Motion Estimation for a Mobile Robot Based on Real-Time Stereo Vision System

Abstract

Vision-based motion estimation is a key technique in autonomously mobile robot. This paper presents an integrated method for motion estimation of the mobile robot based on floor plane extraction. The whole processes include floor plane extraction, pose estimation of the onboard stereo vision system and motion estimation of the mobile robot. First, based on disparity map obtained from the onboard real-time stereo vision system, a two-stage method is used for fast floor plane extraction. Then all the points belong to the floor plane are transformed from disparity space to Euclidean space, and a simple least squares method is employed to fit the floor plane. The fitting parameters of the floor plane are used for the pose estimation of the onboard stereo vision system. Finally, the motion of the mobile robot is estimated with the tracking results of the points on floor plane. The proposed motion estimation method is intended to be used in the motion control of a wheeled mobile robot. Experimental results in real environments are presented.