首页|Manipulating Boxes Using A Zoned Gripper' in Patent Application Approval Process (USPTO 20240001537)

Manipulating Boxes Using A Zoned Gripper' in Patent Application Approval Process (USPTO 20240001537)

扫码查看
The following quote was obtained by the news editors from the background information supplied by theinventors: “Box-like objects represent a large percentage of objects that need to be picked (i.e., removedfrom a pallet or holding container) in industrial, manufacturing, logistics, and commercial environments.Typically, box-like objects are characterized by at least one substantially planar picking surface. Conventionally,during robotic picking, a picking robot handles known sizes, numbers, and types of boxes arrangedin a uniform manner on a structured pallet. Using mechanical fixtures, some current systems pre-position apallet of boxes so that a robot can pick them from known pre-programmed locations. Any deviation fromthis known structure, either in the size of the box, the number of boxes, or the location of boxes resultsin failure of the system. Unfortunately, computer-vision-based systems often rely on the boxes havingclean edges at their boundaries and cannot accurately determine size and/or position of boxes that haveadvertising, printed characters, printed logos, pictures, color, or any other texture on them. Such boxeshave visual edges on their faces (i.e., edges that do not correspond to an actual physical boundary of thebox). Because current computer-vision-based systems cannot distinguish the physical edges between twodifferent boxes from other visual edges on the faces of boxes, these systems tend to misjudge the size andposition of the box(es). Problematically, picking and moving the box where the system has misjudged itssize and location may either cause the box to slip from the grasp of the robot or may cause the robot topick two or more boxes where it should have picked only one.”

Emerging TechnologiesMachine LearningPatent ApplicationRobotRobotics

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Jan.19)