Systems and methods for determining a type of grasp for a robotic end-effector

Abstract

Substantially as described and illustrated herein including devices, methods of operation for the systems or devices, articles of manufacture including processor-executable instructions, and a system including a robot.

1 . A system comprising:
 a robot including an end-effector;   at least one processor communicatively coupled to the end-effector; and   at least one nontransitory processor-readable storage device communicatively coupled to the at least one processor and which stores processor-executable instructions which, when executed by the at least one processor, cause the at least one processor to:
 cause the end-effector to perform an attempt to manipulate an item; 
 receive a position value for the end-effector from a position sensor; 
 receive a velocity value for the end-effector from a velocity sensor; 
 determine a grasp type of the item based at least in part on the received position value and the received velocity value; and 
 create a grasp type signal that includes information that represents the determined grasp type. 
   
     
     
         2 . The system of  claim 1 , wherein, when executed, the instructions further cause the at least one processor to use deep learning techniques to extract features from the received position value and the received velocity value. 
     
     
         3 . The system of  claim 1 , wherein, when executed, the instructions further cause the at least one processor to update at least one processor-readable storage device with at least one of the position value, the velocity value, or the grasp type. 
     
     
         4 . The system of  claim 1 , wherein the received position value and the received velocity value represent positions of two or more parts of the end-effector relative to each other. 
     
     
         5 . The system of  claim 1 , wherein, when executed, the instructions further cause the at least one processor to select a grasp type from at least one of: a failure to grasp the item, a grasp of a bag containing the item, or a grasp of a wrong part of the item. 
     
     
         6 . The system of  claim 1  further comprising:
 an operator interface communicatively coupled to the at least one processor; and 
 wherein, when executed, the processor-executable instructions further cause the at least one processor to:
 receive, at the robot from the operator interface, operator generated processor-executable robot control instructions which, when executed, cause the robot to perform an action. 
 
 
     
     
         7 . The system of  claim 1  wherein, when executed, the processor-executable instructions further cause the at least one processor to:
 receive, at the robot, autonomous processor-executable robot control instructions which, when executed, cause the robot to perform an action. 
 
     
     
         8 . The system of  claim 1  wherein, when executed, the processor-executable instructions further cause the at least one processor to:
 receive autonomous robot control instructions which when executed causes the robot to move the item and release the item. 
 
     
     
         9 . The system of  claim 8  wherein, when executed, the processor-executable instructions further cause the at least one processor to:
 reject the autonomous robot control instructions based on the grasp type. 
 
     
     
         10 . The system of  claim 1  wherein to determine the grasp type, when executed, the processor-executable instructions cause the at least one processor to:
 select a first grasp type value for the grasp type when the velocity value is below a first threshold value and the position value is below a second threshold value; and 
 select a second grasp type value for the grasp type when the velocity value is below the first threshold value and the position value is above a third threshold value. 
 
     
     
         11 . A method of operation for a system including at least one processor and a robot including an end-effector in communication with the at least one processor, the method comprising:
 causing, by the at least one processor, the end-effector to perform an attempt to manipulate an item;   receiving, by the at least one processor, a position value for the end-effector from a position sensor;   receiving, by the at least one processor, a velocity value for the end-effector from a velocity sensor;   determining, by the at least one processor, a grasp type of the item based at least in part on the received position value and the received velocity value; and   generating, by the at least one processor, a grasp type signal that includes information that represents the selected grasp type.   
     
     
         12 . The method of  claim 11 , further comprising using deep learning techniques to extract features from the received position value and the received velocity value. 
     
     
         13 . The method of  claim 11 , further comprising updating, by the at least one processor, at least one processor-readable storage device with at least one of the position value, the velocity value, or the grasp type. 
     
     
         14 . The method of  claim 11 , wherein the received position value and the received velocity value represent positions of two or more parts of the end-effector relative to each other. 
     
     
         15 . The method of  claim 11 , wherein selecting a grasp type comprises selecting a grasp type from at least one of: a failure to grasp the item, a grasp of a bag containing the item, or a grasp of a wrong part of the item. 
     
     
         16 . The method of  claim 11  wherein the system further includes a manipulator physically coupled to the end-effector, the method further comprising:
 causing, by the last least one processor, the end-effector to change a location via the manipulator. 
 
     
     
         17 . The method of  claim 11  wherein the system further includes an operator interface in communication with the at least one processor, the method further comprising:
 receiving, at the robot from the operator interface, operator generated processor-executable robot control instructions which, when executed, cause the robot to perform an action. 
 
     
     
         18 . The method of  claim 11  further comprising:
 receiving, at the robot, autonomous processor-executable robot control instructions which, when executed, cause the robot to perform an action. 
 
     
     
         19 . The method of  claim 11  wherein the system further includes an observer interface in communicatively with the at least one processor; and, the method further comprises:
 receiving, at the robot from the observer interface, observer generated processor-readable information that represents a pose for the end-effector. 
 
     
     
         20 . The method of  claim 11  further comprising:
 receiving, at the at least one processor, robot control instructions which when executed causes the robot to perform at least one action; and 
 rejecting, by the at least one processor, the robot control instructions which when executed causes the robot to perform at least one action. 
 
     
     
         20 . The method of  claim 11  wherein determining, by the at least one processor, a grasp type based on the received position value and the received velocity value comprises:
 selecting, by the at least one processor, a first grasp type value for the grasp type when the velocity value is below a first threshold value and the position value is below a second threshold value; or 
 selecting, by the at least one processor, a second grasp type value for the grasp type when the velocity value is below the first threshold value and the position value is above a third threshold value.