Robust Homing For Autonomous Robots

In autonomous exploration tasks, robots usually rely on a SLAM system to build a map of the environment online and then use it for navigation purposes. Although there has been substantial progress in robustly building accurate maps, these systems cannot guarantee the consistency of the resulting environment model. In this paper, we address the problem of robustly guiding a robot back to its starting location after exploring an unknown environment-even if the mapping system fails to produce a consistent map. To tackle this problem, we propose a two-step procedure. First, we check if the current map is consistent using a statistical test. If the map is consistent, we navigate the robot back to its starting location using a standard navigation system. In case of an inconsistent map, however, we propose to rewind the trajectory from the current location to the start without relying on a map. We implemented the proposed system in ROS and showcase its effectiveness on an autonomous exploration robot in real underground and office environments.