Methods and computer-program products for evaluating grasp patterns, and robots incorporating the same
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-019/00
B25J-009/16
출원번호
US-0640421
(2015-03-06)
등록번호
US-9375839
(2016-06-28)
발명자
/ 주소
Ota, Yasuhiro
Kim, Junggon
Kuffner, James J.
출원인 / 주소
Carnegie Mellon University
대리인 / 주소
Dinsmore & Shohl LLP
인용정보
피인용 횟수 :
0인용 특허 :
24
초록▼
Methods and computer-program products for evaluating grasp patterns for use by a robot are disclosed. In one embodiment, a method of evaluating grasp patterns includes selecting an individual grasp pattern from a grasp pattern set, establishing a thumb-up vector, and simulating the motion of the man
Methods and computer-program products for evaluating grasp patterns for use by a robot are disclosed. In one embodiment, a method of evaluating grasp patterns includes selecting an individual grasp pattern from a grasp pattern set, establishing a thumb-up vector, and simulating the motion of the manipulator and the end effector according to the selected individual grasp pattern, wherein each individual grasp pattern of the grasp pattern set corresponds to motion for manipulating a target object. The method further includes evaluating a direction of the thumb-up vector during at least a portion of the simulated motion of the manipulator and the end effector, and excluding the selected individual grasp pattern from use by the robot if the direction of the thumb-up vector during the simulated motion is outside of one or more predetermined thresholds. Robots utilizing the methods and computer-program products for evaluating grasp patterns are also disclosed.
대표청구항▼
1. A method of evaluating individual grasp patterns of a grasp pattern set for use by a robot, the method comprising: selecting an individual grasp pattern from the grasp pattern set, wherein each individual grasp pattern of the grasp pattern set corresponds to a motion of a manipulator and an end e
1. A method of evaluating individual grasp patterns of a grasp pattern set for use by a robot, the method comprising: selecting an individual grasp pattern from the grasp pattern set, wherein each individual grasp pattern of the grasp pattern set corresponds to a motion of a manipulator and an end effector of the robot for manipulating a target object;establishing, using a processor, a thumb-up vector extending from a top surface of the end effector;evaluating, using the processor, a direction of the thumb-up vector during at least a portion of the motion of the manipulator and the end effector;excluding, using the processor, the selected individual grasp pattern from use by the robot if the direction of the thumb-up vector during the motion is outside of one or more predetermined thresholds according to the selected individual grasp pattern;indicating the selected individual grasp pattern as a grasp pattern candidate if the direction of the thumb-up vector during the motion is within the one or more predetermined thresholds;providing a plurality of grasp pattern candidates to a motion planner module of the robot; andmanipulating the target object by the robot based on at least one grasp pattern candidate of the plurality of grasp pattern candidates. 2. The method of claim 1, wherein the direction of the thumb-up vector is evaluated by determining an end effector angle between the thumb-up vector and a vertical axis extending from a base surface of the robot. 3. The method of claim 2, wherein the selected individual grasp pattern is excluded from use by the robot if the end effector angle is greater than a predetermined angle threshold during the motion, and the selected individual grasp pattern is indicated as a grasp pattern candidate if the end effector angle is less than the predetermined angle threshold during the motion. 4. The method of claim 1, wherein: the end effector of the robot comprises a thumb joint and at least two finger joints;the thumb-up vector is established by determining a position of the thumb joint with respect to the at least two finger joints;the selected individual grasp pattern is excluded from use by the robot if the thumb joint is lower along a vertical axis extending from a base surface of the robot than each of the at least two finger joints during the motion; andthe selected individual grasp pattern is indicated as a grasp pattern candidate if the thumb joint is higher than or level with at least one of the at least two finger joints during the motion. 5. The method of claim 4, wherein: the thumb-up vector is further established by determining a position of an elbow of the manipulator;the selected individual grasp pattern is excluded from use by the robot if the thumb joint is lower along the vertical axis than each of the at least two finger joints during the motion, or if the position of the elbow exceeds a predetermined height along the vertical axis during the motion; andthe selected individual grasp pattern is indicated as a grasp pattern candidate if the thumb joint is higher than or level with at least one of the at least two finger joints during the motion, and if the position of the elbow is below the predetermined height along the vertical axis during the motion. 6. A computer-program product for use with a computing device for evaluating individual grasp patterns of a grasp pattern set for use by a robot, the computer-program product comprising: a non-transitory computer-readable medium storing computer-executable instructions for evaluating grasp patterns that, when executed by the computing device, cause the computing device to: select an individual grasp pattern from the grasp pattern set, wherein each individual grasp pattern of the grasp pattern set corresponds to a motion of a manipulator and an end effector of the robot for manipulating a target object;establish a thumb-up vector extending from a top surface of the end effector;evaluate a direction of the thumb-up vector during at least a portion of the motion of the manipulator and the end effector;exclude the selected individual grasp pattern from use by the robot if the direction of the thumb-up vector during the motion is outside of one or more predetermined thresholds;indicate the selected individual grasp pattern as a grasp pattern candidate if the direction of the thumb-up vector during the motion is within the one or more predetermined thresholds; andprovide a plurality of grasp pattern candidates to a motion planner module of the robot; andmanipulate the target object by the robot based on at least one grasp pattern candidate of the plurality of grasp pattern candidates. 7. The computer-program product of claim 6, wherein the direction of the thumb-up vector is evaluated by determining an end effector angle between the thumb-up vector and a vertical axis extending from a base surface of the robot. 8. The computer-program product of claim 7, wherein the selected individual grasp pattern is excluded from use by the robot if the end effector angle is greater than a predetermined angle threshold during the motion, and the selected individual grasp pattern is indicated as a grasp pattern candidate if the end effector angle is less than the predetermined angle threshold during the motion. 9. The computer-program product of claim 6, wherein: the end effector of the robot comprises a thumb joint and at least two finger joints;the thumb-up vector is established by determining a position of the thumb joint with respect to the at least two finger joints;the selected individual grasp pattern is excluded from use by the robot if the thumb joint is lower along a vertical axis extending from a base surface of the robot than each of the at least two finger joints during the motion; andthe selected individual grasp pattern is indicated as a grasp pattern candidate if the thumb joint is higher than or level with at least one of the at least two finger joints during the motion. 10. The computer-program product of claim 9, wherein: the thumb-up vector is further established by determining a position of an elbow of the manipulator;the selected individual grasp pattern is excluded from use by the robot if the thumb joint is lower along the vertical axis than each of the at least two finger joints during the motion, or if the position of the elbow exceeds a predetermined height along the vertical axis during the motion; andthe selected individual grasp pattern is indicated as a grasp pattern candidate if the thumb joint is higher than or level with at least one of the at least two finger joints during the motion, and if the position of the elbow is below the predetermined height along the vertical axis during the motion. 11. A robot comprising: a base portion comprising a base surface;a manipulator movably coupled to the base portion;an end effector movably coupled to a distal end of the manipulator;a processor;a computer-readable medium storing computer-executable instructions for evaluating grasp patterns that, when executed by the processor, cause the processor to: receive one or more grasp pattern candidates, wherein the one or more grasp pattern candidates are determined by: selecting an individual grasp pattern from a grasp pattern set, wherein each individual grasp pattern of the grasp pattern set corresponds to a motion of the manipulator and the end effector of the robot for manipulating a target object;establishing a thumb-up vector extending from a top surface of the end effector;evaluating a direction of the thumb-up vector during at least a portion of the motion of the manipulator and the end effector; andexcluding the selected individual grasp pattern from use by the robot if the direction of the thumb-up vector during the motion is outside of one or more predetermined thresholds;select one of the one or more grasp pattern candidates and provide the selected grasp pattern candidate to a motion planner module;generate a plurality of motion segments corresponding to the base portion, the manipulator, the end effector or combinations thereof; andcontrol the base portion, the manipulator, or the end effector according to the plurality of motion segments. 12. The robot of claim 11, wherein the one or more grasp pattern candidates are determined by the robot using the computer-executable instructions and the processor. 13. The robot of claim 11, wherein the one or more grasp pattern candidates are provided to the robot by an external computing device. 14. The robot of claim 11, wherein the direction of the thumb-up vector is evaluated by determining an end effector angle between the thumb-up vector and a vertical axis extending from the base surface of the robot. 15. The robot of claim 14, wherein the selected individual grasp pattern is excluded from use by the robot if the end effector angle is greater than a predetermined angle threshold during the motion, and the selected individual grasp pattern is indicated as an individual grasp pattern candidate if the end effector angle is less than the predetermined angle threshold during the motion. 16. The robot of claim 11, wherein: the end effector of the robot comprises a thumb joint and at least two finger joints;the manipulator comprises an elbow;the thumb-up vector is established by determining a position of the thumb joint with respect to the at least two finger joints and determining a position of the elbow of the manipulator;the selected individual grasp pattern is excluded from use by the robot if the thumb joint is lower along a vertical axis extending from a base surface of the robot than each of the at least two finger joints during the motion, or if the position of the elbow exceeds a predetermined height along the vertical axis during the motion; andthe selected individual grasp pattern is indicated as an individual grasp pattern candidate if the thumb joint is higher than or level with at least one of the at least two finger joints during the motion, and if the position of the elbow is below the predetermined height along the vertical axis during the motion.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (24)
Arai Tatsuo (Urawa JPX), Apparatus for control of manipulator.
Coughlan Joel B. (Knox County TN) Harvey Howard W. (Roane County TN) Upton R. Glen (Anderson County TN) White John R. (Roane County TN), Remote manipulator.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.