Communication with a user is more naturally and effectively realized. An information processing apparatus includes an autonomous mobile body (10) that travels while maintaining an inverted state, and an operation control unit (230) that controls an operation of the autonomous mobile body. The autonomous mobile body includes a main body (10), two wheels (570) mounted on the main body, and a drive mechanism (565) that drives the two wheels. The operation control unit controls the drive mechanism to maintain the inverted state of the autonomous mobile body by the two wheels in a first state, and make the autonomous mobile body come to rest by the two wheels and a bottom of the main body when the autonomous mobile body transfers from the first state to a second state.

A system useful to protect a real estate property includes at least one sensor configured to monitor presence of a nuisance animal on the real estate property, a computerized control module including programming to diagnose the presence of the nuisance animal based upon data from the at least one sensor, and at least one mobile robotic device. The mobile robotic device is configured to move to a location of the nuisance animal on the real estate property based upon the data from the at least one sensor and emulate a predator to move the nuisance animal.

The present disclosure discloses a cleaning robot, including a housing, a receiving tank, and a liquid storage tank. The housing is provided with a first groove and a second groove spaced apart from each other. The receiving tank is located in the first groove and configured to receive dirt. The liquid storage tank is located in the second groove and configured to store a cleaning liquid. In the cleaning robot of the present disclosure, the receiving tank and the liquid storage tank are arranged separately and spaced apart from each other, such that the volume of the liquid storage tank is increased, thereby allowing a larger area to be cleaned with a tank of water stored.

A method, performed by a robot vacuum cleaner, of planning a cleaning route includes: dividing an indoor space into at least one cleanable region based on an indoor space map generated using at least one sensor included in the robot vacuum cleaner; dividing the at least one cleanable region into a plurality of partial regions based on a cleaning mode of the robot vacuum cleaner; and planning a first cleaning route to control a number of direction changes of the robot vacuum cleaner with respect to each of the plurality of partial regions based on the cleaning mode being a first mode.

Systems and methods for automated makeup application allow a user to select and apply desired makeup styles to the user's face. The systems and methods include a computer application with a graphical user interface which allows selection of a look from a plurality of preconfigured looks. A camera coupled with a robotic arm records a face map and color coding and sends that data to be stored on a virtual server database. The application calculates formula quantity and a pump extracts desired formula amounts from appropriate formula cartridges which it releases into reservoirs on the robotic arm's head. An airbrush compressor mixes the formula and plug triggers release one of several airbrush nozzles to start spraying the user's face with formula. A cleaning mechanism is provided between makeup applications and after the final application.

The present invention is applied to the human-robot interaction field, and provides a method and an apparatus for interaction between a robot and a user; the method includes: determining an original direction where a voice signal is generated upon receiving a voice signal; adjusting a robot from a current direction to the original direction, and capturing a picture corresponding to the original direction; detecting whether a human face exists in the picture; when a human face exists in the picture, recognizing whether a user corresponding to the human face is a legal user; and when the user corresponding to the human face is a legal user, interacting with the legal user. The method can improve the accuracy of instruction execution of the robot.

A control device that controls an operation of a robot for alerting a human is provided.

A control device that controls a robot includes an acquiring unit that acquires field of view information of a human and a control unit that controls an operation of an alert unit provided on the robot based on the field of view information. The control unit controls the alert unit such that the alert unit performs an alert operation according to a target task of the robot within an auxiliary field of view area of the human. The alert unit includes a manipulator provided on the robot. The alert operation includes an operation of the manipulator gripping an object relating to the target task of the robot.

Each robot effectively appeals its own device even when multiple robots are present in surroundings. A robot comprises a person detector, an appeal permitter, and a movement controller. The person detector detects a person. The appeal permitter permits execution of an appealing movement attracting interest of a person. The movement controller executes the appealing movement when the person detector detects a person and execution of the appealing movement is permitted by the appeal permittter.

A robot includes a mover, a determiner, and a controller. The mover moves the robot. The determiner determines a touch type by a predetermined object. The controller controls the mover so as to move the robot close to the predetermined object when the determiner determines that the touch type by the predetermined object is petting, or so as to move the robot apart from the predetermined object when the determiner determines that the touch type by the predetermined object is to hitting.

Methods, systems, and apparatus, including computer-readable media storing executable instructions, for enhancing robot learning. In some implementations, a robot stores first embeddings generated using a first machine learning model, and the first embeddings include one or more first private embeddings that are not shared with other robots. The robot receives a second machine learning model from a server system over a communication network. The robot generates a second private embedding for each of the one or more first private embeddings using the second machine learning model. The robot adds the second private embeddings to the cache of the robot and removes the one or more first private embeddings from the cache of the robot.