Autonomous positioning of omnidirectional mobile robot based on visual inertial navigation

Abstract

With the development of artificial intelligence, robot intelligence has gradually become a hot research field. Autonomous positioning of robot is an important part of realizing its intelligence. SLAM technology can effectively solve this problem. The monocular camera is cheap and easy to install, but the monocular vision SLAM has the problem of scale uncertainty, which reduces its practicability. Based on the ORB-SLAM2 algorithm, this paper uses the monocular camera as the sensor, uses the integrated IMU inside the omni-directional mobile unmanned car to provide scale information, and carries out information fusion in a tightly coupled way. Finally, the experiment on the autonomous positioning of the actual omni-directional mobile unmanned car platform verifies the feasibility and practicability of the ORB-SLAM2 algorithm with monocular camera as sensor combined with inertial element (IMU) in the autonomous positioning of mobile robot.