JP2008044105A - Robot and control method therefor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a robot having morphology close to an actual pet for a user. <P>SOLUTION: The robot is equipped with a sound determination part for determining whether or not the input sound corresponds to the predetermined sound, a sound direction specifying part for specifying the direction of the sound, and an image pickup part for imaging the direction of the sound on the condition that the input sound corresponds to the predetermined sound. The robot is equipped with the number of times of an image pickup determination part for determining whether or not the number of times of an image pickup that the image pickup part picks up image in a predetermined period of time reaches the predetermined allowable number of times. The image pickup part performs the image pickup on the condition that the number of times of imaging pickup does not reach the allowable number of times. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a robot and a control method thereof. In particular, the present invention relates to a robot that handles images and a control method thereof.

  Conventionally, a pet robot disclosed in, for example, Japanese Patent Application Laid-Open No. 11-126017 is known. The pet robot has an operation unit having a plurality of buttons. Different concepts such as “speak” and “praise” are assigned to the buttons of the operation unit. When the user presses the button, the robot performs an action corresponding to the concept assigned to the pressed button. For example, if the assigned concept is “barking”, an audio signal corresponding to the cry is output from the speaker simultaneously with moving the mouth of the robot. As a result, the invention disclosed in Japanese Patent Application Laid-Open No. 11-126017 intends to provide the pet robot closer to a pet that is actually alive.

  However, pets such as dogs and cats that actually live do not communicate with their owners via operation buttons or the like. A pet that is actually alive communicates with the owner, for example, by receiving food from the owner or by handing out something that is important to them. In other words, a pet that is actually alive communicates with the owner by exchanging something with the owner.

  Accordingly, an object of the present invention is to provide a robot that communicates with a user in a form closer to a form in which a real pet communicates with a human and a control method thereof. This object is achieved by a combination of features described in the independent claims. The dependent claims define further advantageous specific examples of the present invention.

  That is, the robot according to the first aspect of the present invention includes a print receiving unit that receives a print from a user, a print determination unit that determines whether there is a predetermined storage target image in the print, and a memory that stores the print. And a storage unit for storing the storage target image when there is a target image.

  Preferably, the robot further includes a storage unit capable of storing prints, and the print receiving unit stores a print having a storage target image in the storage unit, and ejects the print without the storage target image from the robot. The storage target image is preferably an image relating to a human face. Moreover, it is preferable that the robot further includes an operation control unit that moves the robot in a direction in which a person corresponding to the storage target image stored in the storage unit is present.

  The robot according to the first aspect of the present invention may further include an operation control unit that directs the robot in a direction different from the direction in which another person does not correspond to the storage target image stored in the storage unit. In this case, the motion control unit preferably moves the robot in a direction away from others. The robot may further include an imaging unit that captures another person who does not correspond to the storage target image stored in the storage unit. Furthermore, the robot may further include an operation control unit that moves the robot to a position away from another person by a predetermined distance, and the imaging unit may image the other person after the movement. Furthermore, the robot may further include an acoustic unit that generates a sound that alerts another person after moving and before imaging. Further, in this robot, the operation control unit moves the robot in a direction where there is an acquaintance corresponding to the storage target image stored in the storage unit, and prints another person's image after moving in the direction where the acquaintance exists. And may further be provided.

  The robot according to the first aspect of the present invention is an image capturing unit that captures an image of a person in the surroundings, and whether or not the person captured by the image capturing unit corresponds to a storage target image stored in the storage unit. It is preferable to further include a facial expression changing unit that changes the facial expression of the robot based on the above.

  A robot according to a second aspect of the present invention prints an image captured by an imaging unit, an imaging condition switching unit that switches an imaging condition of the imaging unit according to the frequency of communication with a user, and an image captured by the imaging unit. A printing unit. The imaging condition switching unit preferably specifies the number of communication by the number of times the user touches the robot. The imaging condition switching unit preferably switches the imaging condition so that the imaging unit captures an image that is not in focus on the subject on condition that the frequency is equal to or less than a predetermined reference value.

  A robot according to a third aspect of the present invention includes a voice determination unit that determines whether or not an input voice corresponds to a predetermined voice, a voice direction specification unit that specifies a direction in which the voice is played, and an input And an imaging unit that captures an image of a direction in which the sound is made on condition that the generated sound corresponds to a predetermined sound. The robot further includes an imaging number determination unit that determines whether or not the number of imagings performed by the imaging unit within a predetermined period has reached a predetermined allowable number. Imaging is preferably performed on condition that the number of times of imaging does not reach the allowable number. Further, this robot is based on a volume determination unit that determines whether or not the volume of the input voice exceeds a predetermined reference value, and the allowable number of times and the number of times that the volume exceeds the reference value within a period. It is preferable that the camera further includes a reference value setting unit that resets the reference value, and the imaging unit performs imaging on the condition that the volume exceeds the reference value.

  According to a fourth aspect of the present invention, there is provided a robot control method comprising: a print receiving stage for receiving a print from a user; a print determination stage for determining whether or not the print has a predetermined storage target image; A storage stage for storing the storage target image when there is a target image.

  The robot control method according to the fifth aspect of the present invention includes an imaging stage for imaging a subject, an imaging condition switching stage for switching imaging conditions in the imaging stage according to the frequency of communication with the user, and imaging at the imaging stage. A printing stage for printing an image.

  The robot control method according to the sixth aspect of the present invention includes a voice determination stage for determining whether or not an input voice corresponds to a predetermined voice, and a voice direction specification stage for specifying the direction of the voice. And an imaging stage for imaging the direction of the sound on condition that the input sound corresponds to a predetermined sound.

  The above summary of the invention does not enumerate all the necessary features of the present invention, and sub-combinations of these feature groups can also be the invention.

  Hereinafter, the present invention will be described through embodiments of the invention. However, the following embodiments do not limit the claimed invention, and all combinations of features described in the embodiments are the solution of the invention. It is not always essential to the means.

  FIG. 1 is a functional block diagram showing functions of a robot 100 according to an embodiment of the present invention. The robot 100 is, for example, a pet-type robot that has an outer shape of a dog and moves while walking with four legs. The robot 100 includes a print receiving unit 112 that receives a print from a user, a print determination unit 124 that determines whether or not the print received by the print receiving unit 112 has a predetermined storage target image, and a storage target in the print. When there is an image, the storage unit 126 stores the storage target image. Note that the storage target image of the present embodiment is a human face image.

  The robot 100 further includes a storage unit 114 that can store prints and an imaging unit 104 that captures an image of a subject. The imaging unit 104 is, for example, a CCD camera provided on the robot head. The robot 100 further includes a print unit 116 that can print an image captured by the image capturing unit 104 and an image capturing unit that captures, for example, an image that is in focus on the subject or an image that is not in focus on the subject. An imaging condition switching unit 102 that switches 104 imaging conditions is included.

  Further, the robot 100 does not correspond to the direction in which there is a person corresponding to the storage target image stored in the storage unit 120 (hereinafter referred to as “acquaintance”) or to the storage target image stored in the storage unit 120. An operation control unit 128 that moves the robot 100 in a direction away from a person (hereinafter referred to as “another person”) is provided. In addition, the robot 100 includes an acoustic unit 130 that generates a sound such as a dog's cry and a facial expression changing unit 132 that changes the facial expression of the robot, based on the control of the operation control unit 128, respectively.

  Furthermore, the robot 100 has three microphones 134, 136, and 138 that are directed in different directions and draw ambient sounds (hereinafter referred to as “ambient sounds”). In addition, the robot 100 includes a volume determination unit 122 that determines whether or not the volume of the surrounding sound exceeds a predetermined reference value (hereinafter referred to as “volume reference value”) such as 65 phones, and the surrounding sound is, for example, And a voice determination unit 120 that determines whether or not it corresponds to a predetermined voice such as a laughter (hereinafter referred to as “set voice”). In addition, the robot 100 determines whether or not the number of times that the imaging unit 104 has taken an image within a predetermined period (hereinafter referred to as “reference period”) has reached a predetermined allowable number. A number determination unit 108 is included. In the present embodiment, the reference period is, for example, one week from Monday to Sunday, and the allowable number is, for example, 20 times.

  The robot 100 further includes a voice direction specifying unit 118 that specifies the direction in which the surrounding voice is played (hereinafter referred to as “voice direction”). The audio direction specifying unit 118 specifies the audio direction based on, for example, the volume difference between the surrounding sounds picked up by the microphones 134, 136, and 138 and the direction in which each of the microphones 134, 136, and 138 is directed. . The robot 100 also includes an imaging direction adjustment unit 184 that adjusts the orientation of the imaging unit 104 so that the imaging direction matches the audio direction obtained by the audio direction identification unit 118. In the present embodiment, the imaging direction adjustment unit 184 adjusts the imaging direction of the imaging unit 104 by changing the orientation of the head of the robot 100. In addition to the above, the robot 100 includes a reference value setting unit 110 that resets the sound volume reference value and the allowable number of times based on the number of times the sound volume exceeds the reference value within the reference period.

  FIG. 2 is a functional block diagram illustrating functions of the print receiving unit 112. The print receiving unit 112 receives and holds a print provided from the user, and a print holding unit 152 that discharges the held print to the outside of the robot 100 when a command is received from the print determination unit 124. Have. The print receiving unit 112 includes an image reading unit 150 that reads a print image held by the print holding unit 152. The image reading unit 150 is, for example, an image scanner or a CCD camera. The image reading unit 150 sends the read image to the print determination unit 124. The print receiving unit 112 further includes a transport unit 154 that transports the print held by the print holding unit 152 to the storage unit 114.

  Note that the print receiving unit 112 is preferably provided in a portion corresponding to the mouth of the robot 100, for example, and preferably receives a print inserted by the user into the mouth. In this way, the user can obtain a feeling given to the robot 100 using the print as a bait. For example, when the print is output from the mouth of the robot 100 as a result of the print holding unit 152 discharging the print, the user can feel that the robot 100 has discharged the print from the mouth unfavorably. If the print is stored in the storage unit 114 without being discharged, the user can feel that the robot 100 has swallowed the print.

  FIG. 3 is a functional block diagram illustrating functions of the operation control unit 128. The operation control unit 128 compares the image of the person captured by the imaging unit 104 with the storage target image stored in the storage unit 126 to determine whether the captured person is an acquaintance or another person. A determination unit 160 is included. Further, the operation control unit 128 includes a distance measuring unit 162 that measures the distance between the person imaged by the imaging unit 104 and the robot 100. The distance measuring unit 162 measures a distance to a person who has been imaged using, for example, an automatic focus adjustment function of the imaging unit 104. The motion control unit 128 further includes a movement control unit 164 that moves the robot 100 by controlling, for example, the motion of the foot of the robot 100 based on the determination of the image determination unit 160 and the measurement result of the distance measurement unit 162.

  FIG. 4 is a functional block diagram illustrating functions of the imaging condition switching unit 102. The imaging condition switching unit 102 includes a contact sensor 1170 that detects that the user has touched the robot 100. The contact sensor 170 is, for example, a capacitive touch sensor. In the present embodiment, the contact sensor 170 is provided on the head of the robot 100 and detects that the user has stroked the head of the robot 100. The imaging condition switching unit 102 further performs imaging based on the contact frequency calculating unit 172 that calculates the contact frequency of the user touching the robot 100 based on the output of the contact sensor 170 and the contact frequency obtained by the contact frequency calculating unit 172. An imaging condition setting unit 174 that sets the imaging conditions of the unit 104.

  FIG. 5 is a flowchart showing the operation of the robot 100. In the present embodiment, the robot 100 executes a print receiving process (S100) for receiving a print from a user and a movement control process (S102) for the imaging unit 104 to approach or leave the person who has taken the image. . In addition, the robot 100 performs voice direction imaging processing (S104) for capturing an image in the direction in which the voice corresponding to the set voice is heard, and imaging condition switching processing (S106) for switching the imaging conditions of the imaging unit 104. Execute. The robot 100 repeats the above four processes until the main power is turned off (S108). The order in which the four processes are performed is arbitrary and is not limited to the order shown.

  FIG. 6 is a flowchart showing the contents of the print receiving process (S100). In the print receiving process, first, the print holding unit 152 receives and holds a print provided by the user (S120). Next, the image reading unit 150 reads a print image (S122). Next, the print determination unit 124 determines whether or not a storage target image is included in the read image (S124). As described above, in the present embodiment, the storage target image is a human face image. For example, the print determination unit 124 determines whether or not the read image includes a region having the same hue as the human skin color and whether there is an image corresponding to the human eye in the region. Do.

  When there is a storage target image in the read image, the print determination unit 124 stores the storage target image, that is, an image of a human face in the storage unit 126 (S124: Y, S126). In addition, the print determination unit 124 moves the print received by the print transport unit 154 from the print holding unit 152 to the storage unit 114 (S128). On the other hand, if the print determination unit 124 determines that there is no image to be stored in S124, the print determination unit 124 causes the print holding unit 152 to discharge the print to the outside of the robot 100 (S124: N). , S130). When the process of S128 or S130 ends, the print receiving process ends.

  FIG. 7 is a flowchart showing the contents of the movement control process (S102). In the movement control process, the imaging unit 104 captures an image around the robot 100 and sends the captured image to the operation control unit 128 (S140). In the operation control unit 128, the image determination unit 160 determines whether there is a person in the sent image (S142). If there is no person, the robot 100 ends the movement control process (S142: N). When there is a person, the image determination unit 160 compares the person's image with the storage target image stored in the storage unit 120 to determine whether the imaged person is an acquaintance (S142: Y , S144). The image determination unit 160 determines that the imaged person is an acquaintance when the face of the person imaged within a predetermined error range matches the storage target image (S144: Y), and does not match. In this case, it is determined that the person is another person (S144: N).

  In S144, when the image determination unit 160 determines that the imaged person is another person, the facial expression changing unit 132 next changes the facial expression of the robot 100 to a warning expression (S146). In the present embodiment, the facial expression changing unit 132 changes the facial expression of the robot to a warning expression by, for example, raising the robot's ear. Next, the movement control unit 164 retracts the robot 100 from the other person being photographed (S148). As a result, the robot 100 moves in a direction away from the other person while keeping its face in the direction of the other person. The movement control unit 164 moves the robot 100 backward until the distance to the other person measured by the distance measuring unit 162 reaches a predetermined distance (S150). Here, the predetermined distance is, for example, a distance that allows the imaging unit 104 to capture the whole body of another person.

  When the robot 100 retreats from another person by a predetermined distance, the sound unit 130 then generates a sound (S152). The generated sound is a sound for calling attention of the other person who heard it and turning the other person toward the imaging unit 104. In the present embodiment, the acoustic unit 130 generates a dog bark. After the sound is generated, the imaging unit 104 captures a still image in the direction where another person is present (S154). Further, after imaging, the movement control unit 164 changes the direction of the robot in a direction different from the direction in which another person is present (S156). Thus, the robot 100 can express that the robot 100 does not have an intimate feeling with respect to other people by retreating from another person or changing the direction.

  If the image determination unit 150 determines in S144 that the imaged person is an acquaintance, then the facial expression changing unit 132 changes the facial expression of the robot 100 to an compliant expression (S158). In the case of the present embodiment, the facial expression changing unit 132 creates a submissive facial expression by laying the ears of the robot. Next, the movement control unit 164 moves the robot 100 toward the acquaintance being imaged (S160). The movement control unit 164 moves the robot 100 toward the acquaintance until the distance to the acquaintance measured by the distance measuring unit 162 reaches a predetermined distance, for example, 50 cm (S162).

  Next, the printing unit 116 prints the image captured by the imaging unit 104 and provides it to an acquaintance (S164). The image to be printed includes the other person's image captured by the image capturing unit 104 in S154 and the sound direction image captured by the image capturing unit 104 in the sound direction image capturing process described later. When the process of S156 or S164 ends, the movement control process ends.

  FIG. 8 is a flowchart showing the contents of the voice direction imaging process (S104). In the sound direction imaging process, first, the sound volume determination unit 122 determines whether or not the sound volume of surrounding sounds acquired by the microphones 134, 136, and 138 exceeds the sound volume reference value (S180). When the sound volume determination unit 122 determines that the sound volume of the surrounding sound does not exceed the sound volume reference value, the sound direction imaging process ends (S180: N). On the other hand, when the sound volume determination unit 122 determines that the sound volume of the surrounding sound exceeds the sound volume reference value, the sound determination unit 120 next determines whether or not the sound is compatible with the set sound (S180: Y, S182). . In the present embodiment, the sound determination unit 120 obtains the frequency spectrum of the surrounding sound, and determines that the surrounding sound corresponds to the set sound when the obtained frequency spectrum includes a spectrum indicating a human laughing voice.

  If the sound determination unit 120 determines in S182 that the surrounding sound does not correspond to the set sound, the sound direction imaging process ends (S182: N). On the other hand, when the sound determination unit 120 determines that the surrounding sound corresponds to the set sound, the imaging number determination unit 108 determines whether or not the number of imagings within the reference period has reached the allowable number (S182). : Y, S184). If the number of times of imaging has not reached the allowable number, the voice direction specifying unit 118 next specifies the voice direction based on the outputs of the microphones 134, 136, and 138 (S184: N, S186). Further, the imaging direction adjusting unit 106 matches the imaging direction of the imaging unit 104 with the audio direction specified by the audio direction specifying unit 118 (S188). Next, the imaging unit 104 captures a still image (S190). Thereby, in the case of this embodiment, the image of the direction which made the laughing voice is image | photographed. When the process of S190 ends, the voice direction imaging process ends.

  On the other hand, when the imaging number determination unit 108 determines in S184 that the imaging number has reached the allowable number, the reference value setting unit 110 causes the surrounding audio corresponding to the set audio to exceed the volume reference value within the reference period. The excess number that is the difference between the number of times and the allowable number is obtained, and it is determined whether or not the excess number exceeds a predetermined threshold value (S184: Y, S192). If the excess number does not exceed the threshold value, the voice direction imaging process ends (S192: N). On the other hand, when the excess number exceeds the threshold value, the reference value setting unit 110 resets the volume reference value to a value higher by 5 phones, for example, or the allowable number of times to a value higher by 5 times, for example (S192: Y, S194). When the process of S194 ends, the voice direction imaging process ends.

  FIG. 9 is a flowchart showing the contents of the imaging condition switching process (S106). In the imaging condition switching process, the contact frequency calculation unit 162 obtains the contact frequency every time the user touches the contact sensor (S210, S212). In the present embodiment, the contact frequency calculation unit 162 obtains, for example, the number of times the user has touched the contact sensor in the past week as the contact frequency. On the other hand, the imaging condition setting unit 164 periodically determines, for example, whether or not the contact frequency calculated by the contact frequency calculation unit 162 at a predetermined time once a day exceeds a predetermined value ( S214, S216). When the contact frequency exceeds the specified value, that is, when the number of times the user communicates with the robot 100 is large, the imaging condition setting unit 164 sets the imaging condition of the imaging unit 104 as the first condition. (S216: Y, S218). In the present embodiment, the imaging unit 104 set as the first imaging condition images a subject with a sharp focus and an appropriate exposure condition.

  On the other hand, when the contact frequency is equal to or less than the predetermined value, that is, when communication between the user and the robot 100 is insufficient, the imaging condition setting unit 164 sets the imaging condition of the imaging unit 104 to the second condition. (S216: N, S220). In the present embodiment, the camera 182 set to the second imaging condition captures an image that is not in focus on the subject and underexposed or overexposed. In this way, by switching the shooting conditions of the camera 182 based on the contact frequency, the robot 100 is satisfied with sufficient communication with the user, or because communication with the user is insufficient. We express whether we are dissatisfied in the image quality of the captured image.

  As mentioned above, although this invention was demonstrated using embodiment, the technical scope of this invention is not limited to the range as described in the said embodiment. Various changes or improvements can be added to the above embodiment. It is apparent from the description of the scope of claims that embodiments with such changes or improvements can be included in the technical scope of the present invention.

  As is clear from the above description, according to the present invention, a robot that communicates with the user by exchanging an object called a print is provided, and thus a robot closer to a real pet form is provided for the user. it can.

It is a functional block diagram which shows the function of the robot 100 which concerns on one Embodiment of this invention. 3 is a functional block diagram illustrating functions of a print receiving unit 112. FIG. 3 is a functional block diagram illustrating functions of an operation control unit 128. FIG. 3 is a functional block diagram illustrating functions of an imaging condition switching unit 102. FIG. 3 is a flowchart showing the operation of the robot 100. It is a flowchart which shows the content of a print reception process (S100). It is a flowchart which shows the content of a movement control process (S102). It is a flowchart which shows the content of an audio | voice direction imaging process (S104). It is a flowchart which shows the content of an imaging condition switching process (S106).

Explanation of symbols

DESCRIPTION OF SYMBOLS 102 Imaging condition switching part 104 Imaging part 106 Imaging direction adjustment part 108 Imaging frequency determination part 110 Reference value setting part 112 Print receiving part 114 Storage part 116 Printing part 118 Voice direction specification part 120 Voice determination part 122 Volume determination part 124 Print determination part 126 Storage Unit 128 Operation Control Unit 130 Sound Unit 132 Facial Expression Change Unit

Claims (4)

A sound determination unit that determines whether or not the input sound corresponds to a predetermined sound;
A voice direction identifying unit that identifies a direction in which the voice is played;
A robot, comprising: an imaging unit that captures an image of a direction of the voice on condition that the input voice corresponds to the predetermined voice. An imaging number determination unit that determines whether or not the number of times the imaging unit has performed an imaging within a predetermined period has reached a predetermined allowable number;
The robot according to claim 1, wherein the imaging unit performs the imaging on the condition that the number of times of imaging does not reach the allowable number of times. A volume determination unit for determining whether the volume of the input voice exceeds a predetermined reference value;
A reference value setting unit for resetting the reference value based on the allowable number of times and the number of times the volume exceeds the reference value within the period;
The robot according to claim 2, wherein the imaging unit performs the imaging on the condition that the volume exceeds the reference value. A sound determination step for determining whether or not the input sound corresponds to a predetermined sound; and
A voice direction specifying step for specifying a direction of the voice;
A robot control method comprising: an imaging step of imaging a direction of the voice on condition that the input voice corresponds to the predetermined voice.

Images