Method, system, and non-transitory computer-readable recording medium for generating a map for a robot

A non-transitory computer-readable recording medium having stored thereon a computer program for executing a method for generating a map for a robot, the method comprising the steps of:

• acquiring a raw map associated with a task of the robot by generating the raw map on the basis of sensing information acquired by sensing at least one object disposed outside the robot;
• identifying pixels estimated to be a moving obstacle, pixels estimated to be noises, and pixels estimated to be a fixed obstacle in the raw map, on the basis of colors of pixels specified in the raw map and sizes of areas associated with the pixels;
• performing dilation and erosion operations on the pixels estimated to be the moving obstacle, and determining a polygon-based contour of the moving obstacle;
• and
• generating annotation information of the raw map on the basis of at least one of the contour of the moving obstacle and coordinate data on the contour,
• wherein the robot is configured to perform the task on the basis of the raw map and the annotation information of the raw map,
• wherein the colors of pixels specified in the raw map are represented in a gray scale according to the sensing information, such that white pixels are associated with an area where nothing is located, black pixels are associated with an area where a real world object is located, and gray pixels are associated with an area where there is a possibility of a real world object being located, and
• wherein in the identifying step, pixels in an area that is formed by connecting the gray pixels and black pixels adjacent to each other and has a size not greater than a first threshold size are identified as the pixels estimated to be the noises, pixels in an area that is formed by connecting the black pixels adjacent to each other and has a size greater than the first threshold size and not greater than a second threshold size are identified as the pixels estimated to be the moving obstacle, and pixels in an area that is formed by connecting the black pixels adjacent to each other and has a size greater than the second threshold size are identified as the pixels estimated to be the fixed obstacle.

A system for generating a map for a robot, the system comprising:

• a raw map acquisition unit configured to acquire a raw map associated with a task of the robot by generating the raw map on the basis of sensing information acquired by sensing at least one object disposed outside the robot;
• a pixel identification unit configured to identify pixels estimated to be a moving obstacle pixels estimated to be noises, and pixels estimated to be a fixed obstacle in the raw map, on the basis of colors of pixels specified in the raw map and sizes of areas associated with the pixels;
• and
• a contour determination unit configured to perform dilation and erosion operations on the pixels estimated to be the moving obstacle, determine a polygon-based contour of the moving obstacle, and generate annotation information of the raw map on the basis of at least one of the contour of the moving obstacle and coordinate data on the contour,
• wherein the robot is configured to perform the task on the basis of the raw map and the annotation information of the raw map,
• wherein the colors of pixels specified in the raw map are represented in a gray scale according to the sensing information, such that white pixels are associated with an area where nothing is located, black pixels are associated with an area where a real world object is located, and gray pixels are associated with an area where there is a possibility of a real world object being located, and
• wherein the pixel identification unit is configured to identify pixels in an area that is formed by connecting the gray pixels and black pixels adjacent to each other and has a size not greater than a first threshold size as the pixels estimated to be the noises, to identify pixels in an area that is formed by connecting the black pixels adjacent to each other and has a size greater than the first threshold size and not greater than a second threshold size as the pixels estimated to be the moving obstacle, and to identify pixels in an area that is formed by connecting the black pixels adjacent to each other and has a size greater than the second threshold size as the pixels estimated to be the fixed obstacle.