A method includes enabling a robot to learn a mapping between English language commands and Linear Temporal Logic (LTL) expressions, wherein neural sequence-to-sequence learning models are employed to infer a LTL sequence corresponding to a given natural language command.

This disclosure relates generally to human-robot interaction (HRI) to enable a robot to execute tasks that are conveyed in a natural language. The state-of-the-art is unable to capture human intent, implicit assumptions and ambiguities present in the natural language to enable effective robotic task identification. The present disclosure provides accurate task identification using classifiers trained to understand linguistic and semantic variations. A mixed-initiative dialogue is employed to resolve ambiguities and address the dynamic nature of a typical conversation. In accordance with the present disclosure, the dialogues are minimal and directed to the goal to ensure human experience is not degraded. The method of the present disclosure is also implemented in a context sensitive manner to make the task identification effective.

A first robot may include: a communication circuit configured to transmit and receive a signal; a sensor configured to detect a surrounding environment; a driving device configured to implement movement of the first robot; and a processor configured to control the first robot. The processor may determine a second voice recognition range of a second robot on the basis of a confirmation signal transmitted from the second robot. When a user is positioned outside the determined second voice recognition range, the processor may control the driving device so that the first robot follows the user.

A new technology of prediction of manipulability in response even to an instruction with missing information in an object manipulation task to have a robot manipulate some kind of object is provided. An instruction understanding system includes an obtaining engine configured to obtain a linguistic expression of a name of an object to be manipulated and a linguistic expression of a situation where the object corresponding to the name is placed in a real environment and a classifier configured to receive input of the linguistic expression of the name and the linguistic expression of the situation and output manipulability of the object corresponding to the name in the real environment.

A machine learning device for learning a motion of a robot engaged in a task performed by a human and a robot in cooperation with each other, including a state observation unit that observes a state variable indicating a state of the robot when the human and the robot cooperate with each other and perform a task; a reward calculation unit that calculates a reward based on control data and the state variable for controlling the robot and on an action of the human; and a value function update unit that updates an action value function for controlling a motion of the robot, based on the reward and the state variable.

A method includes enabling a robot to learn a mapping between English language commands and Linear Temporal Logic (LTL) expressions, wherein neural sequence-to-sequence learning models are employed to infer a LTL sequence corresponding to a given natural language command.

A new technology of prediction of manipulability in response even to an instruction with missing information in an object manipulation task to have a robot manipulate some kind of object is provided. An instruction understanding system includes an obtaining engine configured to obtain a linguistic expression of a name of an object to be manipulated and a linguistic expression of a situation where the object corresponding to the name is placed in a real environment and a classifier configured to receive input of the linguistic expression of the name and the linguistic expression of the situation and output manipulability of the object corresponding to the name in the real environment.

Disclosed is a method for synchronizing visual information and auditory information characterized by extracting visual information included in video, recognizing auditory information in a first language that is included in a speech in the first language, associating the visual information with the auditory information in the first language, translating the auditory information in the first language to auditory information in a second language, and editing at least one of the visual information with the auditory information in the second language so as to associate the visual information and the auditory information in the second language with each other.

Example implementations include a method, apparatus, and computer-readable medium comprising determining, by a processor of a control panel, that a security event has happened; and capturing still images or videos by a camera in the control panel subsequent to determining that the security event has happened. In some implementations, the camera is a forward-facing camera. In some implementations, determining that the security event has happened comprises detecting a motion using the camera in the control panel. In some implementations, determining that the security event has happened comprises receiving a signal indicative of activation of a door switch of a door located next to the control panel. In some implementations, the security event is associated with one or more Bluetooth devices being in range, and determining that the security event has happened comprises using a Bluetooth radio in the control panel to detect the Bluetooth devices.

A machine learning device for learning a motion of a robot engaged in a task performed by a human and a robot in cooperation with each other, including a state observation unit that observes a state variable indicating a state of the robot when the human and the robot cooperate with each other and perform a task; a reward calculation unit that calculates a reward based on control data and the state variable for controlling the robot and on an action of the human; and a value function update unit that updates an action value function for controlling a motion of the robot, based on the reward and the state variable.