Long-Term Map Maintenance in Complex Environments

Abstract

Autonomous vehicles should capture the external environment changes into internal representations (for example, maps) for proper behavior and safety. As changes in external environments are inevitable, a lifelong mapping system is desirable for autonomous robots that rely on maps and aim at long-term operation. In this work, we propose a new largescale mapping system for the Intelligent Autonomous Robotic Automobile (IARA) or any other autonomous vehicle. The new mapping system is based on the GraphSLAM algorithm, with extensions to deal with the calibration of odometry directly in the optimization of the graph and to address map merging for long-term map maintenance. The mapping system can use sensor data from one or more robots to build and merge different types of occupancy grid maps. The system’s performance was evaluated in a series of experiments carried out with data captured in complex real-world scenarios. The experimental results indicate that the new large-scale mapping system can provide high-quality occupancy grid maps for later navigation and localization of autonomous vehicles.