Abstract: An example method includes determining, by a controller of an image capture system, a plurality of sets of exposure parameter values for one or more exposure parameters. The plurality of sets of exposure parameter values are determined at an exposure determination rate. The method further includes capturing, by an image capture device of the image capture system, a plurality of images. Each image of the plurality of images is captured according to a set of exposure parameter values of the plurality of sets of exposure parameter values. The method also includes sending, by the controller of the image capture system to an image processing unit, a subset of the plurality of images. Each subset of images is sent at a sampling rate, and the sampling rate is less than the exposure determination rate.

Abstract: Methods for annotating objects within image frames are disclosed. Information is obtained that represents a camera pose relative to a scene. The camera pose includes a position and a location of the camera relative to the scene. Data is obtained that represents multiple images, including a first image and a plurality of other images, being captured from different angles by the camera relative to the scene. A 3D pose of the object of interest is identified with respect to the camera pose in at least the first image. A 3D bounding region for the object of interest in the first image is defined, which indicates a volume that includes the object of interest. A location and orientation of the object of interest is determined in the other images based on the defined 3D bounding region of the object of interest and the camera pose in the other images.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a neural network to predict locations of feeders in an electrical power grid. One of the methods includes training a generative adversarial network comprising a generator and a discriminator; and generating, by the generator, from input images, output images with feeder metadata that represents predicted locations of feeder assets, including receiving by the generator a first input image and generating by the generator a corresponding first output image with first feeder data that identifies one or more feeder assets and their respective locations, wherein the one or more feeder assets had not been identified in any input to the generator.

Abstract: Implementations are described herein for analyzing a sequence of digital images captured by a mobile vision sensor (e.g., integral with a robot), in conjunction with information (e.g., ground truth) known about movement of the vision sensor, to determine spatial dimensions of object(s) and/or an area captured in a field of view of the mobile vision sensor. Techniques avoid the use of visual indicia of known dimensions and/or other conventional tools for determining spatial dimensions, such as checkerboards. Instead, techniques described herein allow spatial dimensions to be determined using less resources, and are more scalable than conventional techniques.

Abstract: The present application discloses implementations that relate to devices and techniques for sensing position, force, and torque. Devices described herein may include a light emitter, photodetectors, and a curved reflector. The light emitter may project light onto the curved reflector, which may reflect portions of that projected light onto one or more of the photodetectors. Based on the illuminances measured at the photodetectors, the position of the curved reflector may be determined. In some implementations, the curved reflector and the light emitter may be elastically coupled via one or more spring elements; in these implementations, a force vector representing a magnitude and direction of a force applied against the curved reflector may be determined based on the position of the curved reflector.

Abstract: The disclosure provides for a system that includes a plurality of stations equipped for free-space optical communications (FSOC) in a network and a central control system. At least one station in the plurality of stations includes a wavelength selectable switch, an OEO module, and one or more first processors. The one or more first processors are configured to control the wavelength selectable switch, process an electrical signal that is extracted using the OEO module, and communicate with the central control system. The central control system includes one or more second processors that are configured to receive data regarding FSOC communication conditions at the plurality of stations, determine a path between stations through the network based on the received data, and transmit instructions to the plurality of stations.

Abstract: Methods, systems, and apparatus, including computer-readable storage devices, for managing voice interface devices. In some implementations, messages are received from a plurality of devices, each of the messages indicating a respective voice input detected by the device that sent the message. Audio signatures are obtained for the voice inputs detected by the plurality of devices. The audio signatures for the voice inputs and times that the voice inputs were detected are evaluated. Based on the evaluation, at least some of the plurality of devices are grouped to form a group of multiple devices that detected a same user utterance. A device from the group is selected to respond to the user utterance, and the multiple devices in the group are managed so that only the selected device outputs a synthesized speech response to the user utterance.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting locations of utility assets. One of the methods includes receiving an input image of an area in a first geographical region; generating, from the input image and using a generative adversarial network, a corresponding reference image; and generating, by an object detection model and from the reference image, an output that identifies respective locations of one or more utility assets with reference to the input image.

Abstract: In some embodiments, techniques are provided for analyzing the manufacturability or fabricability of objects based on segmented designs. In some embodiments, a scanning device scans a manufacturing device and/or an object manufactured by the manufacturing device to characterize a manufacturing capability of the manufacturing device. A paintbrush pattern may be determined based on the characterization, and a proposed design may be determined to be fabricable or non-fabricable using the paintbrush pattern.

Abstract: A fish monitoring system deployed in a particular area to obtain fish images is described. Neural networks and machine-learning techniques may be implemented to periodically train fish monitoring systems and generate monitoring modes to capture high quality images of fish based on the conditions in the determined area. The camera systems may be configured according to the settings, e.g., positions, viewing angles, specified by the monitoring modes when conditions matching the monitoring modes are detected. Each monitoring mode may be associated with one or more fish activities, such as sleeping, eating, swimming alone, and one or more parameters, such as time, location, and fish type.

Abstract: Implementations are described herein for automatically generating synthetic training images that are usable as training data for training machine learning models to detect, segment, and/or classify various types of plants in digital images. In various implementations, a digital image may be obtained that captures an area. The digital image may depict the area under a lighting condition that existed in the area when a camera captured the digital image. Based at least in part on an agricultural history of the area, a plurality of three-dimensional synthetic plants may be generated. The synthetic training image may then be generated to depict the plurality of three-dimensional synthetic plants in the area. In some implementations, the generating may include graphically incorporating the plurality of three-dimensional synthetic plants with the digital image based on the lighting condition.

Abstract: A system, apparatus, and method for optimizing structural parameters of a physical device are described. The method includes receiving an initial description of the physical device describing the structural parameters within a simulated environment. The method further includes performing a simulation of the physical device in response to an excitation source to determine a performance metric of the physical device. The simulation environment includes one or more absorbing boundaries for attenuation of an output of the excitation source during the simulation. The method further includes recording attenuated field values of the simulated environment associated with the attenuation during the simulation.

Abstract: Example systems and methods allow for use of a graphical interface to cause one or more robotic devices to construct an output product. One example method includes causing a graphical interface to be displayed on a display device, receiving input data corresponding to one or more interactions with the graphical interface indicating at least one motion path and at least one sequence of tool actions to execute at one or more points within the at least one motion path for use in construction of an output product, generating a plurality of digital nodes including at least one robot node, at least one motion command node, and at least one tool command node, and providing instructions for the at least one robot actor to move according to the sequence of robot motion commands determined by the at least one motion command node and execute the sequence of tool commands determined by the at least one tool command node to construct the output product.

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing corrections to robot actions. Some implementations are directed to updating a local features model of a robot in response to determining a human correction of an action performed by the robot. The local features model is used to determine, based on an embedding generated over a corresponding neural network model, one or more features that are most similar to the generated embedding. Updating the local features model in response to a human correction can include updating a feature embedding, of the local features model, that corresponds to the human correction. Adjustment(s) to the features model can immediately improve robot performance without necessitating retraining of the corresponding neural network model.

Abstract: A system includes a robotic device, a sensor disposed on the robotic device, and circuitry configured to perform operations. The operations include determining a map that represents stationary features of an environment and receiving, from the sensor, sensor data representing the environment. The operations also include determining, based on the sensor data, a representation of an actor within the environment, where the representation includes keypoints representing corresponding body locations of the actor. The operations also include determining that a portion of a particular stationary feature is positioned within a threshold distance of a particular keypoint and, based on thereon, updating the map to indicate that the portion is to be cleaned. The operations further include, based on the map as updated, causing the robotic device to clean the portion of the particular stationary feature.

Abstract: Grasping of an object, by an end effector of a robot, based on a grasp strategy that is selected using one or more machine learning models. The grasp strategy utilized for a given grasp is one of a plurality of candidate grasp strategies. Each candidate grasp strategy defines a different group of one or more values that influence performance of a grasp attempt in a manner that is unique relative to the other grasp strategies. For example, value(s) of a grasp strategy can define a grasp direction for grasping the object (e.g., “top”, “side”), a grasp type for grasping the object (e.g., “pinch”, “power”), grasp force applied in grasping the object, pre-grasp manipulations to be performed on the object, and/or post-grasp manipulations to be performed on the object.

Abstract: A method of providing decisions to user queries includes: receiving, by at least one processor, a query transmitted from a client device; identifying, from a query database, a first query model; applying, by the at least one processor, the identified first query model to multiple user experience data entries from a user experience database, to obtain at least one correlation resulting from the application of the first query model to the multiple user experience data entries; and identifying, by the at least one processor, an answer to the query from the at least one correlation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for tuning photonic device performance. In one aspect, a method includes receiving an initial photonic device configuration including multiple coupling structures and multiple photonic components. A first amount of light coupling between a first photonic component and a second photonic component of the multiple photonic components is received, which depends upon a subset of the coupling structures that are located between the first photonic component and the second photonic component. One or more coupling structures of the subset of coupling structures located between the first photonic component and the second photonic component are determined to be removed to cause the light coupling between the first photonic component and the second photonic component to change from the first amount of coupling to a target amount of coupling.

Abstract: An application specific integrated circuit (ASIC) chip includes: a systolic array of cells; and multiple controllable bus lines configured to convey data among the systolic array of cells, in which the systolic array of cells is arranged in multiple tiles, each tile of the multiple tiles including 1) a corresponding subarray of cells of the systolic array of cells, 2) a corresponding subset of controllable bus lines of the multiple controllable bus lines, and 3) memory coupled to the subarray of cells.

Abstract: Methods, systems, and apparatus, including computer programs stored on a computer-readable storage medium, for obtaining, from an electric field sensor, measurements of a net electric field resulting from a combination of respective electric fields from two or more electrical power conductors that are proximate to the electric field sensor. The apparatus detects a change in successive measurements of the net electric field. The apparatus determines, based on the change, that an electrical fault has occurred in one of the two or more electric power conductors. The apparatus sends to a server system, data indicating that the electrical fault has occurred in one of the two or more electric power conductors.