Robot apparatus, method for controlling the same, and computer program
First Claim
Patent Images
1. A robot apparatus comprising:
- an output unit configured to display an image including an object on a screen;
an input unit configured to receive, based on an operation performed by a user, a first specification relating to an approximate range including the object in the image;
an object extraction unit configured to extract information regarding a two-dimensional contour of the object based on the first specification received by the input unit;
a position and attitude estimation unit configured to estimate information regarding a three-dimensional position and attitude of the object based on the information regarding the two-dimensional contour;
a holding unit; and
a holding planning unit configured to plan, without receiving a stored shape model from a database, a trajectory of the holding unit for holding the object based on the estimated information regarding the three-dimensional position and attitude of the object.
1 Assignment
0 Petitions
Accused Products
Abstract
A robot apparatus includes an output unit that displays an image including an object on a screen, an input unit that receives an operation performed by a user for specifying information relating to an approximate range including the object in the image, an object extraction unit that extracts information regarding a two-dimensional contour of the object on the basis of the specification received by the input unit, and a position and attitude estimation unit that estimates information regarding a three-dimensional position and attitude of the object on the basis of the information regarding the two-dimensional contour.
-
Citations
19 Claims
-
1. A robot apparatus comprising:
-
an output unit configured to display an image including an object on a screen; an input unit configured to receive, based on an operation performed by a user, a first specification relating to an approximate range including the object in the image; an object extraction unit configured to extract information regarding a two-dimensional contour of the object based on the first specification received by the input unit; a position and attitude estimation unit configured to estimate information regarding a three-dimensional position and attitude of the object based on the information regarding the two-dimensional contour; a holding unit; and a holding planning unit configured to plan, without receiving a stored shape model from a database, a trajectory of the holding unit for holding the object based on the estimated information regarding the three-dimensional position and attitude of the object. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A method for controlling a robot apparatus, the method comprising:
-
displaying, using an output unit of the robot apparatus, an image including an object on a screen; receiving, using an input unit of the robot apparatus, based on an operation performed by a user, a first specification relating to an approximate range including the object in the image; extracting, using an object extraction unit of the robot apparatus, information regarding a two-dimensional contour of the object based on the first specification received using the input unit; estimating, using a position and attitude estimation unit of the robot apparatus, information regarding a three-dimensional position and attitude of the object based on the information regarding the two-dimensional contour; and planning, using a holding planning unit of the robot apparatus, without receiving a stored shape model from a database, a trajectory of a holding unit of the robot apparatus for holding the object based on the estimated information regarding the three-dimensional position and attitude of the object. - View Dependent Claims (15, 16)
-
-
17. A computer-readable storage medium having stored thereon instructions that, when executed by a processor, cause the processor to function as an apparatus, the apparatus comprising:
-
an output unit configured to display an image including an object on a screen; an input unit configured to receive, based on an operation performed by a user, a first specification relating to an approximate range including the object in the image; an object extraction unit configured to extract information regarding a two-dimensional contour of the object based on the first specification received by the input unit; a position and attitude estimation unit configured to estimate information regarding a three-dimensional position and attitude of the object based on the information regarding the two-dimensional contour; a holding unit; and a holding planning unit configured to plan, without receiving a stored shape model from a database, a trajectory of the holding unit for holding the object based on the estimated information regarding the three-dimensional position and attitude of the object. - View Dependent Claims (18, 19)
-
Specification