Unlock instant, AI-driven research and patent intelligence for your innovation.

Grasping of an object by a robot based on grasp strategy determined using machine learning model(s)

A machine learning model, robot technology, used in robots, instruments, manipulators, etc.

Pending Publication Date: 2020-10-16
X DEV LLC
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

While humans innately know how to correctly grasp many different objects, determining the appropriate way to grasp an object in order to manipulate that object can be a daunting task for robots

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Grasping of an object by a robot based on grasp strategy determined using machine learning model(s)
  • Grasping of an object by a robot based on grasp strategy determined using machine learning model(s)
  • Grasping of an object by a robot based on grasp strategy determined using machine learning model(s)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] figure 1An example environment is illustrated in which an object may be grasped by an end effector of a robot (eg, robot 180, robot 190, and / or other robots). Objects may be grasped according to a grasping strategy selected by grasping system 110 using one or more trained machine learning models 160 . For example, grasping system 110 may: use one or more trained machine learning models 160 to select a grasping strategy based on the processing of sensor data from the robot; based on the selected grasping strategy, determine One or more end effector poses, grasping parameters, and / or pre-grasp and / or post-grasp manipulations; and commands may be provided to actuators of the robot to, based on the determined end-effector poses, grasp parameters and / or pre-grasp and / or post-grasp manipulations to cause the robot's end effectors to attempt to grasp the object.

[0040] exist figure 1 Example robots 180 and 190 are illustrated in . The robot 180 is a "robot arm" with mult...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Grasping of an object, by an end effector of a robot, based on a grasp strategy that is selected using one or more machine learning models. The grasp strategy utilized for a given grasp is one of a plurality of candidate grasp strategies. Each candidate grasp strategy defines a different group of one or more values that influence performance of a grasp attempt in a manner that is unique relative to the other grasp strategies. For example, value(s) of a grasp strategy can define a grasp direction for grasping the object (e.g., "top", "side"), a grasp type for grasping the object (e.g., "pinch","power"), grasp force applied in grasping the object, pre-grasp manipulations to be performed on the object, and / or post-grasp manipulations to be performed on the object.

Description

Background technique [0001] Many robots are programmed to grasp one or more objects using one or more end effectors. For example, a robot may utilize grasping end-effectors such as "impact" grasping end-effectors (e.g., jaws, claws, fingers, and / or rods that grasp an object by direct contact with the object) or "invasive" grasping An end effector (eg, using a pin, needle, etc. to physically penetrate the object) to pick up the object from a first location, move the object to a second location, and then drop the object at the second location. Some additional examples of robotic end effectors that can grasp objects include "astrictive" grasping end effectors (e.g., that use suction or vacuum to pick up objects) and one or more "contigutive" grasping end effectors. Take end effectors (e.g. using surface tension, freezing, or adhesives to pick up objects), to name a few. While humans innately know how to properly grasp many different objects, determining the proper way to grasp ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): B25J9/16G05B19/418
CPCG05B19/41885G05B2219/40411B25J9/163Y10S901/03Y10S901/09Y10S901/47Y02P90/02B25J9/1612B25J9/1697
Inventor U.纳加拉詹B.洪贝格
Owner X DEV LLC