Realizing the exploration and rearrangement of multiple unknown objects by an actual mobile robot

Abstract

This paper offers a proposal for realizing the exploration and rearrangement of multiple unknown objects that lay scattered in working environments. The objective of the exploration task is to find all the objects in the environments. On the other hand, the objective of the rearrangement task is to carry all the objects to their goal position. Many applications are possible if the exploration and rearrangement tasks are combined. Some of them are cleaning, mine detecting and housework. An algorithm that integrates two tasks is presented with respect to the effectiveness of the path length and computational cost. In addition, an exploration algorithm is proposed that can work well in an environment that has many objects. In order to verify the algorithm, experiments are conducted with an actual robot. In the experimentals, an environmental recognition method is developed by attaching a mark to the objects. The robot recognizes the objects by finding the mark. It then obtains information from the mark. The mark is also used to modify the odometry error of the robot by computing its configuration relative to a mark attached to a wall. The success rate of this experiment was almost 80% in 20 trials.