公开(公告)号：US20250167890A1

公开(公告)日：2025-05-22

申请号：US18712203

申请日：2022-12-16

Applicant: SRI International

Inventor： Marcus A. BAGNELL ,  Nicole A. HEIDEL ,  Cale M. GENTRY

IPC: H04B10/118 ,  G02B6/293 ,  H04B10/50

Abstract: Improved systems and methods for optical communications are provided that have reduced size, weight, and power use. Such system and methods can find, use between satellites or other distant systems that are in significant relative motion. Such embodiments include the use of a diamagnetically levitated magnetic actuator or other actuator to control the orientation of an optical phased array (OPA), thereby aiming the array at distant target systems. An OPA has reduced size and mass relative to traditional telescopes, providing similar beam apertures while having reduced size, weight, and cost of the OPA and associated actuators. The actuator allows the OPA to omit, or to include fewer, phase shifter elements than previous steerable OPA telescopes, reducing complexity', cost, and power requirements.

公开(公告)号：US20250131027A1

公开(公告)日：2025-04-24

申请号：US18924763

申请日：2024-10-23

Applicant: SRI International

Inventor： Yangyi Chen ,  Karan Sikka ,  Michael A. Cogswell ,  Ajay Divakaran

IPC: G06F16/338 ,  G06F16/33 ,  G06F16/532

Abstract: In an example, a method for fine-tuning a Large Visual Language Model (LVLM) includes providing visual queries, each of the visual queries comprises at least an image and a textual query related to the image; processing, by the LVLM, the visual queries to extract visual embeddings from the visual queries, wherein the LVLM comprises a Visual Language Model (VLM), a first Large Language Model (LLM), and a linear projection layer interconnecting the VLM and the LLM; for visual queries: i) generating, by the LVLM, a response to the corresponding visual query based on the corresponding visual embedding; ii) evaluating, by a second LLM, the generated response to verify that the generated response satisfies predefined criteria; and iii) providing, by the second LLM, a feedback to the LVLM, in response to the evaluating the generated response; and fine-tuning the LVLM using aggregated feedback provided by the second LLM for the visual queries.

公开(公告)号：US20250110989A1

公开(公告)日：2025-04-03

申请号：US18895080

申请日：2024-09-24

Applicant: SRI International

Inventor： Ajay Divakaran ,  Yi Yao ,  Julia Kruk ,  Jesse Hostetler ,  Jihua Huang

IPC: G06F16/901

Abstract: In general, various aspects of the techniques are directed to causal analysis using large scale time series data. A computing system may convert large scale time series data to first time period records and second time period records according to a multi-scale time resolution. The computing system may implement a hierarchical machine learning model to generate embeddings that capture temporal characteristics of features of the large scale time series data. The computing system may generate a graph data structure indicating cause and effect correlations between features of the large scale time series data based on temporal dynamics captured in the cause and second time period records and/or the embeddings.

公开(公告)号：US20250094810A1

公开(公告)日：2025-03-20

申请号：US18823282

申请日：2024-09-03

Applicant: SRI International

Inventor： Zachary A. DANIELS ,  Jun HU ,  Michael R. LOMNITZ ,  Philip MILLER ,  Aswin NADAMUNI RAGHAVAN ,  Yuzheng ZHANG ,  Michael PIACENTINO ,  David C. ZHANG ,  Michael ISNARDI ,  Saurabh FARKYA

IPC: G06N3/084

Abstract: Method and apparatus for processing input information using an adaptable and continually learning neural network architecture comprising an encoder, at least one adaptor and at least one reconfigurator. The encoder, at least one reconfigurator and at least one adaptor determine whether the input information is out-of-distribution or in-distribution. If the input information is in distribution, the architecture extracts features from the input information, creates hyperdimensional vectors representing the features and classifies the hyperdimensional vectors. If the input information is out of distribution, the architecture creates at least one adaptor to operate with the encoder and the at least one reconfigurator to extract features from the input information, create hyperdimensional vectors representing the features and classify the hyperdimensional vectors.

公开(公告)号：US20250065126A1

公开(公告)日：2025-02-27

申请号：US18810905

申请日：2024-08-21

Applicant: John Cornwell ,  SRI International

Inventor： Christopher Ian Connolly ,  Patrick Denis Lincoln ,  John Cornwell

IPC: A61N1/36

Abstract: Embodiments are directed to systems, devices, and methods for perturbing a biosystem to quantify responsiveness. An example system comprises stimulation circuitry configured to output a plurality of biostimulation signals to a target of a subject, sensor circuitry configured to obtain measures of a biosignal from the subject, and processor circuitry. The processor circuitry is configured to cause the stimulation circuitry to output the plurality of biostimulation signals to perturb a biosystem of the subject, and quantify responsiveness of the biosystem to the perturbation based on the plurality of biostimulation signals and measures of the biosignal responsive to the plurality of biostimulation signals applied to the target.

公开(公告)号：US20250045610A1

公开(公告)日：2025-02-06

申请号：US18673036

申请日：2024-05-23

Applicant: SRI International

Inventor： Pedro Daniel Barbosa Sequeira ,  Haochen Wu

IPC: G06N7/01 ,  G06N5/043

Abstract: In an example, a method includes obtaining data indicating a plurality of trajectories representing a behavior of a team comprising a plurality of agents; obtaining a plurality of baseline profiles, wherein each of the plurality of baseline profiles encodes at least one of a preference and/or a goal that is relevant to a task performed by the team; generating a probability distribution of each agent of the plurality of agents over the plurality of baseline profiles, wherein the probability distribution of each agent describes a behavior of the agent; updating the corresponding probability distribution of each agent of the plurality of agents; and generating, based on the updated probability distributions of the plurality of agents, reward functions that explain the observed joint actions performed by the team, wherein each of the reward functions describes the behavior of a corresponding one of the plurality of agents.

公开(公告)号：US12170341B2

公开(公告)日：2024-12-17

申请号：US17579471

申请日：2022-01-19

Applicant: SRI International

Inventor： Winston K. Chan

IPC: H01L31/107 ,  G01J1/44 ,  G01S7/481 ,  G01S17/931 ,  H01L31/0304 ,  H01L31/0352 ,  H01L31/18

Abstract: A photodiode, such as a linear mode avalanche photodiode can be made free of excess noise via having a superlattice multiplication region that allows only one electrical current carrier type, such as an electron or a hole, to accumulate enough kinetic energy to impact ionize when biased, where the layers are lattice matched. A photodiode can be constructed with i) a lattice matched pair of a first semiconductor alloy and a second semiconductor alloy in a superlattice multiplication region, ii) an absorber region, and iii) a semiconductor substrate. A detector with multiple photodiodes can be made with these construction layers in order to have a cutoff wavelength varied anywhere from 1.7 to 4.9 μm as well as a noise resulting from a dark current at a level such that an electromagnetic radiation signal with the desired minimum wavelength cutoff can be accurately sensed by the photodiode.

公开(公告)号：US12146573B2

公开(公告)日：2024-11-19

申请号：US18347294

申请日：2023-07-05

Applicant: SRI INTERNATIONAL

Inventor： Alexander Kernbaum ,  Murphy Kitchell ,  Thomas Egan

IPC: F16H9/20 ,  F16H55/56

Abstract: A variety of shifter mechanisms are provided for controlling the axial distance between half-pulleys of a split pulley variable transmission, thus controlling the transmission ratio of the variable transmission. Some of these embodiments include a differential such that a variable transmission can be driven and shifted differentially by two inputs. A torque or rotation difference between the inputs results in a change in the transmission ratio and in-common torque or rotation is transmitted through the transmission to an output. The same motors used to drive the output of the transmission are thus also able to effect shifts in the transmission ratio. Accordingly, motor mass that is not being used to effect high-speed shifts may be used to drive the transmission output, and vice versa. The provided shifter embodiments are well-suited to application to nested-pulley variable transmissions, including nested-pulley infinitely variable transmissions.

公开(公告)号：US20240379112A1

公开(公告)日：2024-11-14

申请号：US18661313

申请日：2024-05-10

Applicant: SRI International

Inventor： MD Hafizur Rahman ,  Christopher L. Cobo-Kroenke ,  Martin Graciarena

IPC: G10L17/26 ,  G10L17/02 ,  G10L17/04

Abstract: In general, the disclosure describes techniques for detecting synthetic speech in an audio clip. In an example, a computing system may include processing circuitry and memory for executing a machine learning system. The machine learning system may be configured to process an audio clip to generate a plurality of speech artifact embeddings based on a plurality of synthetic speech artifact features. The machine learning system may further be configured to compute one or more scores based on the plurality of speech artifact embeddings. The machine learning system may further be configured to determine, based on the one or more scores, whether one or more frames of the audio clip include synthetic speech. The machine learning system may further be configured to output an indication of whether the one or more frames of the audio clip include synthetic speech.

公开(公告)号：US20240358459A1

公开(公告)日：2024-10-31

申请号：US18770103

申请日：2024-07-11

Applicant: SRI International

Inventor： Karen Shakespear KOENIG ,  Pablo Eduardo GARCIA KILROY ,  Sina NIA KOSARI ,  Thomas D. EGAN

IPC: A61B34/30 ,  A61B17/00 ,  A61B17/29 ,  A61B17/34 ,  A61B34/00 ,  A61B34/37 ,  A61B46/10 ,  B25J3/04 ,  B25J9/00 ,  B25J9/06 ,  B25J9/10 ,  B25J9/12 ,  B25J13/02 ,  B25J13/08 ,  B25J17/02

CPC classification number: A61B34/30 ,  A61B17/34 ,  A61B34/37 ,  A61B34/72 ,  A61B2017/00327 ,  A61B2017/00477 ,  A61B2017/2919 ,  A61B2017/2923 ,  A61B2017/2927 ,  A61B2017/2932 ,  A61B2034/302 ,  A61B2034/303 ,  A61B2034/742 ,  A61B46/10 ,  B25J3/04 ,  B25J9/0027 ,  B25J9/0039 ,  B25J9/06 ,  B25J9/104 ,  B25J9/12 ,  B25J13/02 ,  B25J13/085 ,  B25J17/0283 ,  G05B2219/45117

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.