Loop-Aware Exploration Graph: A concise representation of environments for exploration and active loop-closure

Abstract

Autonomous robots must have the ability to build an accurate map of an unknown environment by fully covering it in an exploration task. Several exploration approaches combine a Simultaneous Localization and Mapping (SLAM) technique with a strategy to move the robot through the environment actively looking for loops to be closed. When closing a loop, the robot revisits a previously mapped area, which allows it to reduce the uncertainty about its pose. In this paper, we present a concise environment representation named Loop-Aware Exploration Graph (LAEG). The LAEG’s nodes represent the essential information to the exploration process, such as the robot’s position and the frontiers of two different kinds, while the LAEG’s edges are the connections between these elements. Furthermore, the LAEG uses a specific type of edge to explicitly represent the predicted loops, facilitating the incorporation of this information into the exploration decision process. We also present an exploration approach that relies on the LAEG to make the decisions. Consequently, our approach maximizes the chances of closing a loop when choosing the next region to be explored, which is eased by the LAEG that represents the predicted loops as edges. The effectiveness of the proposed exploration approach was evaluated through experiments in five environments, comparing it with a greedy approach that only chases the most attractive unknown region and another one that makes the robot actively look for loop-closures.