Patents by Inventor Zhou Teng

Zhou Teng 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).

  • Distributed inference multi-models for industrial applications
    Patent number: 11491650
    Abstract: Robotic visualization systems and methods include running and analyzing perception algorithms and models for robotic visualization systems on multiple computing platforms to obtain a successful complete an object processing request.
    Type: Grant
    Filed: December 19, 2019
    Date of Patent: November 8, 2022
    Assignee: ABB Schweiz AG
    Inventors: Remus Boca, Zhou Teng, Thomas Fuhlbrigge, Magnus Wahlstrom, Johnny Holmberg
  • Method and system to generate a 3D model for a robot scene
    Patent number: 11407111
    Abstract: A robot is configured to perform a task on an object using a method for generating a 3D model sufficient to determine a collision free path and identify the object in an industrial scene. The method includes determining a predefined collision free path and scanning an industrial scene around the robot. Stored images of the industrial scene are retrieved from a memory and analyzed to construct a new 3D model. After an object is detected in the new 3D model, the robot can further scan the image in the industrial scene while moving along a collision free path until the object is identified at a predefined certainty level. The robot can then perform a robot task on the object.
    Type: Grant
    Filed: June 27, 2018
    Date of Patent: August 9, 2022
    Assignee: ABB Schweiz AG
    Inventors: Biao Zhang, Remus Boca, Carlos W. Morato, Carlos Martinez, Jianjun Wang, Zhou Teng, Jinmiao Huang, Magnus Wahlstrom, Johnny Holmberg
  • DISTRIBUTED INFERENCE MULTI-MODELS FOR INDUSTRIAL APPLICATIONS
    Publication number: 20200198129
    Abstract: Robotic visualization systems and methods include running and analyzing perception algorithms and models for robotic visualization systems on multiple computing platforms to obtain a successful complete an object processing request.
    Type: Application
    Filed: December 19, 2019
    Publication date: June 25, 2020
    Inventors: Remus Boca, Zhou Teng, Thomas Fuhlbrigge, Magnus Wahlstrom, Johnny Holmberg
  • SYSTEM AND METHOD FOR GUIDING A SENSOR AROUND AN UNKNOWN SCENE
    Publication number: 20200201268
    Abstract: A robotic system is provided to analyze sensor output data to generate and update a prediction model associated with a virtual scene in the workspace associated with the object.
    Type: Application
    Filed: December 19, 2019
    Publication date: June 25, 2020
    Inventors: Remus Boca, Zhou Teng, Thomas Fuhlbrigge
  • AUTOMATIC VISUAL DATA GENERATION FOR OBJECT TRAINING AND EVALUATION
    Publication number: 20200202178
    Abstract: A robotic system is provided to automatically generate and evaluate visual data used for training neural networks. The robotic system includes a first robotic cell for generating a first visual data set and a second robotic cell for generating a second visual data set for comparison to the first visual data set.
    Type: Application
    Filed: December 19, 2019
    Publication date: June 25, 2020
    Inventors: Remus Boca, Zhou Teng, Thomas Fuhlbrigge, Magnus Wahlstrom, Johnny Holmberg
  • METHOD AND SYSTEM TO GENERATE A 3D MODEL FOR A ROBOT SCENE
    Publication number: 20200001458
    Abstract: A robot is configured to perform a task on an object using a method for generating a 3D model sufficient to determine a collision free path and identify the object in an industrial scene. The method includes determining a predefined collision free path and scanning an industrial scene around the robot. Stored images of the industrial scene are retrieved from a memory and analyzed to construct a new 3D model. After an object is detected in the new 3D model, the robot can further scan the image in the industrial scene while moving along a collision free path until the object is identified at a predefined certainty level. The robot can then perform a robot task on the object.
    Type: Application
    Filed: June 27, 2018
    Publication date: January 2, 2020
    Inventors: Biao Zhang, Remus Boca, Carlos W. Morato, Carlos Martinez, Jianjun Wang, Zhou Teng, Jinmiao Huang, Magnus Wahlstrom, Johnny Holmberg