Object pickup strategies for a robotic device
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G05B-019/18
B25J-009/16
출원번호
US-0213089
(2014-03-14)
등록번호
US-9333649
(2016-05-10)
발명자
/ 주소
Bradski, Gary
Konolige, Kurt
Rublee, Ethan
Straszheim, Troy
Strasdat, Hauke
Hinterstoisser, Stefan
Croft, Steve
Zevenbergen, John
출원인 / 주소
Industrial Perception, Inc.
대리인 / 주소
McDonnell Boehnen Hulbert & Berghoff LLP
인용정보
피인용 횟수 :
19인용 특허 :
23
초록▼
Example embodiments may relate to methods and systems for selecting a grasp point on an object. In particular, a robotic manipulator may identify characteristics of a physical object within a physical environment. Based on the identified characteristics, the robotic manipulator may determine potenti
Example embodiments may relate to methods and systems for selecting a grasp point on an object. In particular, a robotic manipulator may identify characteristics of a physical object within a physical environment. Based on the identified characteristics, the robotic manipulator may determine potential grasp points on the physical object corresponding to points at which a gripper attached to the robotic manipulator is operable to grip the physical object. Subsequently, the robotic manipulator may determine a motion path for the gripper to follow in order to move the physical object to a drop-off location for the physical object and then select a grasp point, from the potential grasp points, based on the determined motion path. After selecting the grasp point, the robotic manipulator may grip the physical object at the selected grasp point with the gripper and move the physical object through the determined motion path to the drop-off location.
대표청구항▼
1. A method comprising: identifying one or more characteristics of a physical object within a physical environment, wherein the identified one or more characteristics of the physical object comprise a set of geometric characteristics from a particular perspective viewpoint of the physical object;mak
1. A method comprising: identifying one or more characteristics of a physical object within a physical environment, wherein the identified one or more characteristics of the physical object comprise a set of geometric characteristics from a particular perspective viewpoint of the physical object;making a comparison between the set of geometric characteristics and one or more virtual geometric shapes from the particular perspective viewpoint of the physical object;based on an output of the comparison indicating that at least one of the geometric characteristics substantially matches a given virtual geometric shape, generating a virtual object representative of the physical object and associated with the matching virtual geometric shape;adjusting one or more identified characteristics of the physical object based on characteristics of the virtual object;based on the adjusted identified one or more characteristics, determining by a computing device two or more potential grasp points on the physical object corresponding to points at which a gripper attached to a robotic manipulator is operable to grip the physical object;determining a motion path for the gripper to follow in order to move the physical object to a drop-off location for the physical object;selecting a grasp point from the two or more potential grasp points based on the determined motion path; andproviding instructions to cause the robotic manipulator to grip the physical object at the selected grasp point with the gripper and move the physical object through the determined motion path to the drop-off location. 2. The method of claim 1, further comprising: receiving at least one sensor scan of the physical object, wherein identifying the one or more characteristics of the physical object is based at least in part on the at least one sensor scan of the physical object. 3. The method of claim 1, wherein determining the two or more potential grasp points comprises identifying of two or more flat areas on the physical object. 4. The method of claim 3, wherein the gripper uses suction to grip objects, and wherein the identified two or more flat areas are each larger in area than a gripping surface of the gripper. 5. The method of claim 1, wherein determining the two or more potential grasp points comprises identifying a first point on a first surface of the physical object and a second point on a second surface of the physical object, wherein the first and second surfaces have opposite surface orientations, and wherein the gripper comprises a two finger gripper configured to clamp onto the identified first and second points. 6. The method of claim 1, wherein selecting the grasp point from the two or more potential grasp points further comprises rejecting, from among the two or more potential grasp points, one or more potential grasp points that result in a collision with an obstructing object when the robotic manipulator moves towards the physical object in order to grip the physical object at the selected grasp point with the gripper. 7. The method of claim 1, wherein selecting the grasp point from the two or more potential grasp points further comprises rejecting one or more potential grasp points that result in a collision with an obstructing object when the robotic manipulator moves the physical object through the determined motion path to the drop-off location. 8. The method of claim 1, wherein selecting the grasp point from the two or more potential grasp points further comprises selecting the grasp point based on geometric characteristics of the drop-off location to cause the one or more identified characteristics of the physical object to accommodate the geometric characteristics of the drop-off location. 9. The method of claim 1, wherein determining the motion path for the gripper comprises determining a sequence of joint angles for the robotic manipulator that minimizes a cost function, wherein the cost function comprises a plurality of weighted criterion associated with different characteristics of the motion path. 10. The method of claim 1, wherein determining the motion path for the gripper comprises determining a sequence of Cartesian coordinates for the physical object that minimizes a cost function, wherein the cost function comprises a plurality of weighted criterion associated with different characteristics of the motion path. 11. The method of claim 1, wherein selecting the grasp point from the two or more potential grasp points comprises selecting a grasp point from the two or more potential grasp points that minimizes a cost function, wherein the cost function comprises a plurality of weighted criterion associated with different characteristics of the grasp point. 12. The method of claim 1, wherein selecting the grasp point from the two or more potential grasp points comprises selecting a grasp point from the two or more potential grasp points that minimizes a cost function, wherein the cost function comprises: a plurality of weighted criterion associated with different characteristics of a pose of the robotic manipulator at the grasp point; anda plurality of weighted criterion associated with different characteristics of a pose of the robotic manipulator at the drop-off location. 13. The method of claim 1, further comprising: storing information, in a memory storage, comprising one or more of: (i) the identified one or more characteristics of the physical object, (ii) the adjusted identified one or more characteristics of the physical object, (iii) the selected grasp point, (iv) the determined motion path, and (v) a performance evaluation of the selected grasp point based on the movement of the physical object through the determined motion path to the drop-off location. 14. The method of claim 13, further comprising: using the stored information to determine other grasp points for the robotic manipulator to use in picking up additional physical objects from the physical environment. 15. The method of claim 13, further comprising: providing the stored information to a second robotic manipulator to determine grasp points for the second robotic manipulator to use to pick up physical objects from a physical environment. 16. The method of claim 1, further comprising: determining one or more adjacent physical objects in contact with the physical object; andproviding instructions to cause the robotic manipulator to create space between the physical object and the one or more adjacent physical objects by using the gripper to cause the physical object to alternately move in at least two opposing directions prior to moving the physical object through the determined motion path. 17. The method of claim 1, further comprising: receiving sensor data from one or more sensors, wherein generating the virtual object is further based at least in part on the sensor data received from one or more sensors. 18. The method of claim 17, wherein the one or more sensors are attached to the robotic manipulator. 19. The method of claim 1, further comprising: identifying a fiducial mark at a particular point on the virtual object, wherein the fiducial mark indicates a reference point for gripping the physical object; anddetermining a point on the physical object corresponding to the fiducial mark as one of the two or more potential grasp points. 20. A system comprising: a robotic manipulator;a gripper attached to the robotic manipulator; anda control system configured to: identify one or more characteristics of a physical object within a physical environment, wherein the identified one or more characteristics of the physical object comprise a set of geometric characteristics from a particular perspective viewpoint of the physical object;make a comparison between the set of geometric characteristics and one or more virtual geometric shapes from the particular perspective viewpoint of the physical object;based on an output of the comparison indicating that at least one of the geometric characteristics substantially matches a given virtual geometric shape, generate a virtual object representative of the physical object and associated with the matching virtual geometric shape;adjust one or more identified characteristics of the physical object based on characteristics of the virtual object;based on the adjusted identified one or more characteristics, determine two or more potential grasp points on the physical object corresponding to points at which the gripper is operable to grip the physical object;determine a motion path for the gripper to follow in order to move the physical object to a drop-off location for the physical object;select a grasp point from the two or more potential grasp points based on the determined motion path; andprovide instructions to cause the robotic manipulator to grip the physical object at the selected grasp point with the gripper and move the physical object through the determined motion path to the drop-off location. 21. The system of claim 20, wherein the control system is configured to determine the two or more potential grasp points by identifying of two or more flat areas on the physical object. 22. The system of claim 21, wherein the gripper uses suction to grip objects, and wherein the identified two or more flat areas are each larger in area than a gripping surface of the gripper. 23. The system of claim 20, wherein selecting the grasp point from the two or more potential grasp points further comprises selecting the grasp point based on geometric characteristics of the drop-off location to cause the one or more identified characteristics of the physical object to accommodate the geometric characteristics of the drop-off location. 24. A non-transitory computer readable medium having stored therein instructions, that when executed by a computing device, cause the computing device to perform functions comprising: identifying one or more characteristics of a physical object within a physical environment, wherein the identified one or more characteristics of the physical object comprise a set of geometric characteristics from a particular perspective viewpoint of the physical object;making a comparison between the set of geometric characteristics and one or more virtual geometric shapes from the particular perspective viewpoint of the physical object;based on an output of the comparison indicating that at least one of the geometric characteristics substantially matches a given virtual geometric shape, generating a virtual object representative of the physical object and associated with the matching virtual geometric shape;adjusting one or more identified characteristics of the physical object based on characteristics of the virtual object;based on the adjusted identified one or more characteristics, determining two or more potential grasp points on the physical object corresponding to points at which a gripper attached to a robotic manipulator is operable to grip the physical object;determining a motion path for the gripper to follow in order to move the physical object to a drop-off location for the physical object;selecting a grasp point from the two or more potential grasp points based on the determined motion path; andproviding instructions to cause the robotic manipulator to grip the physical object at the selected grasp point with the gripper and move the physical object through the determined motion path to the drop-off location.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (23)
Sato, Satoshi; Nakagawa, Masamichi; Nobori, Kunio; Nakata, Mikiya; Kondo, Kenji, Article holding system, robot, and method of controlling robot.
Van Durrett William (Charlotte NC) Hieronymus Gerald W. (Charlotte NC) Pond Marguerite A. (Charlotte NC) Price Todd D. (Charlotte NC) Scurry Margaret L. S. (Charlotte NC) Steene William C. (Gastonia , Automated palletizing system.
Red Walter E. (Provo UT) Davies Brady R. (Orem UT) Wang Xuguang (Provo UT) Turner Edgar R. (Provo UT), Device and method for correction of robot inaccuracy.
Zhao, Wenyi; Hasser, Christopher J J; Nowlin, William C.; Hoffman, Brian D., Methods and systems for robotic instrument tool tracking with adaptive fusion of kinematics information and image information.
Stubbs, Andrew; Marchese, Andrew D.; Longtine, John Gregory; Krishnaswamy, Sarath; Ort, Moses Theodore; Toris, Russell Charles; Wachlin, Jacob Taylor, Feature identification and extrapolation for robotic item grasping.
Stubbs, Andrew; Marchese, Andrew D.; Longtine, John Gregory; Krishnaswamy, Sarath; Ort, Moses Theodore; Toris, Russell Charles; Wachlin, Jacob Taylor, Feature identification and extrapolation for robotic item grasping.
Hicham, El Bernouss; Crest, Karine; Philppe, Agnès, Installation for separating and singulating non-uniform postal articles with a vision system having laser sources.
Stubbs, Andrew; Marchese, Andrew D.; Longtine, John Gregory; Krishnaswamy, Sarath; Ort, Moses Theodore; Toris, Russell Charles; Wachlin, Jacob Taylor, Validation of robotic item grasping.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.