Calibrated vision based robotic system utilizing upward and downward looking cameras
AssigneeWestern Digital Technologies, Inc.
InventorJambunathan Vangal-Ramamurthy
Life of this patent
Estimating the term…
Abstract
A method and apparatus of calibrating a vision based robotic system is disclosed. The apparatus includes a first camera, a second camera, a calibration block having an alignment mark, and a robotic tool having an alignment fiducial. The method includes using the first camera and the calibration block to determine a first camera center position, using the second camera and the calibration block to determine a second camera center position, using the second camera and the robotic tool to determine a robotic tool center position, and calculating a first camera to tool offset value.
Claims33
A method of calibrating a vision based robotic system comprising:
- moving a first camera to be positioned approximately above a calibration block including at least one alignment mark;
- capturing, using the first camera, at least one image of at least one of a first plurality of camera reading points and the at least one alignment mark to determine a first camera center position;
- capturing, using a second camera, at least one image of at least one of a second plurality of camera reading points and the at least one alignment mark to determine a second camera center position;
- moving a robotic tool, including at least one alignment fiducial, to be positioned approximately above the second camera;
- capturing, using the second camera, at least one image of at least one of the alignment fiducials to determine a robotic tool center position;
- and
- calculating a first camera-to-tool offset value.
A calibrated vision based robotic system comprising:
- a robotic tool, including at least one alignment fiducial, to engage a work piece;
- a servo motor assembly configured to move the robotic tool;
- a machine vision assembly including a first camera and a second camera;
- a calibration block including at least one alignment mark;
- and
- a controller coupled to the servo motor assembly and the machine vision assembly, the controller operable to:
- command the servo motor assembly to move the first camera to be positioned approximately above the calibration block;
- command the first camera to capture at least one image of at least one of a first plurality of camera reading points and the at least one alignment mark to determine a first camera center position;
- command the second camera to capture at least one image of at least one of a second plurality of camera reading points and the at least one alignment mark to determine a second camera center position;
- command the servo motor assembly to move the robotic tool to be positioned approximately above the second camera;
- command the second camera to capture at least one image of at least one of the alignment fiducials to determine a robotic tool center position;
- and
- calculate a first camera-to-tool offset value.
In a calibrated vision based robotic system, a non-transitory computer-readable medium having stored thereon instructions, which, when executed by a computer, cause the computer to perform operations comprising:
- moving a first camera to be positioned approximately above a calibration block including at least one alignment mark;
- capturing, using the first camera, at least one image of at least one of a first plurality of camera reading points and the at least one alignment mark to determine a first camera center position;
- capturing, using a second camera, at least one image of at least one of a second plurality of camera reading points and the at least one alignment mark to determine a second camera center position;
- moving a robotic tool, including at least one alignment fiducial, to be positioned approximately above the second camera;
- capturing, using the second camera, at least one image of at least one of the alignment fiducials to determine a robotic tool center position;
- and
- calculating a first camera-to-tool offset value.
Dependencies are inferred from the claim text.