The particle swarm optimization algorithm: convergence analysis and parameter selection
Information Processing Letters
A study of particle swarm optimization particle trajectories
Information Sciences: an International Journal
Bio-inspired multi-agent systems for reconfigurable manufacturing systems
Engineering Applications of Artificial Intelligence
Hi-index | 0.00 |
The paper presents a cooperative control algorithm for a team of Unmanned Aerial Vehicles (UAVs) used in the surveillance of the area around a military base to protect against potential threats. The UAVs are required to search an area of interest, while efficiently allocating their time between zones of varying degrees of importance. Irregular routes are preferred, to reduce the ability of an adversary to predict the patrol routes of the UAVs. In this paper, we consider a team of potentially heterogeneous, dynamically constrained UAVs with constant velocities. The problem is approached as a finite horizon optimization to account for possible alarms as they occur. This approach seeks to optimize the amount of information obtained by the UAVs, with surveillance of pop-up alarms a high but not sole priority. Particle Swarm Optimization (PSO) is used to search the control space and optimize the reward function. This approach guarantees feasible trajectories, without smoothing, in addition to unpredictable paths.