JP4677593B2 - Communication robot - Google Patents

Description

  The present invention relates to a communication robot, and more particularly to a communication robot that executes a communication action with a plurality of communication objects having a unique wireless tag, for example.

An example of a conventional communication robot of this type is disclosed in Patent Document 1. In the robot apparatus disclosed in Patent Document 1, a person who faces the robot apparatus is photographed with a camera, a front face image is acquired from the photographed camera image, and is compared with an identification dictionary stored in advance, and the person is identified. It was specified.
JP 2002-56388 (pages 6 to 11, FIGS. 1 to 10, FIG. 12, FIGS. 19 to 22 and FIG. 33)

  However, since this conventional technique is designed to identify (identify) the person facing the robot, it is difficult to identify the person in the vicinity of or around the robot. Had to face each person and identify the person. Further, since the person is specified by the video shot by the camera, there is a problem that the processing is enormous and it takes time to specify the person. Furthermore, when a plurality of persons are overlapped when viewed from the robot, there is a problem that a person located behind cannot be specified. Therefore, such a conventional technique cannot be applied to a communication robot that executes communication behavior with a plurality of communication objects such as a plurality of persons.

  Therefore, a main object of the present invention is to provide a communication robot capable of easily specifying a communication target and executing a communication action suitable for the specified communication target.

The present invention is a communication robot that executes communication behavior by at least one of behavior and voice between a plurality of communication objects having radio tags having unique tag information, and includes the tag information and the tag information. tag information database for recording in association with communication target carrying a wireless tag, acquiring means for acquiring tag information from the wireless tag held by communication object, double that exist in the vicinity or surroundings on the basis of the obtained results of the acquisition means the number of communication target recognize individually, the recognition means for detecting the magnitude of the distance between the communication target, the communication subject distance from the recognition result of the recognition means is minimized, as a communication object, which executes communication behavior Specifying means for constant, communications history of the behavior, the communication behavior of the history database for recording in association with the communication target has been executed, and communication behavior history recorded in association with one communication target specified by the specifying means It is a communication robot provided with the execution means which performs the communication action according to this communication object .

  The communication robot executes a communication action by at least one of sound and action on a plurality of communication objects such as a human (user) having a unique wireless tag. The communication robot includes a tag information database that records at least tag information. When performing a communication action, the communication robot acquires tag information from a communication target by an acquisition unit. The recognition means individually recognizes a human (user) as a communication target. The specifying unit specifies one communication target based on the recognition result of the recognition unit. That is, one user is specified among users existing near or around the communication robot. And an execution means performs a communication action with respect to the said user.

  For example, since the detecting means detects the distance between each communication object, the specifying means can specify one communication object having the smallest distance. That is, a communication action can be taken with respect to a user existing in the nearest vicinity.

  The wireless tag transmits radio waves, and the acquisition means includes an antenna. The detection means detects the magnitude of the distance according to the radio wave intensity at the antenna when the tag information is acquired by the acquisition means. That is, if the radio field intensity is weaker, the distance from the communication robot is larger, and if the radio field intensity is stronger, the distance from the communication robot is smaller. Therefore, the specifying unit specifies a user having tag information acquired with the strongest radio wave intensity as a communication target.

  However, the wireless tag may transmit (radiate) tag information by ultrasonic waves or infrared rays. When transmitting tag information by ultrasonic waves, the ultrasonic sensor included in the acquisition unit receives the ultrasonic waves from the wireless tag, and the user as a communication target is specified according to the sound wave intensity of the ultrasonic sensor at that time. Is done. In addition, when tag information is transmitted (radiated) by infrared rays, an infrared sensor included in the acquisition unit receives infrared rays from a wireless tag, and a user who is a communication target according to the received light intensity of the infrared sensor at that time. Identified.

  Furthermore, the communication robot includes a history database that records the history of communication behavior executed by the execution unit in association with, for example, the communication target that executed the communication behavior. For this reason, it is possible to execute a communication action suitable for the identified communication target with reference to the history database. For example, for a user who interacts for the first time, he can bow and greet “Mr. XX, nice to meet you”. In addition, there is a fact that the dialogue previously, for a user for the first time dialogue today, with the bow, it is possible to greeting as "○○'s, Hello". In other words, there is no such thing as repeating inappropriate communication behavior.

  The determining unit determines whether or not specific information has been acquired for each communication object recognized by the recognizing unit with reference to the history database. If there is a communication target that is determined not to acquire specific information, the execution means executes a communication action for notifying (presenting) the specific information to at least the communication target. That is, not only communication with a specific user but also communication with other users can be performed.

  On the other hand, when there is no communication target that is determined not to acquire the specific information, the execution means executes a communication action for searching for another communication target. In other words, a new communication object is sought. However, you may make it perform the communication action for alert | reporting other specific information.

  In addition, when the communication means cannot be recognized by the recognition means, that is, when there is no user in the vicinity or surroundings, the execution means executes a communication action for searching for (finding) the communication target.

  According to the present invention, since the communication target is specified based on the tag information, the specification is simple. In addition, since one communication target is specified, the robot can take a communication action suitable for the communication target.

  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, a communication robot (hereinafter, simply referred to as “robot”) 10 of this embodiment is an interaction-oriented communication mainly for the purpose of communicating with a communication target such as a human. It is a robot. However, the communication target may be another communication robot configured similarly to the communication robot 10.

In the vicinity of or around the robot 10 , there are humans or users A, B, and C. The users A, B, and C are RFID tags (hereinafter simply referred to as “tags”) 12, respectively. 14 or 16 is possessed or mounted (owned). Although any tag can be used as the tags 12, 14, and 16, a self-propelled (battery type) tag is used in this embodiment. Therefore, each of the tags 12, 14, and 16 superimposes specific RFID (Radio Frequency Identification) information on a radio wave having a predetermined frequency, and transmits (transmits) it at a constant time interval. However, it may be configured such that radio waves having different frequencies can be transmitted and the tag (user) can be identified by the difference in frequency.

  In this embodiment, the case where there are three users is shown, but it is sufficient that the number of users is one or more.

FIG. 2 is a front view showing the appearance of the robot 10, and the hardware configuration of the robot 10 will be described with reference to FIG. The robot 10 includes a carriage 20, and wheels 22 for autonomously moving the robot 10 are provided on the lower surface of the carriage 20. The wheel 22 is driven by a wheel motor (see FIG. 3: 90), and can move the carriage 20, that is, the robot 10 in any direction, front, back, left, and right.

  Although omitted in FIG. 2, a collision sensor (see FIG. 3: 94) is attached to the front surface of the carriage 20, and this collision sensor 94 detects contact of a person and other obstacles to the carriage 20. . That is, when contact with an obstacle is detected during the movement of the robot 10, the driving of the wheels 22 is immediately stopped to suddenly stop the movement of the robot 10, thereby preventing a collision.

  In this embodiment, the height of the robot 10 is about 100 cm so as not to intimidate people (users), particularly children. However, this height can be changed.

  A polygonal column sensor mounting panel 24 is provided on the carriage 20, and an ultrasonic distance sensor 26 is mounted on each surface of the sensor mounting panel 24. The ultrasonic distance sensor 26 measures the distance from the sensor mounting panel 24, that is, the user mainly around the robot 10.

  Further, on the carriage 20, the lower part is surrounded by the sensor mounting panel 24 so that the body of the robot 10 stands upright. This body is composed of a lower body 28 and an upper body 30, and the lower body 28 and the upper body 30 are connected to each other by a connecting portion 32. Although illustration is omitted, the connecting portion 32 has a built-in lifting mechanism, and the height of the upper body 30, that is, the height of the back of the robot 10 can be changed by using this lifting mechanism. The lifting mechanism is driven by a waist motor (see FIG. 3: 88) as will be described later.

  The height of the robot 10 described above is the height when the upper body 30 is at its lowest position. Therefore, the height of the robot 10 can be 100 cm or more.

  One omnidirectional camera 34 and one microphone 36 are provided in the approximate center of the upper body 30. The omnidirectional camera 34 captures the surroundings of the robot 10 and is distinguished from an eye camera 56 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. The microphone 36 captures ambient sounds, particularly a user's voice that is a communication target.

  Upper arms 40R and 40L are provided on both shoulders of the upper body 30 by shoulder joints 38R and 38L, respectively. The shoulder joints 38R and 38L each have three axes of freedom. That is, the shoulder joint 38R can control the angle of the upper arm 40R around each of the X axis, the Y axis, and the Z axis. The Y axis is an axis parallel to the longitudinal direction (or axis) of the upper arm 40R, and the X axis and the Z axis are orthogonal to the Y axis from different directions. On the other hand, the shoulder joint 38L can control the angle of the upper arm 40L around each of the A axis, the B axis, and the C axis. The B axis is an axis parallel to the longitudinal direction (or axis) of the upper arm 40L, and the A axis and the C axis are axes orthogonal to the B axis 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. The elbow joints 42R and 42L can control the angles of the forearms 44R and 44L around the axes of the W axis and the D axis, respectively.

  In the X axis, Y axis, Z axis, W axis, A axis, B axis, C axis, and D axis that control the displacement of the upper arms 40R and 40L and the forearms 44R and 44L, "0 degrees" is the home position, respectively. In this home position, as shown in FIG. 2, the upper arms 40R and 40L and the forearms 44R and 44L are directed downward.

  Although not shown in the drawings, the shoulder portion including the shoulder joints 38R and 38L of the upper body 30 and the above-mentioned upper arms 40R and 40L and the forearms 44R and 44L are each shown with touch sensors (shown comprehensively in FIG. 3). : 92), and these touch sensors 92 detect whether or not the user has touched each part of the robot 10.

  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 the shape, dimensions, etc. of the robot 10 are set as appropriate, in other embodiments, for example, the upper body 30 includes the front surface, the back surface, the right side surface, the left side surface, the top surface, and the bottom surface, and the right side surface and the left side surface. You may form so that the surface may face diagonally forward. That is, the width of the front surface may be shorter than the width of the back surface, and the shape of the upper body 30 viewed from above may be a trapezoid.

  In such a case, the shoulder joints 38R and 38L are provided on the right side surface and the left side surface via left and right support portions whose surfaces are parallel to the left and right side surfaces, respectively. The rotation range of the upper arm 40R and the upper arm 40L is restricted by the left and right side surfaces or the surface (attachment surface) of the support portion, and the upper arms 40R and 40L do not rotate beyond the attachment surface.

  However, if the inclination angle of the left and right side surfaces, the distance between the B axis and the Y axis, the lengths of the upper arms 40R and 40L, the lengths of the forearms 44R and 44L, etc. are appropriately set, the upper arms 40R and 40L exceed the front. Since it can rotate to the inner side, the arms of the robot 10 can cross forward even if there is no degree of freedom of the arms by the W axis and D axis. Therefore, even when the degree of freedom of arms is small, close communication such as embracing with a person located in front can be performed.

  A head 50 is provided above the center of the upper body 30 via a neck joint 48. The neck joint 48 has a degree of freedom of three axes, and the angle can be controlled around each of the S axis, the T axis, and the U axis. The S-axis is an axis that extends from the neck directly upward (vertically upward), and the T-axis and the U-axis are axes that are orthogonal to the S-axis in different directions. The head 50 is provided with a speaker 52 at a position corresponding to a human mouth. The speaker 52 is used by the robot 10 to communicate with a person around it (sound) including voice (including sound) or voice. However, the speaker 52 may be provided in another part of the robot 10, for example, the trunk.

  The head 50 is provided with eyeball portions 54R and 54L at positions corresponding to the eyes. Eyeball portions 54R and 54L include eye cameras 56R and 56L, respectively. Hereinafter, the right eyeball portion 54R and the left eyeball portion 54L may be collectively referred to as the eyeball portion 54, and the right eye camera 56R and the left eye camera 56L may be collectively referred to as the eye camera 56.

  The eye camera 56 captures the face of the person approaching the robot 10, other parts or objects, and captures a corresponding video signal. As the eye camera 56, a camera similar to the omnidirectional camera 34 described above can be used.

  For example, the eye camera 56 is fixed in the eyeball part 54, and the eyeball part 54 is attached to a predetermined position in the head 50 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 provided with respect to the head 50, the α axis is an axis in a direction toward the top of the head 50, the β axis is orthogonal to the α axis and the front side of the head 50 ( It is an axis in a direction perpendicular to the direction in which the face is facing. In this embodiment, when the head 50 is in 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 50, the tip (front) side of the eyeball part 54 or the eye camera 56 is displaced by rotating the eyeball support part around each of the α axis and the β axis, 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 56, “0 degree” is the home position. At this home position, the camera axis of the eye camera 56 is the head 50, as shown in FIG. The direction of the front side (face) is directed, and the line of sight is in the normal viewing state.

  Further, an antenna 58 is provided that is next to the head 50 and extends from the right shoulder. The antenna 58 receives radio waves on which RFID information (tag information) transmitted from the tags 12, 14, and 16 shown in FIG. 1 is superimposed.

  FIG. 3 is a block diagram showing an electrical configuration of the robot 10. With reference to FIG. 3, the robot 10 includes a CPU 60 that performs overall control. The CPU 60 is also called a microcomputer or a processor, and is connected to the memory 70, the motor control board 72, the sensor input / output board 74 and the audio input / output board 76 via the bus 62.

  Although not shown in the figure, the memory 70 includes a ROM and a RAM, in which a control program for the robot 10 is stored in advance, and voice or voice data to be generated from the speaker 52 when executing the communication action. (Speech synthesis data) and angle data for presenting a predetermined gesture are stored. The RAM is used as a work memory or a buffer memory.

  The motor control board 72 is configured by a DSP, for example, and controls driving of each axis motor such as each arm, head, and eyeball. In other words, the motor control board 72 receives control data from the CPU 60 and controls two angles of the α-axis and β-axis of the right eyeball portion 54R (collectively, “right-eye motor” in FIG. 3). .) Control the rotation angle of 78. Similarly, the motor control board 72 receives control data from the CPU 60, and controls two angles of the α axis and β axis of the left eyeball portion 54L (in FIG. 3, collectively referred to as “left eyeball motor”). Shown) Control the rotation angle of 80.

  The motor control board 72 receives the control data from the CPU 60, and determines the angles of the three motors for controlling the X-axis, Y-axis, and Z-axis angles of the right shoulder joint 38R and the W-axis angle of the right elbow joint 42R. The rotation angle of a total of four motors (one collectively shown as “right arm motor” in FIG. 3) 82 with one motor to be controlled is adjusted. Similarly, the motor control board 72 receives the control data from the CPU 60 and determines the angles of the three motors for controlling the angles of the A-axis, B-axis and C-axis of the left shoulder joint 38L and the D-axis angle of the left elbow joint 42L. The rotation angle of a total of four motors (one collectively shown as “left arm motor” in FIG. 3) 84 including one motor to be controlled is adjusted.

  Further, the motor control board 72 receives control data from the CPU 60 and controls three motors for controlling the angles of the S-axis, T-axis, and U-axis of the head 50 (in FIG. 3, "head motor" collectively). The rotation angle of 86 is controlled. Furthermore, the motor control board 72 receives control data from the CPU 60 and controls the rotation angle of two motors 90 (hereinafter collectively referred to as “wheel motors”) 90 that drive the waist motor 88 and the wheels 22. To do.

  In this embodiment, a motor other than the wheel motor 90 is a stepping motor or a pulse motor in order to simplify the control. However, like the wheel motor 90, a DC motor may be used.

  Similarly, the sensor input / output board 74 is also constituted by a DSP, and takes in signals from each sensor and gives them to the CPU 60. That is, data relating to the reflection time from each of the ultrasonic distance sensors 26 is input to the CPU 60 through the sensor input / output board 74. Further, a video signal from the omnidirectional camera 34 is input to the CPU 60 after being subjected to predetermined processing by the sensor input / output board 74 as required. Similarly, the video signal from the eye camera 56 is also input to the CPU 60. In addition, signals from the plurality of touch sensors described above (collectively indicated as “touch sensor 92” in FIG. 3) are provided to the CPU 60 via the sensor input / output board 74. Further, the signal from the collision sensor 94 described above is also given to the CPU 60 in the same manner.

  Similarly, the voice input / output board 76 is also configured by a DSP, and voice or voice in accordance with voice synthesis data provided from the CPU 60 is output from the speaker 52. Also, the voice input from the microphone 36 is taken into the CPU 60 via the voice input / output board 76.

  The CPU 60 is connected to the communication LAN board 96 and the wireless ID tag device 100 via the bus 62. The communication LAN board 96 is configured by a DSP, gives transmission data sent from the CPU 60 to the wireless communication device 98, and transmits the transmission data from the wireless communication device 98 through a network such as a wireless LAN (not shown). To send to an external computer. The communication LAN board 96 receives data via the wireless communication device 98 and gives the received data to the CPU 60. That is, the communication LAN board 96 and the wireless communication device 98 allow the robot 10 to perform wireless communication with an external computer or the like.

  The wireless ID tag device 100 receives a radio wave superimposed with RFID information transmitted from the tags 12, 14, and 16 shown in FIG. 1 via the antenna 58, amplifies the radio signal, and generates an RFID from the radio signal. The RFID information is demodulated (decoded) and given to the CPU 60, and the radio wave intensity at the antenna 58 when the radio wave superimposed with the RFID information is received is detected and given to the CPU 60. However, the RFID information may be decoded by an external computer and given to the CPU 60.

  As the wireless ID tag device (100) including the tag (12, 14, 16) and the antenna (58) shown in this embodiment, product names “Spider tag” and “Spider” manufactured and sold by RF Code in the United States are used. "readers" can be used respectively.

  Further, in this embodiment, radio waves superimposed with RFID information are transmitted from the tags 12, 14 and 16 and received by the wireless ID tag device 100 via the antenna 58. However, the present invention is not limited to this. Should not. For example, an ultrasonic wave on which RFID information is superimposed can be transmitted from the tags 12, 14, and 16 and received by a receiving device having an ultrasonic sensor. In addition, infrared rays obtained by converting RFID information into infrared signals can be emitted from the tags 12, 14, and 16 and received by a receiving device having an infrared light receiving unit (infrared sensor).

  Further, the CPU 60 is connected to the two databases 102 and 104 via the bus 62. However, these databases may be provided so as to be accessible on an external network. The database 102 is a database for storing user information (hereinafter referred to as “user DB”). In this embodiment, a table of user information as shown in FIG. 4A is recorded. As can be seen from FIG. 4A, the RFID is described in the user information table corresponding to the user name. Therefore, for example, it can be seen that the tag 12 attached to the user A has an RFID of “AAAA”. Such a user DB 102 can be registered in advance by the designer or developer of the robot 10. In addition, when adding a new user, a designer or the like can register the new user or the like in the user DB 102 by operating an external computer. As another example, when the robot 10 has a voice recognition function, the robot 10 and the new user are associated with the user name acquired by communicating such as conversation and the RFID acquired at that time, and the robot 10 10 (strictly speaking, the CPU 60) can also be registered in the user DB 102.

  The database 104 is a history of communication actions performed by the robot 10 for each of the users registered in the user DB 102 (user A, user B, user C,...) Or for all users in the vicinity and surroundings. Is a database (communication action history DB), and records a history information table as shown in FIG. As can be seen from FIG. 4B, the history information table describes the date and time, the content of the communication action, and the RFID in association with each other. Therefore, the example of the first line shown in FIG. 4B shows that the robot 10 executed the communication action 1 for the user C (RFID: CCCC) at 10:20 on January 20, 2003. It is shown. The example of the fifth line shows that the robot 10 executed the communication action 5 for all users (RFID: ZZZZ) in the vicinity or in the vicinity at 15:05 on February 2, 2003. It is shown. For convenience of drawing, the RFID for all users near or around is described as “ZZZ”, but in reality, the RFID corresponding to the users near or around the robot 10 is described. The That is, all RFIDs included in an ID list described later are described.

  In addition, when the robot 10 has a voice recognition function, the contents of communication actions performed by the user on the robot can be recorded in the history. For example, the contents spoken by the user and the video signals from the omnidirectional camera 34 and the eye camera 56 when the user speaks can be stored in the history.

  Further, the content of the communication action is angle data that controls the driving of the motors 78 to 90 and text data corresponding to the voice (voice) output from the speaker 52, but when such information is recorded as history information, Since the amount of data becomes enormous, in practice, identification information (communication ID) assigned corresponding to one communication action (for example, greeting, handshake, hug, information provision, etc.) is recorded.

  Further, in this embodiment, an RFID is recorded in the communication action history DB (hereinafter simply referred to as “history DB”) 104 in association with the date and time and the content of the communication action. However, the user name may be recorded.

  In this embodiment, history information is recorded in chronological order and managed by one table, but history information for each RFID (user) may be managed by a table. In this way, since history information has only to be recorded (added) to a table corresponding to RFID, there is no need to record RFID for each history information.

  For example, when the robot 10 takes (executes) a communication action, the robot 10 recognizes a user that exists in the vicinity of the robot 10 or in the vicinity (periphery), that is, in a range in which the transmission wave of the tag reaches the robot 10 (antenna 58). . That is, the RFID information from the tag is acquired, and the acquired RFID list (ID list) is created. The ID list is shown as in FIG. 4C, and describes the radio field intensity when receiving (acquiring) the RFID information corresponding to the RFID information. For example, the ID list describes the RFID and the radio wave intensity when the RFID information is acquired in the order in which the RFID information is acquired. For example, from the example of the first column shown in FIG. 4C, the RFID “CCCC” Is obtained, and it can be seen that the radio wave intensity at that time was P (dBm).

  When the robot 10 creates the ID list, the robot 10 refers to the ID list and identifies one communication target. In this embodiment, it is determined that the user carrying (attaching) the tag having the strongest radio wave intensity exists at a position (short distance) closest to the robot 10, and the user is specified as a communication target.

  It is also possible to specify a user wearing a tag having the strongest radio wave intensity as the second or third as a communication target, which is a matter determined in advance by the designer or developer. .

  Further, as described above, when RFID information is acquired by ultrasonic waves, a communication target is specified according to the ultrasonic wave intensity (sound wave intensity) in the ultrasonic sensor. In addition, when RFID information is acquired by infrared rays, a communication target is specified according to the infrared ray intensity (light reception intensity) in the infrared sensor.

  When a communication target user is specified, the robot 10 executes communication behavior suitable for the user according to the history information. For example, in this embodiment, it is determined whether or not the identified user is a user who first interacts (communicates).

  If the user is the first user to talk, bow (tilt the head 50 forward and downward) and greet (speak) “Good afternoon” (sound is output from the speaker 52). On the other hand, if the user is not the first user to interact, that is, if the user has interacted before, it is further determined whether or not the user is the first user to interact today.

  Today in the case of a user for the first time dialogue, with the bow, "○○ Hi," utters. On the other hand, if the user has already interacted with today, the robot 10 performs a communication action on the users in the vicinity and the surrounding area. Specifically, it is detected with reference to the history DB 104 whether there is a user who has not acquired specific information (for example, weather forecast) among the users on the ID list.

  When there is a user who has not acquired specific information, for example, the user behaves like calling up to everyone (tilting the head 50 forward and upward) and “Tomorrow is sunny”. Say the information. On the other hand, if there is no user who has not acquired specific information, for example, behave diagonally upward and call out to everyone, and say "I'm free" and select other communication targets. look for. However, when there is no user who has not acquired specific information, the user may behave like calling everyone and speak other specific information (for example, the broadcast time of a sports program). . In this way, communication behavior can be taken not only for the identified user but also for users existing in the vicinity.

  In this embodiment, the weather forecast and the sports program are notified as the specific information, but should not be limited to this. As the specific information, various information such as sports, hobbies, games, and shopping are assumed. Such specific information can be acquired by the robot 10 via a network such as the Internet.

  Further, by adding user-preferred information (hobbies, contents of things of interest, etc.) to the user information, specific information corresponding to the user can be notified.

  Specifically, the CPU 60 shown in FIG. 2 executes communication action processing according to the flowcharts shown in FIGS. As shown in FIG. 5, first, in step S1, it is determined whether there is a stop command. That is, the CPU 60 determines whether there is a stop command from a stop switch (not shown) provided in the robot 10 itself or a stop command from an external computer.

  If “YES” in the step S1, that is, if there is a stop command, it is determined that there is a stop command, and the processing of the communication action is ended as it is. However, when the main power supply of the robot 10 is turned off, the processing is similarly ended. On the other hand, if “NO” in the step S1, that is, if there is no stop command, the tag is detected in a step S3. Specifically, the CPU 60 detects an input from the wireless ID tag device 100.

  In a succeeding step S5, it is determined whether or not a tag is detected. If “NO” in the step S5, that is, if RFID information and radio wave intensity are not acquired from the wireless ID tag device 100, it is determined that no tag is detected, that is, a tag is placed in the vicinity of the robot 10 or in the vicinity thereof. It is determined that the possessed user does not exist, the ID list and the nearest tag ID (RFID) are initialized in step S7, and the process proceeds to step S25.

  On the other hand, if “YES” in the step S5, that is, if RFID information and radio wave intensity are acquired from the wireless ID tag device 100, it is determined that the tag is detected, and the acquired RFID and each RFID are received in a step S9. The ID list as shown in FIG. 4C is created using the radio field intensity at that time. In step S11, the nearest neighbor tag ID is acquired with reference to the ID list. That is, an RFID having a maximum radio field intensity is acquired, and a tag to be communicated, that is, a user is specified.

  Subsequently, in step S13, it is determined whether or not to interact with the user corresponding to the RFID for the first time. Specifically, the CPU 60 refers to the history DB 104 to determine whether or not the RFID exists in the history. If “YES” in the step S13, that is, if the RFID does not exist in the history, it is determined that the user interacts with the user corresponding to the RFID for the first time, the head 50 is turned down in a step S15, and “○ Say hello to (the user name), and go to step S27. Specifically, the CPU 60 calculates the angle data (S-axis 0 degree, T-axis 0 degree, U-axis -45 degrees, X-axis 0 degree, Y-axis 0 degree, Z-axis 0 degree, W-axis 0 degree, A-axis 0 , B-axis 0 degree, C-axis 0 degree, D-axis 0 degree) are sent to the motor control board 72, and voice synthesis data corresponding to “Mr. XX, nice to meet you” is read from the memory 70 and the voice input / output board 76. Then, the head motor 88 (strictly, the motor that controls the U-axis) is driven, and the head 50 is tilted forward and downward. At the same time or almost at the same time, a voice “Nice to meet you” is output from the speaker 52.

  On the other hand, if “NO” in the step S13, that is, if the RFID exists in the history, it is determined that the user corresponding to the RFID has interacted before, and the history DB 104 is referred to in the step S17. Thus, it is determined whether or not to interact with the user corresponding to the RFID for the first time today.

  If “YES” is determined in the step S17, that is, the RFID exists in the history information, but if there is no today's history, it is determined that the user corresponding to the RFID is interacting for the first time today. part of the downward, and greeting as "○○ (the user name) 's, Hello", the process proceeds to step S27.

  Note that the communication behavior in step S19 is the same as the content described in step S15 described above except that the content to be uttered is different, and thus detailed description thereof will be omitted here.

  On the other hand, if “NO” in step S17, that is, if the RFID exists in the history information and there is today's history, it is determined that the user corresponding to the RFID has already interacted with today, and in step S21, It is determined whether or not there is a user who has not heard (acquired) the latest weather forecast (specific information). That is, referring to today's history recorded in the history DB 104, it is determined whether or not an RFID corresponding to a user who has not heard the latest weather forecast exists in the ID list.

  If “YES” in the step S21, that is, if the RFID corresponding to the user who has not heard the latest weather forecast exists in the ID list, the head is turned up in the step S23 and “Tomorrow is sunny”. The weather forecast is notified and the process proceeds to step S27. Specifically, in step S23, the CPU 60 determines the angle data (S axis 0 degree, T axis 0 degree, U axis +45 degrees, X axis 0 degree, Y axis 0 degree, Z axis 0 degree, W axis 0 degree, A-axis 0 degree, B-axis 0 degree, C-axis 0 degree, D-axis 0 degree) are sent to the motor control board 72, and voice synthesis data corresponding to “Tomorrow is sunny” is read from the memory 70 and voice input / The output board 76 is given. Then, the head motor 88 (strictly, the motor that controls the U-axis) is driven, and the head 50 is tilted forward and upward. At the same time or almost the same time, a sound “Tomorrow is fine” is output from the speaker 52.

  On the other hand, if “NO” in the step S21, that is, if the RFID corresponding to the user who has not heard the latest weather forecast does not exist in the ID list, the head is turned up in the step S25, And proceeds to step S27. That is, the communication action in step S25 calls attention to the surroundings and searches for a new communication target. However, if no tag is detected in step S5, that is, if there is no user in the vicinity or surroundings, the communication target is simply searched. Therefore, in such a case, in addition to the communication behavior as described above, it may be possible to further drive the wheel motor 90 to take a behavior that moves the place.

  Note that the communication behavior in step S25 is the same as that described in step S23, except that the content to be uttered is different, so detailed description thereof will be omitted here.

  In step S27, history information about the communication behavior executed in step S15, S19, S23 or S25 is recorded (added) in the history DB 104, and the process returns to step S1. That is, the date and time from the clock circuit (not shown), the communication ID assigned to the executed communication action, and the RFID to be communicated are recorded in the history DB 104.

  According to this embodiment, since the RFID is acquired from the tag and the user is specified, the user can be specified easily.

  Moreover, since the user who exists in the vicinity of the robot and its circumference | surroundings can be recognized separately, the communication action suitable for the user can be performed.

  Furthermore, since the communication behavior history is kept, it is possible to avoid talking to the user again about the contents once spoken to a certain user, and the user is not made uncomfortable or uncomfortable. That is, it is possible to avoid repeating inappropriate communication behavior.

  Note that the processing of communication behavior shown in this embodiment is merely an example, and should not be limited to this. For example, it is also possible to count the number of times of interaction for each user (RFID) to date and execute communication behaviors with the user in different intimacy according to the count. For example, you can greet a certain user with a handshake and say “Mr. XX, long time no see”, and greet other users with a hug and say “Mr. XX, how are you?” . Also, focusing on today alone, you can count the number of interactions, and as the number increases, you can take communication actions such as deepening intimacy or providing different topics (information) .

  In this embodiment, only the case where both the robot behavior (behavior) and the voice are used as the communication action has been described. However, the communication action based on only one of the action and the voice is executed. Also good.

  Further, in this embodiment, specific information such as weather forecast is acquired from the network and provided to the user, but is stored in a storage device (for example, the memory 70) built in the robot 10. Information can also be provided. Specifically, the voice synthesis data of the song is stored in the memory 70 or the like, and the robot 10 can sing the song and teach the song to users in the vicinity or the surrounding area. Also, if you store speech synthesis data for multiple types of songs, you can refer to history information and let a specific user or all users in the vicinity or nearby hear songs you have never heard. Can teach. However, not only songs but also foreign languages (for example, English) words and conversations can be taught.

It is an illustration figure which shows the structure of one Example of this invention. It is a front view which shows the hardware of the robot of the FIG. 1 Example. It is a block diagram which shows the electrical structure of the robot of FIG. 1 Example. It is an illustration figure which shows an example of the content of the database shown in FIG. 3, and an example of ID list. It is a flowchart which shows a part of process of the communication action of CPU shown in FIG. It is a flowchart which shows another part of process of the communication action of CPU shown in FIG.

Explanation of symbols

10 ... Communication robot 12, 14, 16 ... Frequency tag 60 ... CPU
DESCRIPTION OF SYMBOLS 70 ... Memory 72 ... Motor control board 74 ... Sensor input / output board 76 ... Voice input / output board 100 ... Wireless ID receiver 102,104 ... Database

Claims (5)

A communication robot that performs communication behavior by at least one of behavior and voice between a plurality of communication objects having wireless tags having unique tag information,
A tag information database for recording tag information and a communication target having a wireless tag having the tag information in association with each other ;
Acquisition means for acquiring tag information from a wireless tag held by the communication target;
Recognition means for obtaining results in recognizing individual communication target number double that exist in the vicinity or surroundings based, to detect the magnitude of the distance between the communication target of the acquisition unit,
A specifying means for specifying the communication object having the minimum distance as a communication object for executing a communication action from the recognition result of the recognition means ;
The history of the communication behavior, the communication said action has been executed communication target association with history database records, and wherein the communication behavior of history recorded in association with the communication target of the one specified by the specifying means A communication robot comprising execution means for executing a communication action according to the above-described communication target . The wireless tag transmits radio waves,
The acquisition means includes an antenna;
It said detecting means detects the magnitude of said distance depending on the radio wave intensity in the antenna when acquiring the tag information by the acquisition unit, according to claim 1, wherein the communication robot. The wireless tag emits ultrasonic waves,
The acquisition means includes an ultrasonic sensor,
Said detecting means, said detecting the magnitude of said distance depending on the wave intensity in the ultrasonic sensor of claim 1, wherein the communication robot when obtaining the tag information by the acquisition unit. The wireless tag emits infrared rays,
The acquisition means includes an infrared sensor,
Said detecting means, said detecting the magnitude of said distance based on the light intensity in the infrared sensor of claim 1, wherein the communication robot when obtaining the tag information by the acquisition unit. When said unrecognized communication target by the recognition means, said execution means executes the communication behavior to look for communication target, the communication robot according to any one of claims 1 to 4.

Images