Task Allocation Using Clustering and Auctioning Algorithms for Heterogeneous Robotic Swarms

In this research, one of our PhD students Jonathan Lwowski presents a novel centralized robotic swarm of heterogeneous unmanned vehicles, consisting of autonomous surface vehicles (ASVs) and micro-aerial vehicles (MAVs). This swarm operates in an outdoor environment and are equipped with cameras and Global Positioning Systems (GPS), and the swarm demonstrates how the advantages of each robotic platform can be used cooperatively to accomplish task in an efficient manner. The cloud network performs clustering algorithms using the map from the MAVs to build a simplified version of the map for the ASVs. The cloud then performs an auctioning algorithm to assign clusters to the ASVs based on several factors such as position and capacity.