Mujin, Inc.

Jinze Yu

Jose Jeronimo Moreira Rodrigues

Xutao Ye

Rosen Nikolaev Diankov

Yoshiki Kanemoto

Russell Islam

Huan Liu

Ahmed Abouelela

Hamdi Sahloul

Hironori Mizoguchi

Shintaro Matsuoka

Jose Jeronimo Moreira Rodrigue

A computing system including a processing circuit in communication with a camera having a field of view. The processing circuit is configured to perform operations related to detecting, identifying, and retrieving objects disposed amongst a plurality of objects. The processing circuit may be configured to perform operations related to object recognition template generation, feature generation, hypothesis generation, hypothesis refinement, and hypothesis validation.

Systems and methods for object detection

A system and method for operating a transfer robot and a multi-surface gripper to grasp and transfer objects is disclosed.

Robotic multi-surface gripper assemblies and methods for operating the same

Systems and methods for generating an object recognition template

A method performed by a computing system is presented. The method may include the computing system receiving image information that represents an object surface associated with a flexible object, and identifying, as a grip region, a surface region of the object surface that satisfies a defined smoothness condition and has a region size that is larger than or equal to a defined region size threshold, wherein the grip region is identified based on the image information. The method may further include identifying, as a safety region, a three-dimensional (3D) region which surrounds the grip region in one or more horizontal dimensions, and which extends from the grip region along a vertical dimension that is perpendicular to the one or more horizontal dimensions. The method may further include performing robot motion planning based on the grip region and the safety region.

Method and computing system for performing grip region detection

A system and method for estimating aspects of target objects and/or associated task implementations is disclosed.

Robotic system with image-based sizing mechanism and methods for operating the same

Systems and methods for processing spatial structure data are provided. The system accesses spatial structure data, which describes object structure, and which has depth information indicative of a plurality of layers for the object structure. The system further extracts, from the spatial structure data, a portion of the spatial structure data representative of one layer of the plurality of layers. The system identifies, from the portion of the spatial structure data, a plurality of vertices that describe a contour of the layer. Additionally, the system identifies convex corners of the layer based on the plurality of vertices and performs object recognition according to the convex corners.

Method and computing system for object identification

The present disclosure relates to verifying an initial object estimation of an object. A two-dimensional (2D) image representative of an environment including one or more objects may be obtained. The 2D image may be inspected to detect edges of an object. The edges may be processed to verify or update an initial object estimation to increase the accuracy of an object detection result.

Post-detection refinement based on edges and multi-dimensional corners

A system and method for processing candidate edges are presented. The method may be performed when spatial structure information and 2D image information are stored. The method may include identifying, based on the spatial structure information, a 3D location that represents a corner of an object structure; identifying, based on the spatial structure information, a 3D vector that extends from the 3D location and is parallel with an edge; determining a 2D location within the 2D image information that corresponds to the 3D location; determining a 2D vector within the 2D image information that corresponds to the 3D vector; determining an edge detection region; identifying a cluster of candidate edges within the edge detection region that does not represent any object edge; identifying, as a 2D object edge, a candidate edge that is not part of the identified cluster; and performing segmentation based on the 2D object edge.

Method and computing system for processing candidate edges

A system and method for determining occlusion are presented. The system receives camera data generated by at least one camera, which includes a first camera having a first camera field of view. The camera data is generated when a stack having a plurality of objects is in the first camera field of view, and describes a stack structure formed from at least an object structure for a first object of the plurality of objects. The system identifies a target feature of or disposed on the object structure, and determines a 2D region that is co-planar with and surrounds the target feature. The system determines a 3D region defined by connecting a location of the first camera and the 2D region. The system determines, based on the camera data and the 3D region, a size of an occluding region, and determines a value of an object recognition confidence parameter.

Method and system for determining occlusion within a camera field of view

A computing system including a processing circuit in communication with a camera having a field of view. The processing circuit obtains image information based on the objects in the field of view and defines a minimum viable region for a target open corner. Potential minimum viable regions are defined by identifying candidate edges of an object and determining potential intersection points based on the candidate edges. The minimum viable region may then be identified and validated from the potential minimum viable regions.

Robotic system for object size detection

Systems and methods for classifying at least a portion of an image as being textured or textureless are presented. The system receives an image generated by an image capture device, wherein the image represents one or more objects in a field of view of the image capture device. The system generates one or more bitmaps based on at least one image portion of the image. The one or more bitmaps describe whether one or more features for feature detection are present in the at least one image portion, or describe whether one or more visual features for feature detection are present in the at least one image portion, or describe whether there is variation in intensity across the at least one image portion. The system determines whether to classify the at least one image portion as textured or textureless based on the one or more bitmaps.

Method and system for performing image classification for object recognition

A method and computing system for facilitating edge detection are presented. The computing system may include at least one processing circuit configured to receive image information representing a group of objects in a camera field of view, and to identify, from the image information, a plurality of candidate edges associated with the group of objects. The at least one processing circuit may further determine, when the plurality of candidate edges include a first candidate edge which is formed based on a border between a first image region and a second image region, whether the image information satisfies a defined darkness condition at the first candidate edge. The at least one processing circuit may further select a subset of the plurality of candidate edges to form a selected subset of candidate edges for representing the physical edges of the group of objects.

Method and computing system for performing or facilitating physical edge detection

A system and method for operating a robotic system to scan and register unrecognized objects is disclosed. The robotic system may use an image data representative of an unrecognized object located at a start location to implement operations for transferring the unrecognized object from the start location. While implementing the operations, the robotic system may obtain additional data, including scanning results of one or more portions of the unrecognized object not included in the image data. The robotic system may use the additional data to register the unrecognized object.

Robotic system with automated package scan and registration mechanism and methods of operating the same

The present disclosure relates to detecting and registering unrecognized or unregistered objects. A minimum viable range (MVR) may be derived based on inspecting image data that represents objects. The MVR may be determined to be a certain MVR or an uncertain MVR according to one or more features represented in the image data. The MVR may be used to register corresponding objects according to the certain or uncertain determination.

Growing community of inventors

Tokyo, Japan

Jinze Yu