A Distributed Control of Movements and Fuzzy Logic-Based Task Allocation for a Swarm of Autonomous Agents

This paper proposes a decentralized method for controlling a swarm of autonomous agents represented as Unmanned Aerial Vehicles (UAVs) to accomplish a set of tasks cooperatively. The task commissioning is carried out by a Fuzzy Logic-based task allocation strategy, and the movement behavior is based on the internal state of the agent as well as the external data from its neighbors through local communications. The solution was modified from a centralized strategy developed in a previous work in order to be enhanced, so the proposed distributed strategy was tested considering the same experiments, configurations and conditions applied to the centralized approach in a simulated environment. To test the strategy, the planned activity to be performed was planting seeds, in a field composed by a grid of points that represents the places to be sown. Completion times and collision avoidance attempts were measured to test the effectiveness, as well as to perform a comparison between the distributed and centralized methods. Important improvements were found considering the size of agents in a swarm.