Autonomous action robot

• US 6,853,880 B2
• Filed: 08/22/2002
• Issued: 02/08/2005
• Est. Priority Date: 08/22/2001
• Status: Expired due to Term

• Current Assignee: Honda Giken Kogyo Kabushiki Kaisha (Honda Motor Company)
• Original Assignee: Honda Giken Kogyo Kabushiki Kaisha (Honda Motor Company)
• Inventors: Yoshida, Yuichi, Sakagami, Yoshiaki, Higaki, Nobuo, Sumida, Naoaki
• Primary Examiner(s): Black, Thomas G.
• Assistant Examiner(s): Marc, McDieunel, Marc, McDieunel
• Application Number:
  US10/225,287
• Publication Number:
  US 20030055532A1
• Time in Patent Office: 901 Days
• Field of Search: 700/245, 700/247, 700/248, 700/249, 700/258, 700/259, 318/565, 318/568.1, 318/568.11, 318/568.12, 318/568.2, 901/1, 901/46, 901/47
• US Class Current: 700/259
• CPC Class Codes: G05B 2219/39387 Reflex control, follow movement, track face, work, hand, visual servoing
• CPC Class Codes: G06N 3/008 based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour

Abstract

An autonomous action robot which can turn its line of sight to face a person who calls out, can recognize the face of a person, and can perform various actions in response to commands. First, a sound emitted from a person or other sound source is detected by a sound detector, and the direction of the sound source is specified based on the detected sound. Then, a robot head section is controlled, and the imaging direction of the robot head section is moved to face the specified direction of the sound source. Next, an image is captured in the direction of the sound source, and a target image of a specific shape is extracted from the captured image. Then, the imaging direction of the robot head section is controlled and moved to face in the direction of the extracted target image.

Claims

1. An autonomous action robot comprising:

a sound detection unit which detects a sound emitted from a sound source;

a sound source locating unit which specifies a direction of the sound source based on the sound detected by the sound detection unit;

an imaging unit which captures an image of surroundings;

a target image extraction unit which extracts a target image of a specific shape from the image captured by the imaging unit; and

a control unit which controls an imaging direction of the imaging unit to face a direction of the target image based on the specified sound source direction and the extracted target image.

2. An autonomous action robot according to claim 1, wherein

the specific shape is a shape of a human face, and there is further provided an identification unit which identifies a specific human face.

3. An autonomous action robot according to claim 1, further comprising:

a speech recognition unit which recognizes a detected sound as a specific speech command; and

an attitude and position changing unit which changes an attitude and/or a position of the robot based on the recognized speech command.

4. An autonomous action robot according to claim 2, further comprising:

a speech recognition unit which recognizes a detected sound as a specific speech command; and

an attitude and position changing unit which changes an attitude and/or a position of the robot based on the recognized speech command.

6. An autonomous action robot according to claim 1, further comprising:

a contour extraction unit which extracts a contour of the target image by applying a dynamic contour model to the captured image.

8. An autonomous action robot according to claim 1, wherein the imaging unit comprises at least two coordinated imaging devices, and there is further provided a distance information detection unit which detects distance information by viewing a stereo image comprising two of the captured images stereoscopically.

9. An autonomous action robot according to claim 4, wherein

the imaging unit comprises at least two coordinated imaging devices, and

there is further provided a distance information detection unit which detects distance information by viewing a stereo image comprising two of the captured images stereoscopically.

5. An autonomous action robot comprising:

a sound detection unit which detects a sound emitted from a sound source;

a sound source locating unit which specifies a direction of the sound source based on the sound detected by the sound detection unit;

an imaging unit which captures an image of surroundings,

a target image extraction unit which extracts a target image of a specific shape from the image captured by the imaging unit; and

an attitude and position changing unit which changes an attitude and a position of the robot to face towards the target image based on the specified sound source direction and the extracted target image.

7. An autonomous action robot according to claim 5, further comprising:

a contour extraction unit which extracts a contour of the target image by applying a dynamic contour model to the captured image.