Visual navigation and control of mobile robots based on environment mapping

Most of the recent research on autonomous mobile robotics is focused on obstacle detection and path planning in unknown environments. Improved accuracy in environment recognition and high precision in robot control can ensure feasibility of intelligent and autonomous mobile robotic systems in unexplored environments. To reach this goal, effective navigation and control approaches for the mobile robots must be proposed. This paper presents a path planning and control approach for blind robots equipped with no onboard cameras based on 2D navigation map, which is converted from the 3D environment map reconstructed by a scout robot equipped with an onboard camera using VSLAM (visual simultaneous localization and mapping) algorithm. In the region where blind robots can be observed by surveillance cameras, they can be efficiently driven to follow the planned trajectories based on the 2D navigation map. The proposed navigation and control system has been validated by simulations and experiments with a blind robot using available real-time vision from the surveillance cameras.