Advertisement

Online Optimization of Movement Cost for Robotic Applications of PSO

  • Sebastian MaiEmail author
  • Heiner Zille
  • Christoph Steup
  • Sanaz Mostaghim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11805)

Abstract

Particle Swarm Optimization is an optimization algorithm that can be used as a control mechanism in robotic tasks, especially robotic search. Existing algorithms are tuned to use as little evaluations of the objective function as possible. Measuring the objective with a sensor usually has a low cost in terms of time and energy compared to moving the robot. We propose a new algorithm to optimize the particle movement in SMPSO that samples the same points in the environment with less movement cost. Our experiments show that the average movement cost can be reduced by \(50\%\) or more in all test problems we used. The huge gain shows that there is a big potential in adapting swarm intelligence algorithms to robotic applications by optimizing them to better serve the constraints of the application.

Keywords

PSO Swarm robotics Movement cost Energy efficiency 

References

  1. 1.
    Bartashevich, P., Koerte, D., Mostaghim, S.: Energy-saving decision making for aerial swarms: PSO-based navigation in vector fields. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1–8. IEEE, Honolulu, November 2017Google Scholar
  2. 2.
    Bosman, P.A.N., Thierens, D.: The balance between proximity and diversity in multiobjective evolutionary algorithms. IEEE Trans. Evol. Comput. 7(2), 174–188 (2003)CrossRefGoogle Scholar
  3. 3.
    Cheng, R., Jin, Y., Olhofer, M., Sendhoff, B.: Test problems for large-scale multiobjective and many-objective optimization. IEEE Trans. Cybern. PP(99), 1–14 (2016)CrossRefGoogle Scholar
  4. 4.
    Couceiro, M.S., Rocha, R.P., Ferreira, N.M.F.: A novel multi-robot exploration approach based on particle swarm optimization algorithms. In 9th IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2011, pp. 327–332. IEEE, Kyoto (2011)Google Scholar
  5. 5.
    Dadgar, M., Jafari, S., Hamzeh, A.: A PSO-based multi-robot cooperation method for target searching in unknown environments. Neurocomputing 177, 62–74 (2016)CrossRefGoogle Scholar
  6. 6.
    Deb, K., Thiele, L., Laumanns, M., Zitzler, E.: Scalable multi-objective optimization test problems. In: IEEE Congress on Evolutionary Computation (CEC), pp. 825–830. IEEE, Honolulu (2002)Google Scholar
  7. 7.
    Huband, S., Hingston, P., Barone, L., While, L.: A review of multiobjective test problems and a scalable test problem toolkit. IEEE Trans. Evol. Comput. 10(5), 477–506 (2006)CrossRefGoogle Scholar
  8. 8.
    Inácio, F.R., Macharet, D.G., Chaimowicz, L.: Pso-based strategy for the segregation of heterogeneous robotic swarms. J. Comput. Sci. 31, 86–94 (2018)CrossRefGoogle Scholar
  9. 9.
    Jatmiko, W., et al.: Robots implementation for odor source localization using PSO algorithm. WSEAS Trans. Circ. Syst. 10(4), 115–125 (2011)Google Scholar
  10. 10.
    Krishnanand, K.N., Ghose, D.: A glowworm swarm optimization based multi-robot system for signal source localization. In: Liu, D., Wang, L., Tan, K.C. (eds.) Design and Control of Intelligent Robotic Systems. SCI, pp. 49–68. Springer, Heidelberg (2009).  https://doi.org/10.1007/978-3-540-89933-4_3CrossRefGoogle Scholar
  11. 11.
    Mai, S., Zille, H., Steup, C., Mostaghim, S.: Multi-objective collective search and movement-based metrics in swarm robotics. In: Genetic and Evolutionary Computation Conference Companion (GECCO 2019 Companion). ACM, Prague (2019)Google Scholar
  12. 12.
    Mostaghim, S., Steup, C., Witt, F.: Energy aware particle swarm optimization as search mechanism for aerial micro-robots. In: 2016 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1–7. IEEE, Athens, December 2016Google Scholar
  13. 13.
    Nebro, A.J., Durillo, J.J., Garcia-Nieto, J., Coello, C.A., Luna, F., Alba, E.: SMPSO: a new PSO-based metaheuristic for multi-objective optimization. In: 2009 IEEE Symposium on Computational Intelligence in Multi-criteria Decision-Making (MCDM), pp. 66–73. IEEE, Nashville, March 2009Google Scholar
  14. 14.
    Nedjah, N., De Mendonça, R.M., De Macedo Mourelle, L.: PSO-based distributed algorithm for dynamic task allocation in a robotic swarm. Procedia Comput. Sci. 51(1), 326–335 (2015)CrossRefGoogle Scholar
  15. 15.
    Pugh, J., Martinoli, A.: Inspiring and modeling multi-robot search with particle swarm optimization. In: 2007 IEEE Swarm Intelligence Symposium, pp. 332–339. IEEE, Honolulu, April 2007Google Scholar
  16. 16.
    Senanayake, M., Senthooran, I., Barca, J.C., Chung, H., Kamruzzaman, J., Murshed, M.: Search and tracking algorithms for swarms of robots: a survey. Robot. Auton. Syst. 75, 422–434 (2016)CrossRefGoogle Scholar
  17. 17.
    Tian, Y., Cheng, R., Zhang, X., Jin, Y.: Platemo: a MATLAB platform for evolutionary multi-objective optimization. CoRR, abs/1701.00879, 1–20 (2017)Google Scholar
  18. 18.
    Zitzler, E., Deb, K., Thiele, L.: Comparison of multiobjective evolutionary algorithms: empirical results. Evol. Comput. 8(2), 173–195 (2000)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Otto-von-Guericke UniversityMagdeburgGermany

Personalised recommendations