Development of an Omnidirectional AGV by Applying ORB-SLAM for Navigation Under ROS Framework

The development of an automated guided vehicle with omni-wheels for autonomous navigation under a robot operating system framework is presented in this paper. Specifically, laser rangefinder-constructed two-dimensional environment map integrated three-dimensional point cloud to achieve real-time positioning using the oriented features from accelerated segment test and rotated binary robust independent elementary feature detector-simultaneous localisation mapping algorithm. In path planning omnidirectional mobile robot, we applied A* global search algorithm, which uses heuristic function estimate position difference searches best direction. Moreover, employed time-elastic-band method local planning, merges time interval two locations realise optimisation dynamic obstacle avoidance. experimental results verified effectiveness algorithms omni-wheeled robot. Further, showed superior performance over adaptive Monte Carlo window approach planning.