Distributed exploration algorithm for GPS-denied areas based on flocking rules

This paper addresses the problem of having a multi-agent system (MAS) search for areas of higher relative importance as measured by an unknown utility function. In the envisioned scenario, there are inexpensive agents without localisation sensors and limited communication capabilities. More expensive nodes serve as fixed towers and forward noisy position and velocity measurements using directional antennae. There is no assumptions on initial network connectivity. By proposing a set of flocking rules and set-membership estimation, the formation drives to a vicinity of nearby local maximum of the function while having theoretical guarantees of no collisions. The performance of the method is evaluated both in Matlab simulations and using the Crazyswarm package under the robot operating system (ROS) environment, including cases of moving destinations, obstacles, undesirable zones, and different number of nodes and sizes of the mission plane.