利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.016 seconds)

    NEUROMORPHIC SENSORS FOR LOW-POWER WEARABLES
    2.
    发明公开
    NEUROMORPHIC SENSORS FOR LOW-POWER WEARABLES 审中-公开

    公开(公告)号：US20240355121A1

    公开(公告)日：2024-10-24

    申请号：US18136583

    申请日：2023-04-19

    Applicant: Rockwell Collins, Inc.

    Inventor： Kin Gwn Lore ,  Ganesh Sundaramoorthi ,  Kishore K. Reddy

    IPC: G06V20/40 ,  A61B5/00 ,  A61B5/01 ,  A61B5/0533

    CPC classification number: G06V20/44 ,  A61B5/01 ,  A61B5/0533 ,  A61B5/6802

    Abstract: A wearable device includes neuromorphic event cameras. A processor receives data streams from the event cameras and makes application specific predictions/determinations. The event cameras may be outward facing to make determinations about the environment or a specific task, inward facing to monitor the state of the user, or both. The processor may be configured as a trained neural network to receive the data streams and produce output based on predefined sets of training data. Sensors other than event cameras may supply data to the processor and neural network, including other cameras via a feature recognition process.

    SYSTEM AND METHOD FOR DETERMINING INCOMING OBSERVATION TO BE OUT-OF-DISTRIBUTION (OOD) SAMPLE DURING NEURAL NETWORK (NN) INFERENCE
    3.
    发明申请
    SYSTEM AND METHOD FOR DETERMINING INCOMING OBSERVATION TO BE OUT-OF-DISTRIBUTION (OOD) SAMPLE DURING NEURAL NETWORK (NN) INFERENCE 有权

    公开(公告)号：US20250069381A1

    公开(公告)日：2025-02-27

    申请号：US18238180

    申请日：2023-08-25

    Applicant: Rockwell Collins, Inc.

    Inventor： Sudeepta Mondal ,  Ganesh Sundaramoorthi

    IPC: G06V10/82 ,  G06V10/72 ,  G06V10/764

    Abstract: A system may include at least one processor configured to: obtain a trained neural network (NN); obtain or calculate at least one average feature information associated with the trained NN, each of the at least one average feature information including a given average feature information summarizing in-class statistics that each layer of the trained NN uses for a given class; receive an incoming observation influencing a given layer; calculate a corresponding feature information of the incoming observation, the corresponding feature information summarizing statistics of the incoming observation for the given layer; classify the incoming observation as being in the given class; calculate a distance score associated with a distance between the corresponding feature information of the incoming observation and the given average feature information; determine the incoming observation is an out-of-distribution (OOD) sample; and output an alert indicating the incoming observation is OOD and/or discard the incoming observation's classification.

    PUPIL DYNAMICS, PHYSIOLOGY, AND PERFORMANCE FOR ESTIMATING COMPETENCY IN SITUATIONAL AWARENESS
    4.
    发明申请
    PUPIL DYNAMICS, PHYSIOLOGY, AND PERFORMANCE FOR ESTIMATING COMPETENCY IN SITUATIONAL AWARENESS 有权

    公开(公告)号：US20250000372A1

    公开(公告)日：2025-01-02

    申请号：US18216825

    申请日：2023-06-30

    Applicant: Rockwell Collins, Inc.

    Inventor： Peggy Wu ,  Brigid A. Blakeslee ,  Andrew Radlbeck ,  Ganesh Sundaramoorthi

    IPC: A61B5/0205 ,  G06V20/40 ,  G06V40/18

    Abstract: A computer system records eye tracking data and identifies movements in the eye tracking data to determine gaze and pupil dynamics. Eye tracking data is correlated with physiological data including heart rate. The system looks at the heart rate of the operator in real time to evaluate whether they exhibit an anticipatory response to switch attention. The system differentiates between behaviors that are cognitively initiated as opposed to triggered by the environment. The system correlates eye tracking data and physiological data with previously identified knowledge about the training scenario to assess whether the operator is able to direct attention to the right stimuli based on task needs. The system examines whether there is follow through behavior of shifting gaze to specific instruments as defined by the current task.

    Pupil dynamics, physiology, and context for estimating vigilance
    6.
    发明授权
    Pupil dynamics, physiology, and context for estimating vigilance 有权

    公开(公告)号：US12124625B1

    公开(公告)日：2024-10-22

    申请号：US18216841

    申请日：2023-06-30

    Applicant: Rockwell Collins, Inc.

    Inventor： Peggy Wu ,  Brigid A. Blakeslee ,  Andrew Radlbeck ,  Ganesh Sundaramoorthi

    IPC: G06F3/01

    CPC classification number: G06F3/013

    Abstract: A computer system records eye tracking data and identifies movements in the eye tracking data to determine gaze and pupil dynamics. Eye tracking data is correlated with a current task and predetermined vigilance requirements. The system determines if the user is exhibiting an appropriate level of vigilance based on the task or is becoming fixated. When fixation is detected, the system may engage in remedial action. A task flow diagram represents the operator tasks. Interactions between the user and the instrumentation are used to estimate the probability distribution of the task the user is currently conducting. The system correlates eye tracking data and physiological data such as electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRs) to determine neuroactivity. Monitoring neuroactivity reduces the probability of a false positive for fixation.

Patent Agency Ranking