公开(公告)号：US20230247015A1

公开(公告)日：2023-08-03

申请号：US18191599

申请日：2023-03-28

Applicant: X Development LLC

Inventor： Guy Satat ,  Michael Quinlan

IPC: H04L9/40 ,  H04L9/32 ,  H04L9/00 ,  H04L9/30

CPC classification number: H04L63/0807 ,  H04L9/3236 ,  H04L9/006 ,  H04L63/083 ,  H04L63/0876 ,  H04L9/3073 ,  H04L9/3247 ,  H04L9/3263 ,  H04L63/0861 ,  H04L9/321 ,  H04L63/0823 ,  H04L63/0884 ,  H04L63/102 ,  H04L9/3268 ,  H04L9/50

Abstract: A method includes receiving sensor data from a plurality of robot sensors on a robot. The method includes generating a depth map that includes a plurality of pixel depths. The method includes determining, for each respective pixel depth, based on the at least one robot sensor associated with the respective pixel depth, a pixelwise confidence level indicative of a likelihood that the respective pixel depth accurately represents a distance between the robot and a feature of the environment. The method includes generating a pixelwise filterable depth map for a control system of the robot. The pixelwise filterable depth map is filterable to produce a robot operation specific depth map. The robot operation specific depth map is determined based on a comparison of each respective pixelwise confidence level with a confidence threshold corresponding to at least one operation of the robot controlled by the control system of the robot.

公开(公告)号：US11440196B1

公开(公告)日：2022-09-13

申请号：US16717896

申请日：2019-12-17

Applicant: X Development LLC

Inventor： Sean Kirmani ,  Guy Satat ,  Michael Quinlan

IPC: B25J9/16 ,  G06N3/04 ,  G06T7/70 ,  G06N20/20 ,  G06T7/277

Abstract: A method includes receiving sensor data representing a first object in an environment and generating, based on the sensor data, a first state vector that represents physical properties of the first object. The method also includes generating, by a first machine learning model and based on the first state vector and a second state vector that represents physical properties of a second object previously observed in the environment, a metric indicating a likelihood that the first object is the same as the second object. The method further includes determining, based on the metric, to update the second state vector and updating, by a second machine learning model configured to maintain the second state vector over time and based on the first state vector, the second state vector to incorporate into the second state vector information concerning physical properties of the second object as represented in the first state vector.