Stereo-Based Visual Navigation of Mobile Robots in Unknown Environments
Keywords:
Mobile robot, stereo vision, navigation,exploration, unknown outdoor environments.
Abstract:
In this paper a stereo vision-based algorithm formobile robots navigation and exploration in unknown outdoorenvironments is proposed. The algorithm is solely based onstereo images and implemented on a nonholonomic mobilerobot. The first step for exploration in unknown environments isconstruction of the map of circumference in real-time. Bygetting disparity image from rectified stereo images andtranslating its data to 3D-space, point cloud model ofenvironments is constructed. Then by projecting points to XZplane and put local maps together based on visual odometry,global map of environment is constructed in real-time. A*algorithm is used for investigating optimal path and nonlinearback-stepping controller guides the robot to follow theidentified path. Finally, the mobile robot explores for a desiredobject in an unknown environment through these steps. Experimental results verify the effectiveness of the proposedalgorithm in real-time implementations.