Indoor GPS-denied Context Based SLAM Aided Guidance for Autonomous Unmanned Aerial Systems

Abstract

Autonomous exploration and mapping of environments is an important problem in robotics. Efficient exploration of structured environments requires that the robot utilize region-specific exploration strategies and coordinate with search other agents. This paper details the exploration and guidance system of a multi-quadrotor unmanned aerial system (UAS) capable of exploring cluttered indoor areas without relying on any external aides. Specifically, a graph-based frontier search algorithm which is aided by an onboard Simultaneous Localization and Mapping (SLAM) system is developed and flight tested. A technique is developed in for segmenting an indoor office-like environment into regions and to utilize the SLAM map to conduct specific activities in these regions. A goal-directed exploration strategy is created building on existing hybrid deliberative-reactive approaches to exploration. An obstacle avoidance and guidance system is implemented to ensure that the vehicle explores maximum indoor area while avoiding obstacles. The environment is explored and regions are segmented by detecting rooms and hallways which expedites the search. The multi-vehicle system is Georgia Tech Aerial Robotic Team's entry for the annual International Aerial Robotics Competition (IARC).