A method is provided. The method includes obtaining an enhanced state graph. The enhanced state graph represents a set of objects within an environment and a set of positions of the set of objects. The enhanced state graph includes a set of object nodes, a set of property nodes and a set of goal nodes to represent a set of objectives. The method also includes generating a set of instructions for a set of mechanical systems based on the enhanced state graph. The set of mechanical systems is configured to interact with one or more of the set of objects within the environment. The method further includes operating the set of mechanical systems to achieve the set of objectives based on the set of instructions.

Provided is a robot including a microphone configured to acquire a sound signal corresponding to a sound generated near the robot, a camera, an output interface including at least one of a display configured to output a wake-up screen or a speaker configured to output a wake-up sound when the robot wakes up, and a processor configured to recognize whether the acquired sound includes a voice of a person, activate the camera when the sound includes a voice of a person, recognize whether a person is present in an image acquired by the activated camera, set a wake-up word recognition sensitivity based on a recognition result as to whether a person is present, and recognize whether a wake-up word is included voice data of a user acquired through the microphone based on the set wake-up word recognition sensitivity.

In an embodiment, a method includes determining a given material to manipulate to achieve a goal state. The goal state can be one or more deformable or granular materials in a particular arrangement. The method further includes, for the given material, determining, a respective outcome for each of a plurality of candidate actions to manipulate the given material. The determining can be performed with a physics-based model, in one embodiment. The method further can include determining a given action of the candidate actions, where the outcome of the given action reaching the goal state is within at least one tolerance. The method further includes, based on a selected action of the given actions, generating a first motion plan for the selected action.

A system, method and computer-readable storage devices are for processing natural language commands, such as commands to a robotic arm, using a Tag & Parse approach to semantic parsing. The system first assigns semantic tags to each word in a sentence and then parses the tag sequence into a semantic tree. The system can use statistical approach for tagging, parsing, and reference resolution. Each stage can produce multiple hypotheses, which are re-ranked using spatial validation. Then the system selects a most likely hypothesis after spatial validation, and generates or outputs a command. In the case of a robotic arm, the command is output in Robot Control Language (RCL).

An information processor including: an operation control unit that controls a motion of an autonomous mobile body acting on the basis of recognition processing, in a case where a target sound that is a target voice for voice recognition processing is detected, the operation control unit moving the autonomous mobile body to a position, around an approach target, where an input level of a non-target sound that is not the target voice becomes lower, the approach target being determined on the basis of the target sound.

Proposed is a method for determining, by a movable robot, a position of a speaker, wherein the movable robot includes first to fourth microphones installed at four vertexes of a quadrangle of a horizontal cross section of the robot respectively, wherein the method includes: receiving a wake-up voice through first and third microphones disposed respectively at first and third vertices in a diagonal direction; obtaining a first reference value of the first microphone and a second reference value of the third microphone based on the received wake-up voice; comparing the obtained first and second reference values to select the first microphone; selecting a second microphone disposed at a second vertex, wherein the first and second microphones are on a front side of the quadrangle; calculating a sound source localization (SSL) value based on the selected first and second microphones; and tracking a position of the speaker based on the SSL value.

A robot is provided. The robot includes a microphone, a camera, a communication interface including a circuit, a memory storing at least one instruction, and a processor, wherein the processor is configured to acquire a user voice through the microphone, identify a task corresponding to the user voice, determine whether the robot can perform the identified task, and control the communication interface to transmit information on the identified task to an external robot based on the determination result.

Disclosed is a moving robot including: a voice input unit configured to receive a voice input of a user; a first display capable of receiving a touch input; a second display larger than the first display; and a controller configured to perform control such that a screen to be displayed in response to the voice input or the touch input is displayed on at least one of the first display or the second display based on a type and an amount of information included in the screen, and accordingly, it is possible to provide information and services more effectively using the two displays.

A machine learning method includes: a first learning step which is performed in a phase before a neural network is installed in a mobile robot and in which a stationary first obstacle is placed in a set space and the first obstacle is placed at different positions using simulation so that the neural network repeatedly learns a path from a starting point to the destination which avoids the first obstacle; and a second learning step which is performed in a phase after the neural network is installed in the mobile robot and in which, when the mobile robot recognizes a second obstacle that operates around the mobile robot in a space where the mobile robot moves, the neural network repeatedly learns a path to the destination which avoids the second obstacle every time the mobile robot recognizes the second obstacle.

An interview robot that is used in the field of human resources (HR), having a camera, a microphone, an odor sensor, a speaker and touch sensors enabling communication with the interviewed candidate, a utility function determination memory, which addresses the questions to the candidate so as to determine the parameters of the utility functions for the economic, social and environmental attributes of the candidate being interviewed, and stores the utility function parameters calculated with the answers received, the nonlinear assignment program solution memory with uncertain utility functions that performs the best (optimal) job-personnel matching under different scenarios by simultaneously taking into account the situation in which employee satisfaction from the utility function determination memory varies in a mostly non-linear way in parallel with the economic, social and environmental characteristics of the candidate, and the uncertainties that may occur in employee satisfaction.