Patents by Inventor Ben EISNER

Ben EISNER 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).

  • Apparatus for Q-learning for continuous actions with cross-entropy guided policies and method thereof
    Patent number: 11710301
    Abstract: An apparatus for performing continuous actions includes a memory storing instructions, and a processor configured to execute the instructions to obtain a first action of an agent, based on a current state of the agent, using a cross-entropy guided policy (CGP) neural network, and control to perform the obtained first action. The CGP neural network is trained using a cross-entropy method (CEM) policy neural network for obtaining a second action of the agent based on an input state of the agent, and the CEM policy neural network is trained using a CEM and trained separately from the training of the CGP neural network.
    Type: Grant
    Filed: January 22, 2020
    Date of Patent: July 25, 2023
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Riley Simmons-Edler, Ben Eisner, Eric Mitchell, Daniel Dongyuel Lee, Sebastian Seung
  • Method and apparatus for estimating tool trajectories
    Patent number: 11170526
    Abstract: An apparatus for estimating a trajectory of a tool may include: a memory storing instructions; and a processor configured to execute the instructions to: receive a task to be performed by the tool on a target object; receive a grayscale image and a depth image of the target object; and estimate a tool trajectory for performing the task, from the grayscale image and the depth image, via a pixels-to-plans neural network that is trained based on a labeled tool trajectory that is generated from a point cloud model of the target object.
    Type: Grant
    Filed: December 23, 2019
    Date of Patent: November 9, 2021
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Tarik Tosun, Eric Mitchell, Ben Eisner, Jinwook Huh, Bhoram Lee, Daewon Lee, Volkan Isler, Sebastian Seung, Daniel Lee
  • METHOD AND APPARATUS FOR ESTIMATING TOOL TRAJECTORIES
    Publication number: 20200311969
    Abstract: An apparatus for estimating a trajectory of a tool may include: a memory storing instructions; and a processor configured to execute the instructions to: receive a task to be performed by the tool on a target object; receive a grayscale image and a depth image of the target object; and estimate a tool trajectory for performing the task, from the grayscale image and the depth image, via a pixels-to-plans neural network that is trained based on a labeled tool trajectory that is generated from a point cloud model of the target object.
    Type: Application
    Filed: December 23, 2019
    Publication date: October 1, 2020
    Applicant: Samsung Electronics Co., Ltd.
    Inventors: Tarik Tosun, Eric Mitchell, Ben Eisner, Jinwook Huh, Bhoram Lee, Daewon Lee, Volkan Isler, Sebastian Seung, Daniel Lee
  • APPARATUS FOR Q-LEARNING FOR CONTINUOUS ACTIONS WITH CROSS-ENTROPY GUIDED POLICIES AND METHOD THEREOF
    Publication number: 20200250493
    Abstract: An apparatus for performing continuous actions includes a memory storing instructions, and a processor configured to execute the instructions to obtain a first action of an agent, based on a current state of the agent, using a cross-entropy guided policy (CGP) neural network, and control to perform the obtained first action. The CGP neural network is trained using a cross-entropy method (CEM) policy neural network for obtaining a second action of the agent based on an input state of the agent, and the CEM policy neural network is trained using a CEM and trained separately from the training of the CGP neural network.
    Type: Application
    Filed: January 22, 2020
    Publication date: August 6, 2020
    Applicant: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Riley SIMMONS-EDLER, Ben EISNER, Eric MITCHELL, Daniel Dongyuel LEE, Sebastian SEUNG