Patents by Inventor Atil Iscen

Atil Iscen 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).

  • Systems and methods for learning agile locomotion for multiped robots
    Patent number: 12172309
    Abstract: Training and/or using a machine learning model for locomotion control of a robot, where the model is decoupled. In many implementations, the model is decoupled into an open loop component and a feedback component, where a user can provide a desired reference trajectory (e.g., a symmetric sine curve) as input for the open loop component. In additional and/or alternative implementations, the model is decoupled into a pattern generator component and a feedback component, where a user can provide controlled parameter(s) as input for the pattern generator component to generate pattern generator phase data (e.g., an asymmetric sine curve). The neural network model can be used to generate robot control parameters.
    Type: Grant
    Filed: April 22, 2019
    Date of Patent: December 24, 2024
    Assignee: GOOGLE LLC
    Inventors: Jie Tan, Tingnan Zhang, Atil Iscen, Erwin Coumans, Yunfei Bai
  • Determining control policies for robots with noise-tolerant structured exploration
    Patent number: 11697205
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for optimizing the determination of control policies for robots through the performance of simulations of robots and real-world context to determine control policy parameters.
    Type: Grant
    Filed: September 21, 2018
    Date of Patent: July 11, 2023
    Assignee: Google LLC
    Inventors: Vikas Sindhwani, Atil Iscen, Krzysztof Marcin Choromanski
  • SYSTEMS AND METHODS FOR LEARNING AGILE LOCOMOTION FOR MULTIPED ROBOTS
    Publication number: 20210162589
    Abstract: Training and/or using a machine learning model for locomotion control of a robot, where the model is decoupled. In many implementations, the model is decoupled into an open loop component and a feedback component, where a user can provide a desired reference trajectory (e.g., a symmetric sine curve) as input for the open loop component. In additional and/or alternative implementations, the model is decoupled into a pattern generator component and a feedback component, where a user can provide controlled parameter(s) as input for the pattern generator component to generate pattern generator phase data (e.g., an asymmetric sine curve). The neural network model can be used to generate robot control parameters.
    Type: Application
    Filed: April 22, 2019
    Publication date: June 3, 2021
    Inventors: Jie Tan, Tingnan Zhang, Atil Iscen, Erwin Coumans, Yunfei Bai
  • DETERMINING CONTROL POLICIES FOR ROBOTS WITH NOISE-TOLERANT STRUCTURED EXPLORATION
    Publication number: 20200276704
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for optimizing the determination of control policies for robots through the performance of simulations of robots and real-world context to determine control policy parameters.
    Type: Application
    Filed: September 21, 2018
    Publication date: September 3, 2020
    Inventors: Vikas Sindhwani, Atil Iscen, Krzysztof Marcin Choromanski