US 12,427,674 B2 · Task-oriented 3D reconstruction for autonomous robotic operations

Abstract

Autonomous operations, such as robotic grasping and manipulation, in unknown or dynamic environments present various technical challenges. For example, three-dimensional (3D) reconstruction of a given object often focuses on the geometry of the object without considering how the 3D model of the object is used in solving or performing a robot operation task. As described herein, in accordance with various embodiments, models are generated of objects and/or physical environments based on tasks that autonomous machines perform with the objects or within the physical environments. Thus, in some cases, a given object or environment may be modeled differently depending on the task that is performed using the model. Further, portions of an object or environment may be modeled with varying resolutions depending on the task associated with the model.

Claims20

Dependent claims

A method for operating an autonomous machine in a physical environment, the method comprising:

detecting an object within the physical environment, the object defining a plurality of regions;
identifying a task that requires that the autonomous machine interact with the object;
determining a select region of the plurality of regions of the object that is associated with the task;
capturing images of the object by sampling camera poses based on requirements of the task, the images defining different views of the object such that the different views of the object are based on the task;
and
based on the different views of the object, generating an object model of the object,
wherein the object model defines a greater resolution of the select region as compared to the other regions of the plurality of regions.

4 more elements

An autonomous system, the autonomous system comprising:

an autonomous machine configured to operate in a physical environment;
a processor;
and
a memory storing instructions that, when executed by the processor, cause the autonomous system to:
detect an object within the physical environment, the object defining a plurality of regions;
identify a task that requires that the autonomous machine interact with the object;
determine a select region of the plurality of regions of the object that is associated with the task;
capture images of the object by sampling camera poses based on requirements of the task, the images defining different views of the object such that the different views of the object are based on the task;
and
based on the different views of the object, generating an object model of the object,
wherein the object model defines a greater resolution of the select region as compared to the other regions of the plurality of regions.

8 more elements

Dependencies are inferred from the claim text.

Task-oriented 3D reconstruction for autonomous robotic operations

Life of this patent

Task-oriented 3D reconstruction for autonomous robotic operations

Life of this patent

Abstract

Claims20