Handling and pushing objects using unmanned guided vehicles

This paper aims handling box-shape objects combining mapping, searching, and path planning techniques. The proposal enables a mobile robot to push objects autonomously from random positions to a final destination. Laser scanner data are used to build up a 2D map, which aids the objects’ identification in the scene. Next, a topological map is created and Bézier curves provide suitable paths taking into account the position of the robot, objects and final destination. Then, Dijkstra’s algorithm finds the optimal route. Finally, simulations are run in V-REP + Matlab, and real experiments validate the proposal, which demonstrates quite efficient for environments without occlusion of the objects to be transported.