GENERATING A MODEL FOR AN OBJECT ENCOUNTERED BY A ROBOT

Patent №

US 10,671,874

Granted

2020-06-02

Filed 2018

Owner

GOOGLE INC.

+1 more

AI components

6

ml · vision · speech · kr · planning · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16042877

Methods and apparatus related to generating a model for an object encountered by a robot in its environment, where the object is one that the robot is unable to recognize utilizing existing models associated with the robot. The model is generated based on vision sensor data that captures the object from multiple vantages and that is captured by a vision sensor associated with the robot, such as a vision sensor coupled to the robot. The model may be provided for use by the robot in detecting the object and/or for use in estimating the pose of the object.

Machine learningVisionSpeechKnowledge representationPlanningAI hardwareB25J 9/161B25J 9/1692G06T 7/344G06T 7/70G06T 7/75G06T 17/00G06V 20/10G05B 2219/33038+8 more

AI classification

Vision1.00
Machine learning1.00
Planning1.00
AI hardware0.96
Speech0.91
Knowledge representation0.78
Natural language0.20
Evolutionary computation0.03

Ownership

GOOGLE INC.

assignment · 464440789

X DEVELOPMENT LLC

assignment · 466200514

Assignors

KONOLIGE, KURT, RAJKUMAR, NARESHKUMAR, HINTERSTOISSER, STEFAN

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC