Device and method for generating object image, recognizing object, and learning environment of mobile robot
AssigneesYujin Robot Co., Ltd., Miele & Cie. KG
InventorsSeong Ju Park, Gi Yeon Park, Kyu Beom Lee
Life of this patent
Estimating the term…
Abstract
According to the present invention, disclosed are a device and a method of generating an object image, recognizing an object, and learning an environment of a mobile robot which perform a deep learning algorithm which allows a robot to create a map and load environment information acquired during the autonomous movement while the autonomous mobile robot is being charged and may be used for an application which finds out a location by finally recognizing objects such as furniture using a method of checking a location of the recognized objects to mark the location on the map.
Claims11
An environment learning device of an autonomous mobile robot, comprising:
- a memory which stores environment information which is already acquired by an autonomous mobile robot in a state in which a power is managed to be a predetermined reference or higher and movement map information generated with respect to a moving area where autonomous mobile robot moves;
- an environment information acquiring unit which determines feature points to recognize an object located in the moving area using at least some of the environment information and the movement map information stored in the memory and loads the selected environment information in accordance with the determined feature point from the memory;
- a movement environment recognizing unit which recognizes the object using the selected environment information;
- and
- an updating unit which updates the movement map using object information in accordance with the recognized object.
An environment learning method of an autonomous mobile robot, comprising:
- determining feature points to recognize an object located in the moving area using at least some of environment information and movement map information stored in the memory and loading selected environment information in accordance with the determined feature point from a memory, by an environment information acquiring unit;
- recognizing the object using the selected environment information, by a movement environment recognizing unit;
- and
- updating the movement map using object information in accordance with the recognized object, by an updating unit.
Dependencies are inferred from the claim text.