Autonomous Geocaching: Navigation and Goal Finding in Outdoor Domains

This paper describes an autonomous robot system designed to solve the challenging task of geocaching. Geocaching involves locating a goal object in an outdoor environment given only its rough GPS position. No additional information about the environment such as road maps, waypoints, or obstacle descriptions is provided, nor is their often a simple straight line path to the object. This is in contrast to much of the research in robot navigation which often focuses on common structural features, e.g., road following, curb avoidance, or indoor navigation. In addition, uncertainty in GPS positions requires a final local search of the target area after completing the challenging navigation problem. We describe a relatively simple robotic system for completing this task. This system addresses three main issues: building a map from raw sensor readings, navigating to the target region, and searching for the target object. We demonstrate the effectiveness of this system in a variety of complex outdoor environments and compare our system's performance to that of a human expert teleoperating the robot.