US 11,839,986 B2 · Systems and methods for active perception and coordination between robotic vision systems and manipulators

Abstract

The present disclosure generally relates to a robotic control system and method that utilizes active perception to gather the relevant information related to a robot, a robotic environment, and objects within the environment, and allows the robot to focus computational resources where needed, such as for manipulating an object. The present disclosure also enables viewing and analyzing objects from different distances and viewpoints, providing a rich visual experience from which the robot can learn abstract representations of the environment. Inspired by the primate visual-motor system, the present disclosure leverages the benefits of active perception to accomplish manipulation tasks using human-like hand-eye coordination.

Claims21

Dependent claims

A robotic control system that utilizes active coordination to track an object, comprising:

a robot having an end-effector;
an imaging device configured to track a region of interest on the object;
and
one or more processors communicatively coupled to the robot and the imaging device,
wherein the one or more processors are configured to collectively analyze operational data received from the robot and video data received from the imaging device,
wherein the one or more processors are configured to collectively:
generate imaging device commands to adjust the imaging device based on the analyzed operational data and video data;
and
generate robot commands to adjust the robot, so that the region of interest continues to be tracked as the robot manipulates the object.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application

17/078,981Filed 23 Oct 2020 · us provisional application

Priority

25 Oct 2019

Published

US 2021/0122053 A129 Apr 2021

Granted

12 Dec 2023

Term ends

Not estimatedThe source records don’t support an estimate.

Classification33 codes

B25J 9/1697
Characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor…:…
G06T 7/246
Analysis of motion: using feature-based methods, e.g. the tracking of corners or segments
B25J 9/163
Characterised by the control loop: learning, adaptive, model based, rule based expert control
B25J 9/1669
Characterised by programming, planning systems for manipulators: characterised by special application, e.g. multi-arm co-operation, assembly, grasping

Systems and methods for active perception and coordination between robotic vision systems and manipulators

Life of this patent

Systems and methods for active perception and coordination between robotic vision systems and manipulators

Life of this patent

Abstract

Claims21