Efficient transferring of human experiences to robots and other autonomous machines
AssigneeIntel Corporation
InventorsLiwei Ma, Jiqiang Song, Hong Zhang
Life of this patent
Estimating the term…
Abstract
A mechanism is described for facilitating transferring of human experiences to autonomous machines. A method of embodiments, as described herein, includes facilitating sensing, by one or more sensors, one or more inputs relating to a user, and evaluating the one or more inputs to capture one or more behavior traits of the user. The method may further include training a neural network model based on the one or more behavior traits, and applying the trained neural network model to a computing device to facilitate the computing device to adopt the one or more behavior traits to behave as the user.
Claims24
An apparatus to facilitate transferring of human experiences to autonomous machines, the apparatus comprising:
- one or more sensors to sense one or more inputs relating to a user;
- behavior capture/evaluation logic to evaluate the one or more inputs to capture one or more behavior traits of the user;
- learning/training logic to train a neural network model based on the one or more behavior traits;
- and
- transfer/execution logic to apply the trained neural network model to the apparatus to facilitate the apparatus to adopt the one or more behavior traits to behave as the user.
A method for facilitating transferring of human experiences to autonomous machines, the method comprising:
- sensing, by one or more sensors, one or more inputs relating to a user;
- evaluating the one or more inputs to capture one or more behavior traits of the user;
- training a neural network model based on the one or more behavior traits;
- and
- applying the trained neural network model to a computing device to facilitate the computing device to adopt the one or more behavior traits to behave as the user.
At least one machine-readable medium comprising a plurality of instructions, when executed on a computing device, to implement or perform a method comprising:
- sensing, by one or more sensors, one or more inputs relating to a user;
- evaluating the one or more inputs to capture one or more behavior traits of the user;
- training a neural network model based on the one or more behavior traits;
- and
- applying the trained neural network model to a computing device to facilitate the computing device to adopt the one or more behavior traits to behave as the user.
(canceled)
(canceled)
(canceled)
(canceled)
Dependencies are inferred from the claim text.