Abstract: An artificial intelligence server for determining a route of a robot includes a communication unit and a processor. The communication unit is configured to receive image data for a control area from the robot or a camera installed inside the control area. The processor is configured to calculate a current density for the control area from the image data, calculate a future density for the control area using the calculated current density, determine a priority for each of group areas included in the control area based on the calculated future density, and determine the route of the robot based on the determined priority.

Abstract: A treadmill may include two separate left and right belts rotating around two sets of rollers, four legs having an adjustable height via air suspension to customize an inclination of the treadmill, a thermoelectric assembly, a fragrance assembly having a rotating fragrance cartridge to emit various smells toward a user of the treadmill, a display on which exercise programs are played, and an attachment module having a dispensing tray on which treats are dispensed. A handle of the treadmill may have a sensor to sense a height and front-rear position, and a belt divider provided between the left and right belts may have position or proximity sensors to sense a left-right position. An inclination of the treadmill may be automatically adjusted according to positions detected by the sensors, and the fragrance assembly, attachment module, and inclination may be automatically operated in accordance with an exercise program played on the display.

Abstract: A stirrer includes a stirring shaft; a plurality of mixing wings extending from the lower end of the stirring shaft and spaced from each other around the stirring shaft; and a conical hub connecting the lower ends of the mixing wings.

Abstract: Disclosed is a method and apparatus for inspecting defects in a washer based on deep learning. According to an embodiment of the present disclosure, a method for inspecting defects in a washer based on deep learning gathers learning data while the washer operates and trains a first ANN model for diagnosing the condition of the washer and a second ANN model for securing the reliability of the result of inspection of the condition of the washer. Thereafter, the washer may make a diagnosis of whether the washer is defective based on the two pre-trained ANN models and are thereby able to continuously monitor whether the washer has an abnormal condition. According to an embodiment, the artificial intelligence (AI) module may be related to unmanned aerial vehicles (UAVs), robots, augmented reality (AR) devices, virtual reality (VR) devices, and 5G service-related devices.

Abstract: An image decoding method according to the present document comprises the steps of: acquiring prediction-related information and residual-related information for a current block; deriving transform coefficients for the current block on the basis of the residual-related information; and generating residual samples of the current block on the basis of the transform coefficients, wherein the residual-related information includes low-frequency non-separable transform (LFNST) index information indicating information relating to non-separable transform for a low-frequency transform coefficient of the current block on the basis of a matrix-based intra prediction (MIP) flag.

Abstract: A method for receiving a PTRS by a user equipment (UE) in a wireless communication system may comprise the steps of: receiving first information for configuring one or more bandwidth parts (BWPs); receiving second information including threshold value information relating to a frequency density of a PTRS; receiving downlink control information (DCI), wherein the DCI includes a first field indicating an activated BWP among the one or more BWPs configured on the basis of the first information, and a second field related to a transmission configuration indication (TCI) state; and receiving the PTRS in the activated BWP, wherein the frequency density of the PTRS is determined by the number of resource blocks associated with each TCI state.

Abstract: Provided is a movable robot. The movable robot includes a main body provided with a traveling part; at least one through-hole defined in a top surface of the main body, at least one module guide configured to guide an installation position of a service disposed above the main body, and guide supporter rotatably supporting the module guide inside main body. The module guide may rotate between a first position within the main body and a position protruding upward from the main body through the through-hole.

Abstract: An artificial intelligence device is disclosed. In an embodiment, the artificial intelligence device includes a sensor configured to acquire an output value according to control of a control system, and an artificial intelligence unit comprising one or more processors configured to obtain one or more updated parameters of a control function of the control system based on the output value using reinforcement learning, and update the control function for providing a control value to the control system with the one or more updated parameters.

Abstract: A robot cleaner includes a main body, and a wheel unit including a wheel configured to movably support the main body. The wheel unit is installed in a suspension unit and configured to be movable upward or downward. The suspension unit is configured to absorb impact when the wheel unit moves upward or downward, and is installed in a lifting unit coupled to the main body. The suspension unit is configured to be raised or lowered relative to the lifting unit. The lifting unit includes a lifting drive motor including a rotatable shaft disposed in parallel with a direction in which the suspension unit is configured to be raised or lowered, and a transmission unit configured to transmit a rotation force of the lifting drive motor to the suspension unit.

Abstract: Disclosed is a gripper including a pair of main bodies each having an internal space and spaced apart from each other, a pair of openings provided at ends of the pair of main bodies, a pair of moving bodies protruding from the ends of the pair of main bodies through the openings, a pair of inner bodies fixed in the internal space of the pair of main bodies, and a pair of springs configured to be compressed between the inner body and the moving body.

Abstract: A method by which a terminal transmits data in an unlicensed band, and an apparatus using the method are provided. The method comprises: transmitting data to a base station through a physical uplink shared channel (PUSCH) in the unlicensed band; and receiving, from the base station, acknowledgement/negative acknowledgement (ACK/NACK) information about the data in the unlicensed band, wherein the terminal receives, from the base station, timeline information notifying of a time relationship between the PUSCH transmission time point and the ACK/NACK information reception time point.

Abstract: The picture decoding method by a decoding device, according to one embodiment of the present invention, comprises the steps of: deriving a motion vector for a neighboring merge candidate block from among neighboring merge candidate blocks of a current block, if a merge mode is applied to the current block, deriving a reference block in a reference picture indicated by the motion vector for the neighboring merge candidate block, deriving a refinement block having the minimal SAD with the current block, from among refinement candidate blocks within the search range of the reference block, if DMVR is applied to the current block, deriving prediction samples for the current block on the basis of a refinement motion vector for the derived refinement block, and generating restoration samples for the current block on the basis of the prediction samples.

Abstract: A robot can include a cart to receive one or more objects; a camera sensor to photograph a periphery of the robot and capture an image of a user of the robot; a handle assembly coupled to the cart; a moving part to move the robot; a force sensor to sense a force applied to the handle assembly; and a controller configured to generate physical characteristics information on physical characteristics of the user of the robot based on the image of the user, and adjust at least one of a moving direction of the robot, a moving speed of the moving part and a value of torque applied to a motor of the moving part, based on the physical characteristics information and a magnitude of the force applied to the handle assembly sensed by the force sensor.

Abstract: An air-quality detection apparatus is disclosed. The air-quality detection apparatus includes a casing body including a bottom and a side wall extending upwards from the circumference of the bottom, a first printed circuit board (PCB) disposed horizontally above the bottom, a temperature/humidity sensor mounted on the bottom surface of the first PCB, a second PCB disposed horizontally above the first PCB, and a CO2 sensor mounted on the second PCB.

Abstract: Disclosed are an emotion classification information-based text-to-speech (TTS) method and device. The emotion classification information-based TTS method according to an embodiment of the present invention may, when emotion classification information is set in a received message, transmit metadata corresponding to the set emotion classification information to a speech synthesis engine and, when no emotion classification information is set in the received message, generate new emotion classification information through semantic analysis and context analysis of sentences in the received message and transmit the metadata to the speech synthesis engine. The speech synthesis engine may perform speech synthesis by carrying emotion classification information based on the transmitted metadata.

Abstract: A method of processing a broadcast signal in a broadcast transmitter, includes encoding, by an encoder, service data for a service; block interleaving, by a block interleaver, the encoded service data; modulating, by a modulator, the block interleaved service data; and transmitting, by a transmitter, the broadcast signal including the modulated service data, wherein the broadcast signal further includes first signaling information and second signaling information, and wherein the first signaling information includes protocol information to identify whether a Real-Time Object Delivery over Unidirectional Transport (ROUTE) protocol or a Moving Picture Experts Group (MPEG) Media Transport (MMT) protocol is used to deliver the second signaling information for the service, service identification information to identify the service, short name information.

Abstract: A speech recognition apparatus and an operating method thereof which execute a mounted artificial intelligence (AI) algorithm and/or machine learning algorithm to perform speech recognition and communicate with different electronic apparatuses and external servers in a 5G communication environment are disclosed.

Abstract: A robot may include a driving motor, a communication interface configured to communicate with an elevator control device, at least one sensor configured to sense an internal space of an elevator and a processor configured to determine whether boarding on the elevator is possible based on data received from the elevator control device or sensing data of the at least one sensor, set a boarding position based on information on the internal space of the elevator obtained through the communication interface or the at least one sensor when the boarding on the elevator is possible, and control the driving motor to move to the set boarding position.