Particle swarm optimization algorithms for autonomous robots with deterministic leaders using space filling movements
- PDF / 2,606,003 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 84 Downloads / 167 Views
ORIGINAL PAPER
Particle swarm optimization algorithms for autonomous robots with deterministic leaders using space filling movements Doina Logofătu1 · Gil Sobol2 · Christina Andersson1 · Daniel Stamate3 · Kristiyan Balabanov1 · Tymoteusz Cejrowski4 Received: 14 January 2018 / Accepted: 13 June 2018 © Springer-Verlag GmbH Germany, part of Springer Nature 2018
Abstract In this work the swarm behavior principles of Craig W. Reynolds are combined with deterministic traits. This is done by using leaders with motions based on space filling curves like Peano and Hilbert. Our goal is to evaluate how the swarm of agents works with this approach, supposing the entire swarm will better explore the entire space. Therefore, we examine different combinations of Peano and Hilbert with the already known swarm algorithms and test them in a practical challenge for the harvesting of manganese nodules on the sea ground with the use of autonomous agents. We run experiments with various settings, then evaluate and describe the results. In the last section some further development ideas and thoughts for the expansion of this study are considered. Keywords Autonomous agents · Space filling curves · Particle swarm optimization · Deterministic leaders · Application
1 Introduction Simultaneously with the applied research of renewable resources, it is useful to find novel ways for opening up fos‑ sil ones. As example, manganese nodules can be found on the sea bottom. A considerable application field involves rust and corrosion prevention on steel (Rossum 2000; Kim and Kim 2015). The degradation could be reduced substantially by collecting these manganese nodules from the sea bot‑ tom using specialized robots. Our focus in this work is to evaluate different ways in handling the movement of these fictional robots as autonomous agents. * Doina Logofătu [email protected]‑uas.de 1
Faculty of Computer Science and Engineering, Frankfurt University of Applied Sciences, 1 Nibelungenplatz, Frankfurt am Main 60318, Germany
2
Faculty of Industrial Engineering and Management, Technion—Israel Institute of Technology, Haifa 3200003, Israel
3
Department of Computing, Goldsmiths College, University of London, London SE146NW, UK
4
Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Gabriela Narutowicza 11/12, Gdańsk 80‑233, Poland
The experiments can be extended to cover other collect‑ ing tasks. The base for our application is a framework for simulation and improvement of swarm behavior in changing environments (Canyameres and Logofătu 2014), which we redesign and extend (Logofătu et al. 2017a, b). It simulates the swarm behavior by using the principles of Reynolds (2004) pointed out here in Sect. 2.2. The main purpose of the framework regarding the application is to deploy agents with a specific strategy and then to gather them. While gathering, the agents are collecting the manganese which is distributed on every position in the coordinate system. Once gathered together, there is no more movemen
Data Loading...
