Visual Interface And Communications Techniques For Use With Robots
AssigneeSanctuary Cognitive Systems Corporation
InventorsSuzanne Gildert, Rodrigo Furlan
Life of this patent
Estimating the term…
Abstract
A humanoid robot may include one or two eye resembling features in the form of image sensor(s) that capture images of at least a portion of an environment. The fields-of-view of the image sensor(s) will change as a pose (i.e., position, orientation, position and orientation) of the head, torso, or even entire humanoid robot changes. Virtual or augmented representations of the environment may be presented to a human pilot of the robot, where disorienting feeling due to latency in communications can be alleviated by reducing demand on communications channels.
Claims18
A method of operation in a processor-based system to predict physical movement in an environment in which a robot operates, the environment including one or more objects, the method comprising:
- generating a first digital representation of at least a portion of the environment in which the robot operates, the first digital representation including, for each of the one or more objects, a respective three dimensional spatial representation of the object and at least one non-spatial physical characteristic of the object;
- performing a virtual physics simulation on the first digital representation of the at least portion of the environment in which the robot operates;
- and
- for at least one of the one or more objects, predicting at least one of a movement of the respective object or a collision of the respective object with another one of the objects based on the virtual physics simulation.
A method of operation in a processor-based system to predict and drive a robot, the method comprising:
- simulating several instances of a digital representation of the robot with respective sets of movements of at least some of a number of joints or a number of actuators of the robot, the sets of movements differing from one another;
- and
- selecting one of the sets of movements that results in achievement of a goal state of the robot.
A method of operation in a processor-based system to implement a visual interface with a robot, the method comprising:
- generating a sequence of digital representations of at least a portion of an environment in which the robot operates from at least one set of image information that represents at least one view of at least the portion of the environment in which the robot operates at sequential times, the at least one view corresponding to a field-of-view encompassed by at least one image sensor that is coupled to or a part of the robot;
- and
- for at least one subsequent digital representation in the sequence of digital representations, generating at least one update digital representation, the update digital representation which represents a subset of information from at least one previous digital representation in the sequence, the subset of information representative of changes that occurred in the environment between the respective previous and the respective subsequent digital representations.
Dependencies are inferred from the claim text.