Robot device, method of controlling the same, computer program, and robot system

• US 9,463,575 B2
• Filed: 04/01/2014
• Issued: 10/11/2016
• Est. Priority Date: 07/25/2011
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Shimizu, Satoru, Kawamoto, Kenta, Iwai, Yoshiaki
• Primary Examiner(s): Jen, Ian
• Application Number:
  US14/242,319
• Publication Number:
  US 20140214208A1
• Time in Patent Office: 924 Days
• Field of Search: 701/259
• US Class Current: 1/1
• CPC Class Codes: B25J 9/1679 characterised by the tasks executed
• CPC Class Codes: B25J 9/1697 Vision controlled systems
• CPC Class Codes: G05B 2219/37618 Observe, monitor position, posture of tool
• CPC Class Codes: G05B 2219/39478 Control force and posture of hand
• CPC Class Codes: G05B 2219/39517 Control orientation and position of object in hand, roll between plates
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: Y10S 901/01 Mobile robot
• CPC Class Codes: Y10S 901/47 Optical

Abstract

Provided is a robot device including an image input unit for inputting an image of surroundings, a target object detection unit for detecting an object from the input image, an object position detection unit for detecting a position of the object, an environment information acquisition unit for acquiring surrounding environment information of the position of the object, an optimum posture acquisition unit for acquiring an optimum posture corresponding to the surrounding environment information for the object, an object posture detection unit for detecting a current posture of the object from the input image, an object posture comparison unit for comparing the current posture of the object to the optimum posture of the object, and an object posture correction unit for correcting the posture of the object when the object posture comparison unit determines that there is a predetermined difference or more between the current posture and the optimum posture.

Claims

1. A device comprising:

circuitry configured to

detect an object in image data,

acquire surrounding environment information of the object,

acquire a first posture data of the object based on the surrounding environment information with respect to a position of the device,

detect a second posture data of the object from the image data,

compare the second posture data of the object with the first posture data of the object, and

determine whether at least a predetermined difference exists between the second posture data of the object and the first posture data of the object.

2. The device according to claim 1, wherein the circuitry is further configured to generate posture change data when the comparison result indicates that the predetermined difference exists.

3. The device according to claim 2,

wherein the circuitry is further configured to cause an end effector to move according to the posture change data.

4. The device according to claim 3, wherein the device includes the end effector and the end effector is coupled to the circuitry.

5. The device according to claim 1, further comprising:

an image sensor device coupled to the circuitry and configured to generate the image data.

6. The device according to claim 1, wherein the circuitry is further configured to execute a task based on an instruction of a user, and when the circuitry is not executing the task, the circuitry performs the detection of the second posture data of the object, the comparison with the first posture data, and the determination of whether at least the predetermined difference exists.

7. The device according to claim 1, wherein the circuitry is further configured to move a position of the device, and the circuitry detects the second posture data of the object while moving a current position of the device.

8. The device according to claim 1, wherein when a plurality of objects exist, the circuitry acquires first posture data for each of the objects and retains the acquired first posture data for each of the objects in an object posture database.

9. The device according to claim 8, wherein the object posture database further retains posture data for each object as taught from a user.

10. The device according to claim 1, wherein the circuitry is further configured to update an environment map on a basis of the image data.

11. The device according to claim 1, wherein circuitry acquires posture data for placing the object when arranging an environment, and different posture data when transferring the object.

12. The device according to claim 1, wherein the circuitry acquires the surrounding environment information of the object from an environment map including the surrounding environment information.

13. The device according to claim 1, wherein the circuitry compares a current posture of the object to the first posture data of the object retained in an object posture database.

16. The device according to claim 1, wherein the device is a robot.

17. The device according to claim 1, further comprising a plurality of links connected by joints.

18. The device according to claim 17, further comprising a plurality of actuators corresponding to the joints, each actuator operating a respective joint.

19. The device according to claim 18, wherein the plurality of links and joints form a tectonic belt.

14. A method for a device comprising:

detecting, with circuitry, an object in image data;

acquiring surrounding environment information of the object;

acquiring a first posture data of the object based on the surrounding environment information with respect to a position of the device;

detecting a second posture data of the object from the image data;

comparing the second posture data of the object with the first posture data of the object; and

determining whether at least a predetermined difference exists between the second posture data of the object and the first posture data of the object.

15. A non-transitory computer-readable medium encoded with computer readable instructions thereon, the computer-readable instructions when executed by a processor cause the processor to perform a method for a device comprising:

detecting an object in image data;

acquiring surrounding environment information of the object;

acquiring a first posture data of the object based on the surrounding environment information relative to a position of the device;

detecting a second posture data of the object from the image data;

comparing the second posture data of the object with the first posture data of the object; and

determining whether at least a predetermined difference exists between the second posture data of the object and the first posture data of the object.