Robotic system for object size measurement
OwnerJinze YU, Yoshiki KANEMOTO +2inventors
InventorsJinze YU, Yoshiki KANEMOTO, Jose Jeronimo MOREIRA RODRIGUES, Rosen Nikolaev DIANKOV
Life of this patent
Estimating the term…
Abstract
Systems and methods for object detection and robotic control or pickup of the detected objects are provided. Systems and methods described herein provide for the determination and adjustment of minimum viable regions on a surface of an object for robotic pickup. Determination of a minimum viable region may increase the accuracy and efficiency of robotic object handling. The minimum viable region may be used to select grasping areas for a movement operation configured to provide supplemental image information for estimating dimensions of a target object.
Claims20
A computing system comprising:
- at least one processing circuit in communication with a robot, having an arm and an end-effector connected thereto, and a camera having a field of view and configured, when one or more objects are or have been in the field of view, to execute instructions stored on a non-transitory computer-readable medium for:
- obtaining initial image information of one or more objects, wherein the initial image information is generated by the camera;
- detecting a plurality of corners of the one or more objects based on the initial image information;
- identifying a target open corner of a target object from the plurality of corners;
- defining a minimum viable region (MVR) for the target object;
- defining a non-occlusion area based on the minimum viable region;
- transmitting a positioning command for positioning the arm of the robot;
- transmitting a grasping command for grabbing the target object within the minimum viable region;
- transmitting a movement command for moving the target object based on a movement direction, a movement distance, and a movement type, using the arm of the robot;
- obtaining supplemental image information of the one or more objects;
- and
- calculating estimated dimensions for the target object based on the supplemental image information,
- wherein at least one of the positioning command, the grasping command, and the movement command are configured to prevent the arm of the robot from blocking the non-occlusion area of the one or more objects.
A method of controlling a robotic system comprising a non-transitory computer-readable medium, at least one processing circuit in communication with a camera having a field of view and configured to execute instructions, the method comprising:
- obtaining initial image information of one or more Objects, wherein the initial image information is generated by the camera;
- detecting a plurality of corners of the one or more objects based on the initial image information;
- identifying a target open corner of a target object from the plurality of corners;
- defining a minimum viable region (MVR) for the target object;
- defining a non-occlusion area based on the minimum viable region;
- transmitting a positioning command for positioning an arm of a robot;
- transmitting a grasping command for grabbing the target object within the minimum viable region;
- transmitting a movement command for moving the target object based on a movement direction, a movement distance, and a movement type, using the arm of the robot;
- obtaining supplemental image information of the one or more objects;
- and
- calculating estimated dimensions for the target object based on the supplemental image information,
- wherein at least one of the positioning command, the grasping command, and the movement command are configured to prevent the arm of the robot from blocking a non-occlusion area of the one or more objects.
A non-transitory computer-readable medium including instructions for execution by at least one processing circuit in communication with a camera having a field of view and configured, when one or more objects are or have been in the field of view, the instructions being configured for:
- obtaining initial image information of one or more objects, wherein the initial image information is generated by the camera;
- detecting a plurality of corners of the one or more objects based on the initial image information;
- identifying a target open corner of a target object from the plurality of corners;
- defining a minimum viable region (MVR) for the target object;
- defining a non-occlusion area based on the minimum viable region;
- transmitting a positioning command for positioning an arm of a robot;
- transmitting a grasping command for grabbing the target object within the minimum viable region;
- transmitting a movement command for moving the target object based on a movement direction, a movement distance, and a movement type, using the arm of the robot;
- obtaining supplemental image information of the one or more objects;
- and
- calculating estimated dimensions for the target object based on the supplemental image information,
- wherein at least one of the positioning command, the grasping command, and the movement command are configured to prevent the arm of the robot from blocking a non-occlusion area of the one or more objects.
Dependencies are inferred from the claim text.