Patents by Inventor Mohammad Rostami

Mohammad Rostami has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11448753
    Abstract: Described is a system for transferring learned knowledge from an electro-optical (EO) domain to a synthetic-aperture-radar (SAR) domain. The system uses a measured similarity between the EO domain and the SAR domain to train a model for classifying SAR images using knowledge previously learned from the electro-optical (EO) domain. Using the trained model, a SAR image is processed to determine regions of interest in the SAR image. A region of interest is classified to determine whether the region of interest corresponds to an object of interest, and classified regions of interest that contain the object of interest are output. The object of interest is displayed on a visualization map, and the visualization map is automatically updated to reflect a change in position of the object of interest.
    Type: Grant
    Filed: January 24, 2020
    Date of Patent: September 20, 2022
    Assignee: HRL LABORATORIES, LLC
    Inventors: Mohammad Rostami, Soheil Kolouri
  • Patent number: 11176477
    Abstract: Described is a system for unsupervised domain adaptation in an autonomous learning agent. The system adapts a learned model with a set of unlabeled data from a target domain, resulting in an adapted model. The learned model was previously trained to perform a task using a set of labeled data from a source domain. The set of labeled data has a first input data distribution, and the set of unlabeled target data has a second input data distribution that is distinct from the first input data distribution. The adapted model is implemented in the autonomous learning agent, causing the autonomous learning agent to perform the task in the target domain.
    Type: Grant
    Filed: December 18, 2019
    Date of Patent: November 16, 2021
    Assignee: HRL Laboratories, LLC
    Inventors: Alexander J. Gabourie, Mohammad Rostami, Soheil Kolouri, Kyungnam Kim
  • Publication number: 20210294993
    Abstract: A method for product tagging is presented including emitting, by at least one RF backscatter transmitter, a dual-tone Radio Frequency (RF) signal embedded within a standardized RF signal on a frequency channel, reflecting and frequency shifting, by a passive RF backscatter tag associated with a product, the dual-tone RF signal to a different frequency channel, and reading, by at least one RF backscatter receiver, the product on the different frequency channel by detecting a distributed ambient backscatter signal generated by a reflection and frequency shifting of the dual-tone RF signal by the passive RF backscatter tag.
    Type: Application
    Filed: March 16, 2021
    Publication date: September 23, 2021
    Inventors: Karthikeyan Sundaresan, Eugene Chai, Sampath Rangarajan, Mohammad Rostami
  • Publication number: 20210192363
    Abstract: Described is a system for continual adaptation of a machine learning model implemented in an autonomous platform. The system adapts knowledge previously learned by the machine learning model for performance in a new domain. The system receives a consecutive sequence of new domains comprising new task data. The new task data and past learned tasks are forced to share a data distribution in an embedding space, resulting in a shared generative data distribution. The shared generative data distribution is used to generate a set of pseudo-data points for the past learned tasks. Each new domain is learned using both the set of pseudo-data points and the new task data. The machine learning model is updated using both the set of pseudo-data points and the new task data.
    Type: Application
    Filed: October 8, 2020
    Publication date: June 24, 2021
    Inventors: Soheil Kolouri, Mohammad Rostami, Praveen K. Pilly
  • Patent number: 10936927
    Abstract: A product tagging system is provided. The product tagging system includes at least one RF backscatter transmitter configured to emit (i) a main carrier RF signal, and (ii) Radio Frequency (RF) signals on two frequencies whose summation forms a twin carrier RF signal. The product tagging system further includes a passive RF backscatter tag associated with a product and configured to reflect and frequency shift the main carrier RF signal to a different frequency using the twin carrier RF signal. The product tagging system also includes at least one RF backscatter receiver configured to read the product on the different frequency by detecting a distributed ambient backscatter signal generated by a reflection and frequency shifting of the main carrier RF signal by the passive RF backscatter tag.
    Type: Grant
    Filed: January 15, 2020
    Date of Patent: March 2, 2021
    Inventors: Karthikeyan Sundaresan, Eugene Chai, Sampath Rangarajan, Mohammad Rostami
  • Patent number: 10908616
    Abstract: Described is a system for object recognition. The system generates a training image set of object images from multiple image classes. Using a training image set and annotated semantic attributes, a model is trained that maps visual features from known images to the annotated semantic attributes using joint sparse representations with respect to dictionaries of visual features and semantic attributes. The trained model is used for mapping visual features of an unseen input image to its semantic attributes. The unseen input image is classified as belonging to an image class, and a device is controlled based on the classification of the unseen input image.
    Type: Grant
    Filed: July 12, 2018
    Date of Patent: February 2, 2021
    Assignee: HRL Laboratories, LLC
    Inventors: Soheil Kolouri, Mohammad Rostami, Kyungnam Kim, Yuri Owechko
  • Publication number: 20210019632
    Abstract: Described is a system for continual learning using experience replay. In operation, the system receives a plurality of tasks sequentially, from which a current task is fed to an encoder. The current task has data points associated with the current task. The encoder then maps the data points into an embedding space, which reflects the data points as discriminative features. A decoder then generates pseudo-data points from the discriminative features, which are provided back to the encoder. The discriminative features are updated in the embedding space based on the pseudo-data points. The encoder then learns (updates) a classification of a new task by matching the new task with the discriminative features in the embedding space.
    Type: Application
    Filed: May 15, 2020
    Publication date: January 21, 2021
    Inventors: Mohammad Rostami, Soheil Kolouri, Praveen K. Pilly
  • Publication number: 20200264300
    Abstract: Described is a system for transferring learned knowledge from an electro-optical (EO) domain to a synthetic-aperture-radar (SAR) domain. The system uses a measured similarity between the EO domain and the SAR domain to train a model for classifying SAR images using knowledge previously learned from the electro-optical (EO) domain. Using the trained model, a SAR image is processed to determine regions of interest in the SAR image. A region of interest is classified to determine whether the region of interest corresponds to an object of interest, and classified regions of interest that contain the object of interest are output. The object of interest is displayed on a visualization map, and the visualization map is automatically updated to reflect a change in position of the object of interest.
    Type: Application
    Filed: January 24, 2020
    Publication date: August 20, 2020
    Inventors: Mohammad Rostami, Soheil Kolouri
  • Publication number: 20200151532
    Abstract: A product tagging system is provided. The product tagging system includes at least one RF backscatter transmitter configured to emit (i) a main carrier RF signal, and (ii) Radio Frequency (RF) signals on two frequencies whose summation forms a twin carrier RF signal. The product tagging system further includes a passive RF backscatter tag associated with a product and configured to reflect and frequency shift the main carrier RF signal to a different frequency using the twin carrier RF signal. The product tagging system also includes at least one RF backscatter receiver configured to read the product on the different frequency by detecting a distributed ambient backscatter signal generated by a reflection and frequency shifting of the main carrier RF signal by the passive RF backscatter tag.
    Type: Application
    Filed: January 15, 2020
    Publication date: May 14, 2020
    Inventors: Karthikeyan Sundaresan, Eugene Chai, Sampath Rangarajan, Mohammad Rostami
  • Publication number: 20200130177
    Abstract: A method for training a controller to control a robotic system includes: receiving a neural network of an original controller for the robotic system based on origin data samples from an origin domain and labels in a label space, the neural network including encoder and classifier parameters, the neural network being trained to: map an input data sample from the origin domain to a feature vector in a feature space using the encoder parameters; and assign a label of the label space to the input data sample using the feature vector based on the classifier parameters; updating the encoder parameters to minimize a dissimilarity, in the feature space, between: origin feature vectors computed from the origin data samples; and target feature vectors computed from target data samples from a target domain; and updating the controller with the updated encoder parameters to control the robotic system in the target domain.
    Type: Application
    Filed: August 5, 2019
    Publication date: April 30, 2020
    Inventors: Soheil Kolouri, Mohammad Rostami, Kyungnam Kim
  • Publication number: 20200125982
    Abstract: Described is a system for unsupervised domain adaptation in an autonomous learning agent. The system adapts a learned model with a set of unlabeled data from a target domain, resulting in an adapted model. The learned model was previously trained to perform a task using a set of labeled data from a source domain. The set of labeled data has a first input data distribution, and the set of unlabeled target data has a second input data distribution that is distinct from the first input data distribution. The adapted model is implemented in the autonomous learning agent, causing the autonomous learning agent to perform the task in the target domain.
    Type: Application
    Filed: December 18, 2019
    Publication date: April 23, 2020
    Inventors: Alexander J. Gabourie, Mohammad Rostami, Soheil Kolouri, Kyungnam Kim
  • Publication number: 20190025848
    Abstract: Described is a system for object recognition. The system generates a training image set of object images from multiple image classes. Using a training image set and annotated semantic attributes, a model is trained that maps visual features from known images to the annotated semantic attributes using joint sparse representations with respect to dictionaries of visual features and semantic attributes. The trained model is used for mapping visual features of an unseen input image to its semantic attributes. The unseen input image is classified as belonging to an image class, and a device is controlled based on the classification of the unseen input image.
    Type: Application
    Filed: July 12, 2018
    Publication date: January 24, 2019
    Inventors: Soheil Kolouri, Mohammad Rostami, Kyungnam Kim, Yuri Owechko