JP2016149014A - Interactive device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To take measures when an another occupant speaks to a driver, regardless of a large driving load of the driver, in an interactive device issuing a message to the occupant of a vehicle.SOLUTION: The interactive device includes: driving load detection means (14) that detects a driving load of a driver related to driving of a vehicle; occupant speech detection means (13) that detects a speech to the driver from another occupant, with occupants other than the driver of occupants of the vehicle defined as the other occupants; message issue means (5, 16) that when the occupant speech detection means detects the speech, issues the message responding to the speech according to the driving load detected by the driving load detection means.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an interactive device that utters a message to a vehicle occupant.

  2. Description of the Related Art Conventionally, an interactive device that utters a message such as a greeting to a vehicle driver has been proposed. Also, in such a dialogue apparatus, an agent image for dialogue is displayed, and the number and operation of the displayed agent images are changed depending on whether the occupant is one driver or a plurality of occupants. Has also been proposed (see, for example, Patent Document 1).

JP 2006-189394 A

  However, when the driver's driving load is large and the driver must concentrate on driving, a passenger other than the driver (hereinafter referred to as another passenger) speaks to the driver. So far, no device has been proposed to take any measures so that the driver can concentrate on driving.

  The present invention has been made in view of such problems, and in a dialog device that utters a message to a vehicle occupant, when another occupant speaks to the driver even though the driver's driving load is large The purpose is to make it possible to implement countermeasures.

  The interactive device of the present invention made to achieve the above object is a driving load detecting means for detecting a driving load of a driver related to driving of a vehicle, and an occupant other than the driver among the occupants of the vehicle as other occupants, The utterance utterance detection means for detecting an utterance from the other occupant toward the driver, and the utterance according to the driving load detected by the driving load detection means when the occupant utterance detection means detects the utterance. And a message utterance means for uttering a message responding to.

  In this invention comprised in this way, a driving load detection means detects the driving load of the driver who concerns on driving | running | working of a vehicle. The message utterance unit utters a message that responds to the utterance according to the driving load detected by the driving load detection unit when the occupant utterance detection unit detects an utterance from another occupant toward the driver. Therefore, when another occupant speaks to the driver even though the driver's driving load is large, the message utterance means utters a message in response to the utterance according to the large driving load. can do.

It is a block diagram showing the structure of the dialogue apparatus to which this invention is applied. It is a flowchart showing the process by the dialogue apparatus.

Embodiments to which the present invention is applied will be described below with reference to the drawings.
[1. First Embodiment]
[1-1. Constitution]
As shown in FIG. 1, an audio input device 3, an audio output device 5, and various in-vehicle devices 7 are connected to an MPU (microprocessor unit) 1 constituting the interactive apparatus of the first embodiment. The MPU 1, the audio input device 3, the audio output device 5, and the various in-vehicle devices 7 are all mounted on a vehicle that is not shown.

  The voice input device 3 is composed of, for example, a microphone provided on the dashboard of the vehicle. The voice input device 3 can detect a voice uttered by a vehicle occupant, at least a voice uttered by a driver of the vehicle and a voice uttered by another occupant riding in the passenger seat.

  The audio output device 5 is configured by a speaker or the like for uttering a message or the like to be described later toward a vehicle occupant. The audio output device 5 may be configured using an existing car stereo speaker or the like, or may be specially prepared.

  The various in-vehicle devices 7 include various devices used for estimating the driving load of the driver described later. Examples of this type of device include a car navigation device, a position detection device such as a GNSS (Global Navigation Satellite System), a vehicle speed sensor, a steering angle sensor, a millimeter wave radar, and the like.

  The MPU 1 includes a vehicle-mounted device interface 11 (in FIG. 1, the interface is abbreviated as I / F), a voice input interface 12, an occupant-to-driver utterance detection unit 13, a driver driving load estimation unit 14, and the like. A proxy determination unit 15 and a response message generation unit 16 are provided. The MPU 1 may be an ASIC.

  The in-vehicle device interface 11 converts signals sent from the various in-vehicle devices 7 into digital data, and outputs control signals for controlling the various in-vehicle devices 7. The voice input interface 12 converts voice input through the voice input device 3 into digital data.

  The utterance detection unit 13 from the occupant to the driver analyzes the content (more specifically, the meaning) of the voice input from the voice input device 3 via the voice input interface 12, so that the occupant to the driver is directed to the driver. Detects all utterances. For this voice content analysis, for example, a well-known voice analysis technique that is generally implemented in a smartphone or the like can be applied.

  The driver driving load estimation unit 14 estimates and digitizes the driving load of the driver by a known method. For example, the driver driving load estimator 14 is based on the map data of the car navigation device and the current position of the vehicle detected by the position detection device, and the driver driving load estimation unit 14 in the past when traveling on the same road as the currently traveling road. The operating load may be read out. In addition, the driver driving load estimation unit 14 multiplies various parameters such as the vehicle speed detected by the vehicle speed sensor, the steering angle detected by the steering angle sensor, and the inter-vehicle distance detected by the millimeter wave radar, with predetermined coefficients. The combined value may be used as the driving load of the driver. In addition, since these driving load estimation methods are detailed in, for example, Japanese Patent Application Laid-Open No. 2012-108753 and Japanese Patent Application Laid-Open No. 2011-129010, detailed description thereof is omitted here. Further, the value estimated and digitized by the driver driving load estimation unit 14 may be a numerical value having no unit such as a level value, or may be a numerical value having some unit.

  Based on the detection result of the utterance detection unit 13 from the occupant to the driver and the driving load estimated by the driver driving load estimation unit 14, the corresponding proxy determination unit 15 performs a response to another occupant instead of the driver (that is, It is determined whether or not it is necessary to act as a proxy. The response message generation unit 16 generates a response message to be uttered toward the other occupant when the corresponding proxy determination unit 15 determines that the proxy needs to be performed.

[1-2. processing]
Next, processing executed by the MPU 1 will be described. The MPU 1 repeatedly executes the process shown in the flowchart of FIG. 2 at a predetermined period based on a program stored in a ROM built in the MPU 1.

  As shown in FIG. 2, in this process, first, in S1 (S represents a step: the same applies hereinafter), the driving load of the driver at that time is estimated by the process of the driver driving load estimation unit 14. In subsequent S3, it is determined whether or not an utterance from another occupant toward the driver is detected by the processing of the utterance detection unit 13 from the occupant to the driver. When the utterance is not detected (S3: N), the process is temporarily terminated as it is, and when the utterance is detected (S3: Y), the process proceeds to S5.

  In S5, it is determined whether or not the driving load of the driver estimated in S1 (numerized as described above) is larger than a preset specified value. If the estimated driving load of the driver is equal to or less than the specified value (S5: N), the process is temporarily terminated as it is, and if the driving load is greater than a predetermined value (S5: Y), the process proceeds to S7. . The determination processes in S3 and S5 correspond to the process of the corresponding proxy determination unit 15.

  In S7, the response message generator 16 generates a response message according to the content of the voice detected as an utterance from another occupant to the driver, and the response message is output from the voice output device 5 to be processed. Is temporarily terminated.

As a specific example of the response message, for example, the following is assumed.
[Example 1] When the driver is trying to take the vehicle out of the parking lot and the driving load is large (S5: Y), the passenger in the passenger seat (an example of another passenger) puts a song "XX". When speaking to the driver (S3: Y), a response message such as “Please wait a moment because I can't release my hand now” is output (S7).

  [Example 2] When the driver is waiting for a right turn and the driving load is heavy (S5: Y), the child in the rear seat (an example of another passenger) is "warm from the cold." When the user speaks (S3: Y), a response message such as “Because I am busy now, please be patient for a while” is output (S7).

  An example of a response message such as In these cases, the determination that an utterance is made from another occupant to the driver may be made, for example, when the content of the audio input from the audio input device 3 is content that requests some operation. . When generating the response message, the content of the voice is further analyzed, and the age of the speaker is estimated based on the analysis result, thereby selecting terms such as “can't take my hands off” and “busy driving”. May be made.

[1-3. effect]
According to the first embodiment described in detail above, the following effects are produced.
[1A] In this embodiment, when the driver's driving load is large (S5: Y), when another occupant speaks to the driver (S3: Y), the MPU 1 replaces the driver. A response message is output (S7). For this reason, the driver can concentrate on driving even if there is an utterance from another passenger.

  [1B] In this embodiment, the driving load of the driver is detected based on the state of various on-vehicle devices 7 mounted on the vehicle. For this reason, it is not necessary to prepare a special configuration for detecting the driving load of the driver, and the manufacturing cost of the apparatus can be reduced.

  [1C] In the present embodiment, an utterance from another occupant toward the driver is detected based on the content of the voice input from the voice input device 3. For this reason, as the configuration for detecting the utterance (that is, the voice input device 3), there is only one monaural microphone, and the microphone may be provided in advance by the various in-vehicle devices 7. The manufacturing cost of the device can be reduced.

  Note that the driver driving load estimation unit 14 is a driving load detection unit, the occupant-to-driver utterance detection unit 13 is a occupant utterance detection unit, the response message generation unit 16 and the voice output device 5 are message utterance units, and a voice input device. 3 corresponds to the sound detection means.

[2. Other Embodiments]
As mentioned above, although embodiment of this invention was described, this invention can take a various form, without being limited to the said embodiment.

  [2A] In the above embodiment, the driving load of the driver is quantified, but the driving load is not necessarily quantified. For example, it is determined whether or not the driving load is large (corresponding to a case where the driving load is larger than the specified value in the embodiment) based on a logical sum or logical product of conditions such as an intersection or a vehicle speed of 30 km / h or more. Also good.

  [2B] In the above-described embodiment, the driving load of the driver is detected based on the states of the various in-vehicle devices 7, but the present invention is not limited to this. For example, the driving load of the driver may be detected using a biosensor such as a pulse sensor provided as a special configuration for detecting the driving load of the driver. The driving load of the driver may be detected based on the driver's tone input via the voice input device 3. Thus, when the driving | running load of a driver is detected using the voice input device 3, the various vehicle equipment 7 may be abbreviate | omitted.

  [2C] In the above embodiment, an utterance from another occupant toward the driver is detected based on the content of the voice input from the voice input device 3, but the present invention is not limited to this. For example, the position of the speaker can be specified by providing a plurality of microphones in the passenger compartment and referring to the sound volume difference and input timing. In that case, based on the position of the speaker, it is determined whether the speaker is a driver or another occupant, and if the speaker is another occupant, the utterance is for the driver. May be considered. Further, based on the voice print of the voice input from the voice input device 3, it is determined whether the speaker is a driver or another occupant. If the speaker is another occupant, the utterance is directed to the driver. May be considered as utterances.

  [2D] Also, in the case where photographing means such as a camera for photographing the passenger compartment is provided, when another occupant moves toward the driver and moves his / her mouth, the utterance from the occupant to the driver is made. May be considered. In that case, the driving load of the driver may be detected based on the driver's face image (more specifically, eyes or the like) photographed by the photographing means.

  [2E] In the above-described embodiment, the MPU 1 has been described as a dialog device for simply performing a dialog. However, the dialog device of the present invention may also have a function of performing control by voice input. For example, the various in-vehicle devices 7 may include various devices that can be operated by a driver inputting a command (command) to the voice input device 3 by voice. Examples of this type of device include a car air conditioner and a car audio. Since the process for controlling such a device in response to voice input is known, the description thereof is omitted here. When executing such control, depending on the command system of voice input, as shown in [2C] and [2D], the person who specified the speaker without referring to the voice content (that is, meaning) May be preferred.

  [2F] The message may be changed according to the driving load of the driver. For example, when the driving load on the driver is extremely large, a message for stopping another passenger's speech with a stronger tone may be generated and output.

  [2G] Further, in the embodiment, an utterance from another occupant toward the driver is detected, but a conversation between other occupants may be detected separately from the utterance. For example, when important information to be notified to the driver is uttered, and the other occupants are making loud noises, the response message generator 16 generates a message such as “Please be quiet a little.” It may be output. In that case, the important information may be uttered after the message is uttered. By doing so, the important information is better communicated to the driver.

  The important information may be information generated and output by the MPU 1, for example, information generated and output by various in-vehicle devices 7 such as a car navigation device. In the latter case, the MPU 1 can acquire the timing at which the important information is uttered by transmitting / receiving signals to / from various in-vehicle devices 7 and reflect the timing in the control. In the latter case, examples of important information include a left / right turn instruction and information on occurrence of traffic jams or accidents. The MPU 1 may acquire such important information from various in-vehicle devices 7 such as a car navigation device, and may generate and output the important information as processing of the MPU 1.

  [2H] In the above embodiment, it is simply determined whether or not there is an utterance from another occupant to the driver, but the present invention is not limited to this. For example, the content of the utterance may be analyzed in detail to determine whether the utterance is likely to be a load on the driver.

  [2I] The MPU 1 may display a message via the display unit by controlling a display unit such as a display in addition to the voice message. In that case, the display unit may be a display unit specially prepared for this processing and controlled by the MPU 1, and an existing display unit provided in various in-vehicle devices 7 such as a car navigation device is used. May be.

  [2J] In the above embodiment, the interactive device of the present invention is configured as an in-vehicle device, but the present invention is not limited to this. For example, the interactive apparatus of the present invention may be configured by a so-called carry-in device such as a smartphone or a tablet. In that case, as shown in [2D], the driving load of the driver is detected based on the driver's face image captured by the camera of the carry-in device, and based on the image of another occupant captured by the camera. An utterance from another passenger toward the driver may be detected.

  [2K] The functions of one component in the embodiment may be distributed as a plurality of components, or the functions of a plurality of components may be integrated into one component. Further, at least a part of the configuration of the embodiment may be replaced with a known configuration having the same function. Moreover, you may abbreviate | omit a part of structure of the said embodiment. In addition, at least a part of the configuration of the embodiment may be added to or replaced with the configuration of the other embodiment. In addition, all the aspects included in the technical idea specified only by the wording described in the claim are embodiment of this invention.

  [2L] In addition to the above-described dialog device, the present invention is implemented in various forms such as a system including the dialog device as a constituent element, a program for causing a computer to function as the dialog device, a medium storing the program, and a dialog control method. Can also be realized.

DESCRIPTION OF SYMBOLS 1 ... MPU 3 ... Audio | voice input device 5 ... Audio | voice output device 7 ... Various vehicle equipment 11 ... In-vehicle apparatus interface 12 ... Voice input interface 13 ... Speech detection part from a passenger to a driver 14 ... Driver driving load estimation part 15 ... Correspondence substitution judgment Unit 16 ... Response message generation unit

Claims (7)

Driving load detection means for detecting the driving load of the driver related to driving the vehicle;
An occupant utterance detection means for detecting an utterance from the other occupant toward the driver, as an occupant other than the driver among the occupants of the vehicle,
A message utterance unit that utters a message in response to the utterance according to the driving load detected by the driving load detection unit when the occupant utterance detection unit detects the utterance;
An interactive apparatus characterized by comprising:   The interactive device according to claim 1, wherein the driving load detection unit detects a driving load of the driver based on a state of an in-vehicle device mounted on the vehicle. The driving load detection means detects the driving load of the driver as a numerical value,
The message utterance means utters the message when the occupant utterance detection means detects the utterance and the driving load detected by the driving load detection means exceeds a specified value. The interactive apparatus according to claim 1 or 2. Voice detection means for detecting voice inside the vehicle;
In addition,
The said occupant utterance detection means detects the utterance toward the said driver from the said other occupant based on the audio | voice detected by the said audio | voice detection means, The any one of Claims 1-3 characterized by the above-mentioned. The interactive device described.   5. The dialogue apparatus according to claim 4, wherein the occupant utterance detection unit detects an utterance from the other occupant toward the driver based on the content of the voice detected by the voice detection unit.   The occupant utterance detection unit determines whether the utterance is made by the other occupant or the utterance by the driver based on the voice detected by the voice detection unit, and determines that the utterance is made by the other occupant. In this case, the utterance from the other occupant to the driver is detected by regarding the utterance as an utterance from the other occupant to the driver. The interactive device described in 1. The occupant utterance detection means detects a conversation between the other occupants separately from the utterance,
The message utterance means also utters information to be notified to the driver,
When the message utterance means utters the information, if the occupant utterance detection means detects the conversation, the message utterance means utters the information after uttering a message to be quiet. The dialogue apparatus according to any one of claims 1 to 6.

Images