Abstract: A computer-implemented method is provided for learning an action policy. The method includes obtaining, by a processor, environment dynamics including triplets of a state, an action, and a next state. The state in each of the triplets is an expert state. The method further includes training, by the processor using the environment dynamics as training data, a dynamics model which obtains a pair of the state and the action as an input and outputs, for each next state, state-transition probabilities. The method also includes learning, by the processor, the action policy using trajectories of expert states according to a supervised learning technique by back-propagating error gradients through the trained dynamics model.

Abstract: A method, a system, and a computer program product provide for changing a boundary between zones. This includes setting a location of a boundary which defines a part of a zone; detecting that an object moves into the zone across the boundary; and in response to the detection, changing the location of the boundary in a direction away from the object, compared to the location of the boundary before the change.

Abstract: A method, a system, and a computer program product provide for changing a boundary between zones. This includes setting a location of a boundary which defines a part of a zone; detecting that an object moves into the zone across the boundary; and in response to the detection, changing the location of the boundary in a direction away from the object, compared to the location of the boundary before the change.

Abstract: Methods and a system are provided for detecting object pose. A method includes training, by a processor, a first autoencoder (AE) to generate synthetic output images based on synthetic input images. The method further includes training, by the processor, a second AE to generate synthetic output images, similar to the synthetic output images generated by the first AE, based on real input images. The method also includes training, by the processor, a neural network (NN) to detect the object pose using the synthetic output images generated by the first and second AEs. The method additionally includes detecting and outputting, by the processor, a pose of an object in a real input test image by inputting the real input test image to the second AE to generate a synthetic image therefrom, and inputting the synthetic image to the NN to generate an NN output indicative of the pose of the object.

Abstract: A computer-implemented method executed by a robotic system for performing a positional search process in an assembly task is presented. The method includes decomposing, by the robotic system, a perturbation motion into a plurality of actions, the perturbation motion being a motion for an assembly position searched by the robotic system, each action of the plurality of actions related to a specific direction. The method further includes performing reinforcement learning by selecting an action among decomposed actions and assembly movement actions at each step of the positional search process based on corresponding force-torque data received from at least one sensor associated with the robotic system. The method also includes outputting a best action at each step for completion of the assembly task as a result of the reinforcement learning.

Abstract: The present invention can be a method, system, and computer program product. One embodiment of the present invention provides a computer-implemented method for identifying an artificial object. The method includes receiving capacitance data which is obtained by measuring with at least one electrodes in a sensor at least one predefined surfaces of the artificial object placed against the sensor; converting each of the obtained capacitance data into an evaluation level in an evaluation system having more than two evaluation levels, to obtain a capacitance distribution on the surface of the artificial object; determining whether the obtained capacitance distribution matches a pre-registered capacitance distribution or one of pre-registered capacitance distributions; and if the determination result is positive, concluding the artificial object is identified.

Abstract: In order to improve the ductility or formability of a magnesium alloy, addition of rare earth elements or refinement of grain size is often used. However, conventional additional elements inhibit the action of grain boundary sliding for complementing plastic deformation. Therefore, it is required to search for additional elements that act to facilitate the grain boundary sliding not only at a conventional deformation speed but also in a higher speed range while maintaining a microstructure for activating non-basal dislocation. The present invention is to provide a wrought processed Mg-based alloy having excellent ductility at room temperature, which consists of 0.25 mass % or more to 9 mass % or less of Bi, and a balance of Mg and inevitable components, and is characterized by having an average grain size of an Mg parent phase after solution treatment and hot plastic working after casting of 20 ?m or less.

Abstract: A computer-implemented method, a system, and a computer program product manage a blacklist. The method includes, for a detected improper device, transferring a blacklist or an identifier or identifiers, present in the blacklist, respectively, of one or more devices associated with information on at least one geographic position of associated with a position of the improper device to one or more relay devices which exist at or near the at least one geographic position associated with the position of the improper device. The blacklist is used for controlling commutation or communication from or to the improper device.

Abstract: A computer-implemented method for inspecting a clearance size between a hole and an object inserted in the hole, includes: controlling a robot arm so that the robot arm performs a predetermined motion to move the object inserted in the hole; monitoring a response to the predetermined motion from the hole and the object; and calculating information on the clearance size between the hole and the object using the response to the predetermined motion.

Abstract: A computer-implemented method, a system, and a computer program product manage a blacklist. A server computer and method communicate with a device via a relay device, the relay device being connected to the device via a wireless network, in response to a detection of an improper device, adding, into a blacklist, information on a position of the improper device or information on a position associated with a position of the improper device, and an identifier of the improper device, wherein the blacklist is used for controlling commutation from or to an improper device. The blacklist or an identifier in the blacklist of a device associated with the information on the position of the improper device is transferred to a relay device in or near the position of the improper device and/or to a relay device in or near the position associated with the position of the improper device.

Abstract: A computer-implemented method, a system, and a computer program product manage a blacklist. A server computer and method communicate with a device via a relay device, the relay device being connected to the device via a wireless network, in response to a detection of an improper device, adding, into a blacklist, information on a position of the improper device or information on a position associated with a position of the improper device, and an identifier of the improper device, wherein the blacklist is used for controlling commutation from or to an improper device. The blacklist or an identifier in the blacklist of a device associated with the information on the position of the improper device is transferred to a relay device in or near the position of the improper device and/or to a relay device in or near the position associated with the position of the improper device.

Abstract: A method, a system, and a computer program product provide for changing a boundary between zones. This includes setting a location of a boundary which defines a part of a zone; detecting that an object moves into the zone across the boundary; and in response to the detection, changing the location of the boundary in a direction away from the object, compared to the location of the boundary before the change.

Abstract: A method, a system, and a computer program product provide for changing a boundary between zones. This includes setting a location of a boundary which defines a part of a zone; detecting that an object moves into the zone across the boundary; and in response to the detection, changing the location of the boundary in a direction away from the object, compared to the location of the boundary before the change.

Abstract: A system and method for optimizing (designing) a mask pattern, in which SMO and OPC are collaboratively used to exert a sufficient collaborative effect or are appropriately used in different manners. The method for designing a source and a mask for lithography includes a step (S1) of selecting a set of patterns; a step of performing source mask optimization (SMO) using the set of patterns, under an optical proximity correction (OPC) restriction rule which is used for selectively restricting shifting of an edge position of a polygon when OPC is applied to the set of patterns; and a step (S3, S4) of determining a layout of the mask for lithography, by applying OPC to all patterns constituting the mask for lithography using the source optimized through the SMO.

Abstract: The present invention can be a method, system, and computer program product. One embodiment of the present invention provides a computer-implemented method for identifying an artificial object. The method includes receiving capacitance data which is obtained by measuring with at least one electrodes in a sensor at least one predefined surfaces of the artificial object placed against the sensor; converting each of the obtained capacitance data into an evaluation level in an evaluation system having more than two evaluation levels, to obtain a capacitance distribution on the surface of the artificial object; determining whether the obtained capacitance distribution matches a pre-registered capacitance distribution or one of pre-registered capacitance distributions; and if the determination result is positive, concluding the artificial object is identified.

Abstract: Methods and systems for determining a source shape, a mask shape and a target shape for a lithography process are disclosed. One such method includes receiving source, mask and target constraints and formulating an optimization problem that is based on the source, mask and target constraints and incorporates contour-based assessments for the target shape that are based on physical design quality of a circuit. Further, the optimization problem is solved by integrating over process condition variations to simultaneously determine the source shape, the mask shape and the target shape. In addition, the determined source shape and mask shape are output.

Abstract: In one embodiment, a source mask optimization (SMO) method is provided that includes controlling bright region efficiency during at least one optical domain step. The bright region efficiency being the proportion of the total transmitted light that is transferred to bright areas of a target pattern. The optical domain intermediate solution provided by the at least one optical domain step may then be binarized to obtain an initial spatial domain solution with a controlled MEEF (Mask Error Enhancement Factor). The MEEF is controlled during at least one spatial domain step that optimizes the initial spatial domain solution.

Abstract: Methods and systems for determining a source shape, a mask shape and a target shape for a lithography process are disclosed. One such method includes receiving source, mask and target constraints and formulating an optimization problem that is based on the source, mask and target constraints and incorporates contour-based assessments for the target shape that are based on physical design quality of a circuit. Further, the optimization problem is solved by integrating over process condition variations to simultaneously determine the source shape, the mask shape and the target shape.

Abstract: A system and method for optimizing (designing) a mask pattern, in which SMO and OPC are collaboratively used to exert a sufficient collaborative effect or are appropriately used in different manners. The method for designing a source and a mask for lithography includes a step (S1) of selecting a set of patterns; a step of performing source mask optimization (SMO) using the set of patterns, under an optical proximity correction (OPC) restriction rule which is used for selectively restricting shifting of an edge position of a polygon when OPC is applied to the set of patterns; and a step (S3, S4) of determining a layout of the mask for lithography, by applying OPC to all patterns constituting the mask for lithography using the source optimized through the SMO.

Abstract: Methods and systems for determining a source shape, a mask shape and a target shape for a lithography process are disclosed. One such method includes receiving source, mask and target constraints and formulating an optimization problem that is based on the source, mask and target constraints and incorporates contour-based assessments for the target shape that are based on physical design quality of a circuit. Further, the optimization problem is solved by integrating over process condition variations to simultaneously determine the source shape, the mask shape and the target shape. In addition, the determined source shape and mask shape are output.