JP2004283927A - Robot control device, and method, recording medium and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve the recognizing precision of a voice recognition device of a robot by recognizing a voice after confirming the existence of a user when the voice recognition device installed on the robot recognizes the voice of a recognizing object such as the user, etc. <P>SOLUTION: A voice recognizing part 101A outputs a voice signal detected by microphones 82-1 to 82-N to a behavior deciding mechanism 103. A direction recognizing part 101B outputs the direction of a sound source to the behavior deciding mechanism 103 by detecting it in accordance with the voice signal detected by the microphones 82-1 to 82-N. The behavior deciding mechanism 103 controls an attitude transition mechanism 104 so as to take looking-back action in the direction of the sound source. A picture image recognizing part 101D reports to a control part 101a that it detects the face of the user when the picture image recognizing part 101D detects the face of the user in accordance with a picture image signal input by CCD cameras 81L, R after taking the looking-back action. The control part 101a starts a voice recognizing process by controlling the voice recognizing part 101A. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a robot control device and method, a recording medium, and a program, and more particularly, to performing voice recognition processing, by performing voice recognition processing after confirming the presence of a user, thereby erroneously detecting voice due to noise. TECHNICAL FIELD The present invention relates to a robot control device and method, a recording medium, and a program capable of suppressing an error based on a robot.
[0002]
[Prior art]
In recent years, robots having a recognition function such as a voice recognition device (including stuffed toys in the present specification) have been commercialized as toys and the like. For example, a robot equipped with a voice recognition device performs voice recognition of a voice uttered by a user, and performs an action such as performing a certain gesture or outputting a synthesized sound based on the voice recognition result. Has been done.
[0003]
When a robot equipped with a voice recognition device recognizes a voice uttered by a user, if the user uttering the voice is too far away from the robot, the voice of the user acquired by a microphone mounted on the robot is used. The signal value of the speech waveform thus attenuated and the noise level becomes relatively high. That is, the S / N ratio (Signal to Noise ratio) of the user's voice signal acquired by the microphone is low. In general, as the distance between the user (speaker) and the robot (the microphone attached to the robot) increases, the waveform of the audio signal is more affected by the reverberation characteristics. Therefore, when the distance between the user and the robot is too large, the recognition accuracy of the voice recognition device of the robot deteriorates.
[0004]
Conversely, when the distance between the user and the robot is too short, the signal value of the voice waveform emitted by the user obtained by the microphone mounted on the robot exceeds the detectable range of the microphone. Therefore, the sound waveform acquired by the microphone becomes saturated and becomes a waveform distorted from the original sound waveform. If the distance between the user and the robot is too short, the voice recognition device of the robot performs voice recognition of such a distorted waveform, and the accuracy of voice recognition deteriorates.
[0005]
Therefore, along with the speech recognition result, ambient noise detection that detects the effect of ambient noise, power shortage detection that detects the situation where the power of the input voice satisfies a specific threshold condition, and power excess detection are performed, and the speech recognition result is obtained. A method has been proposed for addressing the problem of voice recognition accuracy deterioration in a robot using the result of the situation detection and the situation detection (for example, see Non-Patent Document 1).
[0006]
[Non-patent document 1]
Iwasawa, Onaka, Fujita, "A Method of Speech Recognition Interface for Robots Using Situation Detection and Its Evaluation," Research Papers of the Japanese Society for Artificial Intelligence, Japan Society for Artificial Intelligence, November 2002, p. 33-38
[0007]
Furthermore, the operation sound of the robot itself has a great adverse effect on the accuracy of voice recognition because the noise source is close to the microphone. For example, when a robot having both hands moves a hand near a microphone and moves a finger or the like, very large noise is input to the microphone. Also, when a bipedal walking robot walks on a hard floor surface, the sound of the feet touching the floor surface becomes loud, and large noise may be input to the microphone.
[0008]
[Problems to be solved by the invention]
However, the method disclosed in Non-Patent Document 1 does not consider noise generated by the robot itself. Therefore, for example, even though the user is not talking to the robot, the robot may detect the noise generated by the robot as voice, acquire an incorrect voice recognition result, and perform an incorrect operation. there were. For this reason, even though the user is not talking to the robot, the robot may perform a mysterious operation or generate a mysterious voice. Furthermore, even when there is no user in the vicinity, there is a risk of operating as if there is a user in the vicinity.
[0009]
The present invention has been made in view of such a situation, and for example, when a voice recognition device mounted on a robot recognizes a voice to be recognized, such as a user, after confirming the presence of the user By recognizing the voice, the recognition accuracy of the voice recognition device of the robot is improved.
[0010]
[Means for Solving the Problems]
The robot control device according to the present invention includes a voice detection unit that detects a voice, a voice recognition unit that recognizes the voice detected by the voice detection unit, a direction detection unit that detects a direction of a sound source of the voice, and a direction detection unit. User detection means for detecting a user in the detected direction; and voice recognition control means for controlling to start voice recognition by the voice recognition means when the user is detected by the user detection means. Features.
[0011]
An image pickup means for picking up an image and an image pickup control means for controlling the image pickup means so as to pick up an image in the direction detected by the direction detection means may be further provided, and the image pickup means is controlled by the image pickup control means. In the case where the image is captured in the direction detected by the direction detection unit, the user detection unit may detect the user based on whether or not the image of the user is captured in the video imaged by the imaging unit. it can.
[0012]
When the imaging control unit controls the imaging unit to capture an image in the direction detected by the direction detection unit, the image captured by the imaging unit is based on the frequency of whether or not the user's face is captured. And a reliability detection means for detecting the reliability for each direction, wherein the imaging control means includes a user detected by the reliability detection means in the direction detected by the direction detection means. It is possible to control the imaging means to image the direction based on the reliability of detecting the face.
[0013]
A robot control method according to the present invention includes a voice detection step of detecting a voice, a voice recognition step of recognizing a voice detected in the processing of the voice detection step, a direction detection step of detecting a direction of a sound source of the voice, and a direction detection. A user detection step of detecting a user in the direction detected in the step processing, and control is performed such that when a user is detected in the processing of the user detection step, voice recognition in the processing of the voice recognition step is started. And a voice recognition control step.
[0014]
The program of the recording medium of the present invention includes a voice detection step of detecting voice, a voice recognition step of recognizing the voice detected in the processing of the voice detection step, a direction detection step of detecting a direction of a sound source of the voice, A user detection step for detecting a user in the direction detected in the detection step processing, and control to start speech recognition in the speech recognition step processing when a user is detected in the user detection step processing. And performing a voice recognition control step.
[0015]
The program of the present invention includes a voice detection step of detecting voice, a voice recognition step of recognizing the voice detected in the processing of the voice detection step, a direction detection step of detecting a direction of a sound source of the voice, and a direction detection step. A user detection step of detecting a user in the direction detected by the processing; and voice recognition for controlling to start voice recognition in the processing of the voice recognition step when a user is detected in the processing of the user detection step. A process including a control step is executed by a computer.
[0016]
In the robot control device and method and the program according to the present invention, a voice is detected, the detected voice is recognized, a direction of a sound source of the voice is detected, and a user is detected in the detected direction. If detected, speech recognition is started.
[0017]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, embodiments of the present invention will be described, but before that, in order to clarify the correspondence between each means of the invention described in the claims and the following embodiments, parentheses after each means are described. When the features of the present invention are described by adding a corresponding embodiment (however, an example), the following is obtained.
[0018]
That is, the robot control device of the present invention includes a voice detection unit (for example, the microphones 82-1 to 82-N in FIG. 7) for detecting voice and a voice recognition unit (for example, for recognizing the voice detected by the voice detection unit). 7, a voice recognition unit 101A in FIG. 7, a direction detection unit for detecting the direction of the sound source of the voice (for example, the direction recognition unit 101B in FIG. 7), and a user is detected in the direction detected by the direction detection unit. A user detection unit (for example, the image recognition unit 101D in FIG. 7) and a voice recognition control unit (for example, FIG. 7) for controlling the start of voice recognition by the voice recognition unit when a user is detected by the user detection unit. Control section 101a).
[0019]
Of course, this description does not mean that each means is limited to those described above.
[0020]
FIG. 1 is a schematic perspective view of an exterior showing a configuration of an embodiment of a bipedal walking type robot 1 to which the present invention is applied. The robot 1 is a practical robot that supports human activities in various situations in a living environment and other everyday life, and can act according to internal states (anger, sadness, joy, enjoyment, etc.), and can perform basic operations performed by humans. Behavior can be expressed.
[0021]
As shown in FIG. 1, the robot 1 has a head exterior unit 3 connected to a predetermined position of a trunk exterior unit 2 and two left and right arm exterior units 4R / L (Right / Left: right arm / right arm). (Left arm) and two left and right leg exterior units 5R / L.
[0022]
Next, an internal configuration of the robot 1 will be described with reference to FIG. FIG. 2 shows the internal structure of the exterior parts shown in FIG.
[0023]
FIG. 2 is a perspective view of the inside of the robot 1 in the front direction, and FIG. 3 is a perspective view of the inside of the robot 1 from the back direction. FIG. 4 is a perspective view for describing a shaft configuration of the robot 1.
[0024]
In the robot 1, the head unit 12 is disposed above the torso unit 11, and the arm units 13A and 13B having the same configuration are attached to predetermined positions on the left and right of the upper part of the torso unit 11, respectively. Further, leg units 14A and 14B having the same configuration are attached to predetermined positions on the lower left and right of the body unit 11, respectively. The head unit 12 is provided with a touch sensor 51 and a display unit 55.
[0025]
In the torso unit 11, the frame 21 forming the upper trunk and the waist base 22 forming the lower trunk are connected to each other via a waist joint mechanism 23, and the lower base 22 of the lower trunk is formed. By independently driving the actuators A1 and A2 of the waist joint mechanism 23 fixed to the upper body, the upper trunk is independently rotated around the orthogonal roll axis 24 and pitch axis 25 shown in FIG. It has been made possible.
[0026]
The head unit 12 is attached to the center of the upper surface of a shoulder base 26 fixed to the upper end of the frame 21 via a neck joint mechanism 27. By driving the actuators A3 and A4 of the neck joint mechanism 27, respectively. 4 can be independently rotated around a pitch axis 28 and a yaw axis 29 which are orthogonal to each other.
[0027]
Further, the arm units 13A and 13B are attached to the left and right of the shoulder base 26 via the shoulder joint mechanism 30, respectively, and by driving the actuators A5 and A6 of the corresponding shoulder joint mechanism 30, respectively, as shown in FIG. Each of them can be independently rotated around the orthogonal pitch axis 31 and roll axis 32 shown in the figure.
[0028]
In the arm units 13A and 13B, the actuator A8 forming the forearm is connected to the output shaft of the actuator A7 forming the upper arm via the elbow joint mechanism 33, and the hand 34 is attached to the tip of the forearm. It is constituted by.
[0029]
In the arm units 13A and 13B, the forearm can be rotated with respect to the yaw axis 35 shown in FIG. 4 by driving the actuator A7, and the forearm can be rotated in FIG. It can be rotated with respect to the pitch axis 36 shown.
[0030]
The leg units 14A and 14B are respectively attached to the hip base 22 below the trunk via the hip joint mechanism 37, and by driving the actuators A9 to A11 of the corresponding hip joint mechanism 37, respectively, as shown in FIG. , The yaw axis 38, the roll axis 39, and the pitch axis 40, which are orthogonal to each other, can be independently rotated.
[0031]
In the leg units 14A and 14B, the lower end of the frame 41 forming the thigh is connected to the frame 43 forming the lower leg via the knee joint mechanism 42, and the lower end of the frame 43 is connected to the ankle joint. It is configured by being connected to a foot 45 via a mechanism 44.
[0032]
Thus, in the leg units 14A and 14B, by driving the actuator A12 forming the knee joint mechanism 42, the lower leg can be rotated with respect to the pitch axis 46 shown in FIG. By driving the actuators A13 and A14 of the mechanism 44, respectively, the feet 45 can be independently rotated with respect to the orthogonal pitch axis 47 and roll axis 48 shown in FIG.
[0033]
On the back side of the waist base 22, which forms the lower trunk of the body unit 11, a control unit 52, which is a box containing a main control unit 61 and a peripheral circuit 62 (both shown in FIG. 5) described later, is provided. It is arranged.
[0034]
FIG. 5 shows a configuration example of an actuator of the robot 1 and a control system thereof.
[0035]
The control unit 52 contains a main control unit 61 for controlling the operation of the entire robot 1, peripheral circuits 62 such as a power supply circuit and a communication circuit, a battery 74 (FIG. 6), and the like.
[0036]
The control unit 52 includes sub-control units 63A to 63D provided in each of the constituent units (the body unit 11, the head unit 12, the arm units 13A and 13B, and the leg units 14A and 14B). And supplies necessary power supply voltage to the sub-control units 63A to 63D and communicates with the sub-control units 63A to 63D.
[0037]
The sub-control units 63A to 63D are respectively connected to the actuators A1 to A14 in the corresponding constituent units, and based on various control commands supplied from the main control unit 61, the actuators A1 to A14 in the constituent units. A14 is controlled to be driven to a designated state.
[0038]
FIG. 6 is a block diagram illustrating an example of an electrical internal configuration of the robot 1.
[0039]
The head unit 12 includes an external unit including CCD (Charge Coupled Device) cameras 81L and 81R functioning as “eyes” of the robot 1, microphones 82-1 to 82-N functioning as “ears”, a touch sensor 51, and the like. A sensor unit 71, a speaker 72 functioning as a "mouth" and the like are provided at predetermined positions, respectively, and an internal sensor unit 73 including a battery sensor 91 and an acceleration sensor 92 is provided in the control unit 52. I have. In addition, a display unit 55 for displaying the state of the robot 1 and a response from the user is provided.
[0040]
Then, the CCD cameras 81 </ b> L and 81 </ b> R of the external sensor unit 71 image the surroundings, and transmit the obtained image signal S <b> 1 </ b> A to the main control unit 61. The microphones 82-1 to 82-N collect various command voices (voice commands) such as “walk”, “stop” or “raise your right hand” given as voice input from the user, and the obtained voice signal S1B is obtained. To the main control unit 61. In the following, the microphones 82-1 to 82 -N are referred to as microphones 82 unless it is necessary to distinguish them.
[0041]
The touch sensor 51 is provided, for example, on the upper part of the head unit 12 as shown in FIGS. 2 and 3, and receives a pressure applied by a physical action such as “stroke” or “hit” from the user. And sends the detection result to the main control unit 61 as a pressure detection signal S1C.
[0042]
The battery sensor 91 of the internal sensor unit 73 detects the remaining energy of the battery 74 at a predetermined cycle, and sends the detection result to the main control unit 61 as a remaining battery detection signal S2A. The acceleration sensor 92 detects the acceleration of the movement of the robot 1 in three axial directions (x-axis, y-axis, and z-axis) at a predetermined cycle, and uses the detection result as an acceleration detection signal S2B as the main control unit 61. To send to.
[0043]
The external memory 75 stores programs and data, control parameters, and the like, and supplies the programs and data to the memory 61A incorporated in the main control unit 61 as necessary. The external memory 75 receives data and the like from the memory 61A and stores them. Note that the external memory 75 is detachable from the robot 1.
[0044]
The main control section 61 has a built-in memory 61A. The memory 61A stores programs and data, and the main control unit 61 performs various processes by executing the programs stored in the memory 61A. That is, the main control unit 61 transmits the image signal S1A, the audio signal S1B, and the pressure detection signal S1C (hereinafter, these signals are supplied from the CCD cameras 81L and 81R, the microphone 82, and the touch sensor 51 of the external sensor unit 71, respectively. The external sensor signal S1 is collectively referred to as a battery remaining amount detection signal S2A and an acceleration detection signal S2B (hereinafter collectively referred to as an internal sensor signal) supplied from the battery sensor 91 and the acceleration sensor of the internal sensor unit 73, respectively. Based on S2), the situation around and inside the robot 1, a command from the user, the presence or absence of a user's action, and the like are determined.
[0045]
Then, the main control unit 61 determines a situation around and inside the robot 1, a command from the user, or a result of the determination as to whether or not there is an action from the user, a control program stored in the internal memory 61 </ b> A in advance, or The action of the robot 1 is determined based on various control parameters and the like stored in the external memory 75 loaded at that time, a control command is generated based on the determined result, and the corresponding sub-control units 63A to 63D are determined. To send to. The sub-control units 63A to 63D control the driving of the corresponding one of the actuators A1 to A14 based on the control command supplied from the main control unit 61. Thereby, the robot 1 causes the head unit 12 to swing up, down, left, and right, raise the arm unit 13A or the arm unit 13B, and alternately drive the leg units 14A and 14B. And perform actions such as walking.
[0046]
In addition, the main control unit 61 outputs a sound based on the sound signal S3 to the outside by giving a predetermined sound signal S3 to the speaker 72 as necessary, and, for example, displays a display signal when the sound is detected. A response to the user such as “Dare” is displayed on the display unit 55 based on S4. Further, the main control section 61 blinks the LED by outputting a drive signal to an LED (not shown) provided at a predetermined position of the head unit 12, which functions as an external “eye”, It functions as the display unit 55.
[0047]
In this way, the robot 1 autonomously behaves based on surrounding and internal situations (states), commands from the user and presence / absence of action.
[0048]
FIG. 7 shows an example of a functional configuration of the main control unit 61 of FIG. The functional configuration shown in FIG. 7 is realized by the main control unit 61 executing a control program stored in the memory 61A.
[0049]
The main control unit 61 includes a state recognition information processing unit 101 that recognizes a specific external state, an emotion, instinct, and a growth state of the robot 1 that are updated based on a recognition result of the state recognition information processing unit 101 and the like. The model storage unit 102 stores the model of the robot 1, the action determination mechanism unit 103 that determines the action of the robot 1 based on the recognition result of the state recognition information processing unit 101, and the like. A posture transition mechanism 104 for causing the robot 1 to take an action, and a voice synthesizer 105 for generating a synthesized sound.
[0050]
A voice signal, an image signal, a pressure detection signal, and the like from the microphone 82, the CCD cameras 81L and 81R, the touch sensor 51, and the like are constantly input to the state recognition information processing unit 101 while the power of the robot 1 is turned on. You. The state-recognition information processing unit 101 receives a specific external state or a signal from a user based on a sound signal, an image signal, a pressure detection signal, and the like provided from the microphone 82, the CCD cameras 81L and 81R, the touch sensor 51, and the like. It recognizes a specific action, an instruction from the user, and the like, and constantly outputs state recognition information representing the recognition result to the model storage unit 102 and the action determination mechanism unit 103.
[0051]
The state recognition information processing unit 101 includes a voice recognition unit 101A, a direction recognition unit 101B, a pressure processing unit 101C, and an image recognition unit 101D.
[0052]
The speech recognition unit 101A detects the presence or absence of a speech in the speech signal S1B provided from each of the microphones 82-1 to 82-N, and outputs the detection of the speech when the speech is detected to the action determination unit 103. When a voice is detected, the controller 101a performs a turning operation in the direction of the sound source after the robot 1 detects a user's face based on a signal supplied from the image recognition unit 101D. Control is performed so that recognition processing is started, and control is performed so as not to execute voice recognition processing at other times. That is, the voice recognition unit 101A is controlled by the control unit 101a so as to execute the voice recognition process only when the image recognition unit 101D recognizes the user's face, and not to perform the voice recognition process otherwise. As a result, when performing the voice recognition process, the voice recognition unit 101A is controlled so as to reduce a recognition error caused by noise that occurs when no user is present.
[0053]
The speech recognition unit 101A performs speech recognition when the control unit 101a controls the speech recognition process so that the speech recognition process can be executed. Then, the voice recognition unit 101A sends, for example, commands such as “walk”, “stop”, and “raise your right hand” and other voice recognition results to the model storage unit 102 and the action determination mechanism unit 103 as state recognition information. Notice.
[0054]
The direction recognition unit 101B recognizes the direction of the sound source from the power difference and the phase difference of the audio signals S1B supplied from the microphones 82-1 to 82-N (detects and recognizes the direction of the sound source) and acts on the recognition result. It is supplied to the determination mechanism unit 103.
[0055]
The pressure processing unit 101C processes a pressure detection signal S1C provided from the touch sensor 51. Then, as a result of the processing, the pressure processing unit 101C, for example, when detecting a pressure that is equal to or more than a predetermined threshold value and for a short period of time, recognizes that the user has been “hit” and has determined that the pressure is less than the predetermined threshold value. When the pressure is detected for a long time, it is recognized as "stroke (praised)", and the recognition result is notified to the model storage unit 102 and the action determination mechanism unit 103 as state recognition information.
[0056]
The image recognizing unit 101D performs an image recognizing process using the image signal S1A provided from the CCD cameras 81L and 81R. When the image recognition unit 101D detects, for example, a “red round object” or a “plane that is perpendicular to the ground and equal to or more than a predetermined height” as a result of the processing, the “ball is present” The model storage unit 102 and the action determination mechanism unit 103 are notified of image recognition results such as "there is a wall" or the detection of a human face as state recognition information.
[0057]
Here, since it is generally expected that the user often speaks from the front of the robot 1, the CCD cameras 81 </ b> L and 81 </ b> R that image the surrounding situation are such that the imaging directions are in the front of the robot 1. It is assumed that it is installed in the head unit 12 (FIG. 2).
[0058]
The CCD cameras 81L and 81R move the head unit 12 in the direction detected by the posture transition mechanism unit 104 based on the information on the direction recognized by the direction recognition unit 101B. At 81R, it is possible to image a user.
[0059]
The model storage unit 102 stores and manages an emotion model, an instinct model, and a growth model expressing the emotion, instinct, and growth state of the robot 1, respectively.
[0060]
Here, the emotion model indicates, for example, the state (degree) of emotions such as “joy”, “sadness”, “anger”, and “fun” in a predetermined range (for example, −1.0 to 1.. 0), and the values are changed based on the state recognition information from the state recognition information processing unit 101 or the passage of time. The instinct model expresses the state (degree) of the instinct's desire such as “appetite”, “sleep desire”, and “exercise desire” by a value in a predetermined range. The value is changed based on information, elapsed time, or the like. The growth model represents, for example, growth states (degrees) such as “childhood”, “adolescence”, “mature”, “elderly” and the like by values within a predetermined range, and the state recognition information processing unit 101. The value is changed on the basis of the state recognition information or the passage of time.
[0061]
The model storage unit 102 sends the emotion, instinct, and growth state represented by the values of the emotion model, instinct model, and growth model as described above to the behavior determination mechanism unit 103 as state information.
[0062]
The model storage unit 102 is supplied with the state recognition information from the state recognition information processing unit 101, and also receives the current or past behavior of the robot 1 from the behavior determination mechanism unit 103, specifically, for example, “ The behavior information indicating the content of the behavior such as "walking for time" is supplied. Even if the same state recognition information is given, the model storage unit 102 responds to the behavior of the robot 1 indicated by the behavior information. Thus, different state information is generated.
[0063]
That is, for example, when the robot 1 greets the user and strokes the head, the behavior information that the robot 1 greets the user and the state recognition information that the head is stroked are stored in the model storage unit. In this case, in the model storage unit 102, the value of the emotion model representing “joy” is increased.
[0064]
On the other hand, when the robot 1 is stroked on the head while performing any work, the behavior information indicating that the robot 1 is performing the work and state recognition information indicating that the robot has been stroked on the head are given to the model storage unit 102. In this case, the model storage unit 102 does not change the value of the emotion model representing “joy”.
[0065]
As described above, the model storage unit 102 sets the value of the emotion model while referring to not only the state recognition information but also the behavior information indicating the current or past behavior of the robot 1. Thereby, for example, when the user strokes the head with the intention of mischief while performing any task, an unnatural change in emotion such as increasing the value of the emotion model representing “joy” occurs. Can be avoided.
[0066]
Note that the model storage unit 102 also increases and decreases the values of the instinct model and the growth model based on both the state recognition information and the behavior information, as in the case of the emotion model. Further, the model storage unit 102 increases or decreases the values of the emotion model, the instinct model, and the growth model based on the values of other models.
[0067]
The action determining mechanism unit 103 determines the next action based on the state recognition information from the state recognition information processing unit 101, the state information from the model storage unit 102, the passage of time, and the like. For example, when the voice recognition processing or the image recognition processing such as “dance” is not required, the content of the action is sent to the attitude transition mechanism unit 104 as action command information.
[0068]
In other words, the behavior determining mechanism unit 103 manages a finite state automaton in which the behavior that the robot 1 can take in correspondence with the state (state), as a behavior model that defines the behavior of the robot 1. The state in the finite state automaton is transited based on the state recognition information from the state recognition information processing unit 101, the value of the emotion model, the instinct model, or the growth model in the model storage unit 102, the passage of time, etc. The corresponding action is determined as the next action to be taken.
[0069]
Here, when detecting that there is a predetermined trigger, the action determining mechanism unit 103 changes the state. That is, for example, when the time during which the action corresponding to the current state is being executed reaches a predetermined time, or when specific state recognition information is received, the action determining mechanism unit 103 is supplied from the model storage unit 102. The state is changed when the value of the emotion, instinct, or growth state indicated by the state information is equal to or less than a predetermined threshold.
[0070]
Note that, as described above, the behavior determining mechanism unit 103 performs the processing based on not only the state recognition information from the state recognition information processing unit 101 but also the values of an emotion model, an instinct model, a growth model, and the like in the model storage unit 102. Since the state in the behavior model is changed, even if the same state recognition information is input, the destination of the state is different depending on the value of the emotion model, the instinct model, and the growth model (state information).
[0071]
When the voice recognition unit 101A of the state recognition information processing unit 101 outputs state recognition information indicating that a voice signal has been detected, the action determination mechanism unit 103 sends the robot 1 a sound source to the posture transition mechanism unit 104. Turn around. Further, in a state where the robot 1 turns around in the direction of the sound source, the image recognition unit 101D of the state recognition information processing unit 101 detects and detects a user's face image determined from a skin color region or the like of an image signal. Is transmitted to the control unit 101a of the voice recognition unit 101A, the control unit 101a controls the voice recognition unit 101A to start the voice recognition process.
[0072]
Then, it acquires the state recognition information (for example, information on the command recognized by the voice recognition unit 101A) supplied from the state recognition information processing unit 101, and as described above, for example, "conversing with the user" or " An action determined by the action determining mechanism 103 itself, such as “waving a hand to the user,” is performed (the content of the action is sent to the attitude transition mechanism 104 as action command information).
[0073]
As described above, the action determining mechanism 103 generates action command information for causing the robot 1 to speak, in addition to action command information for operating the head, limbs, and the like of the robot 1. The action command information that causes the robot 1 to make an utterance is supplied to the voice synthesis unit 105. The action command information supplied to the voice synthesis unit 105 includes a synthesized sound generated by the voice synthesis unit 105. The corresponding text and the like are included. Then, upon receiving the action command information from the action determination mechanism unit 103, the speech synthesis unit 105 generates a synthesized sound based on the text included in the action command information, and supplies the synthesized sound to the speaker 72 for output.
[0074]
In addition, the action determination mechanism 103 causes the display unit 55 to display a text corresponding to the utterance or a word that is substituted for the utterance when the utterance is not performed as a prompt. For example, when a voice is detected and turned around, a text such as “Who?” Or “What?” Can be displayed as a prompt on the display unit 55 or generated from the speaker 72.
[0075]
As described above, the posture transition mechanism unit 104 generates the posture transition information for transitioning the posture of the robot 1 from the current posture to the next posture based on the behavior command information supplied from the behavior determination mechanism unit 103. Generated and transmitted to the sub-control units 63A to 63D.
[0076]
FIG. 8 is a functional block diagram illustrating functions of the voice recognition unit 121 of the state recognition information processing unit 101.
[0077]
When the control unit 101a is not in a state in which the voice recognition unit 101A executes the voice recognition processing (in a state of Disable), when the control unit 101a detects a signal indicating that the voice signal has been detected, the control unit 101a outputs the voice signal. A signal indicating the detection is output to the action determination mechanism unit 103. That is, in the state of Disable, the voice recognition unit 101A does not execute the voice recognition process based on the input voice signal.
[0078]
When a signal indicating that an image has been detected is input from the image recognizing unit 101D, the control unit 101a determines that the voice recognition process can be executed (Enable state) and executes the voice recognition process. The sound is input to the microphone 82 and converted to a digital signal by an AD converter (not shown), and is output to the feature extractor 121.
[0079]
The feature extracting unit 121 calculates a feature amount of the input audio signal.
[0080]
The recognition processing control unit 122 is configured to be able to perform recognition processing corresponding to a plurality of language models (vocabulary and grammar) in parallel, and as a module that performs recognition processing corresponding to one language model, Recognition processing units 131-1 to 131-4 are provided, respectively.
[0081]
In the recognition processing control unit 122, a recognition processing unit corresponding to a new language model can be added, or an unnecessary recognition processing unit can be deleted. In addition, the recognition processing can be stopped or started for each recognition processing unit. That is, by simultaneously driving a plurality of recognition processing units or switching the recognition processing units, it is possible to simultaneously drive a plurality of language models or switch language models.
[0082]
The recognition processing units 131-1 to 131-4 are provided with matching units 141-1 to 141-4 that perform voice matching based on the feature amount calculated by the feature extraction unit 121. Dictionary databases 142-1 to 142-4 in which information on grammar is stored, and grammar databases 143-1 to 143-4 in which information on grammar is stored. Further, an acoustic model database 132 in which information on acoustics is stored is connected to the matching units 141-1 to 141-4.
[0083]
In the following description, when it is not necessary to distinguish each of the recognition processing units 131-1 to 131-4, they are collectively referred to as a recognition processing unit 131. The same applies to other parts. In addition, in the example of FIG. 8, four recognition processing units 131-1 to 131-4 are shown, but the number of the recognition processing units is three or less or five as necessary. It may be provided above.
[0084]
The acoustic model database 132 is configured so that the same acoustic model can be shared and used by all the recognition processing units 131, thereby consuming memory and processing for calculating a score generated in the acoustic model. Can be efficiently shared.
[0085]
The acoustic model database 132 stores acoustic models representing acoustic features such as individual phonemes and syllables in the language of the speech to be recognized. As the acoustic model, for example, HMM (Hidden Markov Model) is used. The dictionary databases 142-1 to 142-4 store word dictionaries in which information (phonological information) regarding pronunciation is described for each word (vocabulary) to be recognized. The grammar databases 143-1 to 143-4 are grammar rules (language models) that describe how words registered in the word dictionaries of the dictionary databases 142-1 to 142-4 are linked (connected). I remember. As the grammar rule, for example, a description based on a context-free grammar (CFG), a statistical word chain probability (N-gram), or the like is used.
[0086]
Information about different vocabulary is stored in each of the dictionary databases 142-1 to 142-4, and information about different grammars is also stored in the grammar databases 143-1 to 143-4. A language model is determined by a combination of the dictionary database 142 and the grammar database 143.
[0087]
Next, processing of an operation by a voice command will be described with reference to the flowchart of FIG.
[0088]
In step S1, the voice recognition unit 101A determines whether or not voice has been input (whether or not voice has been detected) via the microphones 82-1 to 82-N, and determines that no voice has been input. If so, the process of step S1 is repeated. That is, the process of step S1 is repeated until it is determined that a voice has been detected (until it is determined that a voice has been input).
[0089]
If it is determined in step S1 that a voice has been detected, that is, for example, it is determined that the user has called for an input of a voice command to the robot 1, the process proceeds to step S2.
[0090]
In step S2, the direction recognition unit 101B detects and recognizes the direction of the sound source based on the sound input through the microphones 82-1 to 82-N. That is, the direction recognition unit 101B detects and recognizes the direction of the sound source from the power difference and the phase difference of the audio signals S1B supplied from the microphones 82-1 to 82-N, and supplies the recognition result to the action determination mechanism unit 103. I do.
[0091]
In step S3, a process of turning around the sound source is performed.
[0092]
Here, the turning operation process will be described with reference to the flowchart in FIG.
[0093]
In step S21, the action determining mechanism unit 103 determines the difference between the current direction of the robot 1 and the direction of the sound source based on the information on the direction of the sound source supplied from the direction recognition unit 101B of the state recognition information processing unit 101. Is calculated, and the relative angle of the sound source direction to the trunk direction is obtained.
[0094]
In step S22, the action determining unit 103 determines the movable range of the yaw axis 29 of the neck joint mechanism 27 shown in FIG. 4 and the maximum angle that can be rotated by one rotation operation when rotating the trunk using the legs. And the trunk (necessary for rotating the head by the relative angle calculated in step S21) (the vertical axis of the main body of the robot 1 rotated using the hip joint mechanism 37). ) Is determined. Here, depending on the sound source direction, the action determining unit 103 determines the rotation angle of only the neck joint mechanism 27. Although the robot 1 has the yaw axis 38 of the hip joint mechanism 37 as shown in FIG. 4, for simplicity, the present embodiment will be described on the assumption that the yaw axis 38 of the hip joint mechanism 37 is not used. I do. However, it is needless to say that the sound source direction can be turned in cooperation with the whole body using the grounding directions of the neck, waist, and feet.
[0095]
This will be specifically described with reference to FIG. FIG. 11A shows an example in which the movable range of the neck of the robot 1 is ± Y degrees and the relative angle of the direction of the sound source S is X degrees with respect to the front direction of the robot 1. In this case, in order for the robot 1 to turn around in the direction of the sound source S, as shown in FIG. 11B, the entire trunk is rotated by at least X-Y degrees using the legs, and the yaw axis of the neck joint mechanism 27 is rotated. 29 needs to be rotated in the direction of the sound source S by Y degrees.
[0096]
In step S23, the action determining mechanism unit 103 supplies the control information of each joint necessary for rotating the angle obtained in step S22 to the posture transition mechanism unit 104, and based on this information, the posture transition mechanism unit The 104 turns the robot 1 toward the sound source by driving various actuators.
[0097]
In step S <b> 24, the action determining mechanism unit 103 calculates the rotation angles of the trunk and the neck required to face the direction of the sound source S. For example, as shown in FIG. 11B described above, when the yaw axis 29 of the neck joint mechanism 27 is rotated by Y degrees in the current posture of the robot apparatus 1, that is, the head is rotated by Y degrees with respect to the trunk. In this case, as shown in FIG. 11C, by rotating the trunk at the Y-degree and simultaneously rotating the yaw axis 29 of the neck joint mechanism 27 by −Y-degree, the twist of the neck is eliminated while the target object is being closely watched, It is possible to directly face the sound source S with a natural motion.
[0098]
In step S25, the posture transition mechanism unit 104 causes the robot 1 to execute the operation calculated in step S24 to face the direction of the sound source, and the action determination mechanism unit 103 outputs, for example, a text such as "Dare". Prompt is displayed on the display unit 55.
[0099]
The robot apparatus 1 recognizes (estimates) the sound source direction as described above, and can turn around the sound source direction by a natural motion by coordinating the whole body.
[0100]
For example, the robot 1 turns around in the direction of the sound source as shown in FIGS. 12A to 12F. That is, when a voice is input from behind while the robot 1 is facing the right side in the figure as shown in FIG. 12A, the neck is rotated and the trunk is rotated using the legs as shown in FIGS. 12B to 12F. Finally, as shown in FIG. 12F, the player turns to the sound source direction in the left direction in the figure. At this time, the action determining mechanism unit 103 may control the display unit 55 to display, for example, “What?” To indicate that the user is responding. As a result, when the user issues a command by voice, the user can react to the voice uttered by the robot 1 and recognize that the robot 1 is responding.
[0101]
Here, the description returns to the flowchart of FIG.
[0102]
In step S4, the image recognition unit 101D of the state recognition information processing unit 101 performs a user face detection process based on image information input from each of the CCD cameras 81L and 81R. The method of detecting a human face may be, for example, a method of detecting a user's face image or the like determined from a skin color region or the like of an image signal. As a technique for detecting a human face, for example, "E. Osuna, R. Freund and F. Girosi:" Training support vector machines: an application to face detection ", described in CVPR'97, 1997. It is also possible to realize by such a method.
[0103]
In step S5, the image recognition unit 101D determines whether a face has been detected. If it is determined that a face has been detected, the process proceeds to step S6.
[0104]
In step S6, the image recognition unit 101D sends a signal indicating that the face has been detected to the voice recognition unit 101A, and based on this information, the control unit 101a of the voice recognition unit 101A A state in which the voice recognition process can be performed, that is, the voice recognition unit 101A is controlled to the Enable state, and after this process, the voice recognition process is performed based on the voice signals supplied from the microphones 82-1 to 82-N. To be able to do.
[0105]
In step S7, a voice recognition process is performed.
[0106]
Here, the speech recognition processing will be described with reference to the flowchart in FIG.
[0107]
In step S41, the feature extraction unit 121 converts the audio signal as a digital signal into a parameter representing a spectrum or other acoustic characteristics of the audio by performing frequency analysis at appropriate time intervals, and the like, Extract.
[0108]
In step S42, the recognition processing control unit 122 selects a recognition processing unit to be driven.
[0109]
For example, assume that the robot 1 is performing chat, singing, and dancing with the user. At this time, in the robot 1, applications for chat, singing, and dancing are running. The robot 1 has one language model for each of chat, singing, and dancing with the user, and the recognition processing unit corresponding to each language model is driven. Further, it is assumed that one language model is used in common for all operations, and the recognition processing unit corresponding to this language model is driven. The language model commonly used for all operations is a language model for recognizing a command having a high degree of importance, such as "stop".
[0110]
At this time, based on the application currently being executed, the robot 1 has a recognition processing unit having a language model commonly used for all operations, a recognition processing unit having a language model for chatting with a user, and a singing unit. The recognition processing unit having a language model and the recognition processing unit having a dance language model are driven. Here, the recognition processing unit 131-1 has a language model commonly used for all operations, the recognition processing unit 131-2 has a chat language model, and the recognition processing unit 131-3 has a singing language. It is assumed that the recognition processing unit 131-4 has a language model for dancing.
[0111]
Therefore, the recognition processing control unit 122 selects the recognition processing units 131-1 to 131-4 as the recognition processing units to be driven. In other words, a total of four recognition processing units 131-1 to 131-4 are operated by the recognition processing control unit 122, and there are two recognition processing units corresponding to one application.
[0112]
As described above, the recognition processing control unit 122 selects and drives the recognition processing unit having the language model corresponding to the application being executed.
[0113]
Thereafter, the process proceeds to step S43. The processing of steps S43 to S46 (hereinafter, the processing of steps S43 to S46 is also referred to as word sequence recognition processing) is executed in parallel by the recognition processing units 131-1 to 131-4.
[0114]
In step S43, the recognition processing units 131-1 to 131-4 match the feature amount of the voice output from the feature extraction unit 121 with the acoustic model database 132, and determine phonemes and syllables.
[0115]
In step S44, the recognition processing units 131-1 to 131-4 match the phonemes and syllables with the dictionary databases 142-1 to 142-4 and the grammar databases 143-1 to 143-4, and set the acoustic score and the language score. Is calculated.
[0116]
That is, the recognition processing units 131-1 to 131-4 compare the acoustic pattern of the input feature amount with the acoustic standard pattern corresponding to each word included in the dictionary database 142, and The evaluation value is calculated as an acoustic score. When a bigram is used as the grammar, for example, the recognition processing units 131-1 to 131-4 determine the linguistic certainty of each word based on the chain probability with the immediately preceding word based on the grammar database 143. Numerical values are calculated as language scores.
[0117]
In step S45, the recognition processing units 131-1 to 131-4 determine the word string with the highest evaluation by integrating the acoustic score and the language score, and proceed to step S46. , And output to the model storage unit 102.
[0118]
For example, when the user utters “Today is good weather”, a series of words such as “today”, “ha”, “good”, “weather”, and “is” is obtained as a recognition result. Will be done.
[0119]
In this way, a word sequence is recognized from the input speech.
[0120]
Here, the description returns to the flowchart of FIG.
[0121]
In step S8, the action determining unit 103 determines an action based on a voice command composed of a word sequence supplied from the voice recognition unit 101A of the state recognition information processing unit 101, and outputs the determined action to the posture transition mechanism unit 104. The posture transition mechanism unit 104 controls the various actuators to perform an action corresponding to the determined action, and causes the robot 1 to act.
[0122]
In step S9, the control unit 101a of the voice recognition unit 101A of the state recognition information processing unit 101 determines whether or not there is an input of a voice command. Returns to step S7. That is, as long as the voice command is continuously input, the processes of steps S7 to S9 are repeated, and the interactive process with the user is continued.
[0123]
In step S9, when it is determined that there is no voice command input, that is, for example, there is no voice command input for a predetermined period of time and there is no request from the user, in step S10, the state recognition information processing unit 101 The control unit 101a of the voice recognition unit 101A controls the voice recognition unit 101A so that the voice recognition process cannot be performed, that is, disables the voice recognition unit 101A, and the voice signal supplied from the microphones 82-1 to 82-N after this process. Is set to a state in which the voice recognition processing cannot be executed.
[0124]
In step S11, a turning motion process in the original direction is performed, and the process returns to step S1. Note that the turning operation processing in the original direction is performed by replacing the sound source direction with the original direction in the processing of the turning operation toward the sound source in the processing in step S3 in FIG. 9 described with reference to the flowchart in FIG. Other than the above, the processing is the same, and a description thereof will be omitted.
[0125]
If no user face is detected in step S5, steps S6 to S10 are skipped, and the process proceeds to step S11.
[0126]
That is, normally, when a command is input by voice, the user is made at a distance at which the robot 1 can be visually recognized by the CCD camera 81. Therefore, when a voice signal is detected in the process of step S1 (the voice signal is first detected). Is detected), the robot 1 is turned around in the direction of the sound source. Only when the user's face is detected in the direction of the sound source in the process of step S5, the audio signal detected by the microphone 82 at the subsequent timing (the audio signal detected after the second time) is used. By executing the voice recognition process, the voice signal input at other timings is regarded as noise (not a voice signal input as a command), and the voice recognition process is not performed. Therefore, it is possible to suppress erroneous recognition due to noise generated in an environment where no user exists.
[0127]
In addition, the operation of turning around in the direction of the sound source detected based on the detected sound may be such that the user's face can be detected, and even if only the head of the robot 1 is turned around. Alternatively, the entire body of the robot 1 may be turned around. Further, at this time, a microphone having high directivity may be directed to the sound source direction. By doing so, it is possible to indicate to the user who is issuing the command by voice that the robot 1 is reacting, and to generate a voice signal required for voice recognition with respect to the sound source with high accuracy. As a result, it is possible to suppress erroneous recognition due to noise or the like in the voice recognition processing.
[0128]
In the above description of the processing of the operation based on the voice command, the robot 1 may perform another operation different from the processing of the operation based on the voice command. In that case, in the processing of step S1, the direction of the sound source is determined. Is detected, the operation that has been performed is interrupted. Further, in step S11, the operation that has been performed until the processing of the operation by the voice command is performed after the turning operation in the original direction is completed in step S11. Will be resumed.
[0129]
In the above processing, the direction of the sound source is detected in response to the sound signal detected first, and the turning operation in the direction of the sound source is executed. There may be a case where the sound is heard from a direction different from the direction of the sound source. That is, the sound reverberates due to a ceiling, a wall, or the like existing around the robot 1, and if the direction is detected based on the reverberated sound, there is a possibility that a direction different from the original direction of the sound source is erroneously detected as the sound source. Get higher. As a result, no matter how much the robot 1 turns in the erroneously detected direction, the face of the user issuing the command by voice cannot be detected, and there is a possibility that an unnecessary turning operation may be repeated.
[0130]
Therefore, in order to cope with the situation where the sound reverberates as described above, the frequency at which the face can be detected is stored for each direction, and according to the frequency at which the face cannot be detected (or In accordance with the frequency at which the user's face can be detected), the reliability of the direction of the sound source is determined. If a direction with a low reliability at which the face can be detected is detected as the sound source direction, the turning operation is not performed at a predetermined rate. (Even if an audio signal is detected, it may be ignored).
[0131]
FIG. 14 shows a main control unit of the robot 1 in which the frequency at which the user's face can be detected is stored, the reliability for each direction is calculated from the detected frequency, and the turning operation is not performed according to the reliability. FIG. 61 is a block diagram showing another configuration of the embodiment.
[0132]
The main control unit 61 in FIG. 14 is basically the same as the configuration of the main control unit 61 in FIG. 7, except that the behavior determination mechanism unit 103 includes a behavior memory 103a and a reliability calculation unit 103b. The difference is that the reliability calculation unit 103b calculates the reliability for each direction based on the information stored in the behavior memory 103a, and controls the posture transition mechanism unit 104 according to the reliability.
[0133]
The action memory 103a is a memory that stores the action determined by the action determining mechanism unit 103. When the player turns around in the direction of the sound source, the frequency of the turning operation and the face of the user are determined for each direction. The detected frequency is updated and stored.
[0134]
The reliability calculation unit 103b calculates and stores, as a percentage, the reliability with which the user's face is detected for each direction based on the information stored in the behavior memory 103a. Since the information stored in the behavior memory 103a is updated every time an operation is performed, the reliability calculation unit 103b also sequentially updates the reliability in accordance with each behavior.
[0135]
The behavior determining mechanism 103 in FIG. 14 controls the turning operation based on the reliability. That is, for example, when the frequency of turning to the right is TR, and the frequency of detecting a face is FR, the reliability calculating unit 103b calculates the reliability of detecting a rightward face is 100. X FR / TR (%). The action determining mechanism unit 103 generates a random number from 1 to 100 based on the direction information input from the direction recognizing unit 101B, and stores the random number value and the face stored in the reliability calculating unit 103b. Is compared with the detected reliability, and when the value of the random number is lower than the reliability, the turning operation is performed in that direction, otherwise, the posture transition mechanism unit is configured not to perform the turning operation. 104 is controlled. The default value of the reliability is 100%.
[0136]
Next, with reference to the flowchart of FIG. 15, the processing of the operation of the robot 1 using the voice command using the main control unit 61 of FIG. 14 will be described. Note that the processing in steps S61 and S62 and steps S65 to S73 in FIG. 15 is the same as the processing in steps S1 to S11 described with reference to the flowchart in FIG. 9, and a description thereof will be omitted.
[0137]
In step S63, the action determining mechanism unit 103 reads the reliability stored in the reliability calculation unit 103b for detecting a face corresponding to the direction of the detected sound source. In the case of the first process, the reliability is 100%, and thereafter, the value is in accordance with the frequency.
[0138]
In step S64, the action determining mechanism unit 103 generates a random number from 1 to 100, and determines whether or not to perform the turning motion by comparing the generated random number with the reliability. More specifically, the action determining mechanism unit 103 generates a random number from 1 to 100, compares the random number with the reliability read from the reliability calculation unit 103b, and, when the reliability is lower than the read reliability, turns around. When it is determined that the operation is to be executed and the random number is higher than the reliability, it is determined that the turning operation is not to be executed.
[0139]
In step S64, for example, when the action determining mechanism unit 103 determines that the generated random number is lower than the reliability, that is, when it determines that the turning motion is to be executed, the process proceeds to step S65.
[0140]
On the other hand, when it is determined in step S64 that the generated random number is higher than the reliability, the action determining mechanism unit 103 determines that the turning motion is not performed, and the process returns to step S61.
[0141]
In step S74, the action determining mechanism unit 103 updates the information on the frequency at which the face is detected based on the determination result as to whether or not the face is detected, and the frequency at which the turning operation in the direction of the sound source is executed, and updates the action. In addition to the storage in the memory 103a, the reliability calculation unit 103b calculates the reliability based on the updated frequency and updates the reliability.
[0142]
With the above processing, the reliability of detecting a face for each turning operation is updated.For example, in an environment where sound is likely to reverberate due to a ceiling or a wall, the face of a sound source that is likely to be erroneously detected is It is possible to suppress the turning operation in accordance with the frequency with which the detection is performed, and as a result, it is possible to realize a highly accurate voice recognition process while suppressing the turning operation in a useless direction that is likely to cause erroneous detection. It becomes possible.
[0143]
The direction viewed from the robot 1 is, for example, when the robot 1 is walking while changing the traveling direction, the reliability in each direction is also changed using the acceleration detection signal S2B or the like. Alternatively, an absolute direction such as east, west, north and south may be set using a compass instead of directions such as front, rear, left, and right, and the reliability may be set for each direction.
[0144]
The series of processes described above can be executed by hardware, but can also be executed by software. When a series of processing is executed by software, a program constituting the software may be executed by a computer built into dedicated hardware or by installing various programs to execute various functions. It is installed from a recording medium into a possible general-purpose personal computer or the like.
[0145]
FIG. 16 shows a configuration of an embodiment of a personal computer in a case where the electrical internal configuration of the robot 1 of FIG. 6 is realized by software. The CPU 201 of the personal computer controls the entire operation of the personal computer. When a user inputs a command from an input unit 206 including a keyboard, a mouse, and the like via a bus 204 and an input / output interface 205, the CPU 201 stores the command in a ROM (Read Only Memory) 202 in response to the command. Execute the program. Alternatively, the CPU 201 reads a program read from the magnetic disk 221, the optical disk 222, the magneto-optical disk 223, or the semiconductor memory 224 connected to the drive 210 and installed in the storage unit 208, and stores the program in a RAM (Random Access Memory) 203. And run it. Thereby, the function of the omnidirectional image data generation unit 13 described above is realized by software. Further, the CPU 201 controls the communication unit 209 to communicate with the outside and execute transmission and reception of data.
[0146]
As shown in FIG. 16, the recording medium on which the program is recorded is a magnetic disk 221 (including a flexible disk) on which the program is recorded, which is distributed separately from the computer to provide the program to the user, An optical disk 222 (including a CD-ROM (Compact Disc-Read Only Memory), a DVD (Digital Versatile Disk)), a magneto-optical disk 223 (including an MD (Mini-Disc)), or a package medium including a semiconductor memory 224 or the like. In addition to the configuration, the configuration includes a ROM 202 storing a program and a hard disk included in the storage unit 208, which are provided to a user in a state where the program is incorporated in a computer in advance.
[0147]
In this specification, a step of describing a program recorded on a recording medium is performed in a time-series manner in the order described. Alternatively, the processing includes individually executed processing.
[0148]
【The invention's effect】
According to the present invention, it is possible to suppress erroneous recognition in the voice recognition processing.
[Brief description of the drawings]
FIG. 1 is a perspective view showing an external appearance of an exterior of a robot to which the present invention is applied.
FIG. 2 is a perspective view showing an internal configuration of the robot shown in FIG.
FIG. 3 is a rear perspective view showing the internal configuration of the robot shown in FIG. 2;
FIG. 4 is a schematic diagram for explaining axes of the robot in FIG. 2;
FIG. 5 is a block diagram for mainly explaining a portion related to control of the robot in FIG. 2;
FIG. 6 is a block diagram showing an internal configuration of control of the robot shown in FIG. 1;
FIG. 7 is a block diagram illustrating a configuration of a main control unit in FIG. 6;
FIG. 8 is a block diagram illustrating a configuration of a speech recognition unit in FIG. 7;
FIG. 9 is a flowchart illustrating processing of an operation by a voice command of the robot.
FIG. 10 is a flowchart illustrating processing of a turning operation in FIG. 9;
FIG. 11 is a diagram illustrating a turning operation.
FIG. 12 is a diagram illustrating a turning operation.
FIG. 13 is a flowchart illustrating a voice recognition process of the robot.
FIG. 14 is a block diagram illustrating another configuration of the main control unit in FIG. 6;
FIG. 15 is a flowchart illustrating processing of an operation by a voice command of the robot using the configuration of the main control unit in FIG.
FIG. 16 is a diagram illustrating a recording medium.
[Explanation of symbols]
1 robot, 61 main control unit, 55 display unit, 63 sub control unit, 71 external sensor unit, 72 speaker, 81L, 81R CCD camera, 82 microphone, 101 state recognition information processing unit, 101A voice recognition unit, 101a control unit, 101B direction recognition section, 101C pressure processing section, 101D image recognition section, 102 model storage section, 103 action determination mechanism section, 103a action memory, 104 attitude transition mechanism section, 105 voice synthesis section

Claims (6)

Voice detection means for detecting voice;
Voice recognition means for recognizing the voice detected by the voice detection means,
Direction detection means for detecting the direction of the sound source of the voice,
User detection means for detecting a user in the direction detected by the direction detection means,
A robot control device, comprising: a voice recognition control unit that controls a start of voice recognition by the voice recognition unit when a user is detected by the user detection unit. Imaging means for capturing an image,
An imaging control unit that controls the imaging unit so as to capture an image of the direction detected by the direction detection unit,
When controlled by the imaging control unit, and the imaging unit captures the direction detected by the direction detection unit, the user detection unit captures the user's face in the video captured by the imaging unit. The robot control device according to claim 1, wherein the user is detected based on whether or not the user is in operation. When the imaging control unit controls the imaging unit to capture an image in the direction detected by the direction detection unit, the image captured by the imaging unit determines whether the user's face is captured. Further comprising a reliability detection means for detecting the reliability of each direction based on the frequency of
The image capturing control unit captures the image in the direction detected by the direction detecting unit based on the reliability of detection of the user's face detected by the reliability detection unit. 3. The robot controller according to claim 2, wherein the controller controls the means. A voice detection step of detecting voice;
A voice recognition step of recognizing the voice detected in the processing of the voice detection step;
A direction detection step of detecting a direction of a sound source of the voice,
A user detection step of detecting a user in the direction detected in the processing of the direction detection step,
A voice recognition control step of performing control to start voice recognition in the voice recognition step when a user is detected in the user detection step. A voice detection step of detecting voice;
A voice recognition step of recognizing the voice detected in the processing of the voice detection step;
A direction detection step of detecting a direction of a sound source of the voice,
A user detection step of detecting a user in the direction detected in the processing of the direction detection step,
A computer-readable program that includes a voice recognition control step of controlling a start of voice recognition in the voice recognition step when a user is detected in the user detection step. Recording medium on which is recorded. A voice detection step of detecting voice;
A voice recognition step of recognizing the voice detected in the processing of the voice detection step;
A direction detection step of detecting a direction of a sound source of the voice,
A user detection step of detecting a user in the direction detected in the processing of the direction detection step,
When a user is detected in the processing of the user detection step, the computer performs processing including a voice recognition control step of controlling to start voice recognition in the processing of the voice recognition step. program.

Images