An emotion recognizer includes: an uni-modal preprocessor configured to include a plurality of recognizers for each modal learned to recognize emotion information of a user contained in uni-modal input data; and a multi-modal recognizer configured to merge output data of the plurality of recognizers for each modal, and be learned to recognize the emotion information of the user contained in the merged data. The emotion recognizer may output a complex emotion recognition result including an emotion recognition result of each of the plurality of recognizers for each modal and an emotion recognition result of the multi-modal recognizer.

A method of operating a robot includes detecting movement of a video call counterpart using a video call counterpart robot included in image data received from the video call counterpart robot; canceling movement of a user from detected movement of the video call counterpart; and determining motion corresponding to the canceled movement of the video call counterpart.

A control method of an interaction robot according to an embodiment of the present invention comprises the steps of: receiving a user input, by the interaction robot; determining a robot response corresponding to the received user input, by the interaction robot; and outputting the determined robot response, by the interaction robot, wherein the step of outputting the determined robot response includes the steps of: outputting a color matching to the received user input or the determined robot response to a light emitting unit, by the interaction robot; and outputting a motion matching to the received user input or the determined robot response to any one or more among a first driving unit and a second driving unit, by the interaction robot.

A biomimetics based robot and process for simulation is disclosed. The robot may include filament driven and fluid pumped elastomer based artificial muscles coordinated for slow twitch/fast twitch contraction and movement of the robot by one or more microcontrollers. A process may provide physics based simulation for movement of a robot in a virtual setting. Successfully tested movement data may be stored and embedded into a robot at build and/or before a new movement in programmed into the robot. Some embodiments include an artificial skin system supporting the artificial muscles.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing goal-based robot animation. One system includes a robot configured to receive a goal that specifies a goal state to be attained by the robot or one of the components. A collection of animation tracks is searched to identify one or more animation tracks that when executed by the robot cause the robot to perform one or more physical movements to satisfy the goal state. The identified one or more animation tracks are executed to perform the one or more physical movements to satisfy the received goal state.

The present invention relates to an educational robot that includes a body which forms the main portion of the robot. The educational robot also includes a head mounted on the body which is capable of making human facial expressions. In addition, the educational robot includes a plurality of limbs that are capable of making human perceptible gesture. Further, the educational robot includes an interface housed in the body and allows the user to interact with the interface. In an example, the interface allows the user to select a multimedia content from a library of multimedia content. The educational robot includes an imaging device to capture an image of the user to identify the user. Further, the educational robot renders the multimedia content in an interactive and intuitive way.

A robot includes an output unit including at least one of a display or a speaker, a camera, and a processor configured to control the output unit to output content, to acquire an image including a plurality of users through the camera while the content is output, to determine a mood of a group including the plurality of users based on the acquired image, and to control the output unit to output feedback based on the determined mood.

A robot according to the present disclosure may include: a casing that has an internal space; a head unit that protrudes upward from the casing and has a first display; a display unit that is disposed ahead of the casing and has a second display; an ascending and descending motor that is disposed in the casing; an ascending and descending plate that ascends and descends between a first position and a second position higher than the first position by power of the ascending and descending motor; a contact bar that has an upper end connected to the head unit and a lower end being in contact with the ascending and descending plate; a fixing plate that is positioned between the ascending and descending plate and the head unit and has an opening through which the contact bar passes; and a link that connects the ascending and descending plate and the fixing plate to the display unit.

A robot includes a display configured to display a face image indicating a face of the robot, an input unit configured to receive a customizing request for the face of the robot, and a processor configured to acquire customizing data based on the received customizing request, to generate a face design based on the acquired customizing data, and to control the display to display a face image based on the generated face design.

A virtual robot image presentation method and an apparatus are provided to improve virtual robot utilization and user experience. In this method, an electronic device generates a first virtual robot image, and presents the first virtual robot image. The first virtual robot image is determined by the electronic device based on scene information. The scene information includes at least one piece of information in first information and second information, the first information is used to represent a current time attribute, and the second information is used to represent a type of an application currently running in the electronic device. According to the foregoing method, in a human-machine interaction process, virtual robot images can be richer and more vivid, so that user experience can be better, thereby improving virtual robot utilization of a user.