Abstract: A system and method for operating a robotic system to use two or more tools to manipulate objects. The robotic system may coordinate planning processes and/or plan implementations based on grouping the objects.

Abstract: A robotic system includes an end-effector configured for grasping an object, the end-effector including a suction cup assembly configured to engage the object, and a contact limit sensor configured to detect a pressure associated with the engagement between the suction cup assembly and the object, wherein the contact limit sensor transmits contact information when the contact limit sensor detects the pressure exceeding a contact threshold, a sensor unit monitoring contact information received from the contact limit sensor, and a controller, coupled to the sensor unit, configured to execute an operation for controlling the end-effector to limit movement of the end-effector toward the object based on the contact information received.

Abstract: A system and method for performing automatic camera calibration is presented. The system communicates with a first camera and a second camera, wherein a transparent platform is disposed between the two cameras. When a 3D calibration pattern is disposed on the platform, the system receives a first set of calibration images from the first camera, and a second set of calibration images from the second camera. The system determines, based on the first set of calibration images, a first set of coordinates for corners of the polyhedron. The system further determines, based on the second set of calibration images, a second set of coordinates for the corners. The system determines, based on the coordinates, a spatial relationship between the first camera and the second camera. The system further uses a description of the spatial relationship to generate a 3D model of an object other than the 3D calibration pattern.

Abstract: 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.

Abstract: A system and method for performing object detection are presented. The system receives spatial structure information associated with an object which is or has been in a camera field of view of a spatial structure sensing camera. The spatial structure information is generated by the spatial structure sensing camera, and includes depth information for an environment in the camera field of view. The system determines a container pose based on the spatial structure information, wherein the container pose is for describing at least one of an orientation for the container or a depth value for at least a portion of the container. The system further determines an object pose based on the container pose, wherein the object pose is for describing at least one of an orientation for the object or a depth value for at least a portion of the object.

Abstract: A system and method for operating a transport robot to simultaneously grasp and transfer multiple objects is disclosed. The transport robot includes a multi-gripper assembly having an array of addressable vacuum regions each configured to independently provide a vacuum. The robotic system receives image data representative of a group of objects. Individual target objects are identified in the group based on the received image data. Addressable vacuum regions are selected based on the identified target objects. The transport robot is command to cause the selected addressable vacuum regions to simultaneously grasp and transfer multiple target objects.

Abstract: Introduced here is an approach to further refining an initial set of target locations that can serve as inputs to machine learning mechanisms. These target locations may refer to unique molecular positions in a reference human genome and/or mutations thereof that are diagnostically relevant for a given cancer type. The system can implement a refinement mechanism to account for unnecessary or problematic data, such as consecutive/overlapping patterns, non-uniform read counts, insufficient data quality, internal processing noises, and/or insufficient data counts.

Abstract: A robotic system includes a user interface configured to receive a jog command for manually operating a robotic unit; a control unit, coupled to the user interface, configured to: real-time parallel process the jog command including to: execute a collision check thread to determine whether the jog command results in a collision or results in an unobstructed status for the robotic unit within an operation environment based on an environment model and a robot model, execute a jog operation thread to determine whether the unobstructed status is provided within a collision check time limit; and execute the jog command by the robotic unit based on the unobstructed status provided before the collision check time limit.

Abstract: 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.

Abstract: 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.

Abstract: A robot system controller and control method that implement sophisticated cooperation among units is provided. The controller may include: a data acquisition unit adapted to acquire first data including information about the handling object and the shelf before storing or retrieving the handling object in/from the shelf; a data storage unit; and a robot control unit adapted to select and transport the shelf to an access position before storing or retrieving the handling object in/from the shelf, create or acquire a control sequence for storing or retrieving the handling object in/from the shelf, instruct the transport robot to execute a task of transporting the shelf to the access position, and instruct the handling robot to execute a task of storing or retrieving the handling object in/from the shelf.

Abstract: A method for operating a transport robot includes receiving image data representative of a group of objects. One or more target objects are identified in the group based on the received image data. Addressable vacuum regions are selected based on the identified one or more target objects. The transport robot is command to cause the selected addressable vacuum regions to hold and transport the identified one or more target objects. The transport robot includes a multi-gripper assembly having an array of addressable vacuum regions each configured to independently provide a vacuum. A vision sensor device can capture the image data, which is representative of the target objects adjacent to or held by the multi-gripper assembly.

Abstract: A method and computing system for performing the method are presented. The method may include receiving image information representing an object; identifying a set of one or more matching object recognition templates associated with a set of one or more detection hypotheses. The method may further include selecting a primary detection hypothesis associated with a matching object recognition template; generating a primary candidate region based on the matching object recognition template; determining at least one of: (i) whether the set of one or more matching object recognition templates has a subset of one or more remaining matching templates, or (ii) whether the image information has a portion representing an unmatched region; and generating a safety volume list based on at least one of: (i) the unmatched region, or (ii) one or more additional candidate regions that are generated based on the subset of one or more remaining matching templates.

Abstract: A method and computing system for performing object detection are presented. The computing system may be configured to: receive first image information that represents at least a first portion of an object structure of an object in a camera's field of view, wherein the first image information is associate with a first camera pose; generate or update, based on the first image information, sensed structure information representing the object structure; identify an object corner associated with the object structure; cause the robot arm to move the camera to a second camera pose in which the camera is pointed at the object corner; receive second image information associated with the second camera pose; update the sensed structure information based on the second image information; determine, based on the updated sensed structure information, an object type associated with the object; determine one or more robot interaction locations based on the object type.

Abstract: A computing system and a method for calibration verification is presented. The computing system is configured to perform a first calibration operation, and to control a robot arm to move a verification symbol to a reference location. The robot control system further receives, from a camera, a reference image of the verification symbol, and determines a reference image coordinate for the verification symbol. The robot control system further controls the robot arm to move the verification symbol to the reference location again during an idle period, receives an additional image of the verification symbol, and determines a verification image coordinate. The robot control system determines a deviation parameter value based the reference image coordinate and the verification image coordinate, and whether the deviation parameter value exceeds a defined threshold, and performs a second calibration operation if the threshold is exceeded.

Abstract: 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.

Abstract: A control apparatus for controlling operation of a work robot for performing work inside a target region using a manipulator includes a trajectory information acquiring unit for acquiring N?1 or N pieces of trajectory information respectively indicating N?1 or N trajectories connecting N work regions where the work robot performs a series of work operations in order of a series of work operations; a classifying unit for classifying the N?1 or N trajectories as (i) trajectories that need correction or (ii) trajectories that do not need correction; and a trajectory planning unit for planning a trajectory of a tip of the manipulator between two work regions relating to the each of the one or more trajectories, for each of the one or more trajectories classified as a trajectory that needs correction by the classifying unit.

Abstract: A system and method for operating a robotic system to dynamically adjust a planned trajectory or a planned implementation thereof is disclosed. The robotic system may derive updated waypoints to replace planned waypoints of the planned trajectory for implementing a task. Using the updated waypoints, the robotic system may implement the task differently than initially planned according to the planned trajectory.

Abstract: A control apparatus includes a first information acquiring section that acquires three-dimensional information of a first region of surfaces of a plurality of objects, the information being obtained by imaging or scanning the plurality of objects from a first location; a second information acquiring section that acquires three-dimensional information of a second region of surfaces of the plurality of objects, the information being obtained by imaging or scanning the plurality of objects from a second location; and a combining section that generates information indicating three-dimensional shapes of at least a portion of the surfaces of the plurality of objects, based on the three-dimensional information of the first region acquired by the first information acquiring section and the three-dimensional information of the second region acquired by the second information acquiring section.

Abstract: A system and related methods for operating a robotic system with a routing mechanism is disclosed herein. The routing mechanism may surround external components that extend across a link and connect to an end effector. The routing mechanism may include guides, brackets, or a combination thereof configured to maintain the external components along a predetermined path relative to the link, the end effector, one or more corresponding joints, or a combination thereof during movement of the link and/or the end effector.