On-vehicle machine and vehicle

Abstract

To provide a robot capable of reducing a burden of a user on learning of the robot.SOLUTION: A robot includes: voice recognition units (a standard program storage unit 23, an artificial intelligence unit 25 and an operational unit 27) for recognizing voice; a learning unit (an artificial intelligence unit) for learning a recognition result of the voice recognition unit; processing units (a standard program storage unit, an artificial intelligence unit and an operational unit) for performing corresponding processing by using a learning result of the learning unit with respect to the recognition result of the voice recognition unit; and a communication unit 26 which is a storage unit for storing the learning result in an external storage device and a learning result acquisition unit for acquiring the learning result from the storage device.SELECTED DRAWING: Figure 1

Description

REFERENCE TO RELATED APPLICATIONS

[0001] This international application claims priority based on Japanese Patent Application No. 2014-262907, filed with the Japan Patent Office on December 25, 2014, the entire contents of which are incorporated herein by reference. [Technical field]

[0002] The present disclosure relates to robots. [Background technology]

[0003] In recent years, robots that can converse with humans have been attracting attention. These robots pick up human speech using a microphone and estimate the meaning of the speech through speech recognition. They then respond to the estimated meaning by making a response that is associated with the speech (see Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 4015424 Summary of the Invention [Problem to be solved by the invention]

[0005] It is conceivable that the conversational ability of a robot can be improved by learning using artificial intelligence or the like. However, even if the conversational ability of a particular robot is improved by learning, when using another robot in a different location, for example, learning must be performed from the basics. One aspect of the present disclosure is to provide a robot that can reduce the burden on a user in terms of learning the robot. [Means for solving the problem]

[0006] The robot of the present disclosure includes a voice recognition unit that performs voice recognition, a learning unit that learns from the recognition results of the voice recognition unit, a processing unit that performs corresponding processing on the recognition results of the voice recognition unit using the learning results of the learning unit, a memory unit that stores the learning results in an external memory device, and a learning result acquisition unit that acquires the learning results from the memory device.

[0007] The robot of the present disclosure can learn from the recognition results of the voice recognition unit, and can store the learning results in an external storage device and retrieve the learning results from the storage device.

[0008] Therefore, for example, a user can store the learning results obtained by using a first robot in an external storage device, and when using a second robot, can introduce the stored learning results into the second robot. As a result, the user can utilize the learning results of the first robot, and does not necessarily have to make the second robot learn from the basics. [Brief description of the drawings]

[0009] [Figure 1] FIG. 2 is a block diagram showing an electrical configuration of the robot according to the embodiment. [Diagram 2] FIG. 2 is a front view showing the configuration of the robot. [Diagram 3] 11 is a flowchart showing a program setting process executed by a robot. [Figure 4] 1 is a flowchart showing a conversation process executed by a robot. [Diagram 5] 11 is a flowchart showing a learning stop determination process executed by a robot. [Figure 6] FIG. 6A is an explanatory diagram showing an example of an operation for instructing to stop learning, and FIG. 6B is an explanatory diagram showing an example of an operation for instructing to restart learning. [Figure 7] FIG. 2 is a block diagram showing the electrical configuration of a computer. [Figure 8]FIG. 1 is a perspective view illustrating an external appearance of a computer. [Figure 9] FIG. 2 is a block diagram showing an electrical configuration of an in-vehicle device. [Figure 10] 4 is a flowchart showing a vehicle control process executed by an in-vehicle device. [Figure 11] FIG. 11 is a block diagram showing an electrical configuration of a robot according to another embodiment. [Figure 12] 11 is a flowchart showing a program installation process executed by a robot. [Figure 13] 1 is a flowchart showing a conversation process executed by a robot. [Figure 14] 13 is a flowchart showing a second artificial intelligence unit learning stop determination process executed by the robot. [Figure 15] 13 is a flowchart showing a program upload process executed by a robot. [Figure 16] FIG. 13 is a block diagram showing an electrical configuration of a robot according to still another embodiment. [Figure 17] 1 is a flowchart showing a conversation process executed by a robot. [Figure 18] FIG. 2 is an explanatory diagram illustrating a configuration for executing a call process. [Figure 19] 10 is a flowchart showing a call pair setting process executed by a host computer. [Figure 20] FIG. 2 is an explanatory diagram showing a display showing icons. [Explanation of symbols]

[0010] 1, 301...robot, 3...control unit, 5...microphone, 7...camera, 9...touch panel, 11...sensor group, 13...GPS, 15...speaker, 17...motor group, 19...display, 21...input unit, 23...standard program storage unit, 25...artificial intelligence unit, 26...communication unit, 27...arithmetic unit, 29...output unit, 31...cloud network, 33...terminal, 35...head, 37...torso, 39...right arm, 41...left arm, 43...right leg, 45...left leg, 47, 49...wheel, 51...movement motor, 53...neck joint, 55...shoulder joint, 57...elbow joint, 59...wrist joint, 61...joint motor, 63...keyboard, 65...mouse, 67...casing, 69...terminal, 71...vehicle control unit, 101...computer, 201...vehicle-mounted device DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] An embodiment of the present disclosure will be described with reference to the drawings. <First embodiment> 1. Robot 1 Configuration The configuration of the robot 1 will be described with reference to Figures 1 and 2. The robot 1 includes a control unit 3, a microphone 5, a camera 7, a touch panel 9, a group of sensors 11, a GPS 13, a speaker 15, a group of motors 17, and a display 19, as shown in Figure 1.

[0012] The control unit 3 includes a microcomputer. Specifically, the control unit includes an input unit 21, a standard program storage unit 23, an artificial intelligence unit 25, a communication unit 26, a calculation unit 27, and an output unit 29.

[0013] The input unit 21 acquires information from the microphone 5 , the camera 7 , the touch panel 9 , the sensor group 11 , and the GPS 13 , and outputs the information to the calculation unit 27 and the artificial intelligence unit 25 .

[0014] The standard program storage unit 23 constantly stores standard programs for executing various operations of the robot 1. The standard programs are different from the AI ​​programs described later. It is a program whose contents do not change.

[0015] The artificial intelligence unit 25 can store AI (artificial intelligence) programs for executing various operations of the robot 1. When the artificial intelligence unit 25 stores an AI program, it changes and develops it through learning. In addition, the artificial intelligence unit 25 can install new AI programs and erase AI programs.

[0016] The communication unit 26 communicates with an external cloud network 31, a terminal 33, etc. The communication may be wireless communication or wired communication. The arithmetic unit 27 executes the calculations required to realize various operations of the robot 1 using a standard program or an AI program.

[0017] The output unit 29 outputs the calculation results of the calculation unit 27 to the speaker 15, the motor group 17, and the display 19. The functions of each unit belonging to the control unit 3 will be described in detail later.

[0018] As shown in FIG. 2, the robot 1 has a humanoid appearance and includes a head 35, a torso 37, a right arm 39, a left arm 41, a right leg 43, and a left leg 45. The microphone 5, the camera 7, and the speaker 15 are provided in the head 35. The display 19 and the touch panel 9 are provided on the front side of the torso 37.

[0019] The right leg 43 and the left leg 45 are each provided with wheels 47, 49 for movement. Two wheels 47, 49 are provided in the front-rear direction. Thus, the robot 1 comes into contact with the ground with a total of four wheels. The wheels 47, 49 are driven by a movement motor 51 belonging to the motor group 17. The wheels 47, 49 are rotated by the driving force of the movement motor 51, thereby enabling the robot 1 to move forward and backward. In addition, by making the rotation speed of the wheel 47 and the rotation speed of the wheel 49 different, the robot 1 can turn right or left.

[0020] The robot 1 includes a neck joint 53, a shoulder joint 55, an elbow joint 57, and a wrist joint 59. The degree of freedom of each joint can be appropriately set from 1 to 3. Each joint is operated by the driving force of a joint motor 61 belonging to the motor group 17. By driving an appropriately selected one of the above joints with the joint motor 61, the robot 1 performs a predetermined operation and expresses a predetermined posture.

[0021] A plurality of sensors belonging to the sensor group 11 detects the position, speed, acceleration, inclination, joint angles, etc. of each part of the robot 1. The detection results are fed back to the arithmetic unit 27 via the input unit 21 and are used to control the operation of the robot 1.

[0022] The standard program storage unit 23, the artificial intelligence unit 25, and the calculation unit 27 are examples of a voice recognition unit, a processing unit, and a learning stop unit. The artificial intelligence unit 25 is an example of a learning unit. The communication unit 26 is an example of a storage unit and a learning result acquisition unit. The input unit 21 and the communication unit 26 are examples of an identification information acquisition unit. The cloud network 31 is an example of an external storage device.

[0023] 2. Processing performed by Robot 1 (2-1) Program setting process The control unit 3 executes a program setting process shown in FIG. 3 to determine which of the standard program and the AI ​​program to use. is repeatedly executed at predetermined time intervals while the power of the robot 1 is on.

[0024] In step 1, it is determined whether or not an AI program is being used at that time. If an AI program is not being used (i.e., if a standard program is being used), proceed to step 2. If an AI program is being used, proceed to step 5.

[0025] In step 2, it is determined whether or not the user's identification information has been input. The identification information can be input, for example, in the following manner. · Transmitting identification information from the terminal 33 to the communication unit 26.

[0026] Electromagnetic waves (e.g., radio waves, infrared rays, etc.) representing the identification information are transmitted to the communication unit 26. The electromagnetic waves representing the identification information may be transmitted from the terminal 33, or from a fixed device (e.g., a beacon, a wireless LAN access point, etc.). The electromagnetic waves representing the identification information may be transmitted periodically, in response to a user's instruction, or when the terminal 33, a fixed device, etc. detects the robot 1.

[0027] The user speaks out the contents of the identification information. The microphone 5 picks up the voice and identifies the identification information through voice recognition. A one-dimensional barcode or two-dimensional barcode representing identification information is photographed by the camera 7.

[0028] · Identification information is input using the touch panel 9. The identification information may be composed of numbers or letters, a one-dimensional or two-dimensional image (e.g., a one-dimensional or two-dimensional barcode), biometric information of the user (e.g., a fingerprint, a vein pattern in any part of the body, iris, face, etc.), or may be composed of voice.

[0029] If the identification information has been input, the process proceeds to step 3; if the identification information has not been input, the process ends. In step 3, the AI ​​program and data set corresponding to the identification information determined to have been input in step 2 are installed from the cloud network 31. The installed AI program and data set are stored in the artificial intelligence unit 25.

[0030] The identification information, the AI ​​program, and the data set are associated with each other and stored in the cloud network 31. The data set is used for use, learning, etc. of the AI ​​program, and includes dictionary data used in voice recognition and voice synthesis.

[0031] In step 4, the program used by the robot 1 is changed from the standard program to the AI ​​program installed in step 3. From this point onwards, the robot 1 uses the AI ​​program.

[0032] On the other hand, if the determination in step 1 is affirmative, it is determined in step 5 whether or not a usage end condition for the robot 1 has been satisfied. The usage end condition may be, for example, as follows.

[0033] - The user does not operate the robot 1 for a specified period of time or longer. A state in which the user cannot be recognized in the images from the camera 7 or in the audio picked up by the microphone 5 continues for a specified period of time or longer.

[0034] - The user inputs an end of use to the robot 1 (for example, (For example, say "End of use" out loud, or input information that indicates the end of use into touch panel 9.)

[0035] Robot 1 is powered off. The preset time arrives. If the usage end condition is satisfied, the process proceeds to step 6; if the usage end condition is not satisfied, the process ends.

[0036] In step 6, the AI ​​program and the data set are uploaded to the cloud network 31. At this time, they are uploaded in association with the user's identification information. Note that if learning, which will be described later, has been performed, the AI ​​program and the data set to be uploaded are those after learning.

[0037] In step 7, the AI ​​programs and data sets are erased from the artificial intelligence unit 25. In step 8, the program to be used is changed from the AI ​​program to the standard program. From this point on, the robot 1 uses the standard program.

[0038] (2-2) Conversation processing The control unit 3 executes a conversation process shown in Fig. 4. This process is executed when the microphone 5 detects a volume equal to or greater than a predetermined threshold.

[0039] In step 11, the microphone 5 is used to capture audio. In step 12, the contents of the voice acquired in step 11 are recognized by a well-known voice recognition technology. At this time, if the standard program is used, the contents of the voice are recognized using standard dictionary data that the robot 1 has in advance. In addition, if the AI ​​program is used, the contents of the voice are recognized using dictionary data that is installed from the cloud network 31 together with the AI ​​program and has been strengthened by past learning.

[0040] In step 13, data of the voice that responds to the contents of the voice recognized in step 12 (hereinafter referred to as "answer voice data") is created. At this time, if the standard program is used, the answer voice data is created using standard dictionary data that the robot 1 has in advance. In addition, if the AI ​​program is used, the answer voice data is created using dictionary data that is installed from the cloud network 31 together with the AI ​​program and reinforced by past learning.

[0041] The contents of the reply voice data can be created, for example, by detecting a keyword from the contents of the voice recognized in step 12, and searching for an item previously associated with the keyword in dictionary data. The contents of the reply voice data can also be inferred from the contents of the voice recognized in step 12 using artificial intelligence.

[0042] In step 14, a voice is spoken using the speaker 15 based on the answer voice data created in step 13. That is, a response to the voice acquired in step 11 is spoken.

[0043] In step 15, it is determined whether or not the AI ​​program is being used at that time. If the AI ​​program is being used, the process proceeds to step 16, and if the standard program is being used, the process ends.

[0044] In step 16, it is determined whether learning is stopped at that point. This is set by the learning stop determination process described later. If learning is not stopped, the process proceeds to step 17, and if learning is stopped, the process ends.

[0045] In step 17, the learning restriction details set at that time are obtained. The learning restriction details include, for example, information (such as names, addresses, telephone numbers, email addresses, career history, and images including faces) about the family and acquaintances of the user (the user corresponding to the identification information determined to have been input in step 2).

[0046] In step 18, the contents of the voice recognized in step 12 are learned. An example of the learning is machine learning. The machine learning may be supervised learning or unsupervised learning. The learning may also be learning by an artificial idiot. In this case, a keyword may be extracted from the voice recognized in step 12, and the keyword may be added to a data set (for example, dictionary data used for voice recognition). The keyword may be used, for example, in the process of creating answer voice data (step 13).

[0047] However, even if the contents of the voice are recognized in step 12, if the contents fall within the learning restriction contents acquired in step 17, they are not learned. In step 19, the AI ​​program and the dataset are updated to reflect the learning results from step 18. The AI ​​program and the dataset updated to reflect the learning results are an example of the learning results.

[0048] (2-3) Learning stop decision process The control unit 3 repeatedly executes the learning stop determination process shown in Fig. 5 at predetermined time intervals. In step 21 of Fig. 5, it is determined whether or not the AI ​​program is being used. If the AI ​​program is being used, the process proceeds to step 22, and if the standard program is being used, the process ends.

[0049] In step 22, the position information of the robot 1 is acquired using the GPS 13. In step 23, an image of the surroundings of the robot 1 is acquired using the camera 7. In step 24, the microphone 5 is used to capture audio.

[0050] In step 25, it is determined whether learning is stopped at that time. The state in which learning is stopped begins in step 28, which will be described later, and ends when learning is resumed in step 30, which will be described later. If learning is not stopped, proceed to step 26, and if learning is stopped, proceed to step 29.

[0051] In step 26, it is determined whether there is anything that may trigger learning to stop in the image acquired in step 23 or the audio acquired in step 24. Examples of learning stop triggers include the following:

[0052] A preset action is recognized as an action instructing the robot to stop learning in the image acquired in step 23. As an example of the action, as shown in Fig. 6A, an action of holding an index finger upright and placing it in front of the mouth is given. Another example of the action is a wink.

[0053] In the voice acquired in step 24, a voice that is preset as a keyword instructing to stop learning is recognized. Examples of the keyword include "secret," "off the record," and "private." Another example of the keyword is the name of the user's family or acquaintance. The user may use the name of a family member or acquaintance as a keyword. These can be registered in advance in the robot 1. In addition, the robot 1 may infer which words are the names of the user's family members or acquaintances based on previously recognized voice data, and register the words that it infers to be the names of the user's family members or acquaintances as keywords.

[0054] The face of a person registered in advance is recognized in the image acquired in step 23. This person may be, for example, the user's family member or acquaintance. The user may register in advance a facial image of a person that will trigger the stopping of learning.

[0055] If there is a trigger to stop learning, proceed to step 28; if there is no trigger to stop learning, proceed to step 27. In step 27, it is determined whether the location information acquired in step 22 corresponds to a location registered in advance as a location where learning should be stopped. Examples of the location where learning should be stopped include the user's home, a conference room, etc.

[0056] A user can register in advance the location where learning should be stopped. Also, the robot 1 can infer the location where learning should be stopped based on past data and register the inferred location. For example, the robot 1 can infer that the location where learning should be stopped is the location where learning was previously recognized as a trigger for stopping learning.

[0057] A learning stop state is initiated in step 28. From this point onwards, a positive determination is made in step 16 in the conversation process, and learning in step 18 is not performed. On the other hand, if the answer is YES in step 25, then in step 29 it is determined whether there is anything in the image acquired in step 23 or the audio acquired in step 24 that may be a trigger for restarting learning. Examples of triggers for restarting learning include the following:

[0058] A preset action that indicates the restart of learning is recognized in the image acquired in step 23. For example, as shown in Fig. 6B, the action is to make a circle with the thumb and index finger (indicating OK).

[0059] A voice that is set in advance as a keyword instructing the user to resume learning is recognized from the voice acquired in step 24. Examples of the keyword include "OK," "resume," and "learn."

[0060] If there is a trigger to restart learning, the process proceeds to step 30, and if there is no trigger to restart learning, the process ends. Learning is resumed in step 30. From this point onwards, a negative determination is made in step 16 in the conversation process, and learning in step 18 is carried out.

[0061] (2-4) Schedule management processing The robot 1 can execute the schedule management process shown below. The user inputs his / her own schedule information to the robot 1 in advance. The schedule information may be input, for example, using the touch panel 9 or by voice input. In addition, the schedule information may be transmitted from the terminal 33 to the communication unit 26.

[0062] The schedule information includes at least a due date and an action to be performed by that due date. Based on the voice captured by the microphone 5, the image captured by the camera 7, the information captured from the terminal 33, etc., the robot 1 judges whether or not the user has performed the action included in the schedule information at a time point (for example, one day or three hours) before the due date. If the action has not been performed yet, the robot 1 informs the user by a voice from the speaker 15 or an image displayed on the display 19. Warn the user.

[0063] 3. Effects of Robot 1 (1A) The robot 1 can change and develop the AI ​​program through learning. The robot 1 can also strengthen the contents of a data set (e.g., dictionary data) through learning. The robot 1 can then upload the AI ​​program and data set after learning to the cloud network 31. The robot 1 can also install the AI ​​program and data set uploaded to the cloud network 31.

[0064] The robot 1 in which the learned AI program and data set are installed may be the same as or different from the robot 1 in which learning was performed in the past. Also, the robot 1 in which the learned AI program and data set are installed may be in the same place as the place in which learning was performed in the past, or in a different place.

[0065] Therefore, the user can install the AI ​​program and data set that have been learned through the user's past use from the cloud network 31 into the robot 1 wherever the user is at the time (e.g., various locations such as the workplace, store, home, etc.), and use the robot 1.

[0066] (1B) The robot 1 allows the installation of an AI program and a data set corresponding to a user's identification information, provided that the user's identification information is input. This makes it possible to prevent a user's AI program and data set from being used by another person without permission.

[0067] (1C) The robot 1 can recognize human voices and produce a voice response to the voice. In other words, the robot 1 can converse with people. In addition, when the robot 1 is using an AI program, the robot 1 learns based on the voice recognition results and uses the learning results to create a voice response, so the more the robot learns, the more advanced the conversation becomes.

[0068] (1D) The robot 1 stops learning depending on the actions of people around it, the results of identifying people, etc. This makes it possible to prevent the robot 1 from learning things that are undesirable for the user and then telling others about them later.

[0069] (1E) The robot 1 stops learning depending on the location it is in. This prevents the robot 1 from telling others about things it learned in a location where it is not desired to learn.

[0070] (1F) The robot 1 resumes learning in response to the actions of people around it. This can promote the learning of the robot 1. (1G) The robot 1 does not learn any matter that falls under the learning restriction content. This prevents the robot 1 from learning any matter that is undesirable for the user and then telling others about it later.

[0071] (1H) The robot 1 can manage the user's schedule. (1I) When the conditions for ending the use of the robot 1 are satisfied, the robot 1 erases the AI ​​program and the data set. This allows the user to prevent others from using the user's AI program and data set later. <Second embodiment> 1. Computer 101 Configuration The configuration of the computer 101 will be described with reference to Figures 7 and 8. The electrical configuration of the computer 101 is basically the same as that of the robot 1 in the first embodiment. However, the input unit 21 in the computer 101 is connected to an external microphone 5, camera 7, keyboard 63, mouse 65, and touch panel 9. In addition, the output unit 29 is connected to an external speaker 15 and display 19.

[0072] 8, the computer 101 has a box-shaped housing 67 and houses various components therein. The computer 101 also has a plurality of terminals 69 to which external devices (for example, a microphone 5, a camera 7, a keyboard 63, a mouse 65, a touch panel 9, a speaker 15, a display 19, etc.) can be connected. The computer 101 is a robot in the broad sense.

[0073] 2. Processing performed by Computer 101 The computer 101 executes program setting processing, conversation processing, learning stop determination processing, and schedule management processing, similar to the robot 1 of the first embodiment. The computer 101 also has the same functions as a well-known computer.

[0074] 3. The Benefits of Computer 101 The computer 101 provides the above-mentioned advantages (1A) to (1I). <Third embodiment> 1. Configuration of the in-vehicle device 201 The configuration of the on-vehicle device 201 will be described with reference to Fig. 9. The on-vehicle device 201 is mounted on a vehicle. The electrical configuration of the on-vehicle device 201 is basically the same as that of the computer 101 in the second embodiment. However, the input unit 21 in the on-vehicle device 201 is connected to a microphone 5, a camera 7, a touch panel 9, a group of sensors 11, and a GPS 13 provided in the vehicle.

[0075] The microphone 5 is provided in the vehicle cabin and detects the voices of the vehicle occupants (driver or other passengers). The camera 7 captures images of the occupants. The touch panel 9 is provided in the vehicle cabin and is operated by the occupants. The sensor group 11 detects the driver's driving operations (steering angle, accelerator depression amount, brake depression amount, shift position, etc.) and the vehicle state (speed, acceleration, yaw rate, state of the power unit (internal combustion engine, motor, etc.), remaining fuel, remaining battery, etc.).

[0076] The output unit 29 is connected to the speaker 15, the display 19, and the vehicle control unit 71. The speaker 15 and the display 19 are provided in the vehicle cabin. The vehicle control unit 71 performs various controls related to the vehicle (e.g., steering, acceleration, deceleration, shift changes, etc.). The in-vehicle device 201 is a robot in a broad sense.

[0077] 2. Processing Executed by the Vehicle-Mounted Device 201 (2-1) Processing the same as for Robot 1 The vehicle-mounted device 201 executes a program setting process, a conversation process, a learning stop determination process, and a schedule management process, similar to the robot 1 of the first embodiment.

[0078] (2-2) Vehicle control processing The control unit 3 of the vehicle-mounted device 201 repeatedly executes the vehicle control process shown in Fig. 10 at predetermined time intervals. This process is executed when the microphone 5 detects a volume equal to or greater than a predetermined threshold.

[0079] In step 31, a voice is acquired using the microphone 5. In step 32, a known voice is Using the recognition technology, instructions to the vehicle (for example, starting, stopping, decelerating, accelerating, turning right or left, lane changing, shifting, etc.) are recognized from the voice acquired in the step 31. At this time, if a standard program is being used, the above instructions are recognized using standard dictionary data that is pre-installed in the in-vehicle device 201. Also, if an AI program is being used, the above instructions are recognized using dictionary data that is installed from the cloud network 31 together with the AI ​​program and that has been strengthened by past learning.

[0080] In step 33, the vehicle control details are determined according to the instruction to the vehicle recognized in step 32. For example, if the instruction to the vehicle is to start, the timing to release the brake, the amount of increase in engine speed and the rate of increase, etc. are determined. At this time, if a standard program is being used, the vehicle control details are determined using the standard program. Also, if an AI program is being used, the control details are determined using an AI program that has evolved through past learning.

[0081] In step 34, the control contents determined in step 33 are output to the vehicle control unit 71. The vehicle control unit 71 controls the vehicle in accordance with the control contents. In step 35, it is determined whether or not the AI ​​program is being used at that time. If the AI ​​program is being used, the process proceeds to step 36, and if the standard program is being used, the process ends.

[0082] In step 36, detection results relating to the state of the vehicle are obtained from the sensor group 11. In step 37, learning is performed based on the control content output in step 34 and the sensor output obtained in step 36. This learning is to modify the control content so that the sensor output obtained in step 36 falls within a preset optimum range.

[0083] For example, if the control content output in step 34 was starting, it is confirmed whether the sensor output during the starting process (e.g., sensor output of speed, acceleration, etc.) was within the optimal range, and if it was outside the optimal range, the control content for starting is modified so that the sensor output at the next and subsequent starts will approach the optimal range.

[0084] In step 38, the AI ​​program is updated to reflect the learning results from step 37. 3. Effects of the in-vehicle device 201 The vehicle-mounted device 201 provides the above-mentioned advantages (1A) to (1I). In addition, the vehicle-mounted device 201 also provides the following advantages.

[0085] (3A) The vehicle-mounted device 201 can recognize human voices and perform vehicle control corresponding to the voices. In addition, when the vehicle-mounted device 201 uses an AI program, the vehicle-mounted device 201 performs learning based on the contents of vehicle control output to the vehicle control unit 71 and the sensor output indicating the vehicle state, so that the more learning progresses, the more advanced the vehicle control can be performed.

[0086] (3B) The in-vehicle device 201 can change and develop the AI ​​program for vehicle control processing through learning. Also, the in-vehicle device 201 can install the AI ​​program uploaded to the cloud network 31.

[0087] The vehicle-mounted device 201 into which the AI ​​program after learning is installed may be the same as the vehicle-mounted device 201 that performed learning in the past, or it may be different. Therefore, a user can install and use an AI program that has been learned through his or her own past use in the on-board device 201 of any vehicle from the cloud network 31. <Fourth embodiment> 1. Configuration of Robot 301 The configuration of the robot 301 of this embodiment is basically the same as that of the robot 1 of the first embodiment. The following mainly describes the differences from the first embodiment. The robot 301 includes a first artificial intelligence unit 73 and a second artificial intelligence unit 75, as shown in FIG.

[0088] The first artificial intelligence unit 73 stores an AI program and a data set for executing various operations of the robot 301. Hereinafter, this program will be referred to as a first AI program, and this data set will be referred to as a first data set.

[0089] The first artificial intelligence unit 73 changes and develops the first AI program and the first data set through learning. The learning performed by the first artificial intelligence unit 73 is not affected by the learning stop and learning limit described below. In addition, the first AI program and the first data set are not uploaded to the cloud network 31.

[0090] The second artificial intelligence unit 75 can store an AI program and a data set. Hereinafter, this program will be referred to as a second AI program, and this data set will be referred to as a second data set.

[0091] The second AI program is basically the same as the first AI program, but is not used to execute various operations of the robot 301. The second artificial intelligence unit 75 changes and develops the second AI program and the second data set through learning. The second AI program and the second data set accumulate the learning results and are uploaded to the cloud network 31. This allows the learning results to be stored in the cloud network 31.

[0092] However, the learning performed by the second artificial intelligence unit 75 is limited by a learning stop and a learning limit, which will be described later. Therefore, the learning results stored in the cloud network 31 by uploading the second AI program and the second data set are limited.

[0093] The second AI program and the second data set can be downloaded from the cloud network 31 to the second artificial intelligence unit 75. Then, based on the downloaded second AI program and the second data set, learning of the first AI program and the first data set can be performed. Details will be described later.

[0094] 2. Processing performed by robot 301 (2-1) Program installation process When the power supply of the robot 301 is turned on, the control unit 3 executes a program installation process shown in FIG.

[0095] In step 41, it is determined whether or not the user's identification information has been input. The identification information may be the same as that in the first embodiment. If the identification information has been input, the process proceeds to step 42, and if the identification information has not been input, the process ends.

[0096] In step 42, the second AI program and the second data set corresponding to the identification information determined to have been input in step 41 are installed from the cloud network 31. The installed second AI program and the second data set are stored in the second artificial intelligence unit 75. If the second AI program and the second data set are already stored in the second artificial intelligence unit 75, they are overwritten.

[0097] In step 43, content that is included in the second AI program and the second data set installed in step 42 but is not stored in the first AI program and the first data set is learned.

[0098] In step 44, the first AI program and the first data set are updated by adding the contents learned in step 43. That is, the first AI program and the first data set are learned based on the downloaded second AI program and second data set.

[0099] (2-2) Conversation processing The control unit 3 executes the conversation process shown in Fig. 13. This process is executed when the microphone 5 detects a volume equal to or greater than a predetermined threshold. The conversation process is performed using a first AI program and a first data set stored in the first artificial intelligence unit 73.

[0100] The processing in steps 51 to 54 is similar to the processing in steps 11 to 14 in the first embodiment. In step 55, the first artificial intelligence unit 73 learns about the contents of the voice recognized in step 52. The contents of the learning are the same as those in the first embodiment.

[0101] In step 56, the first AI program and the first data set are updated to reflect the learning results in step 55. In step 57, it is determined whether or not the second artificial intelligence unit 75 is currently stopping learning. The stopping of learning of the second artificial intelligence unit 75 is set by a second artificial intelligence unit learning stop determination process, which will be described later. If the second artificial intelligence unit 75 is not currently stopping learning, the process proceeds to step 58, and if learning is currently stopping, the process ends.

[0102] In step 58, the learning restriction contents set at that time are obtained. The learning restriction contents include, for example, information (names, addresses, telephone numbers, email addresses, career history, images including faces) about family members and acquaintances of the user (the user corresponding to the identification information determined to have been input in step 41).

[0103] In step 59, the second artificial intelligence unit 75 learns the contents of the voice recognized in step 52. The contents of the learning are the same as those in the first embodiment. However, even if the contents of the voice recognized in step 52 are subject to the learning restriction contents acquired in step 58, they are not learned.

[0104] In step 60, the second AI program and the second data set are updated to reflect the learning results in step 59. (2-3) Processing to determine whether the second artificial intelligence unit will stop learning The control unit 3 repeatedly executes the second artificial intelligence unit learning stop determination process shown in FIG. 14 at predetermined time intervals.

[0105] In step 71, the position information of the robot 301 is acquired using the GPS 13. In step 72, the camera 7 is used to capture an image of the surroundings of the robot 301.

[0106] In step 73, the microphone 5 is used to capture audio. In step 74, the second artificial intelligence unit 75 judges whether learning is stopped at that time. The state of learning being stopped is started in step 77 described later, and The process ends when learning is resumed in step 79. If learning is not stopped, the process proceeds to step 75, and if learning is stopped, the process proceeds to step 78.

[0107] In step 75, it is determined whether there is a trigger for stopping learning in the image acquired in step 72 or the audio acquired in step 73. The trigger for stopping learning is the same as in the first embodiment. If there is a trigger for stopping learning, the process proceeds to step 77, and if there is no trigger for stopping learning, the process proceeds to step 76.

[0108] In step 76, it is determined whether or not the position information acquired in step 71 corresponds to a position registered in advance as a position where learning should be stopped. The position where learning should be stopped is the same as in the first embodiment.

[0109] In step 77, a learning stop state is initiated for the second artificial intelligence unit 75. From this point onwards, a positive determination is made in step 57 in the conversation process, and learning in step 59 is not performed.

[0110] On the other hand, if the determination in step 74 is affirmative, then in step 78 it is determined whether or not there is a trigger for restarting learning in the image acquired in step 72 or the audio acquired in step 73. The trigger for restarting learning is the same as in the first embodiment. If there is a trigger for restarting learning, the process proceeds to step 79, and if there is no trigger for restarting learning, the process ends.

[0111] In step 79, learning is resumed in the second artificial intelligence unit 75. From this point onwards, a negative determination is made in step 57 in the conversation processing, and learning in step 59 is carried out.

[0112] (2-4) Program upload process The control unit 3 repeatedly executes the program upload process shown in FIG. 15 at predetermined time intervals.

[0113] In step 81, it is determined whether or not the usage end condition of the robot 301 has been satisfied. The usage end condition is the same as that determined in step 5 of the first embodiment. If the usage end condition has been satisfied, the process proceeds to step 82, and if the usage end condition has not been satisfied, the process ends.

[0114] In step 82, the second AI program and the second data set are uploaded to the cloud network 31. At this time, they are uploaded in association with the user's identification information. Note that, if the above-mentioned learning has been performed, the second AI program and the second data set to be uploaded are those after learning.

[0115] 3. Effects of Robot 301 The robot 301 has the above-mentioned advantages (1B), (1C), (1F), and (1H). In addition, the robot 301 also has the following advantages.

[0116] (4A) The robot 301 can change and develop the first AI program and the first data set through learning. Furthermore, the learning in the first AI program and the first data set is not affected by the learning stop process and the learning limit process.

[0117] Furthermore, since the first AI program and the first data set are not uploaded to the cloud network 31, their contents can be prevented from being known to others. (4B) The robot 301 can upload the second AI program and the second data set after learning to the cloud network 31. Also, the robot 301 can install the second AI program and the second data set from the cloud network 31.

[0118] The robot 301 in which the learned second AI program and the second data set are installed may be the same as or different from the robot 301 that performed learning in the past. Furthermore, the robot 301 in which the learned second AI program and the second data set are installed may be located in the same place where learning was performed in the past, or in a different place.

[0119] Therefore, the user can install the second AI program and the second data set, which have been learned through the user's own past use, in the robot 301 at the location where the user is at that time (for example, various locations such as the workplace, a store, or a home) from the cloud network 31. Then, learning can be performed using the second AI program and the second data set, and the first AI program and the first data set can be changed and developed.

[0120] (4C) The robot 301 restricts learning of the second AI program and the second data set uploaded to the cloud network 31. That is, the robot 301 stops learning of the second AI program and the second data set depending on the behavior of people around it, the results of identifying people, etc. Also, the robot 301 stops learning of the second AI program and the second data set depending on the location where it is located. Also, the robot 301 does not include any items that fall under the learning restriction contents in the second AI program and the second data set.

[0121] Therefore, it is possible to prevent the second AI program and the second data set, which include information that the user does not want others to know, from being uploaded to the cloud network 31. <Fifth embodiment> 1. Configuration of Robot 401 The configuration of the robot 401 of this embodiment is basically the same as that of the robot 1 of the first embodiment. The following mainly describes the differences from the first embodiment. As shown in FIG. 16, the robot 401 can connect to the Internet 77 using the communication unit 26. The Internet 77 is an example of a network. The robot 401 can be placed in a vehicle. In this case, the robot 401 can converse with the vehicle occupant by a conversation process, which will be described later.

[0122] 2. Processing performed by robot 401 (2-1) Processing the same as for Robot 1 The robot 401 executes a program setting process, a learning stop determination process, and a schedule management process, similar to the robot 1 of the first embodiment.

[0123] (2-2) Conversation processing The control unit 3 of the robot 401 repeatedly executes the conversation process shown in Fig. 17 at predetermined time intervals. This process is executed when the microphone 5 detects a volume equal to or greater than a predetermined threshold.

[0124] The processes in steps 91 and 92 are similar to the processes in steps 11 and 12, respectively, in the first embodiment. In step 93, information related to the content of the voice recognized in step 92 is searched and acquired from the Internet 77 using the communication unit 26. A keyword is extracted from the content of the voice recognized in step 92, and information including items previously associated with the keyword is searched for. Examples of search targets include SNS (social networking services), blogs, and electronic bulletin boards. If the content of the voice recognized in step 92 is a question, an answer to the question is searched for. As a search method, for example, a known search engine can be used.

[0125] In step 94, response voice data is created for the contents of the voice recognized in step 92, basically in the same manner as in step 13 in the first embodiment. However, in this step, the response voice data is created also using the information acquired in step 93. Using the information acquired in step 93 means, for example, including a voiced version of that information in the response voice data.

[0126] In step 95, the type of voice to be pronounced in step 96 described below is determined according to the content of the answer created in step 94. Examples of the type of voice include a male voice, a female voice, an adult voice, a child's voice, etc.

[0127] Specifically, the type of voice is determined as follows: First, the control unit 3 extracts features (e.g., features unique to men, features unique to women, features unique to adults, features unique to children, etc.) from the content of the answer created in step 94.

[0128] The control unit 3 is provided with a map in which the features of the answer contents are associated with the types of voices. The control unit 3 inputs the features extracted as described above into the map, and determines the type of voice corresponding to the extracted features.

[0129] For example, if features specific to men and features specific to adults are extracted from the content of the answer created in step 94, the control unit 3 determines the voice of an adult male. In step 96, a voice is generated from the speaker 15 based on the answer voice data created in step 94. At this time, the voice type set in step 95 is used for the voice.

[0130] In step 97, first, an emotion (e.g., joy, anger, sadness, calm, etc.) corresponding to the content of the voice recognized in step 92 or the content of the answer created in step 94 is acquired. The emotion is acquired as follows.

[0131] The control unit 3 is provided with a map in which characteristics appearing in the contents of the voice and the contents of the answer correspond to emotions. Examples of characteristics appearing in the contents of the voice include volume, intonation, and high and low pitch. Examples of characteristics appearing in the contents of the answer include words and phrases that reflect emotions and are included in the contents of the answer.

[0132] The control unit 3 inputs the features extracted from the voice content recognized in step 92 or the answer generated in step 94 into the map, thereby obtaining the corresponding emotion.

[0133] Next, the control unit 3 creates a facial image of a person or character expressing the acquired emotion, and displays it on the display 19. For example, if the acquired emotion is joy, the control unit 3 displays a facial image of a smiling person or character on the display 19. On the other hand, if the acquired emotion is sadness, the control unit 3 displays a facial image of a crying person or character on the display 19.

[0134] The processes in steps 98 to 102 are similar to the processes in steps 15 to 19 in the first embodiment, respectively. 3. Effects of Robot 401 The robot 401 has the above-mentioned advantages (1A) to (1I). In addition, the robot 401 also has the following advantages.

[0135] (5A) The robot 401 can search and acquire information related to the contents of the voice from the Internet 77. The robot 401 then uses the information acquired in this way to create answer voice data. This allows the robot 401 to create more appropriate answer voice data.

[0136] (5B) The robot 401 can determine the type of voice depending on the content of the answer. Therefore, the user is less likely to feel a discord between the content of the answer and the type of voice that pronounces it.

[0137] (5C) The robot 401 acquires the emotion corresponding to the content of the recognized voice or the content of the reply, and displays a face image of a person or character expressing the acquired emotion on the display 19. This allows the user to feel as if the robot 401 is a human being. Sixth embodiment 1. Configuration of Robot 501 The configuration of a robot 501 of this embodiment is basically the same as that of the robot 1 of the first embodiment.

[0138] 2. Processing performed by the robot 501 (2-1) Processing the same as for Robot 1 The robot 501 executes a program setting process, a conversation process, a learning stop determination process, and a schedule management process, similar to the robot 1 of the first embodiment.

[0139] (2-2) Call processing 18, multiple robots 501 enable a call between a user 79 and a user 81. For example, a robot 501 on the user 79's side (hereinafter referred to as robot 501A) acquires a voice uttered by the user 79 through a microphone 5. In addition, the robot 501A receives an input from the user 79 specifying a robot 501 (hereinafter referred to as robot 501B) as a call partner through a touch panel 9.

[0140] The robot 501A transmits a signal converted from the voice spoken by the user 79 (hereinafter referred to as the voice conversion signal), an identification signal of the robot 501A, and an identification signal of the robot 501B, the other party designated by the user 79, to the host computer 83 using the communication unit 26.

[0141] The host computer 83 judges whether the identification signal of the received robot 501A and the identification signal of the communication partner robot 501B are set as a communication pair. If they are set as a communication pair, the host computer 83 transfers the voice conversion signal to the communication partner robot 501B. The setting of the communication pair will be described later.

[0142] The robot 501B receives the transferred voice conversion signal using the communication unit 26, and produces a sound using the speaker 15 based on the voice conversion signal. Through the above process, the voice produced by the user 79 is transmitted to the user 81 on the robot 501B side. In addition to producing a sound, the robot 501B also converts the voice into characters and displays the characters on the display 19.

[0143] Moreover, the robot 501B performs the above-mentioned processing of the robot 501A, and the robot 501A performs the above-mentioned processing of the robot 501B, so that the voice uttered by the user 81 can be transmitted to the user 79.

[0144] On the other hand, if the identification signal of the received robot 501A and the identification signal of the communication partner robot 501B are not set as a communication pair, the host computer 83 does not transfer the voice-converted signal.

[0145] (2-3) Call pair setting process Next, the process in which the host computer 83 sets up the above-mentioned call pair will be described with reference to FIG.

[0146] In step 111, it is determined whether a new call pair setting request has been received. A call pair setting request is a request that the robot 501A transmits to the host computer 83. The call pair setting request includes an identification signal of the robot 501A that is the sender of the request, characteristics of the user 79 on the robot 501A side (e.g., hobbies, preferences in food, clothing, and shelter, matters of interest, etc.), and image data of a facial photograph of the user 79.

[0147] The request to set up a call pair may be sent by the robot 501A in response to a user's instruction, or may be sent automatically by the robot 501A. If the host computer 83 newly receives a request to set up a call pair, the process proceeds to step 112, and if not, the process ends.

[0148] In step 112, the waiting list is searched for the characteristics of the user 79 included in the call pair setting request (hereinafter referred to as a new setting request) determined to have been received in step 111. Here, the waiting list is a list of call pair setting requests (hereinafter referred to as past setting requests) previously received from any robot 501.

[0149] In step 113, it is determined whether or not a past setting request having characteristics matching those of the user 79 included in the new setting request has been found as a result of the search in step 112. If such a past setting request has been found, the process proceeds to step 114; if not, the process proceeds to step 116.

[0150] In step 114, the robot 501B, which was found in step 113 and was the sender of the past setting request, and the robot 501A, which was the sender of the new setting request, are set as a call pair.

[0151] In step 115, each of the robots 501A and 501B set as a call pair is notified of information about the other robot 501. That is, the robot 501A is notified of information about the robot 501B, and the robot 501B is notified of information about the robot 501A. The notified information includes an identification signal of the other robot 501, image data of a face photo of the corresponding user, and the like.

[0152] On the other hand, if the determination in step 113 is negative, the new configuration request is added to the configuration waiting list in step 116. From this point on, the new configuration request becomes part of the list of past configuration requests.

[0153] The robot 501, which has been notified of the information about the other robot 501, uses the information to create an icon 85 representing the other user in the call pair, and displays it on the display 19 as shown in FIG. 20. The icon 85 includes a facial photograph of the user who is the other user in the call pair. The widget 501 can display a plurality of icons 85 on the display 19 .

[0154] When a specific icon 85 is touched by a user, the robot 501 recognizes the user corresponding to the icon 85 as a call partner. When the robot 501 transmits the converted voice signal to the host computer 83 as described above, the robot 501 transmits an identification signal of the robot 501 corresponding to the touched icon 85 to the host computer 83.

[0155] (2-4) Other processing The host computer 83 analyzes the contents of the converted voice signal transmitted by the robot 501A during the call processing of (2-2) above. If the analysis result corresponds to a prohibited matter (e.g., matter related to a crime) set in advance, the host computer 83 does not start the call processing or terminates the call processing midway. Therefore, the host computer 83 can prevent the call processing from being used for crimes, etc.

[0156] Furthermore, during the call processing of (2-2) above, the robot 501B also uses the voice transmitted from the other computer 501A to learn, which allows the robot 501B to learn more efficiently.

[0157] In addition, in the above-mentioned (2-2) telephone call processing, when the pronunciation of the user 79 is interrupted for a predetermined time or more, or when the user 79 gives an instruction, the robot 501A transmits the voice conversion signal that it has created to the host computer 83. In this case, the robot 501A and the user 81 will be in conversation. The computer 501A can create the voice conversion signal using a learning result obtained by a past telephone call processing. In addition, the robot 501A may store a voice (e.g., a backchannel) that the robot 501A or the robot 501B has made in a past telephone call, and create a voice conversion signal corresponding to that voice.

[0158] 3. Effects of Robot 501 The robot 501 has the above-mentioned advantages (1A) to (1I). In addition, the robot 501 also has the following advantages.

[0159] (6A) A user 79 on the robot 501A side and a user 81 on the robot 501B side can communicate with each other. (6B) A call between user 79 and user 81 is premised on the premise that robot 501A and robot 501B are set as a call pair. A call pair is set when the characteristics of user 79 and user 81 match. Therefore, robot 501 selectively enables a call between users with matching characteristics.

[0160] (6C) The robot 501 creates an icon 85 including a facial photograph of the user who is the other party to the call, and displays it on the display 19. The user can easily select the other party to the call by touching the icon 85. In addition, since the icon 85 includes a facial photograph of the other party to the call, the user can easily understand which icon 85 corresponds to which other party to the call. <Other embodiments> (1) In the first to sixth embodiments, the robot 1, 301, 401, 501, the computer 101, and the vehicle-mounted device 201 may increase or decrease the learning restriction content depending on the situation. For example, when it is recognized that an item that was originally included in the learning restriction content was spoken by multiple people, the item may be excluded from the learning restriction content.

[0161] (2) In the first to sixth embodiments, when the robot 1, 301, 401, 501, the computer 101, and the vehicle-mounted device 201 acquire a voice by the microphone 5, the voice The color may be judged, and depending on the result of the judgment, it may be decided whether or not to learn the contents of the sound.

[0162] (3) In the first to sixth embodiments, the process performed in response to the voice recognition result may be something other than creating answer voice data (step 13) and determining the vehicle control content (step 33). For example, the robot 1, 301, 401, 501 may be moved or an external device connected to the computer 101 may be operated in response to the voice recognition result. Also, for example, a predetermined action (for example, opening and closing a box, opening and closing a window, locking or unlocking a door, operating a home appliance, etc.) may be performed in response to the voice recognition result.

[0163] (4) In the first to sixth embodiments, the AI ​​program and the data set may be stored in something other than the cloud network 31. For example, they may be stored in a well-known server, storage medium, or the like.

[0164] (5) In the third embodiment, the vehicle-mounted device 201 may be mounted on a moving object other than a vehicle (for example, a railroad car, an airplane, a ship, etc.) and may control the moving object. (6) In the first, fourth to sixth embodiments, the form of the robot 1, 301, 401, 501 does not have to be a human form. For example, it may be an animal, a fish, an imaginary character, or the like.

[0165] (7) In the first to third, fifth and sixth embodiments, the robot 1, 401, 501, the computer 101 and the in-vehicle device 201 may use the standard program and the AI ​​program simultaneously. In this case, the standard program can execute basic processing, and the AI ​​program can execute additional processing obtained as a result of learning.

[0166] (8) In the first to sixth embodiments, the robot 1, 301, 401, 501, computer 101, and in-vehicle device 201 may take the form of a home appliance (e.g., a television, a refrigerator, an air conditioner, a vacuum cleaner, a washing machine, etc.), a mobile terminal (e.g., a mobile phone (including a smartphone), a glasses-type terminal, a wristwatch-type terminal), etc.

[0167] (9) In the first to sixth embodiments, the robot 1, 301, 401, 501, computer 101, and in-vehicle device 201 may have a function of automatically acquiring an image using the camera 7 and transmitting the acquired image onto a network. Examples of the destination of the image include a server, a terminal, a vehicle, and another robot. The image to be transmitted may be the image itself acquired using the camera 7, or may be an image of a part (for example, a person's face, a person's whole body, a vehicle, a vehicle license plate, etc.) extracted from the image acquired using the camera 7.

[0168] The robots 1, 301, 401, 501, computer 101, and vehicle-mounted device 201 having the above functions can be used for crime prevention purposes, monitoring other robots, etc. The robots 1, 301, 401, 501, computer 101, and vehicle-mounted device 201 having the above functions can be installed, for example, indoors, on the road, at the entrance to a specific facility (for example, a house, an apartment building, an office, a parking lot, etc.), near other robots, etc.

[0169] Moreover, the robot 1, 301, 401, 501, computer 101, and vehicle-mounted device 201 having the above functions can have a function of flying in the air or can be mounted on an aircraft. In this case, an image of the ground taken from a viewpoint in the sky can be transmitted over a network. In this case, the robot 1, 301, 401, 501, computer 101, and vehicle-mounted device 201 can recognize white lines on the road in the captured image and move along the white lines. Furthermore, the robot 1, 301, 401, 501, computer 101, and vehicle-mounted device 201 can recognize traffic lights in an image of the ground taken from a viewpoint in the sky and transmit the display contents (red light, green light, etc.) to a vehicle on the ground.

[0170] (10) In the first to sixth embodiments, the robot 1, 301, 401, 501, the computer 101, and the vehicle-mounted device 201 may recognize a human action using the camera 7, and output a sound that is associated in advance with the recognition result.

[0171] For example, if the system recognizes that a person leaves the kitchen with the gas on, it can output a voice warning to that person. Also, if the system recognizes that a person is searching for a specific object, it can search for the location of that object and notify the user of its location by voice. Also, if the system recognizes that a person enters a house through the entrance, it can output a voice saying "Welcome home." Human actions and the voices associated with them can be increased through learning.

[0172] When a voice is generated as described above, the type of the voice can be associated with the situation and the content of the voice. For example, when a father is recognized in an image, the type of voice saying "Welcome home" can be determined to be the voice of his child.

[0173] (11) In the first to sixth embodiments, the control unit is equipped with a microcomputer, but it may be a combination of individual electronic circuits, an AISIC (Application Specified Integrated Circuit), a programmable logic device such as an FPGA (Field Programmable Gate Array), or a combination of these. (12) A part or all of the configurations of the first to sixth embodiments may be combined as appropriate. For example, the configurations of the fourth to sixth embodiments may be applied to the second and third embodiments.

Claims

1. A voice recognition unit (23, 25, 27) for performing voice recognition; a learning unit (25) for learning about the recognition result of the speech recognition unit; a processing unit (23, 25, 27) for performing corresponding processing on the recognition result of the speech recognition unit using the learning result of the learning unit; a storage unit (26) for storing the learning result in an external storage device; a learning result acquisition unit (26) for acquiring the learning result from the storage device; A robot (1, 301) comprising:

2. An identification information acquisition unit (21, 26) for acquiring user identification information, The robot according to claim 1 , wherein the learning result acquisition unit acquires the learning result associated with the identification information from the external storage device.

3. 3. The robot according to claim 1 or 2, further comprising a memory limiting unit (23, 25, 27, 75) for limiting the learning results stored in the external memory device in response to a position of the robot or a user instruction.

Images