Abstract:
A method for calibrating a robot system (10) comprising a planar pick surface (90) comprises: bringing a robot gripper (30) to a first location against the pick surface (90); and generating a first image of the robot gripper (30) from below. When knowing that a certain identifiable part of the robot gripper (30) in images always lies against the planar pick surface (90), the position and orientation of the pick surface (90) in relation to a manipulator coordinate frame (70) can be fully defined if the robot gripper's (30) orientation in relation to the pick surface (90) is known, or if there are images on identifiable parts of the robot gripper (30) in at least three different positions against the pick surface (90).
Abstract:
A method for teaching an industrial robot (3) to pick parts (120, 122) comprises the steps of: placing a reference part (7) on a picking surface (2); providing a reference image comprising information about the reference part (7); placing a gripping tool (5) of the industrial robot (3) in relation to the reference part (7) so that the gripping tool (5) is in a grasp configuration in relation to the reference part (7); and storing the grasp configuration. The reference image is a 2D image from below. When the reference part (7) is resting on a known plane a 2D image taken from below is enough for defining the position of the same.
Abstract:
The present invention relates to a component feeder (1) comprising a stationary picking surface (2) for receiving components (14) to be picked, a vision system including an image unit arranged to take images of components distributed on the picking surface and a load device (5) including one or more load sensors adapted to detect the presence of a component on the picking surface and the vision system is configured to automatically trigger the image unit to take an image upon detecting the presence of the component on the picking surface.