Abstract: An unmanned aerial vehicle includes a central body, a plurality of arms extendable from the central body, and one or more joints. Each of the plurality of arms is configured to support one or more propulsion units, and is configured to transform between (1) a flight configuration in which the arm is extending away from the central body and (2) a compact configuration in which the arm is folded against the central body. Each joint is configured to couple one arm to the central body. At least one of the one or more joints includes an elastic element configured to cause at least one of the plurality of arms to automatically retract when the at least one of the plurality of arms is reversibly folded to a first predetermined state, and automatically extend when the at least one of the plurality of arms is reversibly extended to a second predetermined state.

Abstract: Systems and methods for programmatic generation of training data, including: a training data generation engine configured to: identify an image asset corresponding to an entity; identify a training video; select a consecutive subset of frames of the training video based on a procedure for ranking frames on their candidacy for overlaying content; for at least one frame of the subset of frames: perform an augmentation technique on the identified logo image to generate an augmented image asset; overlay at least one variation of the image asset, including the augmented image asset, onto each of the subset of frames to generate a set of overlayed frames; and generate an augmented version of the training video including the overlayed frames; and a model training engine configured to: train an artificial intelligence model for entity detection using the augmented version of the training video.

Abstract: Systems and methods for frequency management, including: an online media service configured to: receive a request for a media item, the request including a recipient identifier; identify a set of candidate media items ranked by a set of matching criteria; a frequency management service configured to: perform a query against a lookup service, where the query includes (i) an entity identifier of at least one candidate media item of the set of candidate media items, and (ii) the recipient identifier; receive a response from the lookup service including a quantity of impressions associated with the entity identifier and the recipient identifier; identify a predefined frequency threshold; determine that the frequency threshold is exceeded and exclude the at least one candidate media item from a result set based on the determination; and provide the result set including an identifier of at least one other candidate media item.

Abstract: Systems and methods for entity detection using artificial intelligence, including: a deep learning model service configured to: select and analyze a set of frames from a media item to determine a set of candidate brand-probability pairs; a voting engine configured to: determining that a first brand-probability pair of a set of candidate brand-probability pairs based on at least one obtained hyperparameter value does not meet a threshold for determining whether candidate brand-probability pairs are to be included in a result set; excluding the first brand-probability pair from the result set based on the determination; sorting the result set; and selecting at least one final brand-probability pair from the result set; and an offline transcoding service configured to: store the final brand-probability pair in a repository with a relation to an identifier of the media item.

Abstract: An apparatus includes a controller that controls operation of an amplifier. The amplifier receives a sample voltage produced by a resistive path; the sample voltage from the resistive path is indicative of a magnitude of current through a motor winding. The controller selects a gain setting to apply to the amplifier based on one or more conditions. The selected gain setting is selected amongst multiple possible gain settings. Subsequent to selection, via application of the selected gain setting to the amplifier, and based on an output of the amplifier, the controller monitors a magnitude of the current through the motor winding. According to one configuration, the amplifier adjusts the magnitude of the selected gain setting depending on one or more parameters such as the magnitude of the current through the motor winding, a selected operational range of controlling current through the motor winding, etc.

Abstract: A power conversion device includes: a plurality of legs, each leg including a high-side switch connected between a voltage supply node and a phase node and a low-side switch connected between the phase node and a reference node; a phase current sensor for each leg and configured to sense current flowing through the high-side switch or the low-side switch of the corresponding leg; a single current sensor connected between the reference node and the low-side switches, or between the voltage supply node and the high-side switches; and a controller. During a subperiod of a switching period, the controller is configured to sample the current sensed by at least one of the phase current sensors and a current sensed by the single current sensor such that the current in one or more of the legs is sampled during the same subperiod as the current flowing through the single current sensor.

Abstract: A system may comprise a processor and a memory having computer readable instructions stored thereon. The computer readable instructions, when executed by the processor, cause the system to record position data for an instrument during an image capture period and determine an instrument position change from the recorded position data. The computer readable instructions, when executed by the processor, may also cause the system to compare the instrument position change to a position change threshold and based on the comparison, determine whether to use image data captured by an imaging system during the image capture period in a registration procedure.

Abstract: A system may comprise a processor and a memory having computer readable instructions stored thereon. The computer readable instructions, when executed by the processor, may cause the system to record shape data from a shape sensor for an instrument during an image capture period and generate a sensor point cloud from the recorded shape data. The computer readable instructions, when executed by the processor, may also cause the system to receive image data from an imaging system during the image capture period, generate an image point cloud for the instrument from the image data, and register the sensor point cloud to the image point cloud.

Abstract: A medical device includes an elongate device and one or more processors coupled to the elongate device. The elongate device includes a steerable distal end and a shape sensor located along a length of the elongate device. While the elongate device is being traversed through one or more passageways of a patient, the one or more processors are configured to, based on information from a sensor, monitor an insertion motion of the elongate device, detect a data collection event, and capture, in response to detecting the data collection event, a plurality of points along the length of the elongate device using the shape sensor. The data collection event is at least partially based on a change in direction of the insertion motion of the elongate device.

Abstract: A method of registering sets of anatomical data for use during a medical procedure is provided herein. The method may include accessing a first set of model points of a patient anatomy of interest and intra-operatively acquiring a second set of model points by visualizing a portion of the anatomical surface in the patient with a vision probe. The method may further include extracting system information, including kinematic information from a robotic arm of a medical system and/or setup information, and generating an initial seed transformation based on the extracted system information. Thereafter, the method may include applying the initial seed transformation to the first set of model points and generating a first registration between the first set of model points and the second set of model points to permit model and actual information to be viewed and used together by an operator.

Abstract: A system comprises a medical instrument including a sensing tool and comprises a processing unit including one or more processors. The processing unit is configured to receive data related to a patient anatomy from the sensing tool while the medical instrument traverses the patient anatomy. The processing unit is further configured to construct an anatomic model of the patient anatomy from the data received from the sensing tool. The processing unit is further configured to generate an image of the anatomic model for display and register a position of the medical instrument to the anatomic model.

Abstract: A system comprises one or more processors. The system further comprises memory having computer readable instructions stored thereon that, when executed by the one or more processors, cause the system to: obtain a reference tree of nodes and linkages for a reference three dimensional volumetric representation of a branched anatomical formation in a reference state; based on the reference tree, generate a reference three dimensional geometric model; based on measurements from a sensor system, detect deformation of the branched anatomical formation; based on the detected deformation, obtain a deformed tree of nodes and linkages; and generate a three dimensional deformation field that represents the detected deformation of the branched anatomical formation.

Abstract: A computer-assisted medical system comprises a fluoroscopic imager having a full scan range in a surgical coordinate space. The system further comprises one or more processors configured to perform a method. The method includes receiving a first fluoroscopic image data set of a patient anatomy. The first fluoroscopic image data set is obtained from the full scan range of the fluoroscopic imager. The method further includes receiving at least one additional fluoroscopic image data set of the patient anatomy from the fluoroscopic imager operating in a constrained range substantially smaller than the full scan range. The method further includes constructing a first planar tomographic image from the first and at least one additional fluoroscopic image data sets.

Abstract: A method of planning a procedure to deploy an interventional instrument comprises receiving a model of an anatomic structure. The anatomic structure includes a plurality of passageways. The method further includes identifying a target structure in the model and receiving information about an operational capability of the interventional instrument within the plurality of passageways. The method further comprises identifying a planned deployment location for positioning a distal tip of the interventional instrument to perform the procedure on the target structure based upon the operational capability of the interventional instrument.

Abstract: A method of registering sets of anatomical data for use during a surgical procedure is provided herein. The method may include segmenting a set of first modality image data representing a model of one or more passageways within a patient and generating a first set of points based on the segmented set of first modality image data representing the model of the one or more passageway's. The method may further include determining a set of matches between a second set of points and the first set of points, wherein the second set of points is obtained by a second modality and discarding a subset of the set of matches based on a first heuristic to generate a modified set of matches. The second set of points may then be moved relative to the first set of points based on the modified set of matches and displayed on a display.

Abstract: A trans-inductor voltage regulator (TLVR) circuit has multiple phases and a regulator block for each phase. Each regulator block is connected to an output capacitor of the TLVR circuit by way of a first winding of a corresponding nonlinear transformer. A second winding of the nonlinear transformers are connected in series with a compensation inductor. The first winding of the corresponding nonlinear transformer has a first inductance when a load current is at a first level, and the first winding of the corresponding nonlinear transformer has a second inductance that is less than the first inductance when the load current is at a second level that is higher than the first level.

Abstract: A tool tracking method comprises receiving stereo image data of a tool. The tool includes a tracking marker. The method also comprises receiving first kinematic data for the tool and determining a three-dimensional image-derived pose of the tool from the stereo image data of the tool and the tracking marker. The method also comprises determining a first kinematic pose of the tool from the first kinematic data and determining a pose offset between the image-derived pose of the tool and the first kinematic pose of the tool. The method also comprises determining a corrected first kinematic pose of the tool based on the pose offset and the first kinematic data.

Abstract: An earpiece includes a housing, a sound transmission component, a sound reception component, a force application structure and a trigger. A cavity is formed in the housing. The sound transmission component is provided in the cavity. The sound reception component is provided on the housing, and can move along a predetermined path. At least a retracted position and a stretched position are arranged on the predetermined path. The force application structure is connected to the sound reception component, and configured to drive the sound reception component to move to the retracted position or the stretched position. The earpiece in the present disclosure stretches out or retracts the sound reception component automatically. The earpiece in the present disclosure does not need the user to stretch out or retract the sound reception component manually, with good user experience.

Abstract: A system may comprise an image capture device to capture an image of a work site. The system may also comprise a processor to determine whether a tool disposed at the work site is energized and determine a first area of the captured image of the work site, including or adjacent to an image of a portion of the tool in the captured image. The processor may also determine a second area of the captured image including a remainder of the captured image that does not include the first area. Conditioned upon determining that the tool is energized, at least one of the first area and the second area of the captured image of the work site may be processed to indicate that the tool in the first area is being energized. The image of the work site with the first area and the second area may be displayed.

Abstract: A system comprises a medical instrument, including a sensing tool, and a processing unit configured to apply a segmentation function using a first seed to a three-dimensional image of a patient anatomy to create a model; receive position data from the instrument while navigating the patient anatomy; register a position of the instrument with the model; receive data related to the patient anatomy from the sensing tool; and update the model in response to detecting a difference between the model and the patient anatomy. Updating the model includes reapplying the segmentation function using a second seed corresponding to a passageway of the patient anatomy that is not present within the model. Detecting the difference between the model and the patient anatomy includes analyzing temporal information obtained from shape data generated by the sensing tool while the instrument traverses portions of the patient anatomy not represented by the model.