Apparatus and method for providing robot interaction services using interactive behavior model

A method for providing robot interaction services using an interactive behavior model for interaction between a user and a robot, the method comprising:

• executing an application loaded to a robot terminal to provide a robot application service to a user;
• extracting service history information of the robot application service provided by the application and external circumstance observation information detected by a plurality of sensors through a middleware and inputting the service history information and the external circumstance observation information to an interactive behavior model engine;
• determining and outputting by the interactive behavior model engine, an interactive behavior signal according to the service history information and the external circumstance observation information, based on behavior models and policy models, the behavior models and the policy models being constructed by an interactive behavior model learning unit using a statistical learning method, the behavior models being previously stored in a behavior model database, and the policy models being previously stored in a policy model database;
• analyzing by the middleware, the output interactive behavior signal to generate a motion operating signal and a function operating signal of the robot;
• and
• performing by a robot function operating unit, a behavior or a function of the robot according to the generated motion operating signal and the generated function operating signal,
• wherein the behavior model database stores models which respectively define an input of the user, an internal parameter, an output behavior parameter and a probability distribution which relates to an error of at least one of a plurality of sensors, so that a robot behavior signal is output with respect to the input of the user according to the external circumstance observation information.

An apparatus which provides robot interaction services using a model between a user and a robot, the apparatus comprising:

• a control unit which comprises a behavior model engine which receives an external signal and outputs a behavior signal based on previously stored models and based on the external signal, the previously stored models including at least one behavior model and at least one policy model;
• an application unit which applies the behavior signal to execute and provide the robot application service;
• an operation unit comprising a sensor which detects an external event and an output unit which outputs a behavior or a function of the robot;
• and
• a middleware unit which receives external event observation information and service history information from the operation unit and the application unit and inputs the external event observation information and the service history information to the control unit as the external signal, analyzes the behavior signal to generate and provide a motion operating signal and a function operating signal to the operation unit,
• wherein at least one from among the control, the application, the operation, and the middleware units is performed by a processor,
• wherein the control module includes a behavior model database (DB) and a policy model DB which respectively store the at least one behavior model and the at least one policy model constructed by an interactive behavior model learning unit using a statistical learning method, and
• wherein the behavior model DB stores at least one model which respectively define an input of the user, an internal parameter, an output behavior parameter and a probability distribution which relates to an error of at least one of a plurality of sensors, so that a robot behavior signal is output with respect to the input of the user according to the detected external event.