INTERACTIVE OBJECT TRAJECTORY PREDICTION SYSTEMS AND METHODS

    公开(公告)号:US20240400231A1

    公开(公告)日:2024-12-05

    申请号:US17896634

    申请日:2022-08-26

    Abstract: An interactive orbital trajectory prediction system including a processor arranged to simultaneously display: i) a surface of the first primary body including the relative predicted trajectory of the object, ii) a surface of the second primary body including the relative predicted trajectory of the object, and iii) the barycenter of the two primary bodies, and the trajectory of the object with respect to the barycentric reference frame. The system includes an input device arranged to receive a user selection of a first sensor module of a plurality of sensor modules used to predict the trajectory of the object orbiting the primary body. The processor, in response to the user selection of the first sensor module, predicts the flight path of the object based on the first sensor module.

    Six dimensional tracking of sparse LADAR data

    公开(公告)号:US12153139B2

    公开(公告)日:2024-11-26

    申请号:US17138386

    申请日:2020-12-30

    Abstract: An apparatus, and method of operating the same processes of LADAR data including iterating back and forth between target detection in a 2-D array having range and range rate dimension, and a 4-D array having azimuth, azimuthal velocity, elevation, & elevation velocity dimensions. The apparatus includes a receiver and a processor arranged to generate photo events including target signal photo events and background photo events, transform the photo events into the 2-D target tracking array including range and range-rate parameters and tag photo events determined to be 2-D target signal photo events. The processor transforms tagged photo events into the 4-D target and tags photo events determined to be 4-D target signal photo events.

    FEATURE FUSION WITH MEASUREMENT UNCERTAINTY

    公开(公告)号:US20240386073A1

    公开(公告)日:2024-11-21

    申请号:US18198645

    申请日:2023-05-17

    Abstract: Embodiments regard feature fusion with uncertainty, such as for classification. A method includes altering, for each feature of features to be fused and based on a marginal uncertainty distribution corresponding to a feature of the features and the marginal uncertainty distribution accounting for uncertainty in measuring the feature, a marginal feature distribution of the feature resulting in respective marginal feature distributions that account for uncertainty, altering, based on a joint uncertainty covariance of the features, a joint feature covariance of the features resulting in a covariance that jointly accounts for feature covariance and uncertainty covariance, generating, based on the covariance that jointly accounts for feature covariance and uncertainty covariance and the respective marginal feature distributions that account for uncertainty, a joint density function that accounts for feature values and uncertainty, and classifying the features based on the joint density function that accounts for feature values and uncertainty.

    Energy storage power source using a wound-rotor induction machine (WRIM) to charge and discharge energy storage elements (ESEs)

    公开(公告)号:US12136844B2

    公开(公告)日:2024-11-05

    申请号:US17557758

    申请日:2021-12-21

    Abstract: A stored energy power source uses a wound-rotor induction machine (WRIM) to receive energy from an external source, store the energy in N energy storage elements (ESEs) via tertiary windings, and discharge the ESEs to deliver energy via a secondary winding to a load producing output. Each discharging ESE contributes to a total flux at the secondary winding to sum the individual ESEs voltages. These voltages can be stepped up or down by a transformation ratio between the secondary winding and each of the tertiary windings. A flywheel may be coupled to the secondary to store and delivery energy. Load factor power control can be used to stabilize the output voltage. The source may be configured to allow for the bi-directional flow of energy between an external power source, the ESEs, the flywheel and the load. The WRIM provides a safe, reliable and efficient system to provide high-level AC and DC output voltages.

    COVERT SENSING AND COMMUNICATIONS USING SPREAD SPECTRUM WAVEFORM CODING

    公开(公告)号:US20240361458A1

    公开(公告)日:2024-10-31

    申请号:US18646096

    申请日:2024-04-25

    Inventor: Mark J. Meisner

    CPC classification number: G01S17/36 G01S7/006 G01S7/4911 G01S7/4917

    Abstract: In a system for covert sensing and communications a broadband light source is encoded using spread spectrum waveform coding to spread a narrow-band signal over frequency. The modulated broadband light is suitably hidden in additional noise and then split into two portions, a first portion of which illuminates a target, and a second portion of which is delayed and provided as a local oscillator. Light reflected from the target is combined with the local oscillator, detected using heterodyne, homodyne or quasi-homodyne techniques, demodulated and decoded to estimate the phase of the reflected light relative to the transmitted light to provide fine range estimates for the target. Waveform coding allows for time-correlation of the transmitted and received coded waveforms to provide improved resolution for adjusting the delay of the local oscillator to improve the detection schemes. The waveform coding also provides a covert communications channel.

    NEUROMORPHIC SENSOR-BASED VIRTUAL SENSOR
    27.
    发明公开

    公开(公告)号:US20240357245A1

    公开(公告)日:2024-10-24

    申请号:US18640778

    申请日:2024-04-19

    CPC classification number: H04N23/951 G06T3/4046 G06T3/4053

    Abstract: Embodiments regard implementing operations that provide a virtual sensor. A method includes receiving, from a neuromorphic sensor, a time series of delta images, receiving auxiliary data indicating (i) an orientation, location, direction, or speed of the neuromorphic sensor, or (ii) metadata of the neuromorphic sensor, the auxiliary data associated with about a same time as the time series of images, operating, based on an image of the time series of delta images and auxiliary data of the auxiliary data associated with the image as occurring at about a same time, a first machine learning (ML) model resulting in a low-resolution image, and operating, based on the low-resolution image, a second ML model resulting in a high-resolution image, the high-resolution image of a type different than that produced by the neuromorphic sensor.

    DYNAMIC MODULATOR BIAS CONTROLLER WITH CONTINUOUS WAVEFORM CHARACTERIZATION VIA TWO OR MORE BIAS POINTS

    公开(公告)号:US20240356653A1

    公开(公告)日:2024-10-24

    申请号:US18137005

    申请日:2023-04-20

    CPC classification number: H04B10/54 G02F1/212

    Abstract: A communication system includes a laser that generates a laser light and a modulator that includes a modulation element configured to modulate the laser light with an input signal based on a bias voltage to produce an output signal. Control circuitry provides the bias voltage to a bias input of the modulation element and is configured to maintain a bias lock on at least two bias points of the modulation element during operation. The control circuitry is programmed to perform a bias lock operation that includes performing an initial voltage sweep on the modulation element and establish initial bias values for the at least two bias points. The circuit also providing a bias waveform to the bias input of the modulation element that varies over time and contains identifiable dither tones, determines harmonic power at the at least two bias points; and varies the bias waveform to determine harmonic power until the harmonic power is minimized to establish a bias lock with locked bias values.

    MACHINE LEARNING MODEL GRAFTING AND INTEGRATION

    公开(公告)号:US20240354662A1

    公开(公告)日:2024-10-24

    申请号:US18305034

    申请日:2023-04-21

    CPC classification number: G06N20/20

    Abstract: A method includes obtaining multiple machine learning models, where each machine learning model includes a backbone and a head. The method also includes selecting a first of the machine learning models to retain its backbone. The method further includes back-propagating error terms for synthetic activation data through at least a portion of the backbone of a second of the machine learning models to generate an inception basis set. In addition, the method includes configuring a bridge using the inception basis set, where the bridge is configured to translate features generated by the backbone of the first machine learning model into features for use by the head of the second machine learning model.

Patent Agency Ranking