Frontier based exploration with task cancellation

Abstract

Traditional frontier based exploration strategies operate by iteratively selecting the next best sensing location myopically and moving to the specified location, until the entire environment is explored. And it does not consider the new information added to the map through continuous observations by the robot along the way to a selected location. This can sometimes lead to redundant traversal by the robot, such as traveling towards a dead-end when the nearby area is already mapped. In this work, we augment the traditional frontier based exploration strategy to include a probabilistic decision step that decides whether further motion on the planned path to the next sensing location is desirable or not. If the motion is not desirable, it is cancelled and a new sensing location is selected as the next sensing task. Simulation and real world experiments conducted in indoor and outdoor environments validate that the introduction of a sensing task cancellation step reduces the redundant motions of robots thus improves the efficiency of exploration missions, which is vital when used in time critical search and rescue robotic missions.