A system for analyzing geometric properties for an object includes designing the object in a first computer process and producing information relating to the geometric properties of the object, and receiving the information in a second computer processor which identifies a first portion of the geometric property information as masked or private and second portion identified as public or shared, analysis is performed by the second processor on the public/shared portion of the geometric property information. An output based on the analysis may be provided to an industrial system performing processes on the object. A binary privacy label may be assigned to each triangle in a set of triangles representing the surfaces of the object in a 3D object mesh. The privacy label denotes an associated triangle as being private or shared. The system may be used to produce a set of planned grasps for a robotic gripper.

A method for operating a robotic system including determining an initial pose of a target object based on imaging data; calculating a confidence measure associated with an accuracy of the initial pose; and determining that the confidence measure fails to satisfy a sufficiency condition; and deriving a motion plan accordingly for scanning an object identifier while transferring the target object from a start location to a task location.

An object manipulation apparatus according to an embodiment of the present disclosure includes a memory and a hardware processor coupled to the memory. The hardware processor is configured to: calculate, based on an image in which one or more objects to be grasped are contained, an evaluation value of a first behavior manner of grasping the one or more objects; generate information representing a second behavior manner based on the image and a plurality of evaluation values of the first behavior manner; and control actuation of grasping the object to be grasped in accordance with the information being generated.

The invention relates to a method for gripping an object by a handling system, including a robot with at least one robot arm, a gripping device which is connected to the robot arm and has a pneumatically operated suction gripper having an elastically deformable contact portion for contact with an outer surface of the object to be gripped, an identification means for identifying the outer surface of the object to be gripped and a control means which interacts with the identification means and is designed to control the robot, wherein an outer surface of an object to be gripped is identified, wherein a distinction is made between planar portions of the outer surface on the one hand and convex elevations or outer edges on the other, and wherein the suction gripper is made to approach the outer surface of the object to be gripped in such a way that at least a part of the contact portion of the suction gripper clings to a convex elevation or outer edge of the outer surface. The invention also relates to a suction gripper for use in such a method.

A robot hand controller includes an air supply unit configured to supply air into fingers of a robot hand and configured to discharge air in the fingers, and a controller configured to control the air supply unit, where the air supply unit includes two or more air passages respectively connected to the different fingers, the air passages capable of supplying the air into the fingers and discharging the air in the fingers independently from each other, and the controller controls supply and discharge of the air through each of the two or more air passages in response to a shape of the workpiece and an object in a vicinity of a transport destination of the workpiece.

A robot system (2a . . . 2d) is specified, which comprises a robot (1a, 1b) having a gripping unit (4) for collecting and placing down/throwing goods (26a, . . . 26g), wherein the goods (26a, . . . 26g) are differentiated into multiple types with respect to their dimensional stability, compressive stability, flexural rigidity, strength, their absolute weight and/or specific weight. When the goods (26a, . . . 26g) are manipulated, the robot (1a, 1b) and/or the gripping unit (4) are controlled depending on the type determined for the goods (26a, . . . 26g). Moreover, a method for operating the robot system (2a, . . . 2d) is specified.

A gripping method relates to a gripping method for gripping an object using a multi-fingered hand provided with a plurality of fingers. A three-dimensional measurement sensor is used to measure an area that contains the object to obtain three-dimensional information. If the area includes an area for which no three-dimensional information can be obtained, the area is separated and is interpolated using the range information indicating the closer one of distances obtained at two positions on an axis extending along a direction in which the fingers are opened and closed, the two positions being adjacent to the unmeasured area with the unmeasured area interposed therebetween. Then, the distance between the fingers for gripping the object is decided, and the multi-fingered hand is controlled based on the distance.

In at least one embodiment, a system determines a set of possible grasp poses that allow a robot to successfully grasp an object by generating a set of potential grasp poses, and then evaluating the performance of each potential grasp pose. In at least one embodiment, the system performs a refinement operation on the grasp poses, and based on an evaluation of the poses, creates an improved set of possible grasps for the object.

Implementations are directed to training a machine learning model that, once trained, is used in performance of robotic grasping and/or other manipulation task(s) by a robot. The model can be trained using simulated training examples that are based on simulated data that is based on simulated robot(s) attempting simulated manipulations of various simulated objects. At least portions of the model can also be trained based on real training examples that are based on data from real-world physical robots attempting manipulations of various objects. The simulated training examples can be utilized to train the model to predict an output that can be utilized in a particular taskand the real training examples used to adapt at least a portion of the model to the real-world domain can be tailored to a distinct task. In some implementations, domain-adversarial similarity losses are determined during training, and utilized to regularize at least portion(s) of the model.

Grasping remains a complex topic for simulation. Embodiments provide a method to automatically determine grasping cues for tools. An example embodiment scans a CAD model representing a real-world tool to generate a series of sections from the CAD model. In turn, properties of each section are extracted and one or more regions of the CAD model are identified based upon the extracted properties and a tool family to which the tool represented by the CAD model belongs. To continue, a respective classification for each of the one or more identified regions is identified and grasping cues for the CAD model are generated based upon the determined respective classification for each of the one or more regions.