Abstract: Systems and methods determines that a trailer being towed by an autonomous electric tractor has its brakes applied when a motor current value of a drive motor of the autonomous electric tractor reaches or exceeds a first current threshold. a recover handler initiates a set of actions to recover resolve the trailer brake problem. A trailer lift status indicating whether a landing gear of the trailer is off the ground and a lift metric indicative of a height of the landing gear off the ground are determined by a perception module using one or more of images, point clouds, and radar data that include the trailer.

Abstract: A system including: one or more processors; a memory storing instructions that, when executed by the one or more processors are configured to cause the system to: receive a plurality of user names and a plurality of anonymized user identifiers; receive a plurality of user attributes associated with one or more users of the plurality of users; receive a first plurality of hash values that uniquely identify an association between each user attribute and one or more users; receive a first request for a listing of user names associated with a first user attribute; receive a first secret key; generate a second plurality of hash values; determine a first subset of the first plurality of hash values that match the second plurality of hash values; generate a first graphical user interface including the listing of user names; and transmit the first graphical user interface to the first user device.

Abstract: A system including: one or more processors; a memory storing instructions that, when executed by the one or more processors are configured to cause the system to: receive a plurality of user names and a plurality of anonymized user identifiers; receive a plurality of user attributes associated with one or more users of the plurality of users; receive a first plurality of hash values that uniquely identify an association between each user attribute and one or more users; receive a first request for a listing of user names associated with a first user attribute; receive a first secret key; generate a second plurality of hash values; determine a first subset of the first plurality of hash values that match the second plurality of hash values; generate a first graphical user interface including the listing of user names; and transmit the first graphical user interface to the first user device.

Abstract: In various examples, as a user is speaking or presenting content during an online video conference, the data stream may be processed to generate a textual representation (e.g., transcript) of the audio and/or information relating to the video. The textual representation and/or video related information may then be processed to determine a context or one or more topic(s) of discussion. Based on the determined context/topic(s), a corresponding neural network(s) may be selected. Once a neural network has been selected, comments may be retrieved from a chat feature of the application and applied to the neural network. The neural network may then output data to indicate the relevance of the comments to the determined discussion topic. Based on the relevance of the comment, the comment may be allowed, prioritized, deleted, de-emphasized, or otherwise filtered in the chat feature.

Abstract: In various examples, as a user is speaking or presenting content during an online video conference, the data stream may be processed to generate a textual representation (e.g., transcript) of the audio and/or information relating to the video. The textual representation and/or video related information may then be processed to determine a context or one or more topic(s) of discussion. Based on the determined context/topic(s), a corresponding neural network(s) may be selected. Once a neural network has been selected, comments may be retrieved from a chat feature of the application and applied to the neural network. The neural network may then output data to indicate the relevance of the comments to the determined discussion topic. Based on the relevance of the comment, the comment may be allowed, prioritized, deleted, de-emphasized, or otherwise filtered in the chat feature.

Abstract: Systems and methods for generating real-time synthetic crowd responses for events, to augment the experience of event participants, remote viewers, and the like. Various sensors monitor the event in question, and various event properties are derived from their output using an event state model. These event properties, along with various event parameters such as score, time remaining, etc., are then input to a machine learning model that determines a real-time synthetic audience reaction tailored to the immediate state of the event. Reaction parameters are used to generate a corresponding crowd or audience audio signal, which may be broadcast to event participants, viewers, spectators, or anyone who may be interested. This instantaneous, realistic crowd reaction more closely simulates the experience of events with full on-site audiences, enhancing the viewing experience of both event participants and those watching.

Abstract: Systems and methods are presented for reliable transmission of time-sensitive data. In particular, various embodiments provide for the generation of compressed sequential data, where individual instances of a sequence represent differentials from prior instances in that sequence. In order to reduce an amount of data that needs to be transmitted, instances of data (such as individual video frames) can be provided using a prior video frame as a reference, sending only data for those pixel locations where the pixel value differs from the reference frame. A reference frame can include a previously-received and successfully-decoded frame, in order to minimize the impact of dropped, incomplete, or corrupted frames. In order to further reduce data transmission requirements, a reference frame can be selected which is determined to be optimal for the current frame, such as may represent a least amount of data to be transmitted for a given frame.

Abstract: Annotations can be correlated to components of a document image so that the annotations track movements of the document image. A transparent overlay is generated to include the annotations and is linked to various components of the document image. Movement of the underlying document image is tracked and then adjustments in components positions are applied to associated annotations to maintain a contextual relationship between the annotations and the components of the document image.

Abstract: Systems and methods for generating real-time synthetic crowd responses for events, to augment the experience of event participants, remote viewers, and the like. Various sensors monitor the event in question, and various event properties are derived from their output using an event state model. These event properties, along with various event parameters such as score, time remaining, etc., are then input to a machine learning model that determines a real-time synthetic audience reaction tailored to the immediate state of the event. Reaction parameters are used to generate a corresponding crowd or audience audio signal, which may be broadcast to event participants, viewers, spectators, or anyone who may be interested. This instantaneous, realistic crowd reaction more closely simulates the experience of events with full on-site audiences, enhancing the viewing experience of both event participants and those watching.

Abstract: In various examples, as a user is speaking or presenting content during an online video conference, the data stream may be processed to generate a textual representation (e.g., transcript) of the audio and/or information relating to the video. The textual representation and/or video related information may then be processed to determine a context or one or more topic(s) of discussion. Based on the determined context/topic(s), a corresponding neural network(s) may be selected. Once a neural network has been selected, comments may be retrieved from a chat feature of the application and applied to the neural network. The neural network may then output data to indicate the relevance of the comments to the determined discussion topic. Based on the relevance of the comment, the comment may be allowed, prioritized, deleted, de-emphasized, or otherwise filtered in the chat feature.

Abstract: In various examples, communications having insecure protocols are dynamically hardened. For example, communications that are formatted in an outdated or otherwise insecure version of a protocol (e.g., sent by a device aged out of a service window) may be isolated within a network, converted to an updated protocol format, or any combination thereof. These systems and methods may be implemented on a general purpose network device (e.g., a hub of a Local Area Network (LAN)).

Abstract: Apparatuses, systems, and techniques to detect abnormal behavior on clients using one or more neural networks on said clients. In at least one embodiment, use of or behavior on one or more clients is analyzed by a first neural network to detect abnormal behavior compared to a baseline of accepted behavior, and said baseline of accepted behavior is revised over time by a second neural network based on behavior observed on said one or more clients.

Abstract: Apparatuses, systems, and techniques to accelerate training of one or more neural networks. In at least one embodiment, training values for individual nodes in a first neural network are estimated using a second neural network or other estimation technique in order to decrease time required to train the first neural network.

Abstract: A security enhancement technique provides users of an application program with a perceptible cue, such as a visual or audible indication, that a domain and/or link is safe according to a list of safe domains/sites and links. Each identified domain and/or link is compared with domains and/or links defined in a trusted list. The trusted list is maintained by an enterprise system administrator or is provided via an internet browser program. Advantages of this technique are that the user can easily identify domain names that are trusted and does not need to examine each URL path to determine whether or not the domain and/or link is safe. Users may be motivated to scrutinize domains and/or links that are not indicated to be trusted, reducing security breaches.

Abstract: A surgical system includes a drive unit on a support. The drive unit includes motors or other actuators and a plurality of output elements arranged such that operation of each drive unit linearly translates a corresponding one of the output elements. A surgical device has actuation elements extending through an elongate shaft to a distal articulation section, and an input subsystem carried at the proximal end of the shaft. Linear translatable input elements or pistons of the input subsystem are each associated with a corresponding one of the actuation elements. The input and output elements are positioned such that operation of an actuator linearly translates an output element, causing linear translation of a corresponding input element and engagement of an actuation element. A sterile drape is positionable between the input elements and the output elements.

Abstract: A surgical system includes a drive unit on a support. The drive unit includes motors or other actuators and a plurality of output elements arranged such that operation of each drive unit linearly translates a corresponding one of the output elements. A surgical device has actuation elements extending through an elongate shaft to a distal articulation section, and an input subsystem carried at the proximal end of the shaft. Linear translatable input elements or pistons of the input subsystem are each associated with a corresponding one of the actuation elements. The input and output elements are positioned such that operation of an actuator linearly translates an output element, causing linear translation of a corresponding input element and engagement of an actuation element. A sterile drape is positionable between the input elements and the output elements.

Abstract: A surgical suturing device has an elongate shaft has a proximal end, a distal end, and a longitudinal axis between the proximal and distal ends. An actuator is connected to the proximal end of the elongate shaft. A circular needle applier is on the distal end of the elongate shaft. The circular needle applier has an arced needle and a needle driver operatively connected to the actuator to rotate the arced needle in a circular path. A joint is positioned between the proximal and distal ends of the elongate shaft. The joint is operatively connected to the actuator to selectively articulate the shaft. A bearing is on the shaft positioned distally of the joint. The bearing is operatively connected to the actuator to selectively rotate the circular needle applier about the longitudinal axis.

Abstract: A surgical suturing device has an elongate shaft has a proximal end, a distal end, and a longitudinal axis between the proximal and distal ends. An actuator is connected to the proximal end of the elongate shaft. A circular needle applier is on the distal end of the elongate shaft. The circular needle applier has an arced needle and a needle driver operatively connected to the actuator to rotate the arced needle in a circular path. A joint is positioned between the proximal and distal ends of the elongate shaft. The joint is operatively connected to the actuator to selectively articulate the shaft. A bearing is on the shaft positioned distally of the joint. The bearing is operatively connected to the actuator to selectively rotate the circular needle applier about the longitudinal axis.

Abstract: A suture needle driving instrument comprises a shaft and an end effector. The end effector is located at the distal end of the shaft and includes a pair of grasping arms. Each grasping arm comprises a respective pair of jaws. Each pair of jaws is operable to cooperate to grasp and release a suture needle. Each jaw has a needle grasping member operable to align a suture needle along a predetermined arc path. The end effector is further operable to pass the needle from one arm to the other arm during a suturing procedure. The instrument may be used through a trocar during minimally invasive surgery.

Abstract: A surgical needle includes a pair of ends, a mid-region extending between the ends, and at least one grasping feature configured for grasping by a suturing instrument. An end of a suture is secured to the mid-region of the needle in a manner such that the end of the suture defines an oblique angle with at least part of the centerline defined by the mid-region of the needle. The end of the suture may be disposed in a hollow portion of the needle. The grasping feature may include a notch such as a scallop. The suture may be pivotally coupled with the needle via a ball or pin. The needle may have one or more sharp points. The sharp point may include three converging cutting edges, at least two planar surfaces bounded by the three cutting edges, and a rounded surface bounded by two of the three cutting edges.