CPC G05D 1/0274 (2013.01) [G05D 1/024 (2013.01); G05D 1/0255 (2013.01); G05D 1/027 (2013.01); G05D 1/0278 (2013.01)] | 19 Claims |
1. A multi-sensor-fusion-based autonomous mobile robot indoor and outdoor positioning method, comprising:
acquiring GPS information and three-dimensional point cloud data of a robot at a current position;
acquiring, based on a correspondence relationship between GPS information and two-dimensional maps, a two-dimensional map corresponding to the GPS information of the robot at the current position, wherein connection lines between three-dimensional coordinates corresponding to any two points on the two-dimensional map are at a substantially same angle with a horizontal plane, and a pitch angle corresponding to a pose change during a movement of the robot on a same two-dimensional map is less than a set angle;
projecting the three-dimensional point cloud data of the robot at the current position onto a road surface where the robot is currently moving, to form two-dimensional point cloud data of the robot at the current position by using points closest to the robot from the robot in various directions away from the robot;
matching the two-dimensional point cloud data of the robot at the current position with the two-dimensional map corresponding to the GPS information of the robot at the current position, and selecting a position with the highest matching degree as the current position of the robot; and
controlling the robot according to the selected position with the highest matching degree.
|