Abstract: A single volume soft sensor capable of sensing real-time continuous contact and stretching. An electrical impedance tomography (EIT) technique with support vector machine (SVM) learning is employed to estimate changes of resistance distribution on the sensor caused by fingertip contact even during sensor deformation events. A deformation switch is incorporated to maintain the localization during deformation events.

Abstract: A method and system for localizing a plurality of stationary devices, such as Internet of Things (IoT devices), arranged in an environment is disclosed. A mobile device is configured to survey an environment to generate a three-dimensional map of the environment using simultaneous localization and mapping (SLAM) techniques. The mobile device and the stationary devices are equipped with wireless transceivers, such as Ultra-wideband radios, for measuring distances between the devices using wireless ranging techniques. Based on the measured distances, the mobile device is configured to determine locations of the stationary devices in a reference frame of the three-dimensional map. In some embodiments, the determined locations can be used to enable a variety of spatially aware augmented reality features and interactions between the mobile device and the stationary device.

Abstract: Techniques are disclosed relating to compression of pixel data using different quantization for different regions of a block of pixels being compressed. In some embodiments, compression circuitry is configured to determine, for multiple components included in pixels of the block of pixels being compressed, respective smallest and greatest component values in respective regions of the block of pixels. The compression circuitry may determine, based on the determined smallest and greatest component values, to use a first number of bits to represent delta values relative to a base value for a first component in a first region and a second, different number of bits to represent delta values relative to a base value for a second component in the first region. The compression circuitry may then quantize delta values for the first and second components of pixels in the first region of the block of pixels using the determined first and second numbers of bits.

Abstract: Techniques are disclosed relating to data compression. In some embodiments, compression circuitry determines, at least partially in parallel for multiple different lossless compression techniques, a number of bits needed to represent a least compressible pixel, using that technique, in a set of pixels being compressed. The compression techniques may include neighbor, origin, and gradient techniques, for example. The compression circuitry may select one of the compression techniques based on the determined numbers of bits for the multiple compression techniques and corresponding header sizes. In some embodiments, the compression circuitry determines, for multiple regions of pixels in the set of pixels, for ones of the compression techniques, a region number of bits needed to represent a least compressible pixel, using that technique. The selection of a compression technique may be further based on region numbers of bits.

Abstract: A unique storytelling system is disclosed herein in which a plug-and-play hardware platform with an integrated augmented reality (AR) environment brings stories to life. The storytelling system includes an electronics toolkit and a structure toolkit which enable the user to prototype interactive physical devices for storytelling. The interactive physical devices crafted by the user are easily programmed using a simple visual programing environment of the storytelling system. Additionally, a story event planning tool of the storytelling system enables the user to create customized interactions between the interactive physical devices and virtual AR objects, such as virtual AR avatars or the like. Finally, an AR storytelling application of the storytelling system utilizes an AR device, such as a smartphone, to bring the interactive physical devices to life and enable the user to tell stories using the custom interactions that he or she created.

Abstract: A method using a two-dimensional (2D) image representation of three-dimensional (3D) geometric objects in a machine learning framework has been developed. The method includes generating a single 2D geometry image corresponding to a 3D object model, and providing the single geometry image as input to a shape analysis task to enable shape analysis of the 3D object model based only on information encoded in the single 2D geometry image in the machine learning framework.

Abstract: A stable pharmaceutically formulation containing antibody, a buffer, a non-ionic surfactant, and a lyoprotectant/cryoprotectants. Also disclosed are associated methods for preparing, storing, and using such formulations.

Abstract: A system and method for authoring and performing Human-Robot-Collaborative (HRC) tasks is disclosed. The system and method adopt an embodied authoring approach in Augmented Reality (AR), for spatially editing the actions and programming the robots through demonstrative role-playing. The system and method utilize an intuitive workflow that externalizes user's authoring as demonstrative and editable AR ghost, allowing for spatially situated visual referencing, realistic animated simulation, and collaborative action guidance. The system and method utilize a dynamic time warping (DTW) based collaboration model which takes the real-time captured motion as inputs, maps it to the previously authored human actions, and outputs the corresponding robot actions to achieve adaptive collaboration.

Abstract: A method and system for enabling a self-localizing mobile device to localize other self-localizing mobile devices having different reference frames is disclosed. Multiple self-localizing mobile devices are configured to survey an environment to generate a three-dimensional map of the environment using simultaneous localization and mapping (SLAM) techniques. The mobile devices are equipped with wireless transceivers, such as Ultra-wideband radios, for measuring distances between the mobile devices using wireless ranging techniques. Based on the measured distances and self-localized positions in the environment corresponding to each measured distance, at least one of the mobile devices is configured to determine relative rotational and translational transformations between the different reference frames of the mobile devices.

Abstract: A method for generating a multi-modal video dataset with pixel-wise hand segmentation is disclosed. To address the challenges of conventional dataset creation, the method advantageously utilizes multi-modal image data that includes thermal images of the hands, which enables efficient pixel-wise hand segmentation of the image data. By using the thermal images, the method is not affected by fingertip and joint occlusions and does not require hand pose ground truth. Accordingly, the method can produce more accurate pixel-wise hand segmentation in an automated manner, with less human effort. The method can thus be utilized to generate a large multi-modal hand activity video dataset having hand segmentation labels, which is useful for training machine learning models, such as deep neural networks.

Abstract: A method of operating an augmented reality (AR) system includes capturing images of a first real-world workspace using a camera of a first head mounted AR device of the AR system being worn by a first user, processing the images using a first processor of the AR system to identify physical objects in the first real-world workspace and detect 3D positions of the identified physical objects in a 3D space corresponding to the first real-world workspace, rendering virtual objects representing the identified physical objects on the display of the first head mounted AR device at the respective 3D positions for the identified physical objects, manipulating a first one of the virtual objects using at least one hand-held controller of the AR system in a manner that mimics a performance of a first procedural task using the physical object associated with the first one of the virtual objects, recording the manipulation of the first one of the virtual objects that mimics the performance of the first procedural task as fi

Abstract: Disclosed is a visual and spatial programming system for robot navigation and robot-IoT task authoring. Programmable mobile robots serve as binding agents to link stationary IoT devices and perform collaborative tasks. Three key elements of robot task planning (human-robot-IoT) are coherently connected with one single smartphone device. Users can perform visual task authoring in an analogous manner to the real tasks that they would like the robot to perform with using an augmented reality interface. The mobile device mediates interactions between the user, robot(s), and IoT device-oriented tasks, guiding the path planning execution with Simultaneous Localization and Mapping (SLAM) to enable robust room-scale navigation and interactive task authoring.

Abstract: A collaborative 3D modeling system, comprising a computer processing unit, a digital memory, and an electronic display, the computer processing unit and the digital memory configured to provide 3D model representations of a first plurality of versions of an object component for a first user, the versions being selectable along a first axis, and using the electronic display, provide a plurality of user identifications which are selectable along a second axis, wherein selecting a subsequent user causes a second plurality of said versions of said object component to be displayed on the electronic display.

Abstract: Systems, apparatuses, and methods for efficiently allocating data in a cache are described. In various embodiments, a processor decodes an indication in a software application identifying a temporal data set. The data set is flagged with a data set identifier (DSID) indicating temporal data to drop after consumption. When the data set is allocated in a cache, the data set is stored with a non-replaceable attribute to prevent a cache replacement policy from evicting the data set before it is dropped. A drop command with an indication of the DSID of the data set is later issued after the data set is read (consumed). A copy of the data set is not written back to the lower-level memory although the data set is removed from the cache. An interrupt is generated to notify firmware or other software of the completion of the drop command.

Abstract: A virtual reality system, comprising an electronic 2d interface having a depth sensor, the depth sensor allowing a user to provide input to the system to instruct the system to create a virtual 3D object in a real-world environment. The virtual 3D object is created with reference to at least one external physical object in the real-world environment, with the external physical object concurrently displayed with the virtual 3D object by the interface. The virtual 3D object is based on physical artifacts of the external physical object.

Abstract: Disclosed is a visual and spatial programming system for robot navigation and robot-IoT task authoring. Programmable mobile robots serve as binding agents to link stationary IoT devices and perform collaborative tasks. Three key elements of robot task planning (human-robot-IoT) are coherently connected with one single smartphone device. Users can perform visual task authoring in an analogous manner to the real tasks that they would like the robot to perform with using an augmented reality interface. The mobile device mediates interactions between the user, robot(s), and IoT device-oriented tasks, guiding the path planning execution with Simultaneous Localization and Mapping (SLAM) to enable robust room-scale navigation and interactive task authoring.

Abstract: A method for hand pose identification in an automated system includes providing depth map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.

Abstract: System and method for multi-level visualization of object lifecycle is provided. A visualization network displaying data associated with the object life cycle is provided. An object is selected from the visualization network to correlate the object across and within one or more object lifecycle stages from the visualization network by generating a relationship configuration. A multi-level visualization is generated for the selected object corresponding one or more object life cycle stage. The generated at least one multi-level visualization is modified based on a criterion of interest, the criterion of interest comprises one or more attribute associated with the selected object and relation derived from the relationship configuration.

Abstract: Techniques are disclosed relating to filtering cache accesses. In some embodiments, a control unit is configured to, in response to a request to process a set of data, determine a size of a portion of the set of data to be handled using a cache. In some embodiments, the control unit is configured to determine filtering parameters indicative of a set of addresses corresponding to the determined size. In some embodiments, the control unit is configured to process one or more access requests for the set of data based on the determined filter parameters, including: using the cache to process one or more access requests having addresses in the set of addresses and bypassing the cache to access a backing memory directly, for access requests having addresses that are not in the set of addresses. The disclosed techniques may reduce average memory bandwidth or peak memory bandwidth.

Abstract: A method for hand pose identification in an automated system includes providing depth map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.