Extraction of Line Segment based on the Orientation Probability in a Grid Map

그리드지도 내에서 방향확률을 이용한 직선선분의 위치평가

The paper presents an efficient method of extracting line segment in a local map of a robot's surroundings. The local map is composed of 2-D grids that have both the occupancy and orientation probabilities using sonar sensors. To find the shape of an object in a local map from orientation information, the orientations are clustered into several groups according to their values. The line segment is , then, extracted from the clusters based on Hough transform. The proposed technique is illustrated by experiments in an indoor environment.