cautionary utterance and asks a person to adjust the body direction and the line-of-sight direction. Accordingly, it is possible to flexibly cope with a situation in which the robot 10 cannot go around the front area fz of the person due to a narrow space in front of the person, and more natural and smooth interaction can be performed with the person.

  Further, in this embodiment, adjustment movement to a more appropriate place for dialogue (dialogue-shaped adjustment movement) is also executed. This is because the spatial formation for starting a conversation is not necessarily the same as the spatial formation for performing a conversation. By performing coordinated movement of the dialog formation, more natural and smooth interaction is achieved. Can be executed between.

  In the above-described embodiment, the motion capture system 12 is used to detect the arrangement information of the robot 10 and the person, that is, the position, the body direction, and the line-of-sight direction. The method can be used as appropriate. For example, the method using the LRF disclosed in Japanese Patent Application Laid-Open No. 2009-168578 previously filed by the present inventors can be used for the position detection of the person and the robot 10 and the detection of the body orientation. In addition, as an example of an apparatus for measuring the line-of-sight direction, the technology of the line-of-sight measurement system “eye mark recorder” of NAC Image Technology Co., Ltd. can be used.

  In the above-described embodiment, the CPU 62 of the robot 10 recognizes the dialogue participation state by analyzing the space formation between the robot 10 and the person (corresponding to step S3), and the next operation according to the dialogue participation state. However, the present invention is not limited to this. For example, an external computer is separately provided as a robot control device (or space formation recognition device), and the external computer is caused to execute part or all of these processes for determining the operation of the robot 10 by analyzing the space formation. Operation control data may be transmitted from the computer to the robot 10.

  Note that the specific numerical values such as the predetermined distance mentioned above are merely examples, and can be appropriately changed as necessary.

DESCRIPTION OF SYMBOLS 10 ... Communication robot 12 ... Motion capture system 22 ... Wheel 26 ... Wheel motor 54 ... Speaker 62 ... CPU
66 ... Memory 100 ... Robot system

Claims (11)

A robot system including a robot that performs communication with a person using at least speech,
Detecting means for detecting arrangement information of the person and the robot including a position, a body direction, and a line-of-sight direction;
Determination means for analyzing a spatial formation of the person and the robot based on the arrangement information detected by the detection means, and for determining a dialog participation state of the person and the robot;
Spatial shape adjustment means for controlling the operation of the robot so that both the person and the robot enter a dialog participation state when the determination means determines that at least one of the person and the robot is not in the dialog participation state; And a robot system comprising greeting execution means for causing the robot to execute a greeting utterance to the person when the determination means determines that both the person and the robot are in a dialog participation state.   The determination means determines that both the person and the robot are in a dialog participation state when both the person's head and the robot's head are in a space formation in a state where they enter the line-of-sight area of the opponent. The robot system according to claim 1.   The said determination means determines that both the said person and the said robot are dialog participation states, when the said person and the said robot become the space formation form of the state which enters into the front area of the other party. Robot system.   The determination means is not in a state where the head of the person and the head of the robot are in the line-of-sight area of the opponent, the robot enters the front area of the person, and the person does not enter the front area of the robot. The robot system according to any one of claims 1 to 3, wherein only the person is determined to be in a dialog participation state when the space is formed so that the person enters the field of view of the robot.   The determination means is not in a state where the head of the person and the head of the robot are both in the line-of-sight area of the opponent, the person enters the front area of the robot, and the robot does not enter the front area of the person. 5. The robot system according to claim 1, wherein only the robot is determined to be in a dialog participation state when the robot is in a space formation state in which the robot enters the visual field region of the person.   The space formation adjusting means includes main movement adjusting means for causing the robot to perform a main movement adjustment movement of a space formation when it is determined by the determination means that neither the person nor the robot is in a dialog participation state. 6. The robot system according to any one of 5 to 5.   The robot system according to claim 6, wherein when there is an object to be explained, the main motion adjusting unit selects a point where the object is easily explained as a movement target position of the robot.   The space formation adjusting means includes passive adjustment means for causing the robot to perform a space adjustment passive adjustment movement when it is determined by the determination means that only the person is in a dialog participation state. The robot system according to any one of the above.   9. The space formation adjusting means according to any one of claims 1 to 8, wherein said space formation adjusting means includes attention executing means for causing said robot to execute a warning utterance when it is determined by said determining means that only said robot is in a dialog participation state. The robot system described in 1.   The apparatus further comprises dialogue shape adjusting means for controlling the operation of the robot so as to obtain a space shape suitable for dialogue when both of the person and the robot are judged to be in a dialogue participation state by the decision means. The robot system according to any one of 1 to 9. A spatial formation recognition device used for motion control of a robot that performs communication with a person using at least speech,
Detecting means for detecting arrangement information of the person and the robot including a position, a body direction and a line-of-sight direction, and analyzing a spatial formation of the person and the robot based on the arrangement information detected by the detecting means. A spatial formation recognizing device, comprising: determination means for determining a dialog participation state of the person and the robot.

Images