Abstract: Provided are a method and an apparatus for generating a task plan. A method of generating a task plan for performing an arbitrary task includes generating a search tree based on a plurality of task states of the task and a plurality of task actions for performing the task, estimating a recommended path for an internal connection of the search tree by inputting the plurality of task states and the plurality of task actions to a neural network based on the search tree, and generating the task plan by determining a target path that reaches from an initial state of the task to a target state of the task based on the recommended path.

Abstract: Provided is a method for reproducing a situation using a mobile device having an image shooting function. The method may include extracting first keypoints from a live view output to a display of the mobile device, extracting second keypoints from a previously shot image, calculating a tilt of the mobile device at which the first keypoints are mapped to the second keypoints within a critical range, and synthesizing the previously shot image with the live view in a state where the mobile device has been adjusted according to guide information based on a result of the calculating.

Abstract: Provided is a method for reproducing a situation using a mobile device having an image shooting function. The method may include extracting first keypoints from a live view output to a display of the mobile device, extracting second keypoints from a previously shot image, calculating a tilt of the mobile device at which the first keypoints are mapped to the second keypoints within a critical range, and synthesizing the previously shot image with the live view in a state where the mobile device has been adjusted according to guide information based on a result of the calculating.

Abstract: Provided is a method for constructing a place database using data transmitted from a mobile device to a server. The method may include receiving an image of a target shot by the mobile device and coordinates of an image shooting place of the target, providing a recommendation list of a section to which the received coordinates belong, receiving, from the mobile device, a name of the target selected or not selected from the recommendation list, receiving keywords related to the target for constructing or updating the database, and constructing or updating the database on the basis of the image and the keywords.

Abstract: The present invention relates to a system for cooperation of multiple mobile robots and a method thereof that allow the multiple mobile robots to cooperatively execute one complicated task. The system and method can use centralized control architecture, create robot cooperation application codes on the basis of conceptual behavior units without depending on actual physical robots, and dynamically bind behavior units used to create the robot cooperation application at the time of executing the robot cooperation application to actual functions of the robots, thereby actively adjusting to changes in a dynamical environment, such as a change in the types, the number, and the functions of robots for cooperation.

Abstract: The user-defined inference rule is created using a knowledge base search language that is basically provided in a knowledge base management system. Accordingly, the user-defined inference rule is a knowledge base search statement and is processed using a function of searching a knowledge base as a base function of the knowledge base management system. The user-defined inference rule is applied by including a knowledge base search process and a search result in the knowledge base, when the knowledge base is changed. The user-defined inference rule is managed by a user-defined inference rule manager. The user-defined inference rule manager monitors a change in the knowledge base to determine when the user-defined inference rule is applied, executes the user-defined inference rule to obtain the execution result, and includes the execution result in the knowledge base.

Abstract: Provided proposes a structure of a robot management server and an internal structure of a robot that can interwork with an external server providing functions such as voice recognition, voice synthesis, image recognition, speaker recognition, gesture recognition, etc., and provide the corresponding functions as basic functions of the robot. Through the structure, the same interface, which accesses the internal structure of the robot, can be provided and the robot developer can develop applications handling multi-kinds robots and applications without being limited by the basic functions of the robot, by using the interface. In addition, malfunction and failure, which can occur during the operation of the robot, are checked by diagnosing, such that applications capable of appropriately processing the malfunction and failure can be developed.

Abstract: The present invention relates to an apparatus and method for controlling a multi-robot linked in virtual space, and when an event is generated in accordance with information change in virtual space including the web as well as the environmental change around a robot, the present invention controls individual behavior or collective behavior or corresponding robots by transmitting behavior data corresponding to the generated event to a plurality of robots. According to the present invention, by making a robot perform specific behavior in response to not only changes in the real environment, but information changes in the web, it is possible to arouse the user's interest or the developer's originality while removing due to complicity of the real environment, which is a problem limiting application of the robot, or dynamic response.

Abstract: The present invention relates to a system for cooperation of multiple mobile robots and a method thereof that allow the multiple mobile robots to cooperatively execute one complicated task. The system and method can use centralized control architecture, create robot cooperation application codes on the basis of conceptual behavior units without depending on actual physical robots, and dynamically bind behavior units used to create the robot cooperation application at the time of executing the robot cooperation application to actual functions of the robots, thereby actively adjusting to changes in a dynamical environment, such as a change in the types, the number, and the functions of robots for cooperation.

Abstract: The user-defined inference rule is created using a knowledge base search language that is basically provided in a knowledge base management system. Accordingly, the user-defined inference rule is a knowledge base search statement and is processed using a function of searching a knowledge base as a base function of the knowledge base management system. The user-defined inference rule is applied by including a knowledge base search process and a search result in the knowledge base, when the knowledge base is changed. The user-defined inference rule is managed by a user-defined inference rule manager. The user-defined inference rule manager monitors a change in the knowledge base to determine when the user-defined inference rule is applied, executes the user-defined inference rule to obtain the execution result, and includes the execution result in the knowledge base.