Abstract: Systems and methods for designing, testing, and validating a robotic system for space are provided. A system includes: a robotic manipulator; a dynamic system emulator configured to simulate a motion behaviour response of a first space robotic system based on forces and moments measured by the first robotic manipulator during physical interaction of the first robotic manipulator with a second robotic manipulator emulating motion behaviour of a second space robotic system; an arm controller configured to generate a manipulator tip reference trajectory command based on the motion behaviour response simulated by the dynamic system emulator and provide the manipulator tip reference trajectory command to the robotic manipulator; and an arm mechanism in the robotic manipulator configured to track a trajectory based on the manipulator tip reference trajectory command, such that the robotic manipulator emulates motion behaviour of the first space robotic system.

Abstract: Audio systems comprise an electronic controller configured to receive an input audio signal via a microphone, receive prerecorded audio from a computing device, combine the input audio signal with the prerecorded audio to create an output audio signal, and transmit the output audio signal to an online game environment. Associated software is configured to receive a user input and transmit the prerecorded audio to the electronic controller responsive to receipt of the user input.

Abstract: Embodiments are disclosed for a generating graph representations of neural networks to be used as input for one or more metanetworks. Architectural information can be extracted from a neural network and used to generate graph a representation. A subgraph can be generated for each layer of the neural network, where each subgraph includes nodes that correspond to neurons and connecting edges that correspond to weights. Each layer of the neural network can be associated with a bias node that is connected to individual nodes of that layer using edges representing bias weights. Various types of neural networks and layers of neural networks can be represented by such graphs, which are then used as inputs for metanetworks. The subgraphs can be combined into a comprehensive graph representation of the neural network, which can be provided as input to a metanetwork to generate network parameters or perform another such operation.

Abstract: Audio devices comprise a housing, a first audio connection supported by the housing, a second audio connection supported by the housing, and a controller supported by the housing that is configured to receive an input audio signal via the first audio connection, combine the input audio signal with a sound bite to create an output audio signal, and transmit the output audio signal via the second audio connection. Audio systems comprise an audio device and software that directs a computing device to receive a user input and transmit a sound bite to the audio device responsive to receipt of the user input.

Abstract: Apparatuses, system, and techniques use one or more neural networks to generate a modified bounding box based, at least in part, on one or more second bounding boxes.

Abstract: Provided are a method, system, and non-transitory computer-readable medium for real-time autonomous path planning for a robotic device. The method includes receiving data about the robotic device in a three-dimensional workspace, encapsulating objects in the environment of the robotic device including the robotic device, a target, and one or more obstacles in simulated robotic space, calculating a direction of movement for the robotic device according to three virtual forces including a virtual attractive force, a virtual repulsive force, and a virtual tangential force acting at least partially perpendicularly relative to the virtual repulsive force, mapping each virtual force in the three-dimensional workspace into torque vectors in the simulated robotic space at each joint, converting a sum of the torque vectors into one or more commands for the robotic device defining a path to reach the target, and sending the one or more commands to the robotic device.

Abstract: Approaches presented herein provide systems and methods for generating three-dimensional (3D) objects using compressed data as an input. One or more models may learn from a hash table of latent features to map different features to a reconstruction domain, using a hash function as part of a learned process. A 3D shape for an object may be encoded to a multi-layered grid and represented by a series of embeddings, where given point within the grid may be interpolated based on the embeddings for a given layer of the multi-layered grid. A decoder may then be trained to use the embeddings to generate an output object.

Abstract: A workstation having modular components is described. Modular components include a support column, a head unit assembly including a worksurface, and one or more display mounts among other things. Modular components are coupled to a structure including a wall, a pole, a cabinet, a rack, a wheeled base, or the like. Modular components include features to interface with each other and with the structure. The workstation is easily configurable by the user of the workstation to include the desired modules coupled to a desired structure to perform intended workstation functions.

Abstract: Apparatuses, systems, and techniques to indicate data dependencies. In at least one embodiment, one or more neural networks are used to generate one or more indicators of one or more data dependencies and one or more indicators of direction of the one or more data dependencies.

Abstract: A motion-assisted positioning arm for a medical procedure. The positioning arm includes a base, an arm coupled to the base, and an end effector coupled to the arm. The arm includes a plurality of arm segments. The arm includes a plurality of joints for connecting the arm segments. The end effector may be manipulable with six degrees of freedom in a task-coordinate space based on motion by at least one joint in the plurality of joints. The positioning arm includes a processor to: detect manipulation of and determine forces or torques acting on the end effector; determine a surgical mode for constraining movement of the end effector in the task-coordinate space; determine an end effector velocity based on the determined forces or torques and the surgical mode for moving end effector; and apply at least one joint space movement based on the end effector velocity.

Abstract: Systems and methods for designing, testing, and validating a robotic system for space are provided. A system includes: a robotic manipulator; a dynamic system emulator configured to simulate a motion behaviour response of a first space robotic system based on forces and moments measured by the first robotic manipulator during physical interaction of the first robotic manipulator with a second robotic manipulator emulating motion behaviour of a second space robotic system; an arm controller configured to generate a manipulator tip reference trajectory command based on the motion behaviour response simulated by the dynamic system emulator and provide the manipulator tip reference trajectory command to the robotic manipulator; and an arm mechanism in the robotic manipulator configured to track a trajectory based on the manipulator tip reference trajectory command, such that the robotic manipulator emulates motion behaviour of the first space robotic system.

Abstract: Approaches for training data set size estimation for machine learning model systems and applications are described. Examples include a machine learning model training system that estimates target data requirements for training a machine learning model, given an approximate relationship between training data set size and model performance using one or more validation score estimation functions. To derive a validation score estimation function, a regression data set is generated from training data, and subsets of the regression data set are used to train the machine learning model. A validation score is computed for the subsets and used to compute regression function parameters to curve fit the selected regression function to the training data set. The validation score estimation function is then solved for and provides an output of an estimate of the number additional training samples needed for the validation score estimation function to meet or exceed a target validation score.

Abstract: In various examples, estimating optimal training data set sizes for machine learning model systems and applications. Systems and methods are disclosed that estimate an amount of data to include in a training data set, where the training data set is then used to train one or more machine learning models to reach a target validation performance. To estimate the amount of training data, subsets of an initial training data set may be used to train the machine learning model(s) in order to determine estimates for the minimum amount of training data needed to train the machine learning model(s) to reach the target validation performance. The estimates may then be used to generate one or more functions, such as a cumulative density function and/or a probability density function, wherein the function(s) is then used to estimate the amount of training data needed to train the machine learning model(s).

Abstract: The present disclosure provides compositions comprising an opsin polypeptide and an arrestin polypeptide and their use thereof. Exemplary embodiments provide a composition including an opsin polypeptide, or an opsin polypeptide and an arrestin polypeptide, wherein at least one of the opsin or arrestin polypeptide comprises at least one mutation that increases a temporal resolution of the opsin polypeptide’s response to light. The opsin polypeptide and the arrestin polypeptide can be operably linked or separate. Additionally, use of said compositions for restoring retinal photosensitivity or treating a retinal degenerative condition is also provided.

Abstract: Audio devices comprise a housing, a first audio connection supported by the housing, a second audio connection supported by the housing, and a controller supported by the housing that is configured to receive an input audio signal via the first audio connection, combine the input audio signal with a sound bite to create an output audio signal, and transmit the output audio signal via the second audio connection. Audio systems comprise an audio device and software that directs a computing device to receive a user input and transmit a sound bite to the audio device responsive to receipt of the user input.

Abstract: A smoke detection assembly for indicating when organic material has been smoked in an area includes a decal that has an adhesive layer is integrated such that the decal can be adhered to a surface in a cab of a vehicle. A chemical reagent is provided and the chemical reagent is infused into the decal. The chemical reagent is chemically reactive with one or more chemicals that are unique to smoke from combustion of organic material. Moreover, the chemical reagent changes colors when the chemical reagent is exposed to airborne nicotine. In this way the chemical reagent can visually indicate when organic material has been smoked in the vehicle.

Abstract: A charging and storage cart can be configured to support and charge a plurality of electronic devices. The charging and storage cart can include a frame, a panel, a tray, a support bracket, and an extension. The panel can be secured to the frame and can include a body and plurality of apertures extending through the body. The support bracket can be coupled to the tray and can be configured to engage the panel to support the tray. The extension can be connected to the support bracket can be insertable into any aperture of the plurality of apertures to connect the tray to the body of the panel in any location as desired.

Abstract: A height adjustable device including a counterbalance mechanism configured to be affixed adjacent to a rear portion of a vertical support member, a worksurface configured to be affixed adjacent to a front portion of the vertical support member, and a mounting member configured to slidably couple the worksurface to the counterbalance mechanism; wherein a portion of the mounting member extends through an opening defined in the vertical support member.

Abstract: The present invention relates to methods of regulating G protein activity, and related methods for the treatment of therapeutic conditions, for example retinal degeneration, by transforming a cell with a bistable opsin to activate a G protein, and provide a phototransduction response.

Abstract: The present invention relates to an improved method of providing photoreceptor function to a cell, for example for use in the treatment of retinal degeneration. The present invention also relates to compositions and kits, in particular for use in such methods.