Abstract: An example method includes receiving first and second images from a first and second imager. The method further includes determining first correlation scores between a target pixel from the first image and respective pixels from the second image based on a first similarity measure. The method also includes identifying a candidate matching pixel to the target pixel based on the first correlation scores. The method further includes determining second correlation scores between the target pixel and each of the candidate matching pixel, a left neighboring pixel, and a right neighboring pixel based on a second similarity measure. The method also includes determining whether the candidate matching pixel is better correlated to the target pixel than each of the neighboring pixels based on the second correlation scores. After determining that the candidate matching pixel is better correlated, the method further includes determining a disparity value by interpolating the second correlation scores.

Abstract: A non-transitory computer-readable storage medium having instructions stored thereon that, in response to execution by one or more processors of a computing system, cause the computing system to perform actions. The actions include receiving a pool of known fabricable designs for a physical device, generating proposed fabricable designs capable of being fabricated by a fabrication system based on pre-determined design rules, obtaining metadata characterizing the proposed fabricable designs, and updating the pool of the known fabricable designs by adding one or more of the proposed fabricable designs to the pool based, at least in part, on the metadata.

Abstract: An apparatus includes a precursor dispenser for dispensing a precursor material into a workspace, one or more acoustic sources configured to direct acoustic waves towards the workspace to provide acoustic fields that arrange the precursor material in a three-dimensional shape in the workspace, one or more sensors configured to detect a distribution of the precursor material in the workspace, and an electronic controller in communication with the precursor dispenser, the one or more acoustic sources, and the one or more sensors, the electronic controller being programmed to cause the one or more acoustic sources to adjust the acoustic fields to reduce deviations in the distribution of the precursor material from the three-dimensional shape in the workspace.

Abstract: Systems and methods are described include a robot and/or an associated computing system that can use various cues about an environment of the robot to apply a bias to increase the accuracy of speech transcription. In some implementations, audio data corresponding to a spoken instruction to a robot is received. Candidate transcriptions of the audio data are obtained. A respective action of the robot corresponding to each of the candidate transcriptions of the audio data is determined. One or more scores indicating characteristics of a potential outcome of performing the respective action corresponding to the candidate transcription of the audio data are determined for each of the candidate transcriptions of the audio data. A particular candidate transcription is selected from among the candidate transcriptions based at least on the one or more scores. The action determined for the particular candidate transcription is performed.

Abstract: A method includes determining a voxel grid representation of occupied voxels of an environment of a robotic device based on sensor data from a depth sensor on the robotic device. The method further includes assigning a plurality of occupied voxels from the voxel grid representation to a surface within the environment. The method additionally includes determining an image to project onto the surface with a projector on the robotic device. The method further includes modifying the image to fit the surface within the environment based on the plurality of occupied voxels assigned to the surface. The method also includes causing the projector coupled to the robotic device to project the modified image onto the surface in the environment.

Abstract: A robotic gripping device is provided. The robotic gripping device includes a palm and a plurality of digits coupled to the palm. The robotic gripping device also includes a time-of-flight sensor arranged on the palm such that the time-of-flight sensor is configured to generate time-of-flight distance data in a direction between the plurality of digits. The robotic gripping device additionally includes an infrared camera, including an infrared illumination source, where the infrared camera is arranged on the palm such that the infrared camera is configured to generate grayscale image data in the direction between the plurality of digits.

Abstract: In embodiments, obtaining a plurality of image sets associated with a geographical region and a time period, wherein each image set of the plurality of image sets comprises multi-spectral and time series images that depict a respective particular portion of the geographical region during the time period, and predicting presence of a crop at particular locations within the particular portion of the geographical region associated with an image set of the plurality of image sets. Determining crop boundary locations within the particular portion of the geographical region based on the predicted presence of the crop at the particular locations, and generating a crop indicative image comprising at least one image of the multi-spectral and time series images of the image set overlaid with indication of crop areas, wherein the crop areas are defined by the determined crop boundary locations.

Abstract: A method that includes: providing a substrate including a layer of a crystalline material having a first surface; and exposing the first surface to an environment under conditions sufficient to cause epitaxial growth of a layer of a deposition material on the first surface, wherein exposing the first surface to the environment includes illuminating the substrate with light at a first wavelength while causing the epitaxial growth of the layer of the deposition material. The first surface includes one or more discrete growth sites at which an epitaxial growth rate of the quantum confined nanostructure material is larger than areas of the first surface away from the growth sites by an amount sufficient so that the deposition material forms a quantum confined nanostructure at each of the one or more discrete growth sites.

Abstract: A computer-implemented method for revising structural parameters of a physical device is provided. The method comprises configuring a simulated environment to be representative of the physical device based on an initial description that describes structural parameters of the physical device. The method further includes performing an operational simulation of the physical device based on training data representative of physical stimuli within a physical domain to simulate an interaction between the physical device and the physical stimuli. The method further includes computing a loss value based on a simulated output of the physical device and performing and adjoint simulation by backpropagating the loss value through the simulated environment. The method also includes generating a revised description of the physical device by updating the structural parameters to reduce the loss value.

Abstract: A bipartite graph structure is utilized to better store data. The bipartite graph structure may be used in a biochemical database to efficiently store a variety of molecules and processes that might occur between the molecules. Molecules are represented as molecule nodes, which may have metadata fields including a molecule name, a molecule type, a molecular formula, a sequence, a molecular charge, a set of molecular properties, and a set of component molecules. Processes operating on the molecules are represented by process nodes, which may have metadata fields including a process name, a set of process roles, a set of process properties, and a set of sub-processes. Edges, called roles, each associate a molecule node with a process node and represent the role the associated molecule plays in the associated process. The roles may contain metadata identifying the role type and the stoichiometry coefficient of the molecule in the process.

Abstract: Implementations are described herein for automatically generating synthetic training images that are usable, for instance, as training data for training machine learning models to detect and/or classify various types of plant diseases at various stages in digital images. In various implementations, one or more environmental features associated with an agricultural area may be retrieved. One or more synthetic plant models may be generated to visually simulate one or more stages of a progressive plant disease, taking into account the one or more environmental features associated with the agricultural area. The one or more synthetic plant models may be graphically incorporated into a synthetic training image that depicts the agricultural area.

Abstract: Methods, systems, apparatus, and computer-readable media for data band selection using machine learning. In some implementations, image data comprising information for each of multiple wavelength bands is obtained. A multi-layer neural network is trained using the image data to perform one or more classification or regression tasks. A proper subset of the wavelength bands is selected based on parameters of a layer of the trained multi-layer neural network, where the parameters were determined through training of the multi-layer neural network using the image data. Output is provided indicating that the selected wavelength bands are selected for the one or more classification or regression tasks.

Abstract: A method for allocating resources among multiple sub-models in a simulation of a biological cell is described herein. The method receives an initial state dataset including initial aggregate resources in a plurality of sub-models, which make up a whole cell model. The method calculates, at a first time step, an outcome of each of the sub-models, which includes a local production, a local consumption and local net value of at least one resource shared between at least two sub-models. The method calculates a subsequent state dataset based on the outcome of each of the sub-models. The subsequent state dataset includes subsequent aggregate resources, the local production, the local consumption and local net value. The method determines, at a second time step, a second outcome of each of the plurality of sub-models based on the subsequent aggregate resources and the local production, local consumption and local net value.

Abstract: A system is described for constructing a biological simulation using inputs from a knowledge base data structure and one or more templates. The knowledge base data structure comprises a set of entries representing distinct molecules and chemical reactions specific within the cell. Each template defines a sub-model program specification and a set of sub-model parameters to further characterize the sub-model specification. A graphical user interface is presented on a display for a user to view and select a templates and to assign information from the knowledge base to the selected template. From the graphical user interface, the user selects multiple templates to be included in the simulation and information from the knowledge base generally describing the cell. Based on the information selected from the graphical user interface, a compiler generates a simulation configuration data file comprising computer code capable of being executed by a simulation engine.

Abstract: Aspects of the disclosure provide an optical communication system. The system may include a receiver lens system configured to receive a light beam from a remote optical communication system and direct the light beam to a photodetector. The system may also include the photodetector. The photodetector may be configured to convert the received light beam into an electrical signal, and the photodetector may be positioned at a focal plane of the receiver lens system. The system may also include a phase-aberrating element arranged with respect to the receiver lens system and the photodetector such that the phase-aberrating element is configured to provide uniform angular irradiance at the focal plane of the receiver lens system.

Abstract: A technique for simulating and optimizing the fabrication and design of a physical device is described. The technique includes executing a fabrication simulation of the physical device with a fabrication model that receives a fabrication specification as input and outputs a structural design for the physical device in response to the fabrication simulation. An operational simulation of the physical device is executed with a design model that simulates a field response propagating through a simulated environment of the physical device. The structural design output from the fabrication model is forward cascaded to the design model and an output from backpropagation of a performance loss error through the design model is reverse cascaded to the fabrication model.

Abstract: Examples relate to simultaneous localization and calibration. An example implementation may involve receiving sensor data indicative of markers detected by a sensor on a vehicle located at vehicle poses within an environment, and determining a pose graph representing the vehicle poses and the markers. For instance, the pose graph may include edges associated with a cost function representing a distance measurement between matching marker detections at different vehicle poses. The distance measurement may incorporate the different vehicle poses and a sensor pose on the vehicle. The implementation may further involve determining a sensor pose transform representing the sensor pose on the vehicle that optimizes the cost function associated with the edges in the pose graph, and providing the sensor pose transform. In further examples, motion model parameters of the vehicle may be optimized as part of a graph-based system as well or instead of sensor calibration.

Abstract: Techniques are described for determining the strain on a cell wall using two models: 1) a short timescale model, describing the relationship between physical properties assumed to be fixed and 2) a long timescale model, describing the dynamic chemical composition of a cell wall. Short term modeling of the physical properties in a cell wall is used to properly understand how physical factors such as osmotic pressure affects the strain on the cell wall, which is in turn used to identify conditions under which a cell wall will cease to function properly or lyse entirely. Although temporally the physical properties which cause cell walls to underperform/lyse can be evaluated under a short time frame, the chemical properties that lead to the physical properties which cause that behavior themselves change over much longer timescales, in a relative sense.