Skip to main content Accessibility help
×
×
Home

Distributed Particle Swarm Optimization for limited-time adaptation with real robots

  • Ezequiel Di Mario (a1) and Alcherio Martinoli (a1)

Summary

Evaluative techniques offer a tremendous potential for online controller design. However, when the optimization space is large and the performance metric is noisy, the overall adaptation process becomes extremely time consuming. Distributing the adaptation process reduces the required time and increases robustness to failure of individual agents. In this paper, we analyze the role of the four algorithmic parameters that determine the total evaluation time in a distributed implementation of a Particle Swarm Optimization (PSO) algorithm. For an obstacle avoidance case study using up to eight robots, we explore in simulation the lower boundaries of these parameters and propose a set of empirical guidelines for choosing their values. We then apply these guidelines to a real robot implementation and show that it is feasible to optimize 24 control parameters per robot within 2 h, a limited amount of time determined by the robots' battery life. We also show that a hybrid simulate-and-transfer approach coupled with a noise-resistant PSO algorithm can be used to further reduce experimental time as compared to a pure real-robot implementation.

Copyright

Corresponding author

*Corresponding author. E-mail: ezequiel.dimario@epfl.ch

References

Hide All
1.Liang, J. J., Qu, B. Y., Suganthan, P. N. and Hernández-Díaz, A. G., “Problem Definitions and Evaluation Criteria for the CEC 2013 Special Session on Real-Parameter Optimization”, 2013.
2.Floreano, D. and Mondada, F., “Evolution of homing navigation in a real mobile robot”, IEEE Trans. Syst. Man Cybern. 26 (3), 396407 (1996).
3.Watson, R. a., Ficici, S. G. and Pollack, J. B., “Embodied Evolution: Distributing an evolutionary algorithm in a population of robots”, Robot. Auton. Syst. 39 (1–18) (Apr. 2002).
4.Kennedy, J. and Eberhart, R., “Particle Swarm Optimization”, IEEE International Conference on Neural Networks, vol.4 (1995) pp. 19421948.
5.Poli, R., “Analysis of the publications on the applications of particle swarm optimisation”, J. Artif. Evol. Appl. 2008 (2), 110 (2008).
6.Akat, S. B. and Gazi, V., “Decentralized Asynchronous Particle Swarm Optimization”, IEEE Swarm Intelligence Symposium, DOI: 10.1109/SIS.2008.4668304 (Sep. 2008).
7.Rada-Vilela, J., Zhang, M. and Seah, W., “Random Asynchronous PSO”, The 5th International Conference on Automation, Robotics and Applications (Dec. 2011) pp. 220–225.
8.Turduev, M. and Atas, Y., “Cooperative Chemical Concentration Map Building Using Decentralized Asynchronous Particle Swarm Optimization Based Search by Mobile Robots”, IEEE/RSJ International Conference on Intelligent Robots and Systems (2010) pp. 4175–4180.
9.Marques, L., Nunes, U. and Almeida, A. T., “Particle swarm-based olfactory guided search”, Auton. Robots 20, 277287 (May 2006).
10.Hereford, J. and Siebold, M., “Using the Particle Swarm Optimization Algorithm for Robotic Search Applications”, IEEE Swarm Intelligence Symposium (2007) pp. 53–59.
11.Jin, Y. and Branke, J., “Evolutionary optimization in uncertain environments: A survey”, IEEE Trans. Evolutionary Comput. 9, 303317 (June 2005).
12.Arnold, D. and Beyer, H.-G., “A general noise model and its effects on evolution strategy performance”, IEEE Trans. Evolutionary Comput. 10, 380391 (Aug. 2006).
13.Parsopoulos, K. E. and Vrahatis, M. N., “Particle Swarm Optimizer in Noisy and Continuously Changing Environments”, Artificial Intelligence and Soft Computing (Hamza, M. H., ed.) (IASTED/ACTA Press, 2001) pp. 289294.
14.Pan, H., Wang, L. and Liu, B., “Particle swarm optimization for function optimization in noisy environment”, Appl. Math. Comput. 181, 908919 (Oct. 2006).
15.Pugh, J., Zhang, Y. and Martinoli, A., “Particle Swarm Optimization for Unsupervised Robotic Learning”, IEEE Swarm Intelligence Symposium (2005) pp. 92–99.
16.Pugh, J. and Martinoli, A., “Distributed scalable multi-robot learning using particle swarm optimization”, Swarm Intell. 3, 203222 (May 2009).
17.Di Mario, E., Talebpour, Z. and Martinoli, A., “A Comparison of PSO and Reinforcement Learning for Multi-Robot Obstacle Avoidance”, IEEE Conference on Evolutionary Computation, vol. 1 (June 2013) pp. 149156.
18.De Jong, K. A., An Analysis of the Behavior of a Class of Genetic Adaptive Systems Ph.D. Thesis (University of Michigan, 1975).
19.Michel, O., “Webots: Professional mobile robot simulation”, Adv. Robot. Syst. 1 (1), 3942 (2004).
20.Lochmatter, T., Roduit, P., Cianci, C., Correll, N., Jacot, J. and Martinoli, A., “Swistrack-a Flexible Open Source Tracking Software for Multi-Agent Systems”, IEEE/RSJ International Conference on Intelligent Robots and Systems (2008) pp. 4004–4010.
21.Di Mario, E., Mermoud, G., Mastrangeli, M. and Martinoli, A., “A Trajectory-Based Calibration Method for Stochastic Motion Models”, IEEE/RSJ International Conference on Intelligent Robots and Systems (Sep. 2011) pp. 4341–4347.
22.Bratton, D. and Kennedy, J., “Defining a Standard for Particle Swarm Optimization”, IEEE Swarm Intelligence Symposium (Apr. 2007) pp. 120–127.
Recommend this journal

Email your librarian or administrator to recommend adding this journal to your organisation's collection.

Robotica
  • ISSN: 0263-5747
  • EISSN: 1469-8668
  • URL: /core/journals/robotica
Please enter your name
Please enter a valid email address
Who would you like to send this to? *
×

Keywords

Metrics

Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed