Abstract: A method for controlling a robot having a plurality of modular robots for performing requested service-related tasks includes individually controlling each of the plurality of modular robots through a robot control system without interactions between the plurality of modular robots.

Abstract: Provided is a method for controlling, in a space where a plurality of robots autonomously travel, the robots such that each of the plurality of robots can successively pass through a designated region, by identifying the designated region to be passed through by the robots and i) controlling the robots to pass through the corresponding designated region via a first point defined in the designated region or ii) triggering a designated region traveling mode of the robots and controlling the robots to pass through the corresponding designated region in the designated region traveling mode.

Abstract: The present invention relates to remotely controlling robots and provides a method and a system, for remotely controlling robots, that are capable of controlling moving paths of a plurality of robots. The method for remotely controlling traveling robots comprises the steps of: controlling a specific robot to move along a preset first path; receiving an obstacle event for a specific area of the first path; generating a second path avoiding the specific area on the basis of the obstacle event; and controlling the specific robot so that same moves along the second path, wherein the destination of the second path is related to the destination of the first path.

Abstract: The data collecting method includes: collecting first and second sensor data respectively through a first and a second sensors while a data collecting apparatus moves within a target area, and tagging a first and a second timestamp values respectively to the first and the second sensor data; generating map data of the target area and location data at a point of time corresponding to the first timestamp value, based on the first sensor data; generating map information of the target area based on the map data, and generating moving path information on the map based on the location data; and estimating a sensing location at a point of time corresponding to the second timestamp value based on the moving path information, and tagging the sensing location to the second sensor data.

Abstract: A charging pad according to the exemplary embodiment of the present invention may include an input terminal connected to a high-priority charging pad; an output terminal connected to a low-priority charging pad; a charging unit configured to charge a robot positioned on the charging pad in accordance with a preset operating state; and a control unit configured to switch an operating state of the charging unit from an operation stop state to an operation standby state when a status signal for the high-priority charging pad is received from the input terminal. The control unit is configured to output the status signal for the charging pad through the output terminal when occupation of the charging unit by the robot is detected in the operation standby state.

Abstract: A method for optimizing autonomous driving includes applying different autonomous driving parameters to a plurality of robot agents in a simulation through an automatic setting by means of the system or a direct setting by means of a manager, so that the robot agents learn robot autonomous driving; and optimizing the autonomous driving parameters by using preference data for the autonomous driving parameters.

Abstract: A method of determining an action of a device for a given situation, implemented by a computer system, includes for a learning model that learns a distribution of rewards according to the action of the device for the situation using a risk-measure parameter associated with control of the device, selectively setting a value of the risk-measure parameter in accordance with an environment in which the device is controlled; and determining the action of the device for the given situation when controlling the device in the environment, based on the set value of the risk-measure parameter.

Abstract: A method of operating a cloud server to control a robot providing a service in connection with a service application includes receiving an instruction to provide the service from the service application; and based on the received instruction, generating a plurality of sub-instructions by specifying the received instruction; and transmitting each sub-instruction, from among the plurality of sub-instructions, to the robot, wherein the transmitted sub-instructions are instructions for controlling the robot.

Abstract: Disclosed are a method and a system for training an autonomous driving agent on the basis of deep reinforcement learning (DRL). The agent training method according to one embodiment may comprise a step of training an agent through an actor-critic algorithm in a simulation for DRL. The step of training may include inputting first information to an actor network to determine an action of the agent, and inputting second information to a critic to evaluate how helpful the action is to maximizing a reward in the actor-critic algorithm, the second information comprising the first information and additional information.

Abstract: An end device including a communication module configured to wirelessly communicate with an edge server managed by a cloud server, and at least one processor connected to the communication module, the at least one processor configured to receive a control command from the edge server through the communication module, and operate according to the control command.

Abstract: A charging pad according to the exemplary embodiment of the present invention may include an input terminal connected to a high-priority charging pad; an output terminal connected to a low-priority charging pad; a charging unit configured to charge a robot positioned on the charging pad in accordance with a preset operating state; and a control unit configured to switch an operating state of the charging unit from an operation stop state to an operation standby state when a status signal for the high-priority charging pad is received from the input terminal. The control unit is configured to output the status signal for the charging pad through the output terminal when occupation of the charging unit by the robot is detected in the operation standby state.

Abstract: The data collecting method includes: collecting first and second sensor data respectively through a first and a second sensors while a data collecting apparatus moves within a target area, and tagging a first and a second timestamp values respectively to the first and the second sensor data; generating map data of the target area and location data at a point of time corresponding to the first timestamp value, based on the first sensor data; generating map information of the target area based on the map data, and generating moving path information on the map based on the location data; and estimating a sensing location at a point of time corresponding to the second timestamp value based on the moving path information, and tagging the sensing location to the second sensor data.