Data generation device for vision sensor and detection simulation system
US-9519736-B2 · Dec 13, 2016 · US
US9868215B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9868215-B2 |
| Application number | US-201615133231-A |
| Country | US |
| Kind code | B2 |
| Filing date | Apr 20, 2016 |
| Priority date | May 13, 2015 |
| Publication date | Jan 16, 2018 |
| Grant date | Jan 16, 2018 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An object pick-up system able to use a simpler configuration to place picked up objects at a predetermined location with the directions of the picked up objects aligned. The object pick-up system is provided with a robot hand, manipulator, vision sensor, arrangement determination part setting the position and posture of the robot hand when gripping an object, manipulator controller controlling the manipulator, and robot hand controller controlling the robot hand. The manipulator controller places the robot hand at a position and posture giving rise to a moment in the object. The robot hand controller prevents an object from dropping from the robot hand while the object is rotated by the action of gravity.
Opening claim text (preview).
The invention claimed is: 1. An object pick-up system for picking up stacked objects, the object pick-up system comprising: a robot hand configured to grip an object; a manipulator which moves the robot hand; a vision sensor configured to detect a position and posture of the object; an arrangement determination part which determines a position and posture of the robot hand when the robot hand grips the object based on the position and the posture of the object detected by the vision sensor; a manipulator controller which controls the manipulator so as to arrange the robot hand at the position and posture of the robot hand determined by the arrangement determination part; and a robot hand controller which controls the robot hand so as to grip the object so that the object is immovable with respect to the robot hand, wherein the manipulator controller controls the manipulator so as to arrange the robot hand as a position and posture in which a moment is generated at the object when the robot hand gripping the object lifts up the object, the robot hand controller controls the robot hand so as to decrease a force, by which the robot hand grips the object, after the robot hand is arranged at the position and posture in which the moment is generated at the object, to allow the object to rotate relative to the robot hand by the action of gravity while preventing the object from dropping from the robot hand, the object is formed with a through hole at a position separated from a center of gravity of the object, the robot hand includes: plurality of claws; and a claw driver which moves the plurality of claws in directions approaching and separating away from each other, the arrangement determination part determines the position and posture of the robot hand in which the plurality of claws is positionable inside the through hole, and the robot hand controller controls the claw driver so as to move the plurality of claws in directions separating away from each other to press the plurality of claws against a wall surface which defines the through hole, to grip the object by the plurality of claws; and controls the claw driver so as to move the plurality of claws in directions approaching each other to allow the object to rotate relative to the robot hand, when the robot hand is arranged at the position and posture in which the moment is generated at the object. 2. The object pick-up system according to claim 1 , wherein the claws are arranged horizontally, or are arranged to be inclined with respect to the horizontal direction so that distal ends of the claws are positioned vertically upward of proximal ends of the claws, when the robot hand is arranged at the position and posture in which the moment is generated at the object. 3. The object pick-up system according to claim 1 , wherein the robot hand further includes an arm attached to the manipulator and holding the plurality of claws, wherein the plurality of claws extend so as to be inclined with respect to the arm. 4. The object pick-up system according to claim 1 , wherein the arrangement determination part determines the position and posture of the robot hand to grip the object without the robot hand and the manipulator interfering with a surrounding member. 5. The object pick-up system according to claim 1 , wherein the robot hand controller controls the robot hand so as to grip the object so that the object is again immovable relative to the robot hand, when the rotation of the object stops. 6. A method of gripping and picking up stacked objects by a robot hand, the method comprising: detecting a position and posture of an object; determining a position and posture of the robot hand when the robot hand grips the object based on the detected position and posture of the object; arranging the robot hand at the determined position and posture of the robot hand; gripping the object by the robot hand so that the object is immovable with respect to the robot hand; arranging the robot hand at a position and posture in which a moment is generated at the object when the robot hand gripping the object lifts up the object; and decreasing a force, by which the robot hand grips the object, after the robot hand is arranged at the position and posture in which the moment is generated at the object, to rotate the object relative to the robot hand by the action of gravity while preventing the object from dropping from the robot hand, wherein the object is formed with a through hole at a position separated from a center of gravity of the object, the robot hand includes: a plurality of claws; and a claw driver which moves the plurality of claws in directions approaching and separating away from each other, said determining the position and posture of the robot hand is performed when the plurality of claws is positioned inside the through hole, said gripping the object by the robot hand comprises controlling the claw driver so as to move the plurality of claws in directions separating away from each other to press the plurality of claws against a wall surface which defines the through hole, to grip the object by the plurality of claws, and said decreasing the force, by which the robot hand grips the object, comprises controlling the claw driver so as to move the plurality of claws in directions approaching each other to allow the object to rotate relative to the robot hand, when the robot hand is arranged at the position and posture in which the moment is generated at the object.
characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion · CPC title
Vision controlled systems · CPC title
Grasp slightly, rotate object between two fingers by action of gravity · CPC title
Vacuum or mangetic · CPC title
Optical · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.