IP Library › Granted Patent US 11,176,948
Granted Patent B2
US 11,176,948 · App. 16/677,733 · Granted Nov 16, 2021

Agent device, agent presentation method, and storage medium

Inventors: Hiroshi Sugihara (Wako, JP); Ryosuke Tanaka (Wako, JP); Atsushi Sekiguchi (Wako, JP); Yuki Matsuura (Wako, JP); Wataru Endo (Wako, JP); Eisuke Soma (Wako, JP)
Assignee: HONDA MOTOR CO., LTD.
G10L17/00G06F3/167G06K9/00832G10L15/24H04N5/2253H04R1/403H04R3/12
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,176,948
App. No.
16/677,733
Granted
Nov 16, 2021
Kind
B2
Abstract

An agent device includes a display unit, a microphone configured to collect a voice in an occupant compartment, a plurality of speakers configured to enable localization of a sound image through a combination of outputs, and an agent controller configured to cause the display unit to display an agent image and cause the speakers to output sounds, wherein the agent controller is configured to identify a speaking person who has spoken the voice collected by the microphone among occupants in a vehicle and to cause the agent image to be displayed in a mode of talking to the occupant in a partial area of the display unit near the speaking person while causing a sound image to be localized at a display position of the agent image.

Claims (32)

1. An agent device comprising:

a display unit;

a microphone configured to collect a voice in an occupant compartment;

a plurality of speakers configured to enable localization of a sound image through a combination of outputs; and

an agent controller configured to cause the display unit to display an agent image and cause the speakers to output sounds,

wherein the agent controller is configured to identify a speaking person who has spoken the voice collected by the microphone among occupants in a vehicle and to cause the agent image to be displayed in a mode of talking to the occupant in a partial area of the display unit near the speaking person while causing a sound image to be localized at a display position of the agent image,

wherein the display unit has a display area that is wide enough that two or more of the occupants recognize the agent image as being displayed at a position facing the two or more occupants.

2. The agent device according to claim 1 , wherein the display unit includes individual displays facing the occupants and/or includes a display provided over a vicinity of the plurality of occupants.

3. The agent device according to claim 2 , further comprising a camera configured to image the occupant compartment,

wherein the agent controller is configured to identify the speaking person by analyzing an image including the occupant captured by the camera.

4. The agent device according to claim 3 , wherein the agent controller is configured to identify whether the speaking person is speaking toward the agent image or speaking to another occupant by analyzing the image including the occupant captured by the camera.

5. The agent device according to claim 4 , wherein the agent controller is configured to identify that the speaking is for the agent image when a silent time equal to or greater than a threshold has been detected after the occupant completes the speaking as a result of analyzing the voice collected by the microphone or a result of analyzing the imaging of the camera.

6. The agent device according to claim 4 , wherein the agent controller is configured to identify whether or not the speaking is for the agent image on the basis of an evaluation of component analysis of the voice collected by the microphone.

7. The agent device according to claim 4 , wherein the agent controller is configured to identify that a driver has performed the speaking for the agent image when content indicated by the voice relates to a driving operation.

8. The agent device according to claim 1 , wherein the agent controller is configured to make a localization position of the sound image non-directional when the speaking person cannot be determined.

9. The agent device according to claim 4 , wherein the agent controller is configured to make a localization position of the sound image non-directional when the speaking person cannot be determined.

10. An agent device comprising:

a display unit;

a microphone configured to collect a voice in an occupant compartment;

a plurality of speakers configured to enable localization of a sound image through a combination of outputs; and

an agent controller configured to cause the display unit to display an agent image and cause the speakers to output sounds,

wherein the agent controller is configured to be capable of changing a display position of the agent image on the display unit, and

the agent controller is configured to identify a speaking person who has spoken the voice collected by the microphone among occupants in a vehicle and to set the display positon of the agent image based on the identified speaking person to cause the agent image to be displayed in a mode of talking to the occupant in a partial area of the display unit near the speaking person while causing a sound image to be localized at the set display position of the agent image,

wherein the display unit has a display area that is wide enough that two or more of the occupants recognize the agent image as being displayed at a position facing the two or more occupants.

11. The agent device according to claim 10 , wherein the agent controller is configured to cause the agent image to be displayed in the mode of talking to the occupant in the partial area of the display unit near the speaking person such that a face orientation of the agent image is toward the speaking person.

12. An agent device comprising:

a display unit;

a microphone configured to collect a voice in an occupant compartment;

a plurality of speakers configured to enable localization of a sound image through a combination of outputs; and

an agent controller configured to cause the display unit to display an agent image and cause the speakers to output sounds,

wherein the agent controller is configured to identify a speaking person who has spoken the voice collected by the microphone among occupants in a vehicle, and to cause the agent image to be displayed in a mode of talking to the occupant in a partial area of the display unit near the speaking person such that a face orientation of the agent image is toward the speaking person while causing a sound image to be localized at a display position of the agent image,

wherein the display unit has a display area that is wide enough that two or more of the occupants recognize the agent image as being displayed at a position facing the two or more occupants.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 8, 2019
From: SUGIHARA, HIROSHI; TANAKA, RYOSUKE; SEKIGUCHI, ATSUSHI; MATSUURA, YUKI; ENDO, WATARU; SOMA, EISUKE
To: HONDA MOTOR CO., LTD.
Reel/Frame 050954/0469 →
Priority Claims (1)
JP JP2018-213589 · Nov 14, 2018 · national
Continuity (1)
Related Publication 20200152203A1 · May 14, 2020