Thang C To, 53Springfield, VA
Thang To Phones & Addresses
Springfield, VA
Woodbridge, VA
Falls Church, VA
Alexandria, VA
Des Moines, WA
Mentions for Thang C To
Publications & IP owners
Us Patents
Robotic Control System
US Patent:
2020006, Feb 27, 2020
Filed:
Aug 23, 2019
Appl. No.:
16/549831
Inventors:
- Santa Clara CA, US
Jonathan Tremblay - Redmond WA, US
Thang Hong To - Redmond WA, US
Jia Cheng - Monroe WA, US
Erik Leitch - Bishop CA, US
Duncan J. McKay - Woodinville WA, US
Stanley Thomas Birchfield - Sammamish WA, US
Jonathan Tremblay - Redmond WA, US
Thang Hong To - Redmond WA, US
Jia Cheng - Monroe WA, US
Erik Leitch - Bishop CA, US
Duncan J. McKay - Woodinville WA, US
Stanley Thomas Birchfield - Sammamish WA, US
International Classification:
B25J 9/16
G06T 7/73
G06N 3/08
G06T 7/73
G06N 3/08
Abstract:
In at least one embodiment, under the control of a robotic control system, a gripper on a robot is positioned to grasp a 3-dimensional object. In at least one embodiment, the relative position of the object and the gripper is determined, at least in part, by using a camera mounted on the gripper.
Detecting And Estimating The Pose Of An Object Using A Neural Network Model
US Patent:
2019035, Nov 21, 2019
Filed:
May 7, 2019
Appl. No.:
16/405662
Inventors:
- Santa Clara CA, US
Thang Hong To - Redmond WA, US
Stanley Thomas Birchfield - Sammamish WA, US
Thang Hong To - Redmond WA, US
Stanley Thomas Birchfield - Sammamish WA, US
International Classification:
G06T 7/73
G06N 3/08
G06N 3/08
Abstract:
An object detection neural network receives an input image including an object and generates belief maps for vertices of a bounding volume that encloses the object. The belief maps are used, along with three-dimensional (3D) coordinates defining the bounding volume, to compute the pose of the object in 3D space during post-processing. When multiple objects are present in the image, the object detection neural network may also generate vector fields for the vertices. A vector field comprises vectors pointing from the vertex to a centroid of the object enclosed by the bounding volume defined by the vertex. The object detection neural network may be trained using images of computer-generated objects rendered in 3D scenes (e.g., photorealistic synthetic data). Automatically labelled training datasets may be easily constructed using the photorealistic synthetic data. The object detection neural network may be trained for object detection using only the photorealistic synthetic data.
Learning Robotic Tasks Using One Or More Neural Networks
US Patent:
2019022, Jul 25, 2019
Filed:
Jan 23, 2019
Appl. No.:
16/255038
Inventors:
- Santa Clara CA, US
Stan Birchfield - Sammamish WA, US
Stephen Tyree - University City MO, US
Thang To - Redmond WA, US
Jan Kautz - Lexington MA, US
Artem Molchanov - Bellevue WA, US
Stan Birchfield - Sammamish WA, US
Stephen Tyree - University City MO, US
Thang To - Redmond WA, US
Jan Kautz - Lexington MA, US
Artem Molchanov - Bellevue WA, US
International Classification:
G06T 1/00
G06T 7/73
B25J 9/16
G06T 7/73
B25J 9/16
Abstract:
Various embodiments enable a robot, or other autonomous or semi-autonomous device or system, to receive data involving the performance of a task in the physical world. The data can be provided as input to a perception network to infer a set of percepts about the task, which can correspond to relationships between objects observed during the performance. The percepts can be provided as input to a plan generation network, which can infer a set of actions as part of a plan. Each action can correspond to one of the observed relationships. The plan can be reviewed and any corrections made, either manually or through another demonstration of the task. Once the plan is verified as correct, the plan (and any related data) can be provided as input to an execution network that can infer instructions to cause the robot, and/or another robot, to perform the task.
Possible Relatives
NOTICE: You may not use BackgroundCheck or the information it provides to make decisions about employment, credit, housing or any other purpose that would require Fair Credit Reporting Act (FCRA) compliance. BackgroundCheck is not a Consumer Reporting Agency (CRA) as defined by the FCRA and does not provide consumer reports.