Implementations process, using a large language model, a free-form natural language (NL) instruction to generate to generate LLM output. Those implementations generate, based on the LLM output and a NL skill description of a robotic skill, a task-grounding measure that reflects a probability of the skill description in the probability distribution of the LLM output. Those implementations further generate, based on the robotic skill and current environmental state data, a world-grounding measure that reflects a probability of the robotic skill being successful based on the current environmental state data. Those implementations further determine, based on both the task-grounding measure and the world-grounding measure, whether to implement the robotic skill.

A controlling method of a cleaning robot is provided. The controlling method includes obtaining lidar data while a lidar sensor rotates multiple times, calculating a reference value which is the average value of distances from a subject according to angles, based on the obtained lidar data, after the reference value is calculated, comparing the obtained lidar data with the reference value, sensing a motion of an object based on a comparison result, and determining that the object is located in a rotation section where the motion has been detected.

Robots, including robot arms, can interface with other modules to affect the world surrounding the robot. However, designing modules from scratch when human analogues exist is not efficient. In an embodiment, a mechanical tool, converted from human use, to be used by robots includes a monolithic adaptor having two interface components. The two interface components include a first interface component cabal be of mating with an actuated mechanism on the robot side, the second interface capable of clamping to an existing utensil. In such a way, utensils that are intended for humans can be adapted for robots and robotic arms.

A robot includes a microphone configured to receive sound signals, and one or more controllers configured to determine a reference sound pressure level of background noise based on a sound signal received at a first time point via the microphone, detect occurrence of a sound event based on the reference sound pressure level and a sound pressure level of a sound signal received at a second time point via the microphone, recognize an event corresponding to the detected sound event, and control an operation of the robot based on the recognized event.

The disclosure generally relates to methods and systems for enabling human robot interaction by cognition sharing which includes gesture and audio. Conventional techniques that use the gestures and the speech, require extra hardware setup and are limited to navigation in structured outdoor driving environments. The present disclosure herein provides methods and systems that solves the technical problem of enabling the human robot interaction with a two-step approach by transferring the cognitive load from the human to the robot. An accurate shared perspective associated with the task is determined in the first step by computing relative frame transformations based on understanding of navigational gestures of the subject. Then, the shared perspective transformed to the robot in the field view of the robot. The transformed shared perspective is then given to a language grounding technique in the second step, to accurately determine a final goal associated with the task.

A method and apparatus for controlling a social robot includes operating an electronic output device based on social interactions between the social robot and a user. The social robot utilizes an algorithm or other logical solution process to infer a user mental state, for example a mood or desire, based on observation of the social interaction. Based on the inferred mental state, the social robot causes an action of the electronic output device to be selected. Actions may include, for example, playing a selected video clip, brewing a cup of coffee, or adjusting window blinds.

A robot is equipped with a processor. The processor detects external appearance or audio of a living being, and by controlling the robot, causes the robot to execute an operation in accordance with liking data indicating preferences of the robot regarding external appearance or audio and the detected external appearance or audio of the living being.

A robot includes a driver; a camera; and a processor configured to: during an interaction session in which a first user identified in an image obtained through the camera is set as an interaction subject, perform an operation corresponding to a user command received from the first user, and determine whether interruption by a second user identified in an image obtained through the camera occurs, and based on determining that the interruption by the second user occurred, control the driver such that the robot performs a feedback motion for the interruption.

A robot obtains image data representative of an environment comprising a first region and a second region. A microphone receives sound from the environment. The robot determines, using the image data and audio data derived based on the received sound, whether the sound is received from the first region, and outputs a control signal for controlling the robot based on the audio data. Sounds received from the first region are processed as voice commands on the basis that one of the first region and the second region comprises a predetermined type of inanimate object. Sounds received from the second region are processed in a different manner.

An artificial intelligence robot for providing a voice recognition service includes a memory configured to store voice identification information, a microphone configured to receive a voice command; and a processor configured to extract voice identification information from a wake-up command included in the voice command and used to activate the voice recognition service and operate the voice recognition function in a deactivation state when the extracted voice identification information does not match the voice identification information stored in the memory.