Back to results
US 10,046,459 B2Granted
Three-dimensional visual servoing for robot positioning
AssigneeABB Schweiz AG
InventorsJianjun Wang, Biao Zhang, Carlos Martinez, Carlos Winsor Morato
Life of this patent
Estimating the term…
Abstract
Three-dimensional visual servoing for positioning a robot in an environment is facilitated. Three-dimensional point cloud data of a scene of the environment is obtained, the scene including a feature. The three-dimensional point cloud data is converted into a two-dimensional image, and a three-dimensional position of the feature is identified based on the two-dimensional image. An indication of the identified three-dimensional position of the feature is then provided.
Claims20
A method comprising:
- facilitating three-dimensional visual servoing for positioning a robot in an environment, the facilitating comprising:
- obtaining three-dimensional point cloud data of a scene of the environment, the scene including a feature;
- converting the three-dimensional point cloud data into a two-dimensional image, including projecting a plurality of points of the point cloud data onto a common plane and determining a plurality of image values for the plurality of points, each image value of the plurality of image values being for a respective point of the plurality of points, and each image value indicating a distance value for the point relative to the common plane;
- identifying based on the two-dimensional image a three-dimensional position of the feature;
- and
- providing an indication of the identified three-dimensional position of the feature to a controller for positioning the robot.
3 more elements
A computer system configured to perform a method, the method comprising:
- facilitating three-dimensional visual servoing for positioning a robot in an environment, the facilitating comprising:
- obtaining three-dimensional point cloud data of a scene of the environment, the scene including a feature;
- converting the three-dimensional point cloud data into a two-dimensional image, including projecting a plurality of points of the point cloud onto a common plane and determining a plurality of image values for the plurality of points, each image value of the plurality of image values being for a respective point of the plurality of points, and each image value of the plurality of image values indicating a distance value for the point relative to the common plane, the plurality of image values being image intensity values of the two-dimensional image;
- identifying based on the two-dimensional image a three-dimensional position of the feature;
- and
- providing an indication of the identified three-dimensional position of the feature to a controller for positioning the robot.
3 more elements
An apparatus, comprising:
- a non-transitory computer readable storage medium readable by a processor and storing instructions for execution by the processor to:
- facilitate three-dimensional visual servoing for positioning a robot in an environment, the facilitate comprising:
- obtain three-dimensional point cloud data of a scene of the environment, the scene including a feature;
- convert the three-dimensional point cloud data into a two-dimensional image including projecting a plurality of points of the point cloud onto a common plane and determining a plurality of image values for the plurality of points, each image value of the plurality of image values being for a respective point of the plurality of points, and each image value of the plurality of image values indicating a distance value for the point relative to the common plane, the plurality of image values being image intensity values of the two-dimensional image, the image intensity values being grayscale or color intensity values;
- identify based on the two-dimensional image a three-dimensional position of the feature;
- and
- provide an indication of the identified three-dimensional position of the feature to a controller for positioning the robot.
4 more elements
Dependencies are inferred from the claim text.