Advancing evolutionary coordination for fixed-wing communications UAVs

In this paper we present advances to our previously proposed coordination system for groups of unmanned aerial vehicles that provide a network backbone over mobile ground-based vehicles. Evolutionary algorithms are employed in order to evolve flying manoeuvres that position the aerial vehicles. The updates to the system include obstacle representation, a packing mechanism to permit efficient dynamic allocation of ground-based vehicles to their supporting aerial vehicles within large-scale environments, and changes to time synchronisation. The experimental results presented in this paper show that the system is able to adaptively form sparse formations that cover as many ground-based vehicles as possible, optimising the use of the available power.

This is an Accepted Manuscript version of the following work: Giagkos, A., Tuci, E., Wilson, M.S. (2015). Advancing Evolutionary Coordination for Fixed-Wing Communications UAVs. In: Dixon, C., Tuyls, K. (eds) Towards Autonomous Robotic Systems. TAROS 2015. Lecture Notes in Computer Science(), vol 9287. Springer, Cham. This version of the manuscript has been accepted for publication, after final editorial and peer review (where applicable) is complete, but is not the Version of Record and does not reflect post-acceptance improvements (such as copyediting or typesetting), or any corrections. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-319-22416-9_14 . Use of this Accepted Manuscript version is subject to the publisher’s Accepted Manuscript terms of use: https://www.springernature.com/gp/open-research/policies/accepted-ma...”