Mobile Robot Automatic Aiming Method Based on Binocular Vision

Abstract

Aiming at the task that robots can automatically aim and accurately shoot projectiles to hit enemy armor plates in the complex confrontation environment, an automatic aiming control method is proposed. Firstly, the two-dimensional position coordinates of the target are obtained by the improved object detection algorithm. Secondly, the depth information of the target is obtained by the binocular depth camera. Finally, the actual three-dimensional position information of the target is obtained by combining the object detection and depth ranging. Then, by calculating the attitude angle of the pan-tilt, the angle that can guide the pan-tilt to aim and rotate is obtained, thus realizing automatic aiming control on the mobile robot. Through many real confrontation experiments, high precision and real-time performance are obtained, which proves the rationality and feasibility of this method.