Abstract: A training system for training a trained model for use by a navigating robot to perform visual navigation includes memory including N base virtual training environments, each of the N base virtual training environments including a field of view at a location within an indoor space, where N is an integer greater than 1. A randomization module is configured to generate N varied virtual training environments based on the N base virtual training environments, respectively, by varying at least one characteristic of the respective N base virtual training environments. A training module is configured to train the trained model for use by the navigating robot to perform visual navigation based on a training set including: the N base virtual training environments; and the N varied virtual training environments.

Abstract: Provided is a method, performed by a computing device communicating with a server, of generating 3-dimensional (3D) mode data. The method includes: capturing, by a camera, an image of a target object at a first time point and storing first pose data of the camera at this time; generating a second image by capturing, by the camera, the target object at a second time point and generating second pose data of the camera at this time; calculating a distance between the camera at the second time point and the target object, based on the first pose data and second pose data of the camera; generating pose data of the target object, based on the distance and the second pose data of the camera; and estimating second relative pose data of the target object, based on the second pose data of the camera and the pose data of the target object.

Abstract: A method of training a predictor to predict a location of a computing device in an indoor environment incudes: receiving training data including strength of signals received from wireless access points at positions of an indoor environment, where the training data includes: a subset of labeled data including signal strength values and location labels; and a subset of unlabeled data including signal strength values and not including labels indicative of locations; training a variational autoencoder to minimize a reconstruction loss of the signal strength values of the training data, where the variational autoencoder includes encoder neural networks and decoder neural networks; and training a classification neural network to minimize a prediction loss on the labeled data, where the classification neural network generates a predicted location based on the latent variable, and where the encoder neural networks and the classification neural network form the predictor.

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: A training system for a robot includes: a model having a transformer architecture and configured to determine how to actuate at least one of arms and an end effector of the robot; a training dataset including sets of demonstrations for the robot to perform training tasks, respectively; and a training module configured to: meta-train a policy of the model using first ones of the sets of demonstrations for first ones of the training tasks, respectively; and optimize the policy of the model using second ones of the sets of demonstrations for second ones of the training tasks, respectively, where the sets of demonstrations for the training tasks each include more than one demonstration and less than a first predetermined number of demonstrations.

Abstract: A computer-implemented method of determining a position of a portable electronic device in an indoor environment includes: at a first rate, updating an absolute position of a portable electronic device within the indoor environment based on at least one of radio signal data and magnetic field data captured using the portable electronic device; at a second rate that is different than the first rate, selectively updating an estimated displacement of the portable electronic device within the indoor environment, the updating the estimated displacement comprising generating an estimated displacement, by a neural network module, based on inertial sensor data of the portable electronic device; and determining a present position of the portable electronic device within the indoor environment by updating a previous position based on at least one of (a) the estimated displacement and (b) the absolute position.

Abstract: Security check methods and systems over a user on a vehicle may be provided. The security check method including checking an allowed security right to a destination of a vehicle for entry, detecting a security right of a user on the vehicle, and performing a security process related to getting off the vehicle, based on the security right of the user and the allowed security right may be provided.

Abstract: A visual localization method includes generating a first feature point map by using first map data calculated on the basis of a first viewpoint; generating a second feature point map by using second map data calculated on the basis of a second viewpoint different from the first viewpoint; constructing map data for localization having the first and second feature point maps integrated with each other, by compensating for a position difference between a point of the first feature point map and a point of the second feature point map; and performing visual localization by using the map data for localization.

Abstract: A method of generating a map for visual localization includes specifying a virtual camera pose by using 3-dimensional (3D) model data which is based on an image of an outdoor space captured from the air; rendering the image of the outdoor space from a perspective of the virtual camera, by using the virtual camera pose and the 3D model data; and generating a feature point map by using the rendered image and the virtual camera pose.

Abstract: In a moving path guide providing method, device, system, and computer program, an information point easily recognizable around a path where a user moves is selected and the moving path is provided to the user on the basis of the selected information point, so as to allow the user to more conveniently and easily move via the path according to the guide.

Abstract: A planetary gear actuator including a sun gear, a rotary internal gear being concentric with the sun gear, a fixed internal gear being concentric with the sun gear, compound planetary gears, and a carrier connected to each of the compound planetary gears so as to be rotatable relative to each of compound planetary gears may be provided, Each of the compound planetary gears may include a first planet gear engaged with the sun gear, a second planet gear at one side of the first planet gear, engaged with the rotary internal gear, and having a smaller number of teeth than the first planet gear, and a third planet gear at another side of the first planet gear, engaged with the fixed internal gear, and having a smaller number of teeth than the first planet gear. One compound planetary gear may overlap another compound planetary gear in a thickness direction.

Abstract: A head up display for a vehicle including a display device configured to output light forming an image, an optical system configured to control a path of the light such that the image is output towards a light transmission region, and a controller configured to generate the image based on a first view and a second view such that a virtual image is produced on a ground surface in the light transmission region, the first view being towards the ground surface , the second view being towards a 3D space above the ground surface, the first view and the second view being based on an eye-box, the ground surface being in front of the vehicle, and the virtual image including a graphic object having a stereoscopic effect, and control the display device to output the image.

Abstract: A control method and system for a robot. The robot control method includes allocating a task to a robot, the task associated with a place and a target user, determining a location of the target user based on an image received from a camera, the camera being arranged in a space including the place, and controlling a performance time of the task based on the location of the target user and the place.

Abstract: A robot control method includes receiving an image of a space where a robot drives; receiving driving information related to driving of the robot, from the robot; controlling a display unit to output a graphic object corresponding to the driving information, together with the image; and determining a visual characteristic of the graphic object based on the driving information, wherein the controlling includes controlling the display unit to output the graphic object in an overlapping manner with the image.

Abstract: According to at least some example embodiments, a delivery method includes acquiring invoice information of an object based on scanning of the object by a scanner; specifying a target user matched with the invoice information by using a user database (DB); extracting target information corresponding to the target user from the user DB; generating identification information based on the invoice information and the target information; generating an identification mark, including the identification information, to be attached to the object; and controlling a robot which has scanned the identification mark to deliver the object to the target user.

Abstract: A robot remote control method and system capable of remotely controlling navigation of a robot. The robot remote control method includes outputting both a map image and an ambient image to a display, the map image including location information corresponding to the ambient image, the ambient image being of surroundings of a robot, and the ambient image being received from a camera at the robot, generating a control command for controlling the robot in response to an input to the display during the outputting, and causing the robot to drive according to the control command by transmitting the control command to the robot.