Apparatus and methods for controlling attention of a robot
First Claim
1. A method, comprising:
- receiving, from an imaging device associated with a robotic apparatus, an image signal including an object of interest represented in the image signal;
receiving, by the robotic apparatus from an external agent, a task indication related to the object of interest, the task indication representative of a task to be performed by the robotic apparatus with respect to the object of interest; and
responsive to receipt of the task indication;
storing, by the robotic apparatus, a task context, the task context comprising data pertaining to the task indication and being configured to cause the robotic apparatus to perform the task;
commencing, by the robotic apparatus, the task with respect to the object of interest; and
providing, by the robotic apparatus to the external agent, a confirmation signal that the robotic apparatus has commenced task execution.
5 Assignments
0 Petitions
Accused Products
Abstract
A method includes receiving, from an imaging device associated with a robotic apparatus, an image signal including an object of interest represented in the image signal; receiving, by the robotic apparatus from an external agent, a task indication related to the object of interest, the task indication representative of a task to be performed by the robotic apparatus with respect to the object of interest; and responsive to receipt of the task indication: detecting salient features of the object of interest within the image; storing, by the robotic apparatus, a task context, the task context comprising data pertaining to the salient features and data pertaining to the task indication; and commencing, by the robotic apparatus, the task with respect to the object of interest.
-
Citations
20 Claims
-
1. A method, comprising:
-
receiving, from an imaging device associated with a robotic apparatus, an image signal including an object of interest represented in the image signal; receiving, by the robotic apparatus from an external agent, a task indication related to the object of interest, the task indication representative of a task to be performed by the robotic apparatus with respect to the object of interest; and responsive to receipt of the task indication; storing, by the robotic apparatus, a task context, the task context comprising data pertaining to the task indication and being configured to cause the robotic apparatus to perform the task; commencing, by the robotic apparatus, the task with respect to the object of interest; and providing, by the robotic apparatus to the external agent, a confirmation signal that the robotic apparatus has commenced task execution. - View Dependent Claims (2, 3, 4)
-
-
5. A method, comprising:
-
receiving, from an imaging device associated with a robotic apparatus, an image signal including an object of interest represented in the image signal; receiving, by the robotic apparatus from an external agent, a task indication related to the object of interest, the task indication representative of a task to be performed by the robotic apparatus with respect to the object of interest; and responsive to receipt of the task indication; detecting salient features of the object of interest within the image signal; storing, by the robotic apparatus, a task context, the task context comprising data pertaining to the salient features and being configured to cause the robotic apparatus to perform the task; and commencing, by the robotic apparatus, the task with respect to the object of interest. - View Dependent Claims (6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16)
-
-
17. An interface apparatus for a robot operable in an environment, comprising:
-
an input interface that receives a sequence of images of the environment; and an input/output interface that receives a physical input executed by an external agent, wherein the physical input identifies a task to perform in reference to an object of interest present in the sequence of images of the environment, and wherein the physical input provides a specific robotic context configured to cause the robot to perform the task using previous training for the task over a plurality of different contexts. - View Dependent Claims (18, 19, 20)
-
Specification