Abstract: A flexible exosuit includes rigid and flexible elements configured to couple forces to a body of a wearer. Further, the flexible exosuit includes flexible linear actuators and clutched compliance elements to apply and/or modulate forces and/or compliances between segments of the body of the wearer. The flexible exosuit further includes electronic controllers, power sources and sensors. The flexible exosuit can be configured to apply forces to the body of the wearer to enable a variety of applications. In some examples, the flexible exosuit can be configured to augment the physical strength or endurance of the wearer. In some examples, the flexible exosuit can be configured to train the wearer to perform certain physical tasks. In some examples, the flexible exosuit can be configured to record physical activities of the wearer.

Abstract: In general, the disclosure describes various aspects of techniques for attention-based explanations for artificial intelligence behavior. A device comprising a memory and a computation engine executing a processor may be configured to perform the techniques. The memory may store the artificial intelligence model and the image. The computation engine may receive a query regarding the image, and execute the artificial intelligence model to analyze the image in order to output the result to the query. The artificial intelligence model may, when analyzing the image to output the result, segment the image into hierarchically arranged semantic areas in which objects in the image are segmented into parts, determine, based on the query, an attention mask for the areas, update, based on the attention mask, the image to visually identify which of the areas formed a basis for the result, and output the updated image.

Abstract: An example system includes a vehicle, a robot, and a controller. The vehicle may include an accelerator operator and a steering operator. The robot may include as accelerator actuator configured to operate the accelerator operator, and a steering actuator configured to operate-the steering operator. The controller is configured to: in response to an accelerator command, send a first signal to the accelerator actuator to operate the accelerator operator of the vehicle, and in response to a steering command, send a second, signal to the steering actuator to steer the vehicle.

Abstract: Methods and systems of using machine learning to create a trusted model that improves the operation of a computer system controller are provided herein. In some embodiments, a machine learning method includes training a model using input data, extracting the model, and determining whether the model satisfies the trust-related constraints. If the model does not satisfy the trust-related constraint, modifying at least one of: the model using one or more model repair algorithms, the input data using one or more data repair algorithms, or a reward function of the model using one or more reward repair algorithms, and re-training the model using at least one of the modified model, the modified input data, or the modified reward function. If the model satisfies the trust-related constraints, providing the model as a trusted model that enables a computer system controller to perform system actions within predetermined guarantees.

Abstract: The present inventors have developed antigen-binding reagents and antigen-binding conjugates that recognize a cancer-specific glycan (carbohydrate) modification on the human Periostin protein. Various in vitro and in vivo diagnostic and/or therapeutic methods using these compositions are also disclosed herein specifically for treating cancers that have amplification of the Mgat3 gene.

Abstract: Methods, computing devices, and computer-program products are provided for implementing a virtual personal assistant. In various implementations, a virtual personal assistant can be configured to receive sensory input, including at least two different types of information. The virtual personal assistant can further be configured to determine semantic information from the sensory input, and to identify a context-specific framework. The virtual personal assistant can further be configured to determine a current intent. Determining the current intent can include using the semantic information and the context-specific framework. The virtual personal assistant can further be configured to determine a current input state. Determining the current input state can include using the semantic information and one or more behavioral models. The behavioral models can include one or more interpretations of previously-provided semantic information.

Abstract: Embodiments in accordance with the present disclosure are directed to polymer beads and uses thereof, including forming libraries of compounds for screening and assay purposes. A polymer bead, in accordance with embodiments, has an interior surface and an exterior surface that are topologically segregated from one another. The interior surface includes a protecting group and the exterior surface includes a deprotected group, which can also be referred to as a deprotected functional group. The protecting group can includes a nitrobenzenesulfonamide group that protects an amine group.

Abstract: An apparatus includes a first ring having an open annular space and a variable-width groove disposed on an interior peripheral surface of the first ring; a second ring rotatable within the open annular space of the first ring, where the second ring has a respective variable-width groove disposed on an exterior peripheral surface of the second ring; and a plurality of rollers disposed between, and configured to roll on, the interior peripheral surface of the first ring and the exterior peripheral surface of the second ring and rotatable therebetween.

Abstract: This disclosure is related to devices, systems, and techniques for automatically generating software packages to provide Secure Computation as a Service (SCaaS). For example, a computing device includes processing circuitry configured to receive a set of information comprising an indication of a first party and an indication of a second party. Additionally, the processing circuitry is configured to generate, based on the set of information, a first software package corresponding to the first party, the first software package configured to implement a secure computation, and generate, based on the set of information, a second software package corresponding to the second party, the second software package configured to implement the secure computation. Additionally, the processing circuitry is configured to export the first software package and export the second software package, enabling the first party device and the second party device to perform the secure computation.

Abstract: A microrobot assembly system includes a substrate containing conductive traces formed into at least one holding zone and one moving zone, a diamagnetic layer on the substrate, at least two magnetic structures movable across the diamagnetic layer in response to voltages applied to the conductive traces, wherein the holding zone holds one of the magnetic structures and the moving zone allows another of the magnetic structures to attach to the magnetic structure being held. The system may include a plate spaced above the substrate and rails to guide the moving magnetic structures.

Abstract: Systems and methods for embodiments of a hyperdexterous robotic system using groundless user input devices (UIDs). In some embodiments, the hyperdexterous system allows for the slave control to follow the master control even when the two are misaligned. The motion of the master control occurring in multiple degrees of freedom may be decoupled into its component parts and processed differently. Each degree of freedom may be processed independently and scaled differently. For example, in some embodiments, only the roll motion of the groundless user interface device is transferred, in some embodiments, the master slave control is only allowed when the master and slave are within a certain region of each other.

Abstract: An example imaging apparatus comprises a light source, an imaging spectrometer, an image sensor, control circuitry, and processing circuitry. The light source generates power for delivery at a molecular sample, which can include at least 100 mW. The imaging spectrometer separates light emitted from the molecular sample into a plurality of different component wavelengths. The control circuitry causes the image sensor to scan one or more regions of the molecular sample while the imaging spectrometer is aligned with the image sensor and collects hyperspectral image data of the molecular sample from the light emitted that corresponds to the plurality of different component wavelengths. The processing circuitry performs an image processing pipeline by transforming the hyperspectral image data into data that is representative of a quantification of emitters, absorbers, and/or scatterers present in the one or more regions of the molecular sample.

Abstract: In general, techniques are described for processing a set of high-resolution images of an integrated circuit, the images captured at different locations with respect to the integrated circuit, to automatically align and “stitch” the set of high-resolution images into a larger composite image. For example, an imaging system as described herein may use sampled feature points distributed across different grid tiles within overlap regions for pairs of images to match feature points to inform the alignments of a pair with respect to each image in the pair. The system may in some cases further apply a bundle adjustment to iteratively align and refine the alignment results for each image in a set of images being processed. In some examples, the bundle adjustment is a best-fit adjustment based on minimizing the net error associated with the alignment of the set of images.

Abstract: A robotic arm according to various implementations includes: a tool driver configured to hold a surgical tool; a first section comprising a first end coupled to a base, a second end distal from first end; a first link that includes a motor configured to rotate at least a portion of the first section around a pitch axis; a second link coupled to the first link, the second link including a motor configured to rotate at least a portion of the first section around a roll axis; and a second section comprising: a first end coupled to the second end of the first section, a second end distal from the first end, a first link that includes a motor configured to rotate at least a portion of the second section around a roll axis, a second link coupled to the first link.

Abstract: A computing system for virtual personal assistance includes technologies to, among other things, correlate an external representation of an object with a real world view of the object, display virtual elements on the external representation of the object and/or display virtual elements on the real world view of the object, to provide virtual personal assistance in a multi-step activity or another activity that involves the observation or handling of an object and a reference document.

Abstract: Systems and methods for improving the accuracy of a computer system for object identification/classification through the use of weakly supervised learning are provided herein. In some embodiments, the method includes (a) receiving at least one set of curated data, wherein the curated data includes labeled images, (b) using the curated data to train a deep network model for identifying objects within images, wherein the trained deep network model has a first accuracy level for identifying objects, receiving a first target accuracy level for object identification of the deep network model, determining, automatically via the computer system, an amount of weakly labeled data needed to train the deep network model to achieve the first target accuracy level, and augmenting the deep network model using weakly supervised learning and the weakly labeled data to achieve the first target accuracy level for object identification by the deep network model.

Abstract: This disclosure describes techniques that include generating, based on a description of a scene, a movie or animation that represents at least one possible version of a story corresponding to the description of the scene. This disclosure also describes techniques for training a machine learning model to generate predefined data structures from textual information, visual information, and/or other information about a story, an event, a scene, or a sequence of events or scenes within a story. This disclosure also describes techniques for using GANs to generate, from input, an animation of motion (e.g., an animation or a video clip). This disclosure also describes techniques for implementing an explainable artificial intelligence system that may provide end users with information (e.g., through a user interface) that enables an understanding of at least some of the decisions made by the AI system.

Abstract: Systems, Methods, and Apparatuses for an image sensor and a control system to cooperate with each photodiode in individual pixels to allow multiple pixels in a set of pixels to operate in a different imaging-mode of operation simultaneously within multiple window regions of the image. The image sensor has multiple window regions each capable of operating in different operating modes. Each pixel contains multiple photodiodes. The imager is fabricated with an additional semiconductor layer containing one or more metallization layers for interconnections and providing active CMOS circuits for control.

Abstract: An identification system includes a radar sensor configured to generate a time-domain or frequency-domain signal representative of electromagnetic waves reflected from one or more objects within a three-dimensional space over a period of time and a computation engine executing on one or more processors. The computation engine is configured to process the time-domain or frequency-domain signal to generate range and velocity data indicating motion by a living subject within the three-dimensional space. The computation engine is further configured to identify, based at least on the range and velocity data indicating the motion by the living subject, the living subject and output an indication of an identity of the living subject.

Abstract: The disclosure describes vehicle mountable robotic and communication systems and techniques that can facilitate communications between a police officer and a driver within vehicles in a manner that removes the police officer from a proximity of the driver and enables real-time communication between the police officer and the driver. A vehicle mountable robotic and communication system can deliver a communication device from a police vehicle to a driver vehicle so that the police officer and the driver may remain separated during part or all of a traffic stop or other temporary detention. This communication device can provide a sensory or communicative interface to permit the police officer to collect additional information of the environment of the driver and/or permit the police officer and the driver to engage in two-way communication.