JP5411789B2 - Communication robot - Google Patents

Description

  The present invention relates to a communication robot that communicates with a conversation target.

  Conventionally, a communication robot and an automatic response system for communicating with a conversation target (person) have been proposed (for example, see Patent Document 1). The automatic response system described in Patent Document 1 retains speech data of unknown words that cannot be recognized by speech corresponding to the attribute information, and uses the retained speech data for utterance to a conversation target.

JP 2002-297179 A

However, conventional communication robots sometimes utter incorrectly by recognizing speech other than monologue, unknown words or noise other than speech. In this case, the conventional communication robot fails to communicate because the conversation target cannot understand the utterance content.
In addition, the automatic response system described in Patent Document 1 has a problem that a database for dealing with unknown words is required and the dialogue processing thereof is complicated.

  Therefore, an object of the present invention is to provide a communication robot that can easily continue communication with a simple configuration.

To solve the problems described above, communication robot according to the first aspect of the present invention includes at least voice recognition unit that recognizes the voice dialogue target speech input unit inputs, an audio output unit for audio output based on the speech information A communication robot having a movable part that performs a predetermined operation, wherein the voice recognition unit calculates the reliability of the result of the voice recognition when the voice input unit inputs a voice to be interacted with, and outputting, on the basis of the dialogue object of speech in reliability wherein the speech recognizer has been calculated, the speech dialogue target impossible reply indicating that the has been able speech recognition can not answer the voice of the conversation target behavior A response action determination unit that calculates an evaluation value as to whether or not to perform the response and determines that the answer impossible action is performed when the evaluation value is less than a preset threshold value If the response action determining unit determines that performing the answer incapacitated, the predetermined response action possible the communication robot, a response action selector for selecting the answer incapacitated, the response action selection unit selects A response behavior command unit that commands execution of the unanswerable behavior to at least one of the voice output unit and the movable unit; and an average volume calculation unit that calculates an average volume of the voice of the dialogue target for each dialogue target; The response action determination unit calculates a volume coefficient obtained by dividing the volume of the conversation target voice input by the voice input unit by the average volume of the conversation target voice calculated by the average volume calculation unit. A value obtained by multiplying the reliability by a coefficient is calculated as the evaluation value.

  According to this configuration, the communication robot uses the response behavior determination unit to indicate an index indicating whether or not the communication robot answers the conversation target (that is, whether or not the conversation target has spoken to the communication robot. An evaluation value is calculated as an index). Then, the communication robot uses the response behavior determination unit to compare the calculated evaluation value with a threshold value and determine whether to reply to the conversation target. In this determination, the communication robot does not require an unknown word database and complicated processing.

Here, when the evaluation value is low, it is considered that there is a high possibility that the speech to be talked is an answer-free one (for example, self-word, unknown word, or noise other than speech). In this case, even if the conversation target voice is answered, the conversation target cannot understand the answer content and it is difficult to continue communication. Further, even if the voice of the dialogue target is an answer-free one, if the communication robot does not perform any operation, the dialogue target does not know whether the communication robot is listening to the voice of the dialogue target . Therefore, communication robot, the response action selection unit, when the evaluation value is low, the voice dialogue object has been recognized speech to select an answer incapacitated that it can not answer the voice dialogue target.
Furthermore, the communication robot can prevent an erroneous utterance even when there is no need to answer the dialogue target when the volume of the voice of the dialogue target is low (for example, to speak alone).

In order to solve the above-described problem, a communication robot according to the second invention of the present application includes a speech recognition unit that recognizes at least speech to be spoken inputted by the speech input unit, and speech output that outputs speech based on speech information. And a movable part that performs a predetermined operation, wherein the voice recognition unit determines the reliability of the result of the voice recognition when the voice input unit inputs a voice to be interacted with. An answer indicating that the voice of the dialogue target can be recognized by the voice recognition unit based on the reliability calculated by the voice recognition unit for the dialogue target voice, but cannot be answered to the voice of the dialogue target. A response action determination is made to calculate an evaluation value as to whether or not to perform the impossible action, and to determine that the answer impossible action is performed when the evaluation value is less than a preset threshold value. And a response behavior selection unit that selects the response impossible behavior from predetermined response behaviors that the communication robot can perform when the response behavior determination unit determines to perform the response impossible behavior, and the response behavior selection unit A response behavior command unit that commands at least one of the voice output unit and the movable unit to execute the unanswerable behavior selected by the voice recognition unit, and the voice recognition unit further includes a dialog input by the voice input unit An utterance time of a target voice is calculated, and the response behavior determination unit calculates an utterance time coefficient obtained by dividing the utterance time calculated by the voice recognition unit by a preset utterance reference time, and at least the utterance time coefficient is calculated. A value obtained by multiplying the reliability is calculated as the evaluation value.

According to such a configuration, the communication robot is likely to require an answer to the conversation target when the utterance time of the conversation target voice is long, and in this case, the action that cannot be answered may be erroneously selected. Can be prevented.

Further, in the communication robot according to the third invention of the present application, when the response behavior determination unit has the evaluation value less than the threshold, the pronunciation of one word, the predetermined operation of the movable unit, or the one word It is preferable to determine that the unanswerable action is performed, which is a combination of the pronunciation of the voice and the predetermined operation of the movable part.

According to this configuration, when the evaluation value is less than the threshold value , the communication robot selects an unreplyable action that prompts the communication target to continue communication when the evaluation value is less than the threshold value. Here, this unanswerable action may be, for example, a one-word voice (pronounced “e”, “he” or “n”), a predetermined action of the movable part (an action of raising the neck), or a combination thereof (neck This is an action that prompts the conversation target to continue the communication, such as “speaking“ n ””.

The present invention has the following excellent effects.
Since the first and second inventions of the present application determine whether or not to perform an unanswerable action without requiring an unknown word database and complicated processing, the configuration can be simplified. In the first and second inventions of the present application, when the evaluation value is low, communication is performed in order to select an unanswerable action indicating that the voice of the dialogue target can be recognized but cannot be answered to the voice of the dialogue target. Easy to continue.

The first invention of the present application calculates an evaluation value in consideration of the utterance time of the speech to be spoken, so that it is possible to prevent an erroneous utterance from occurring even though there is no need to reply to the dialogue subject. Is easier to continue.
Since the second invention of the present application calculates an evaluation value in consideration of the average volume for each conversation target, even if there is a high possibility that a reply is required for the conversation target, the action that cannot be answered is erroneously selected. Communication, and it becomes easier to continue communication.
In the third invention of the present application, since the communication robot performs an unanswerable action for prompting continuation of communication with respect to the conversation target, communication becomes easier to continue.

It is a figure which shows typically the structure of the robot system containing the robot which concerns on embodiment of this invention. It is a figure which shows typically an example of the self position detection and object detection by a robot. It is a figure which shows an example of the local map used with the robot system shown in FIG. It is a figure which shows an example of the task information database memorize | stored in the memory | storage means of the management computer shown in FIG. It is a figure which shows an example of the task schedule table memorize | stored in the memory | storage means of the management computer shown in FIG. It is a block diagram which shows the structure of the robot which concerns on embodiment of this invention. It is a block diagram which shows the structure of the main control part of the robot shown in FIG. It is a block diagram which shows the structure of the response action control part shown in FIG. It is a figure which shows an example of rule DB memorize | stored in the rule DB memory | storage means shown in FIG. It is a figure which shows an example of operation | movement DB memorize | stored in the rule DB memory | storage means shown in FIG. It is a figure which shows an example of situation DB memorize | stored in the situation DB memory | storage means shown in FIG. It is explanatory drawing of the setting method of the threshold value which the response action determination part of FIG. 8 uses. It is a flowchart which shows operation | movement of the response action control part of FIG.

  DESCRIPTION OF EMBODIMENTS Hereinafter, an embodiment (hereinafter referred to as “embodiment”) for carrying out a communication robot (hereinafter referred to as “robot”) of the present invention will be described in detail with reference to the drawings. First, an overall configuration of a robot control system A including a robot according to an embodiment of the present invention will be described with reference to FIG.

(Configuration of robot control system A)
As shown in FIG. 1, a robot control system A includes a robot R, a base station 1 connected to the robot R by wireless communication, and a management computer connected to the base station 1 via a robot dedicated network 2. 3 and a terminal 5 connected to the management computer 3 via a network 4.

As shown in FIG. 1, the robot control system A has a plurality of robots R _A , R _B , and R _C having a moving function (however, when a robot is not specified, it is simply referred to as a robot R). Each robot R executes a task in accordance with a task execution plan (task schedule) preset for each robot R in the management computer 3.

Here, an autonomous mobile biped robot will be described as an example.
The robot R executes a task in accordance with an execution command input from the management computer 3, and at least one robot R is arranged in a task execution area set in advance as an area where the robot R executes the task.
Here, FIG. 1 shows a robot _RA that is executing a task (guidance task) for guiding a visitor to a predetermined place such as a conference room, and a task (package) for delivering a package to a person. and the robot R _B running delivery tasks), and the robot R _C waiting until a new task is assigned is illustrated. In this example, three battery replenishment areas B ₁ , B ₂ , and B ₃ are provided in the task execution area, and the robot R can perform battery charging (battery charging task) as necessary. it can.

  As shown in FIG. 2, the robot R has a head R1, an arm R2, a leg R3, a torso R4, and a rear housing R5, and the head R1 and arms connected to the torso R4, respectively. The part R2 and the leg part R3 are each driven by an actuator (driving means), and bipedal walking is controlled by the autonomous movement control part 50 (see FIG. 6). Details of this bipedal walking are disclosed in, for example, Japanese Patent Application Laid-Open No. 2001-62760.

  For example, when executing a guidance task, the robot R guides the person H in a predetermined guidance area (a movement area such as an office or a corridor). Here, the robot R detects whether or not the person H having the tag T exists in the peripheral area by transmitting light (for example, infrared light, ultraviolet light, laser light, etc.) and radio waves to the surroundings. Then, the position of the detected person H is specified and approached, and based on the tag T, personal identification as to who the person H is is performed. The tag T receives infrared light and radio waves emitted from the robot R to specify the position (distance and direction) of the person. The tag T generates a reception report signal including a tag identification number based on the signal indicating the light receiving direction included in the received infrared light and the robot ID included in the received radio wave, and returns it to the robot R. To do. The robot R that has received the reception report signal can recognize the distance and direction to the person H wearing the tag T based on the reception report signal, and can approach the person H.

  When the robot R autonomously moves within the guidance area to execute a certain task (for example, a guidance task or a package delivery task), the robot R irradiates laser slit light or infrared rays to search for a road surface state or a mark on the road surface. It is supposed to be. In other words, the robot R knows where the robot is moving in the moving area, and when in the normal moving area, the robot R irradiates the road surface with laser slit light to check for road steps, swells, and obstacles. When the mark M is within the installation area of the mark M, the mark M is detected by irradiating the road surface with infrared rays, and the self position is confirmed and corrected. Here, the mark M is a member made of a reflective material that recursively reflects infrared rays, for example. The mark M has position data, and the position data is stored in the storage unit 30 (see FIG. 6) in a form included in the map data. The map data includes the position data of the mark M installed at a specific location in the guidance area and the data related to the installation area of the mark M having a predetermined width (range) in the position data. . The mark M installation area refers to an area within a predetermined distance from the mark M. For example, a circular area having a radius of 1 to 3 m centered on the mark M, or in front of the mark M (on the robot side). It is arbitrarily set like a 3 m rectangular area.

Returning to FIG. 1, the description of the configuration of the robot control system A will be continued.
The base station 1 mediates data exchange between the robot R and the management computer 3.
Specifically, the base station 1 transmits an execution command output from the management computer 3 to the robot R, and also transmits data (status information) on the state of the robot R transmitted from the robot R and the execution command from the robot R. Is received and a signal (reception report signal) is received and output to the management computer 3.
At least one base station 1 is provided in the task execution area in order to ensure data exchange between the robot R and the management computer 3.
In addition, when the task execution area is set over several floors of the building, it is preferable to be provided for each floor. When one base station 1 cannot cover all the task execution areas, A plurality of base stations 1 are preferably provided in the task execution area.

  The robot dedicated network 2 connects the base station 1, the management computer 3, and the network 4, and is realized by a LAN (Local Area Network) or the like.

  The management computer 3 manages a plurality of robots R, and performs various controls such as movement and speech of the robot R via the base station 1 and the robot dedicated network 2 and information necessary for the robot R. I will provide a. Here, the necessary information corresponds to the name of the detected person, a map around the robot R (local map), and the like. These pieces of information are stored in the storage unit 3a of the management computer 3. ing.

  Here, as shown in FIG. 3A, the guide area 301 is a rectangular area on the floor where the building is located. The robot R and a person to be guided by the robot R enter the guidance area 301 through the corridor 303 outside the entrance 302 of the guidance area 301. A hall 304 extends inside the entrance / exit 302, and a reception 305 is disposed in the back corner of the hall 304, and a plurality of conference rooms 306 (306a, 306b) partitioned as private rooms on the wall side of the guide area 301 are provided. , 306c). The reception 305 includes an L-shaped counter table 305a and a counter space 305b in which reception staff are arranged. The base station 1 is installed in the counter space 305b. The management computer 3 includes a local map (local map data) in which information on local maps such as passages and rooms is registered in association with position coordinate data, and a global map that is map information of a task execution area in which the local maps are accumulated. Are stored in the storage unit 3a (see FIG. 1).

Further, the management computer 3 holds a task information database that stores information (task data) related to tasks to be executed by the robot R in the storage unit 3a (see FIG. 1).
As shown in FIG. 4, the task information database 400 includes a task ID that is a unique identifier assigned to each task, a task priority, a task importance, a robot ID that is an identifier of a robot that executes the task, Contents of tasks such as guidance and transportation (package delivery), the position where the task starts within the task execution area (start position), the position where the task ends within the task execution area (end position), and the time required to execute the task ( Time required), scheduled task start time (start time), scheduled task end time (end time), task status, and the like are included as information items.

The management computer 3 sets an execution plan (task schedule) for tasks to be executed by the robot R for each robot R.
As shown in FIG. 5, the task schedule table 500 includes an execution order of tasks to be executed by the robot R, a task ID for identifying a task registered in the task information database 400 (see FIG. 4), a task priority, It is a table that includes task contents and task status as information items.
In this task schedule table 500, these information items are arranged for each robot R arranged in the task execution area, and what kind of tasks are assigned to each robot R in what order. It is possible to grasp.

Returning to FIG. 1 again, the description of the configuration of the robot control system A will be continued.
The terminal 5 is connected to the management computer 3 via the network 4 and registers information related to a person in the storage unit 3a of the management computer 3 or corrects the registered information. The terminal 5 is used for registering tasks to be executed by the robot R, changing a task schedule set in the management computer 3, inputting an operation command for the robot R, and the like.

  Hereinafter, the robot R will be described in detail.

[robot]
In addition to the head R1, the arm R2, the leg R3, the trunk R4, and the rear housing R5, the robot R includes cameras C and C, speakers as shown in FIG. S, microphone MC, MC, image processing unit 10, audio processing unit 20, storage unit 30, main control unit 40, autonomous movement control unit 50, wireless communication unit 60, battery 70, object detection unit 80, and surrounding state detection unit 90.
Furthermore, the robot R includes a gyro sensor SR1 that detects the direction in which the robot R is facing, and a GPS (Global Positioning System) receiver SR2 that acquires the position coordinates of the robot R on a preset map. Have.

[camera]
Cameras (visual sensors) C and C are capable of taking an image of the robot R in the forward movement direction as digital data, and for example, a color CCD (Charge-Coupled Device) camera is used. The cameras C and C are arranged side by side in parallel on the left and right, and the captured image is output to the image processing unit 10. The cameras C and C, the speaker S, and the microphones (voice input units) MC and MC are all disposed inside the head R1. The speaker (sound output unit) S can emit a predetermined sound synthesized by the sound processing unit 20.

[Image processing unit]
The image processing unit 10 processes images (captured images) taken by the cameras C and C, and recognizes surrounding obstacles and persons in order to grasp the situation around the robot R from the taken images. It is. The image processing unit 10 includes a stereo processing unit 11a, a moving body extraction unit 11b, and a face recognition unit 11c. The image processing unit 10 can function as an external information acquisition unit together with the cameras C and C.
The stereo processing unit 11a performs pattern matching on the basis of one of the two images taken by the left and right cameras C and C, calculates the parallax of each corresponding pixel in the left and right images, and generates a parallax image. The generated parallax image and the original image are output to the moving object extraction unit 11b. This parallax represents the distance from the robot R to the photographed object.

The moving body extraction unit 11b extracts a moving body in the photographed image based on the data output from the stereo processing unit 11a. The reason for extracting the moving object (moving body) is to recognize the person by estimating that the moving object is a person.
In order to extract the moving object, the moving object extraction unit 11b stores images of several past frames (frames), compares the newest frame (image) with the past frames (images), and Pattern matching is performed, the movement amount of each pixel is calculated, and a movement amount image is generated. Then, from the parallax image and the movement amount image, when there is a pixel with a large movement amount within a predetermined distance range from the cameras C and C, it is estimated that there is a person, and as a parallax image of only the predetermined distance range The moving body is extracted, and an image of the moving body is output to the face recognition unit 11c.

The face recognition unit 11c recognizes the face area and the face position from the size, shape, etc. of a part of the extracted moving body. Similarly, the position of the hand is also recognized from the size and shape of a part of the extracted moving body.
The recognized face position is output to the main control unit 40 as information when the robot R moves and to communicate with the person.

[Audio processor]
The voice processing unit 20 includes a voice synthesis unit 21a, a voice recognition unit 21b, and a sound source localization unit 21c.
The voice synthesizer 21a is a part that generates voice data from character information (text data) and outputs the synthesized voice to the speaker S based on a speech action command determined and output by the main controller 40. For the generation of the voice data, the correspondence between the character information (text data) stored in the storage unit 30 in advance and the voice data is used. The audio data is acquired from the management computer 3 and stored in the storage unit 30.

  The voice recognition unit 21b receives voice data (for example, human voice) from the microphones MC and MC, and generates character information (text data) from the inputted voice data by voice recognition. Specifically, the speech recognition unit 21b performs speech recognition using, for example, a hidden Markov model (HMM), and a word reliability indicating the reliability of the speech recognition result for each word included in the input speech data. Is calculated. Here, in the field of speech recognition, the word reliability is calculated based on the likelihood indicating the certainty of the word when applied to a word model modeled using a known hidden Markov model. it can.

  As such a speech recognition engine for calculating the word reliability, for example, Julius speech recognition system which is open source software can be used (http://julius.sourceforge.jp/index.php?q=doc /cm.html).

  In addition, the voice recognition unit 21b calculates the volume of the input voice data and the utterance time thereof. The voice recognition unit 21b performs main control on the character information (text data), the word reliability of all words included in the input voice data, the volume of the input voice data, and the calculated utterance time. To the unit 40.

This volume can be calculated as follows. First, the voice recognition unit 21b divides the voice data into voice frames having a predetermined length (frame length) of about 10 ms, for example. Then, the voice recognition unit 21b can obtain the volume in the voice frame by calculating the power spectrum for each voice frame. Furthermore, the voice recognition unit 21b can calculate and use the maximum value or the average value of the volume in the utterance section as the volume in the utterance.
The utterance length can be calculated by counting the number of audio frames included in the utterance section and multiplying by the frame length.

  In addition, the voice input unit 21b may analyze the converted voice data and detect whether or not voice (person's voice) is included in the input voice data, that is, whether or not voice is present.

  The sound source localization unit 21 c specifies a sound source position (a planar position recognized by the robot R) based on the sound pressure difference between the microphones MC and MC and the sound arrival time difference, and outputs the sound source position to the main control unit 40. The sound source position is represented by, for example, a rotation angle θz around the direction in which the robot R stands (z-axis direction).

[Memory]
The storage unit 30 is composed of, for example, a general hard disk and stores necessary information (local map data, conversation data, etc.) transmitted from the management computer 3. Further, the storage unit 30 stores information necessary for performing various operations of the main control unit 40, as will be described later.

[Main control section]
The main control unit 40 controls the image processing unit 10, the sound processing unit 20, the storage unit 30, the autonomous movement control unit 50, the wireless communication unit 60, the target detection unit 80, and the surrounding state detection unit 90. The data detected by the gyro sensor SR1 and the GPS receiver SR2 is output to the main control unit 40 and used to determine the behavior of the robot R. The main control unit 40 includes, for example, control for communicating with the management computer 3, control for executing a predetermined task based on a task execution command acquired from the management computer 3, and the robot R as a destination. In order to perform control for movement, control for identifying a person, and control for interacting with a person, various determinations are made and commands for the operation of each unit are generated.

[Autonomous Movement Control Unit]
The autonomous movement control unit 50 drives the head R1, the arm R2, the leg R3, and the trunk R4 in accordance with instructions from the main control unit 40. Although not shown, the autonomous movement control unit 50 includes a neck control unit that drives the neck joint of the head R1, a hand control unit that drives the finger joint at the tip of the arm R2, and a shoulder joint of the arm unit R2. , Arm control unit for driving the elbow joint and wrist joint, waist control unit for rotating the torso R4 horizontally with respect to the leg R3, foot control unit for driving the hip joint, knee joint and ankle joint of the leg R3 have. The neck control unit, hand control unit, arm control unit, waist control unit, and foot control unit output drive signals to actuators that drive the head R1, arm R2, leg R3, and torso R4.

[Wireless communication part]
The wireless communication unit 60 is a communication device that transmits and receives data to and from the management computer 3. The wireless communication unit 60 includes a public line communication device 61a and a wireless communication device 61b.
The public line communication device 61a is a wireless communication means using a public line such as a mobile phone line or a PHS (Personal Handyphone System) line. On the other hand, the wireless communication device 61b is a wireless communication unit using short-range wireless communication such as a wireless LAN conforming to the IEEE802.11b standard.
The wireless communication unit 60 performs data communication with the management computer 3 by selecting the public line communication device 61 a or the wireless communication device 61 b in accordance with a connection request from the management computer 3.

  The battery 70 is a power supply source necessary for the operation and processing of each unit of the robot R. The battery 70 has a rechargeable configuration. The robot R is fitted into the charger of the battery 70 in the battery replenishment area (see FIG. 1) and is charged by the battery.

[Target detection unit]
The target detection unit 80 detects whether or not there is a person with the tag T around the robot R. The target detection unit 80 includes a plurality of light emitting units 81 (only one is displayed in FIG. 6). These light emitting units 81 are constituted by LEDs, for example, and are arranged on the front and rear, right and left along the outer periphery of the head R1 of the robot R (not shown). The target detection unit 80 transmits infrared light including a signal indicating a light emitting unit ID for identifying each light emitting unit 81 from the light emitting unit 81 and receives a reception report signal from the tag T that has received the infrared light. To do. The tag T that has received any infrared light generates a reception report signal based on the light emitting unit ID included in the infrared light, so that the robot R determines the light emitting unit ID included in the reception report signal. By referencing, it is possible to specify in which direction the tag T exists as viewed from the robot R. Further, the target detection unit 80 has a function of specifying the distance to the tag T based on the radio wave intensity of the reception report signal acquired from the tag T. Therefore, the target detection unit 80 can specify the position (distance and direction) of the tag T as the position of the person based on the reception report signal. Further, the target detection unit 80 not only emits infrared light from the light emitting unit 81 but also transmits a radio wave including a signal indicating the robot ID from an antenna (not shown). Thus, the tag T that has received the radio wave can correctly identify the robot R that has transmitted infrared light. Details of the target detection unit 80 and the tag T are disclosed in, for example, Japanese Patent Application Laid-Open No. 2006-192563. The target detection unit 80 can function as an external information acquisition unit.

  Each tag T has a unique tag identification number (personal identification information) associated with the person with the tag T. The tag identification number is included in the reception report signal and transmitted to the robot R. To do. Then, the target detection unit 80 outputs the tag identification number received from the tag T to the main control unit 40. Thereby, the robot R can specify the person with the tag T by the tag identification number included in the reception report signal transmitted from the tag T.

[Ambient condition detector]
The peripheral state detection unit 90 detects the peripheral state of the robot R, and can acquire self-position data detected by the gyro sensor SR1 and the GPS receiver SR2. The peripheral state detection unit 90 includes a laser irradiation unit 91 that irradiates slit light toward the search region, an infrared irradiation unit 92 that irradiates infrared light toward the search region, and a search region irradiated with slit light or infrared rays. And a floor camera 93. The peripheral state detection unit 90 detects a road surface state by analyzing a slit light image (an image when the slit light is irradiated) captured by the floor camera 93. Further, the peripheral state detection unit 90 analyzes the infrared image captured by the floor camera 93 (image when irradiated with infrared rays) to detect the mark M (see FIG. 2), and the position of the detected mark M The relative positional relationship between the mark M and the robot R is calculated from (coordinates). Details of the peripheral state detection unit 90 are disclosed in, for example, Japanese Patent Application Laid-Open No. 2006-167844. The peripheral state detection unit 90 can function as an external information acquisition unit.

[Configuration of main controller]
The main control unit 40 includes a stationary obstacle integration unit 41, an object data integration unit 42, an action pattern unit 43, a gesture integration unit 44, an internal state detection unit 45, and an action plan management unit 46. .

  The stationary obstacle integration unit 41 integrates information related to the peripheral state of the robot R detected by the peripheral state detection unit 90 and outputs the information to the behavior pattern unit 43. For example, when the stationary obstacle integration unit 41 detects an obstacle such as a cardboard box on the floor surface of the path of the robot R or detects a step on the floor surface, the behavior pattern unit 43 is integrated. Based on the obstacle information, a bypass route is searched by a local avoidance module (not shown).

  The object data integration unit 42 integrates identification data (object data) related to the object (object) based on the posture data of the robot R, the input data from the image processing unit 10, the target detection unit 80, and the sound source localization unit 21c. The integrated object data is output to the object data storage means 31 of the storage unit 30. As a result, an object map, which is data in which object data is recorded for each object and for each time, is generated in the object data storage unit 31.

  The behavior pattern unit 43 stores various programs (modules) for executing the behavior pattern, and reflects the behavior pattern by referring to the storage unit 30 when the behavior pattern is executed.

  Further, the behavior pattern unit 43 includes a response behavior control unit 47. The response behavior control unit 47 generates, for example, a voice input status or a voice recognition processing status of the input voice generated by the behavior pattern unit 43 when the robot R executes a task including an utterance. It is constantly monitored with a period of about milliseconds, and the action according to the situation at that time is executed. Details of the response behavior control unit 47 will be described later.

  In this embodiment, as shown in FIG. 7, in addition to the object data storage unit 31, the local map data storage unit 32, the rule DB storage unit 33, the situation DB storage unit 34, and the speech information are stored in the storage unit 30. Storage means 35.

  The local map data storage means 32 stores a map (local map) around the robot R described with reference to FIG. This local map is acquired from the management computer 3, for example.

  The rule DB storage unit 33 stores scenarios (scripts) corresponding to various behavior patterns, rules (response behaviors) according to the situation, specific operation contents and utterance contents for executing the rules, and the like. Further, the rule indicates the operation content or utterance content of the robot R according to the situation. Here, a rule indicating that the voice of the person can be recognized but cannot be answered to the voice of the person is called an unanswerable action. Further, the scenario relates to an operation such as, for example, stopping at 1 m before an object when encountering a person or an obstacle (object) while walking, or raising the arm R2 to a predetermined position 10 seconds after stopping. There are things related to utterances. In addition, the rule DB storage unit 33 specifies in advance a gesture that is a body motion that moves at least one of the head R1, the arm R2, the leg R3, and the torso R4 when performing a predetermined utterance. The created scenario is stored. The rule DB and operation DB stored in the rule DB storage unit 33 will be described later.

  The situation DB storage unit 34 stores information on the current situation (situation DB). In the present embodiment, the situation DB is the processing result of the image processing unit 10 that processes the images acquired via the cameras C and C, and the processing result of the voice recognition unit 21b that recognizes the voice input to the microphones MC and MC. The data indicating the situation including the recognition result of the tag T by the object detection unit 80 as the surrounding situation is stored. Information stored in the situation DB storage unit 34 is used when a rule stored in the rule DB storage unit 33 is selected. A specific example of the situation DB stored in the situation DB storage unit 34 will be described later.

  The situation DB storage means 34 stores an average volume DB (not shown) that stores the average volume of the voice data for each person, and a volume history data DB (not shown). In this embodiment, since personal identification is performed using personal identification information, the average volume DB stores the personal identification information and the average volume of the person indicated by the personal identification information in association with each other. The volume history data DB manages how many people speak at what volume and how many times. The average sound volume DB and the sound volume history data DB are written by the average sound volume calculation means 474 described later.

In the present embodiment, the average volume is determined by identifying a person who is a speaker based on a tag identification number for identifying a tag T (see FIG. 6) worn by the person and identifying the person. Although the average volume stored in the situation DB is input in association with each other, the present invention is not limited to this. For example, a person is specified by object data indicating a person to be integrated by the object data integration unit 42 (see FIG. 7), and the volume when the person speaks is associated with the object data for specifying the person in the situation DB. The storage unit 34 stores the volume of the person as a history. Then, when this person speaks again, the average sound volume is obtained by calculating the average sound volume when speaking in the past stored in the situation DB storage means 34 in association with the object data. Also good.
Thereby, even a person who does not wear the tag T (see FIG. 6) can refer to the average volume in the second and subsequent utterances.
Even if there are a plurality of persons near the robot R (see FIG. 6) and it is difficult to recognize the tag identification number of each person, the sound source localization information output from the sound source localization unit 21c (see FIG. 6) is used. Thus, it is possible to specify object data of the person who made the utterance. Then, by storing the volume of this utterance in association with the specified object data in the situation DB storage means 34 as a history of the volume of this person, a tag identification number is assigned to the person who has spoken once. Even if it cannot be specified, the average volume of this person can be referred to in the second and subsequent utterances.

  The utterance information storage means 35 stores information used for the utterance of the robot R. The utterance information storage means 35 stores conversation information defined by scenarios corresponding to various behavior patterns. Here, conversation information is, for example, fixed phrase that indicates the greeting "○○'s, Hello", "this, we pass to △△'s" boilerplate statement that indicates the confirmation is included, and the like. Further, the utterance information storage unit 35 stores information on the utterance contents when executing the rules stored in the rule DB storage unit 33. Here, the utterance content information at the time of executing the rule includes, for example, “high” indicating a reply, a fixed phrase “□ hour □ minute” indicating a time, and the like. These pieces of information (conversation data) are transmitted from the management computer 3, for example.

  The behavior pattern unit 43 uses the object data storage unit 31, the local map data storage unit 32, the rule DB storage unit 33, the situation DB storage unit 34, and the utterance information storage unit 35 as appropriate to perform actions according to various scenes and situations. A module for executing patterns is provided. Examples of the module include a destination movement module, a local avoidance module, a delivery module, a guidance module, a response behavior control module, and a human correspondence module.

The destination movement module performs route search (for example, search for a route between nodes) and movement from the current position of the robot R to a destination such as a task execution position in the task execution area. This destination movement module obtains the shortest distance to the destination while referring to the map data and the current position.
The local avoidance module searches for a detour route for avoiding an obstacle based on the obstacle information integrated by the stationary obstacle integration unit 41 when an obstacle is detected during walking.

The delivery module operates when a package delivery task is executed. The delivery module receives (holds) an article from a person requesting transportation of the article (client), and delivers the received article to the recipient (article). The action is performed.
The guidance module executes, for example, a task for guiding a visitor who has visited a guidance start point in the task execution area to a reception staff in the reception 305 of the guidance area 301 (see FIG. 3).

  The person handling module performs, for example, speech, posture change, vertical movement and gripping of the arm R2 based on a predetermined scenario when executing an article transport task or a guidance task. The person handling module can intentionally speak a light greeting, a weather topic or the like for any purpose regardless of the execution of the task.

  In addition, the person support module includes an encounter response module that performs operations such as greetings various people, and a presentation QA (presentation and question and answer) module that executes services such as explanations and question-and-answer sessions for specific parties. Submodules are included.

  The response behavior control module is a module for controlling the behavior with respect to the input voice when the robot R detects the input voice at the time of executing a task including an utterance such as a human correspondence module. The response behavior control module is activated by the behavior pattern unit 43 when it is necessary to perform such behavior, and the response behavior control unit 47 is generated in the behavior pattern unit 43 by activation. Details of the response behavior control unit 47 will be described later.

  The gesture integration unit 44 extracts gestures corresponding to utterances to be performed on the target person from the rule DB storage unit 33 and outputs a command for designating the extracted gestures to the autonomous movement control unit 50. Gestures by the movement of the head R1, for example, by tilting the head R1 downward, displaying “bowing”, “thanks”, “agreement”, “apology”, etc., and tilting the head R1 left and right ( It includes an action that conveys an intentional expression of “I don't know”. The gesture by the movement of the arm part R2 is, for example, an action of displaying “joy”, “praise”, etc. by raising the arm part R2, expanding the arm part R2 to the left and right, or shaking hands. This includes an action to convey an expression of “welcome”. The gesture by the operation of the leg portion R3 includes, for example, an operation of transmitting intention indications such as “joy” and “goodness” by running on the spot.

  The internal state detection unit 45 detects the internal state of the robot R. In the present embodiment, the internal state detection unit 45 detects the charging status (information indicating whether or not the battery has been fitted) and the remaining amount of the battery 70. Further, the internal state detection unit 45 generates data relating to the state of the robot R (current position, charging state, remaining battery level, task execution state, etc.) as status information at predetermined time intervals. Further, the internal state detection unit 45 outputs the generated status information to the management computer 3 via the wireless communication unit 60. Then, the management computer 3 registers the input status information for each robot R in a robot information database (not shown) stored in the storage unit 3a.

  The action plan management unit 46 manages an action plan for executing various modules included in the action pattern unit 43 according to a predetermined schedule. In the present embodiment, the action plan management unit 46 manages an action plan for executing a predetermined task based on a task execution command acquired from the management computer 3, and is a module necessary for work to be currently executed. Is appropriately selected.

[Configuration of Response Action Control Unit]
As shown in FIG. 8, the response behavior control unit 47 includes a response behavior determination unit (response behavior determination unit) 471, a behavior selection unit (response behavior selection unit) 472, a behavior command unit (response behavior command unit) 473, And an average sound volume calculation means (average sound volume calculation unit) 474, which perform later-described control based on various information and data stored in the storage unit 30.

  The rule DB storage means 33 provided in the storage unit 30 stores the rule DB (response action list) and the action DB (action database) as described above. Here, specific examples of the rule DB and the action DB will be described with reference to FIGS. 9 and 10.

  The rule DB (response action list) 900 stores a plurality of rules (response actions) including unanswerable actions. As illustrated in FIG. 9, the rule DB 900 includes, as items, a rule ID 901, a rule content 902, an answer impossible flag 903, and an operation ID 904.

The rule ID 901 is an identifier that uniquely identifies the rule.
The rule content 902 indicates the content of the rule.

  The unanswerable flag 903 is a flag that indicates whether the rule is an unanswerable action or a rule other than an unanswerable action. For example, the rule with the rule ID = “1” indicates that it is a rule other than the answer impossible action because the answer impossible flag = “0”. Further, for example, the rule with the rule ID = “7” indicates an unanswerable action because the unanswerable flag = “1”. Hereinafter, rules other than the unanswerable behavior are assumed to be normal rules.

  The action ID 904 indicates a correspondence relationship between the rule contents 902 and the action contents of the action DB (see FIG. 10). For example, the rule with the rule ID = “1” indicates that it corresponds to the operation ID = “4” of the operation DB (see FIG. 10). This indicates “surprise (= surprised)” in the operation DB (see FIG. 10). Further, for example, the rule with the rule ID = “7” indicates that it corresponds to the operation ID = “11” of the operation DB (see FIG. 10). This indicates “pronounces“ n ”by raising the neck” in the operation DB (see FIG. 10).

As shown in FIG. 10, the action DB 1000 includes, as items, an action ID 1001, action contents 1002, and a neck 1003, a palm 1004, a waist 1005, an arm 1006, and a mouth 1007 as an example of a movable part. Yes. Here, the site refers to, for example, the neck (head R1), palm or arm (arm R2), waist (leg R3, torso R4), mouth (speaker S).
For example, the action ID = “5” indicates that the action “raise the hand with the face or body toward the target” is performed by using the neck, the waist, and the arm. Further, for example, the operation ID = “11” indicates that the operation “pronounces“ n ”by raising the neck” is performed by using the neck and mouth.

Further, although details are not shown for the operation ID = “7” and “8”, the operation is determined for each degree of freedom of the joint of the arm R2 to be moved by the autonomous movement control unit 50 and the rotation angle of each joint. Different operation IDs were assigned. Here, the degree of freedom of the joint indicates movement such as bending the joint in the front-rear direction, bending in the up-down direction, and rotating. In addition, it can set similarly also in parts other than arm part R2.
The operation ID = “9”, “10” is not shown in detail, but a different operation ID is assigned to each sound volume synthesized by the speech synthesizer 21a. In addition to the operations shown in FIG. 10, for example, operations such as “twisting hips”, “waving arms hanging”, “closing or opening fingers”, “waving articles such as gripped flags”, etc. May be included.

Returning to FIG. 8, the description of the configuration of the response behavior control unit 47 is continued.
The situation DB storage means 34 provided in the storage unit 30 stores the situation DB as described above. The situation DB stores data indicating a situation including the result of image processing or voice recognition processing as a surrounding situation. In the present embodiment, the situation DB stores data indicating whether or not the battery is being charged as data indicating the internal situation in addition to the surrounding situation.

Here, a specific example of the situation DB will be described with reference to FIG.
As shown in FIG. 11, the situation DB 1100 has a situation ID 1101, a situation content 1102, and a current display 1103 as items of the current situation. The current display 1103 indicates the current value of the situation content 1102. Here, “on” indicates “1”, and “off” indicates “0”. Information is written to the item of the current display 1103 by the object data integration unit 42 and the internal state detection unit 45.

  Specifically, the object data integration unit 42 sets the corresponding information on the situation indicated by the situation IDs “0” and “3” shown in FIG. 11 based on the image processing result from the image processing unit 10. Write to DB. Note that the method for recognizing the situation “there is a person approaching” indicated by the situation ID = “3” is, for example, the number of pixels of the recognized face image increased as a result of the image processing by the image processing unit 10. Can be recognized as such. Further, the object data integration unit 42 writes the corresponding information in the situation DB based on the input data from the target detection unit 80 for the situation indicated by the situation ID = “1”, “2”, for example. The object data integration unit 42 writes, for example, the situation indicated by the situation ID = “4” and “5” in the situation DB when voice is input from the microphones MC and MC. For example, for the situation indicated by the situation ID = “7”, the object data integration unit 42 writes the corresponding information in the situation DB based on the input data from the sound source localization unit 21c. For example, for the situation indicated by situation ID = “8”, the object data integration unit 42 writes corresponding information in the situation DB based on the object map stored in the object data storage unit 31 (see FIG. 7). For example, for the situation indicated by situation ID = “6”, the internal state detection unit 45 writes the corresponding information in the situation DB.

Returning to FIG. 8, the description of the configuration of the response behavior control unit 47 is continued.
The response behavior determination means 471 receives from the voice processing unit 20 character information obtained by voice recognition of voice data, word reliability of all words included in the voice data, volume of the voice data, and speech time of the voice data. Are entered. The response behavior determination unit 471 receives personal identification information from the target detection unit 80. Then, the response action determination unit 471 calculates an evaluation value from this word reliability, and compares the evaluation value with a value less than the threshold value to determine whether or not to perform an unanswerable action. Furthermore, the response action determination unit 471 outputs the input character information and the determination result as to whether or not to perform an answer impossible action to the action selection unit 472. Hereinafter, four specific examples of calculating the evaluation value will be described. Note that this evaluation value is a value that is a criterion for determining whether or not to perform an unanswerable action.

<First example: word reliability>
Here, for example, with respect to “Tell me about the episode of development” that has been successfully voice-recognized, the word reliability of each word is the word reliability “0.427” of the word “,” and the word “development”. Word reliability “0.978”, word “no”, word reliability “0.342”, word “episode”, word reliability “0.235”, word “o”, word reliability “0.106” , The word reliability “0.487” of the word “teach”, the word reliability “0.174” of the word “te”, and the word reliability “0.935” of the word “.”. For example, assume that the threshold is “0.3”. In this case, the response action determination unit 471 calculates an average value “0.4605” of the word reliability of each word, and uses this average value as an evaluation value. Then, the response behavior determination unit 471 determines that the response impossible behavior is not performed because the evaluation value “0.4605” is not less than the threshold value “0.3”.

  As another example, a case will be described in which the voice data “Hey, yes” is an unknown word and is erroneously recognized as “Fun. In this case, the word reliability of each word is the word reliability “0.233” of the word “Fun”, the word reliability “0.024” of the word “.”, And the word reliability “0. 239 ”, the word reliability“ 0.05 ”, and the word reliability“ 0.352 ”of the word“. ”. For example, assume that the threshold is “0.3”. In this case, the response behavior determination unit 471 calculates an average value “0.18” of the word reliability of each word, and uses this average value as an evaluation value. Then, the response action determination unit 471 determines that an unanswerable action is performed because the evaluation value “0.18” is less than the threshold value “0.3”.

  As described above, when the voice is recognized by mistake, the word reliability of each word may be high, but the average score is relatively low. On the contrary, when the voice can be recognized correctly, some words have low word reliability, but the average score is relatively high. Therefore, the success or failure of speech recognition can be determined with higher accuracy by using the average score.

  In the present embodiment, the necessity of answer is determined based on the average score of word reliability. However, the present invention is not limited to this, and other evaluations indicating the reliability of the result of speech recognition. You may determine based on a value (score).

<Second example: Considering word reliability and average volume>
Here, the response behavior determination unit 471 searches the average sound volume DB using the personal identification information input from the target detection unit 80 as a search condition, and extracts the average sound volume of the person performing communication from the average sound volume DB. Further, the response behavior determination unit 471 calculates the volume coefficient by dividing the volume of the voice data input from the voice processing unit 20 (that is, the current volume) by the average volume extracted from the average volume DB. Then, the response action determination unit 471 calculates the evaluation value by multiplying the average value of the word reliability of the first example by the volume coefficient. That is, the response behavior determination unit 471 calculates the evaluation value using the following formula (1) and formula (2).

Evaluation value = average value of word reliability × volume coefficient (1)
Volume coefficient = current volume / average volume (2)
The unit of volume is, for example, decibel (dB).

Here, the volume coefficient will be described.
When a robot R (refer to FIG. 6) speaks while a person to be talked speaks, when the volume is low, there are many cases where the answer is not necessary, and when the volume is high, a question that requires an answer It is often a request. Therefore, the response behavior determination unit 471 calculates a volume coefficient for correcting the average score based on the volume level using the equation (2).

<Third example: Considering word reliability and utterance time>
Here, the response action determination unit 471 calculates the utterance time coefficient by dividing the utterance time input from the target detection unit 80 by the utterance reference time. Then, the response behavior determination unit 471 calculates an evaluation value by multiplying the average value of the word reliability of the first example by the utterance time coefficient. That is, the response behavior determination unit 471 calculates the evaluation value using the following formulas (3) and (4). Note that the utterance reference time is set in advance to, for example, 1.5 seconds from the distribution of voice data that the robot R does not need to answer, such as a person's conflict.

Evaluation value = average value of word reliability × speaking time coefficient (3)
Utterance time coefficient = Utterance time / Utterance reference time (4)
The unit of time is, for example, second.

Here, the speech time coefficient will be described.
When the robot R (see FIG. 6) speaks while the person to be talked is speaking, if the utterance length is short, there are many cases where the answer is not necessary, the answer is not necessary, and if the utterance length is long, the reply is necessary. This is often a question or request. Therefore, the response behavior determination unit 471 calculates an utterance time coefficient for correcting the average score according to the length of the utterance length, using Expression (4).

<Fourth example: Considering word reliability, average volume and utterance time>
Here, the response behavior determination unit 471 includes the average value of the word reliability of the first example, the volume coefficient of the second example (see formula (2)), and the utterance time coefficient of the third example (see formula (4)). Is multiplied to calculate an evaluation value. That is, the response action determination unit 471 calculates an evaluation value using the following equation (5).

  Evaluation value = average value of word reliability × volume coefficient × speech time coefficient (5)

  Note that the response behavior determination unit 471 may calculate the evaluation value by any of the methods described above, and may be set in advance by which method the evaluation value is calculated.

  A predetermined value is set as the threshold used by the response behavior determination unit 471 for the determination. Hereinafter, an example of a threshold setting method will be described with reference to FIG. First, teaching data with correct answers for a voice that requires an answer and a voice that does not require an answer is prepared. Here, the teaching data with correct answer is, for example, a plurality of pieces of data having different attributes (gender, age), utterance contents (vocabulary), volume, and utterance time. And in each teaching data with a correct answer, a score and frequency (data number) are calculated | required and a threshold value is set. For example, the intersection α of the teaching data D2 with correct answer that requires an answer illustrated by a solid line in FIG. 12 and the teaching data D1 with correct answer that does not require an answer illustrated by a broken line in FIG. 12 is obtained. Further, a score corresponding to the intersection α is set as a threshold value. Accordingly, the response behavior determination unit 471 can perform the necessity determination with high accuracy without biasing the erroneous determination toward the necessity.

Returning to FIG. 8, the description of the configuration of the response behavior control unit 47 is continued.
The action selection unit 472 receives the character information and the determination result from the response action determination unit 471 and selects an action according to the determination result. Here, for example, the action selecting unit 472 selects a response action from the rule DB of FIG. 9 using an answer impossible flag in accordance with the determination result. Specifically, when a determination result indicating that an unreplyable action is performed is input, the action selecting unit 472 refers to the rule DB and selects a rule with an unanswerable flag = “1”. Then, the action selection unit 472 outputs the rule ID (for example, rule ID = “7”) of the selected rule to the action command unit 473.

  Moreover, the action selection means 472 selects the action which answers with respect to the input audio | voice, when the determination result that an answer impossible action is not performed is input. In this case, the action selection unit 472 outputs information indicating an action to be answered to the person and the input character information to the action command unit 473.

  Moreover, the action selection means 472 may select a normal rule when the determination result is not input (that is, when communication is not performed). For example, the action selection unit 472 refers to the rule DB and the situation DB, and selects a rule (ordinary rule) with an unanswerable flag = “0”. Specifically, the action selection means 472 refers to the situation DB and, in the situation where there is a person (situation ID = “2”), sees the closest person when the person is present (rule ID = “3”) is selected. In addition, for example, the action selection unit 472 refers to the situation DB, and in the situation where a small sound is made (situation ID = “4”), the action selection unit 472 sees the person making the small sound (rule ID = “4”). ) Is selected. Then, the action selection unit 472 outputs the rule ID of the selected rule (for example, rule ID = “3” or “4”) to the action command unit 473.

The behavior command unit 473 commands the execution of the behavior selected by the behavior selection unit 472 to at least one of the speaker S and the movable unit via the voice processing unit 20, the behavior pattern unit 43, and the gesture integration unit 44. . As an example, when the action selection unit 472 selects an unreplyable action (for example, rule ID = “7”), the action command unit 473 refers to the rule DB and operates the rule having the rule ID. ID (for example, operation ID = “11”) is extracted. Then, the action command unit 473 refers to the action DB, and outputs an action command for causing the “neck” and “mouth” defined by the action ID = “11” to perform an unanswerable action. Accordingly, the gesture integration unit 44 causes the head R1 to perform an action (gesture) of raising the neck. In addition, the voice processing unit 20 causes the speaker S to utter the voice “n” stored in the utterance information storage unit 35.

  For example, when the action selection unit 472 selects an action of answering a person, the action command unit 473 extracts an appropriate answer for the input character information from the utterance information storage unit 35. Then, the behavior command unit 473 commands the voice processing unit 20 to utter the extracted answer (voice). Thus, the voice processing unit 20 causes the answer (voice) stored in the utterance information storage unit 35 to utter from the speaker S.

  For example, when the action selection unit 472 selects a normal rule, the action command unit 473 refers to the rule DB and extracts the operation ID of the rule having the rule ID. Then, the action command unit 473 refers to the action DB, and issues an action command corresponding to the rule to the part defined by the action ID. For example, when the rule ID = “3”, the action command unit 473 has the action DB = “5”, and therefore the rule “turn the head or body toward the target” is applied to “neck”, “waist”, and “arm”. The operation command to be performed is output.

  The average sound volume calculation means 474 receives the sound data volume from the sound processing unit 20 and personal identification information from the target detection unit 80. Then, the average volume calculation means 474 calculates the average volume of the audio data for each person using the volume of the audio data and the personal identification information. Here, for example, every time the volume of the voice data is input from the voice processing unit 20, the average volume calculation means 474 associates the volume of the voice data with the personal identification information of the person who spoke the voice data. Store in the volume history data DB. Then, the average volume calculation unit 474 calculates the average volume for each person by dividing the total volume value stored in the volume history data DB by the number of utterances. Further, the average volume calculation means 474 writes the personal identification information of the person and the average volume of the person in association with each other in the average volume DB.

[Robot motion]
With reference to FIG. 13, the operation of the robot R will be described focusing on the operation of the response behavior control unit 47 (see FIG. 8 as appropriate). In FIG. 13, the evaluation value is calculated by the method of the first example described above.

  First, the response behavior control unit 47 receives the word reliability of all words included in the speech data from the speech processing unit 20 to the response behavior determination unit 471 (step S1). Further, the response behavior control unit 47 calculates the average word reliability by the response behavior determination means 471 and calculates the average value as an evaluation value (step S2). And the response action control part 47 determines whether an evaluation value is less than a threshold value by the response action determination means 471 (step S3).

When the evaluation value is not less than the threshold value (No in Step S3), the response behavior control unit 47 selects the behavior of answering the person by the behavior selection unit 472 (Step S4).
On the other hand, when the evaluation value is less than the threshold value (Yes in Step S3), the response behavior control unit 47 selects an unreplyable behavior by the behavior selection means 472 (Step S5).

  Subsequent to the processing of step S4 or step S5, the response action control unit 47 instructs the action command means 473 to execute the action selected by the action selection means 472 (behavior that cannot be answered or action that answers a person). (Step S6).

  In the present embodiment, since the robot R determines whether or not to perform an unanswerable action by simple threshold determination without requiring an unknown word database and complicated interaction processing, the configuration of the robot R is simplified. be able to. Further, the robot R selects an unanswerable action when the evaluation value is low. At this time, a person communicating with the robot R can easily grasp that the robot R cannot answer his / her voice (for example, some question) by the robot R performing an unanswerable action. Therefore, this person has a high possibility of trying to communicate with the robot R again, for example, generating the same voice with a loud voice at a slow speed or changing the content of the voice. This increases the possibility that the robot R can appropriately answer the voice of a person, and can easily continue communication.

  Further, in the present embodiment, the robot R performs, for example, an operation of “pronuncing the neck and pronounces“ n ”” as an unanswerable action. This unanswerable action is the same as the action of prompting the other party to continue communication in communication between humans. Therefore, the person who is communicating with the robot R can grasp very easily that the robot R cannot reply to his / her voice due to the unanswerable behavior. This makes it easier for the robot R to continue communication.

  Here, although it has been described that the unanswerable behavior is “pronounced with“ necked and pronounced ””, the present invention is not limited to this. The unanswerable behavior may be, for example, a one-word voice of “e”, “he”, or “n”. Further, the unanswerable action may be only an action of, for example, raising the neck. The present invention can achieve the same effects as those of the present embodiment even by these unanswerable behaviors.

  In the present embodiment, the robot R calculates the evaluation value in consideration of the speech utterance time (third example, fourth example). For this reason, although it is not necessary for the robot R to reply to the conversation target, it is possible to prevent the robot R from speaking erroneously and to facilitate communication.

  In the present embodiment, the robot R calculates the evaluation value in consideration of the average sound volume for each person (second example and fourth example). For this reason, the robot R can prevent erroneous selection of an unanswerable action even when there is a high possibility that a person will need an answer, and communication can be continued more easily.

  In the present embodiment, the robot R can also calculate an evaluation value that takes into account the average volume for each person by a method other than the second example and the fourth example. Here, the response behavior determination means 471 can calculate the volume coefficient by the following equation (6) because the maximum change amount is about plus or minus 6 (dB) without significant change in the volume of the person. . Then, the response behavior determination unit 471 calculates an evaluation value using this volume coefficient.

  Volume coefficient = {6- (average volume−current volume)} / 6 (6)

  According to Expression (6), when the volume of the input voice is equal to the average volume, the volume coefficient is “1.0”. On the other hand, when the volume is a substantial lower limit (average volume −6) [dB], the volume coefficient is “0.0”. On the other hand, when the volume is a practical upper limit (average volume + 6) [dB], the volume coefficient is “2.0”. In this way, by using the equation (6), it is possible to calculate a volume coefficient in a suitable and sensitive range corresponding to a change in volume.

  Further, in the present embodiment, the situation DB storage means 34 for storing the situation DB alone is provided, but it may be shared with the object data storage means 31 for storing the object map. Since the object map is data in which object data is recorded by object and by time, a part of the object map can be used as a situation DB.

  Further, in the present embodiment, in the operation DB, the movable part that realizes the operation of the robot R has been described as a neck, a palm, a waist, an arm, and a mouth (speaker). , Shoulders, feet may be included. Furthermore, these parts may be further subdivided and defined.

  In the present embodiment, the robot R has been described as an autonomous mobile robot capable of walking on two legs, but the present invention is not limited to this, and application to an autonomous mobile robot that moves on wheels is also possible. In this case, the same effect as that of the present embodiment can be obtained except that the movable part corresponding to the “foot” of the autonomous mobile robot capable of walking on two legs becomes a “wheel”.

A Robot system R Robot (communication robot)
R1 Head R2 Arm R3 Leg R4 Torso R5 Back storage 1 Base station 2 Robot dedicated network 3 Management computer 3a Storage unit 4 Network 5 Terminal 10 Image processing unit 20 Audio processing unit 21a Audio synthesis unit 21b Audio recognition unit 21c Sound source localization unit 30 storage unit 31 object data storage unit 32 local map data storage unit 33 rule DB storage unit 34 status DB storage unit 35 utterance information storage unit 40 main control unit 41 stationary obstacle integration unit 42 object data integration unit 43 behavior Pattern unit 44 Gesture integration unit 45 Internal state detection unit 46 Action plan management unit 47 Response behavior control unit 471 Response behavior determination means (response behavior determination unit)
472 Action selection means (response action selection unit)
473 Action command means (Response action command section)
474 Average volume calculation means (average volume calculation unit)
DESCRIPTION OF SYMBOLS 50 Autonomous movement control part 60 Wireless communication part 70 Battery 80 Object detection part 90 Peripheral state detection part C Camera (visual sensor)
MC microphone (voice input unit)
S Speaker (Audio output unit)
SR1 Gyro sensor SR2 GPS receiver

Claims (3)

A communication robot having a voice recognition unit for recognizing at least a voice to be interacted inputted by a voice input unit, a voice output unit for outputting voice based on speech information, and a movable unit for performing a predetermined operation,
The voice recognition unit calculates and outputs the reliability of the result of the voice recognition when the voice input unit inputs a voice to be interacted with,
On the basis of the dialogue object of speech in reliability wherein the speech recognizer has been calculated, or while the sound of the dialogue target can be recognized the speech carried a reply incapacitated that it can not answer the voice of the conversation subject A response action determination unit that calculates an evaluation value of whether or not to perform the unanswerable action when the evaluation value is less than a preset threshold value;
When it is determined that the response behavior determination unit performs the response impossible behavior, the response behavior selection unit that selects the response impossible behavior from the predetermined response behavior that the communication robot is capable of,
A response behavior command unit that commands execution of the unanswerable behavior selected by the response behavior selection unit to at least one of the voice output unit and the movable unit;
An average volume calculation unit for calculating an average volume of the voice of the dialogue target for each dialogue target;
Equipped with a,
The response behavior determination unit calculates a volume coefficient obtained by dividing the volume of the conversation target voice input by the voice input unit by the average volume of the conversation target voice calculated by the average volume calculation unit, and calculates the volume coefficient. A communication robot characterized in that a value obtained by multiplying reliability is calculated as the evaluation value. A communication robot having a voice recognition unit for recognizing at least a voice to be interacted inputted by a voice input unit, a voice output unit for outputting voice based on speech information, and a movable unit for performing a predetermined operation,
The voice recognition unit calculates and outputs the reliability of the result of the voice recognition when the voice input unit inputs a voice to be interacted with,
Based on the reliability calculated by the voice recognition unit for the conversation target voice, whether or not to perform an unanswerable action indicating that the conversation target voice can be recognized but cannot be answered to the conversation target voice A response action determination unit that calculates an evaluation value of whether or not to perform the unanswerable action when the evaluation value is less than a preset threshold value;
When it is determined that the response behavior determination unit performs the response impossible behavior, the response behavior selection unit that selects the response impossible behavior from the predetermined response behavior that the communication robot is capable of,
A response behavior command unit that commands execution of the unanswerable behavior selected by the response behavior selection unit to at least one of the voice output unit and the movable unit;
With
The voice recognition unit further calculates a speech duration of the voice to be interacted input by the voice input unit,
The response behavior determination unit calculates an utterance time coefficient obtained by dividing the utterance time calculated by the voice recognition unit by a preset utterance reference time, and at least a value obtained by multiplying the reliability by the utterance time coefficient A communication robot characterized by being calculated as a value. Said response action determining unit, when the evaluation value is less than the threshold, 1 pronounce words sound voices, predetermined operation of the movable portion, or a predetermined operation of pronunciation and the movable portion of the one word of the speech The communication robot according to claim 1 , wherein the communication robot is determined to perform the unanswerable behavior that is a combination of the communication robot and the communication robot.

Images