中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

888 records (took 0.027 seconds)

    Failsafe brake device for robotic and other applications
    32.
    发明授权
    Failsafe brake device for robotic and other applications 有权

    公开(公告)号：US11732768B2

    公开(公告)日：2023-08-22

    申请号：US17202013

    申请日：2021-03-15

    Applicant: SRI INTERNATIONAL

    Inventor： Joseph Eckerle ,  Alexander Kernbaum ,  Marisa de Souza

    IPC: F16D67/06 ,  F16D13/10 ,  H02N13/00 ,  F16D27/02 ,  F16D13/08 ,  B25J19/00

    CPC classification number: F16D67/06 ,  B25J19/0004 ,  F16D13/10 ,  H02N13/00 ,  F16D13/08 ,  F16D27/025

    Abstract: A variety of brake and/or clutch mechanisms, and improvements thereof, are provided having improved braking power, reduced size and weight, and other benefits. The braking mechanisms include a wrap spring clutch that is operable to mechanically couple a rotating member to a brake rotor that is in consistent contact with a brake pad. Actuation of the wrap spring clutch allows the wrap spring to engage with the rotating member, coupling the rotating member to the brake rotor thus braking the rotating member. The combination of the wrap spring clutch with the brake rotor and pad provides an overall braking mechanism that exhibits the decreased power cost, weight, size, and engagement time of the wrap spring clutch while having a braking power that can be moderated by specifying the area, engagement force, coefficient of friction, or other properties of the brake rotor and pad.

    Pure rolling cycloid transmissions with variable effective diameter rollers and roller constraints
    33.
    发明授权
    Pure rolling cycloid transmissions with variable effective diameter rollers and roller constraints 有权

    公开(公告)号：US11674564B2

    公开(公告)日：2023-06-13

    申请号：US17633790

    申请日：2020-08-26

    Applicant: SRI International

    Inventor： Alexander Kernbaum ,  Murphy Kitchell

    IPC: F16H1/32 ,  F16H13/08

    CPC classification number: F16H1/32 ,  F16H13/08 ,  F16H2001/323

    Abstract: A variety of transmissions, and improvements thereof, are provided having improved efficiency and other benefits. The transmissions include one or more inner members that are driven by one or more cams or other means to engage in precessional rotation about an axis of rotation that, itself, orbits about a primary axis of rotation. A plurality of shaped rollers are in contact with shaped cutouts on the inner member(s) and on a ground member such that an input rotation/torque applied via the cam is realized as an output rotation/torque at an output member that is coupled to the inner member(s). Tire rollers and contact surfaces are shaped such that the rollers engage in rolling motion relative to the contact surfaces, providing improved efficiency. Multiple inner members, and corresponding sets of shaped rollers, can be provided to increase power capacity, reduce torque ripple, reduce wobble, or provide other benefits.

    CONVERSATION-DEPTH SOCIAL ENGINEERING ATTACK DETECTION USING ATTRIBUTES FROM AUTOMATED DIALOG ENGAGEMENT
    34.
    发明公开
    CONVERSATION-DEPTH SOCIAL ENGINEERING ATTACK DETECTION USING ATTRIBUTES FROM AUTOMATED DIALOG ENGAGEMENT 审中-公开

    公开(公告)号：US20230179628A1

    公开(公告)日：2023-06-08

    申请号：US18059496

    申请日：2022-11-29

    Applicant: SRI International

    Inventor： Phillip Porras ,  Kenneth Nitz ,  Keith Skinner ,  Dayne Freitag

    IPC: H04L9/40 ,  G06F40/30

    CPC classification number: H04L63/1483 ,  G06F40/30

    Abstract: A method of determining an adversarial attack playbook includes receiving, from an adversarial actor, an electronic communication intended for a target user. The method includes engaging in a deep dialog with the adversarial actor by deploying a synthetic persona dynamically during the electronic communication. The deep dialog includes multiple rounds of communication exchanges. The method includes determining a length and type of the deep dialog to obtain attributes related to the adversarial actor. The method includes identifying a conversational pattern from the deep dialog. The conversational pattern comprises dialog interaction elements utilized by the adversarial actor. The method includes dynamically producing, based on the conversational pattern, the playbook associated with the adversarial actor. The playbook is indicative of a dialog interaction strategy implemented by the adversarial actor. The method includes providing the playbook to a social engineering attack (SEA) system in order to detect, avoid and/or mitigate future attacks.

    Single-track magnetic encoding
    37.
    发明授权
    Single-track magnetic encoding 有权

    公开(公告)号：US11566917B2

    公开(公告)日：2023-01-31

    申请号：US17284312

    申请日：2019-10-09

    Applicant: SRI International

    Inventor： Paolo Sechi ,  Alan Leong

    IPC: G01D5/14

    Abstract: A system includes a substrate, a first and a second magnetic field sensor, and a computing device communicatively coupled to the first and second magnetic field sensors. The substrate has a surface encoded with a magnetic pattern sequenced along a direction of movement of the substrate. The magnetic pattern includes a data pattern that indicates a position of the substrate along the direction of movement and a clock pattern interleaved and substantially colinear with the data pattern that indicates a plurality of clock transitions. The computing device is configured to receive, from the first and second magnetic field sensors positioned above the magnetic pattern, a plurality of magnetic field signals detected from the magnetic pattern. The computing device is configured to determine, based on the plurality of magnetic field signals, the position of the substrate and output the position of the substrate.

    ONE-DIMENSIONAL-CONVOLUTION-BASED SIGNAL CLASSIFIER
    38.
    发明申请
    ONE-DIMENSIONAL-CONVOLUTION-BASED SIGNAL CLASSIFIER 有权

    公开(公告)号：US20230004799A1

    公开(公告)日：2023-01-05

    申请号：US17852954

    申请日：2022-06-29

    Applicant: SRI International

    Inventor： Bradley Clymer

    IPC: G06N3/08

    Abstract: An output module cooperates with a machine learning architecture to analyze parameter-varying signals. The signal-analyzing neural-network contains at least a one-dimensional-convolution layer to apply a series of i) a one-dimensional convolutional-based operation on the data of the parameter-varying signals ii) followed by a non-linear activation function on the data of the parameter-varying signals, under analysis, with multiple representations of the parameter-varying signals. Each representation of the parameter-varying signal is analyzed in a different domain in order to produce a classification of an entity into a specific category of an object corresponding to identifying features of the time-varying signals. Branches of the signal-analyzing neural-network are constructed to apply at least two or more successive layers of the one-dimensional-convolution layer followed by the non-linear activation function layer to values of time and frequency features of the parameter-varying signals, under analysis.

    Runtime-throttleable neural networks
    39.
    发明授权
    Runtime-throttleable neural networks 有权

    公开(公告)号：US11494626B2

    公开(公告)日：2022-11-08

    申请号：US16600154

    申请日：2019-10-11

    Applicant: SRI International

    Inventor： Jesse Hostetler ,  Sek Meng Chai

    IPC: G06N3/04 ,  G06N3/063 ,  G06F1/3287 ,  G06N20/20 ,  G06N3/08

    Abstract: In general, the disclosure describes techniques for creating runtime-throttleable neural networks (TNNs) that can adaptively balance performance and resource use in response to a control signal. For example, runtime-TNNs may be trained to be throttled via a gating scheme in which a set of disjoint components of the neural network can be individually “turned off” at runtime without significantly affecting the accuracy of NN inferences. A separate gating neural network may be trained to determine which trained components of the NN to turn off to obtain operable performance for a given level of resource use of computational, power, or other resources by the neural network. This level can then be specified by the control signal at runtime to adapt the NN to operate at the specified level and in this way balance performance and resource use for different operating conditions.

    Machine learning system for building renderings and building information modeling data
    40.
    发明授权
    Machine learning system for building renderings and building information modeling data 有权

    公开(公告)号：US11468206B2

    公开(公告)日：2022-10-11

    申请号：US15999553

    申请日：2018-08-20

    Applicant: SRI International

    Inventor： Chih-hung Yeh ,  Karen Myers ,  Mohamed Amer

    IPC: G06F30/13 ,  G06N3/04 ,  G06N20/00

    Abstract: Techniques are disclosed for using a computation engine executing a machine learning system to generate, according to constraints, renderings of a building or building information modeling (BIM) data for the building, wherein the constraints include at least one of an architectural style or a building constraint. In one example, an input device is configured to receive an input indicating one or more surfaces for the building and one or more constraints. A machine learning system executed by a computation engine is configured to apply a model, trained using images of buildings labeled with corresponding constraints for the buildings, to the one or more surfaces for the building to generate at least one of a rendering of the one or more surfaces for the building according to the constraints or BIM data for the building according to the constraints. Further, the machine learning system is configured to output the rendering or the BIM data.

Patent Agency Ranking