Abstract: Implementations described herein generally relate to a method for detecting anomalies in time-series traces received from sensors of manufacturing tools. A server feeds a set of training time-series traces to a neural network configured to derive a model of the training time-series traces that minimizes reconstruction error of the training time-series traces. The server extracts a set of input time-series traces from one or more sensors associated with one or more manufacturing tools configured to produce a silicon substrate. The server feeds the set of input time-series traces to the trained neural network to produce a set of output time series traces reconstructed based on the model. The server calculates a mean square error between a first input time series trace of the set of input time series traces and a corresponding first output time series trace of the set of output time-series traces.

Abstract: A physical space contains stationary objects that do not move over time (e.g., a couch) and may have non-stationary objects that do move over time (e.g., people and pets). An autonomous mobile device (AMD) determines and uses an occupancy map of stationary objects to find a route from one point to another in a physical space. Non-stationary objects are detected and prevented from being incorrectly added to the occupancy map. Point cloud data is processed to determine first candidate objects. Image data is processed to determine second candidate objects. These candidate objects are associated with each other and their characteristics assessed to determine if the candidate objects are stationary or non-stationary. The occupancy map is updated with stationary obstacles. During navigation, the occupancy map may be used for route planning while the non-stationary objects are used for local avoidance.

Abstract: An autonomous mobile device (AMD) that interacts with a user operates more effectively with reliable information about that user's pose. Occlusion due to obstacles or sensor field-of-view limits may prevent a sensor from “seeing” a user's torso or lower body while the face may remain visible. Face orientation alone produces unreliable results because a user frequently moves their head. Sensor data is acquired over time and used to determine face and body poses, with each pose representing a location and orientation in physical space of that portion of the user. A transform is determined that represents the relative arrangement of a face pose and a body pose at a particular time. If available, the body pose may be used as the user's pose. If the body pose is unavailable or unreliable at a given time, it may be inferred by applying the previously determined transform to the current face pose.

Abstract: Implementations described herein generally relate to a method for detecting anomalies in time-series traces received from sensors of manufacturing tools. A server feeds a set of training time-series traces to a neural network configured to derive a model of the training time-series traces that minimizes reconstruction error of the training time-series traces. The server extracts a set of input time-series traces from one or more sensors associated with one or more manufacturing tools configured to produce a silicon substrate. The server feeds the set of input time-series traces to the trained neural network to produce a set of output time series traces reconstructed based on the model. The server calculates a mean square error between a first input time series trace of the set of input time series traces and a corresponding first output time series trace of the set of output time-series traces.

Abstract: Implementations described herein generally relate to a method for detecting anomalies in time-series traces received from sensors of manufacturing tools. A server feeds a set of training time-series traces to a neural network configured to derive a model of the training time-series traces that minimizes reconstruction error of the training time-series traces. The server extracts a set of input time-series traces from one or more sensors associated with one or more manufacturing tools configured to produce a silicon substrate. The server feeds the set of input time-series traces to the trained neural network to produce a set of output time series traces reconstructed based on the model. The server calculates a mean square error between a first input time series trace of the set of input time series traces and a corresponding first output time series trace of the set of output time-series traces.

Abstract: A physical space contains stationary objects that do not move over time (e.g., a couch) and may have non-stationary objects that do move over time (e.g., people and pets). An autonomous mobile device (AMD) determines and uses an occupancy map of stationary objects to find a route from one point to another in a physical space. Non-stationary objects are detected and prevented from being incorrectly added to the occupancy map. Point cloud data is processed to determine first candidate objects. Image data is processed to determine second candidate objects. These candidate objects are associated with each other and their characteristics assessed to determine if the candidate objects are stationary or non-stationary. The occupancy map is updated with stationary obstacles. During navigation, the occupancy map may be used for route planning while the non-stationary objects are used for local avoidance.

Abstract: Implementations described herein generally relate to a method for detecting anomalies in time-series traces received from sensors of manufacturing tools. A server feeds a set of training time-series traces to a neural network configured to derive a model of the training time-series traces that minimizes reconstruction error of the training time-series traces. The server extracts a set of input time-series traces from one or more sensors associated with one or more manufacturing tools configured to produce a silicon substrate. The server feeds the set of input time-series traces to the trained neural network to produce a set of output time series traces reconstructed based on the model. The server calculates a mean square error between a first input time series trace of the set of input time series traces and a corresponding first output time series trace of the set of output time-series traces.

Abstract: A method of classifying substrates with a metrology tool is herein disclosed. The method begins by training a deep learning framework using convolutional neural networks with a training dataset for classifying image dataset. Obtaining a new image from the meteorology tool. Running the new image through the deep learning framework to classify the new image.

Abstract: A method of classifying substrates with a metrology tool is herein disclosed. The method begins by training a deep learning framework using convolutional neural networks with a training dataset for classifying image dataset. Obtaining a new image from the meteorology tool. Running the new image through the deep learning framework to classify the new image.

Abstract: A method of classifying substrates with a metrology tool is herein disclosed. The method begins by training a deep learning framework using convolutional neural networks with a training dataset for classifying image dataset. Obtaining a new image from the meteorology tool. Running the new image through the deep learning framework to classify the new image.

Abstract: A method, apparatus and system for controlling the processing of a substrate within a process chamber are described herein. In some embodiments, a method of controlling a substrate process within a process chamber includes determining a position of a moveable magnetron in the process chamber relative to a reference location on a surface of the substrate and modulating a power parameter of at least one power supply affecting substrate processing based on the determined position of the magnetron to control, for example, at least one of a deposition rate or an etching rate of the substrate processing. In one embodiment, the modulated power parameter is a power set point of at least one of a direct current (DC) source power, a radio frequency (RF) bias power, a DC shield bias voltage, or an electromagnetic coil current of the at least one power supply.

Abstract: A method of classifying substrates with a metrology tool is herein disclosed. The method begins by training a deep learning framework using convolutional neural networks with a training dataset for classifying image dataset. Obtaining a new image from the meteorology tool. Running the new image through the deep learning framework to classify the new image.

Abstract: A method, apparatus and system for controlling the processing of a substrate within a process chamber are described herein. In some embodiments, a method of controlling a substrate process within a process chamber includes determining a position of a moveable magnetron in the process chamber relative to a reference location on a surface of the substrate and modulating a power parameter of at least one power supply affecting substrate processing based on the determined position of the magnetron to control, for example, at least one of a deposition rate or an etching rate of the substrate processing. In one embodiment, the modulated power parameter is a power set point of at least one of a direct current (DC) source power, a radio frequency (RF) bias power, a DC shield bias voltage, or an electromagnetic coil current of the at least one power supply.

Abstract: A disk drive is disclosed comprising a head, a disk surface comprising servo information, and a dual stage actuator (DSA) servo loop comprising a voice coil motor (VCM) servo loop comprising a VCM and a microactuator servo loop comprising a microactuator operable to actuate the head over the disk surface. A position error signal (PES) is generated based on the servo information, and a first control signal is generated based on the PES. The first control signal is adjusted based on a function of the first control signal to generate a second control signal that compensates for a gain variation of the microactuator, and the microactuator is controlled based on the second control signal.

Abstract: A disk drive is disclosed comprising a head, a disk surface, and a dual stage actuator (DSA) servo loop comprising a voice coil motor (VCM) servo loop comprising a VCM and a microactuator servo loop comprising a microactuator operable to actuate the head over the disk surface. A microactuator compensator processes a position error signal (PES) to generate a first control signal, and a disturbance sinusoid is injected into the first control signal to generate a second control signal, wherein the microactuator is controlled in response to the second control signal. Feed-forward compensation is generated corresponding to the injected disturbance sinusoid, and a third control signal is generated in response to the PES and the feed-forward compensation, wherein the VCM is controlled in response to the third control signal. A gain of the microactuator is estimated in response to the feed-forward compensation.