Evaluating Surrogate Models for Robot Swarm Simulations

evolutionary algorithm; machine learning; predictors; robot formation; surrogate models; swarm robotics; Machine-learning; Optimisations; Predictor; Robot formation; Robot swarms; Robotic simulation; Surrogate modeling; Swarm robotics; SWARM simulation; Swarm size; Computer Science (all); Mathematics (all); HPC

Abstract :

[en] Realistic robotic simulations are computationally demanding, especially when considering large swarms of autonomous robots. This makes the optimisation of such systems intractable, thus limiting the instances’ and swarms’ size. In this article we study the viability of using surrogate models based on Gaussian processes, Artificial Neural Networks, and simplified simulations, as predictors of the robots’ behaviour, when performing formations around a central point of interest. We have trained the predictors and tested them in terms of accuracy and execution time. Our findings show that they can be used as an alternative way of calculating fitness values for swarm configurations which can be used in optimisation processes, increasing the number evaluations and reducing execution times and computing cluster budget.

Research center :

Interdisciplinary Centre for Security, Reliability and Trust (SnT) > PCOG - Parallel Computing & Optimization Group
ULHPC - University of Luxembourg: High Performance Computing

Disciplines :

Computer science

Author, co-author :

STOLFI ROSSO, Daniel ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > PCOG

DANOY, Grégoire ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)

External co-authors :

Language :

English

Title :

Evaluating Surrogate Models for Robot Swarm Simulations

Publication date :

2023

Event name :

Optimization and Learning - 6th International Conference, OLA 2023

Event place :

Malaga, Esp

Event date :

03-05-2023 => 05-05-2023

Main work title :

Optimization and Learning - 6th International Conference, OLA 2023, Proceedings

Publisher :

Springer Nature Switzerland, Switzerland

Pages :

224-235

Peer reviewed :

Peer reviewed

Additional URL :

https://link.springer.com/content/pdf/10.1007/978-3-031-34020-8_17

FnR Project :

FNR14762457 - Automating The Design Of Autonomous Robot Swarms, 2020 (01/05/2021-30/04/2024) - Gregoire Danoy

Name of the research project :

R-AGR-3933 - C20/IS/14762457/ADARS (01/05/2021 - 30/04/2024) - DANOY Grégoire

Funders :

FNR - Luxembourg National Research Fund

Funding number :

C20/IS/14762457

Funding text :

This work is supported by the Luxembourg National Research Fund (FNR) – ADARS Project, ref. C20/IS/14762457.

Available on ORBilu :

since 16 November 2023

Statistics

Number of views

122 (4 by Unilu)

Number of downloads

1 (1 by Unilu)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

OpenAlex citations

Bibliography

Alizadeh, R., Allen, J.K., Mistree, F.: Managing computational complexity using surrogate models: a critical review. Res. Eng. Des. 31(3), 275–298 (2020). https://doi.org/10.1007/s00163-020-00336-7
Asher, M.J., Croke, B.F.W., Jakeman, A.J., Peeters, L.J.M.: A review of surrogate models and their application to groundwater modeling. Water Resour. Res. 51(8), 5957–5973 (2015). https://doi.org/10.1002/2015WR016967
Benítez-Hidalgo, A., Nebro, A.J., García-Nieto, J., Oregi, I., Ser, J.D.: jMetalPy: a python framework for multi-objective optimization with metaheuristics. Swarm Evolut. Comput. 100598 (2019). https://doi.org/10.1016/j.swevo.2019.100598
Cheng, S., Prentice, I.C., Huang, Y., Jin, Y., Guo, Y.K., Arcucci, R.: Data-driven surrogate model with latent data assimilation: Application to wildfire forecasting. J. Comput. Phys. 464, 111302 (2022). https://doi.org/10.1016/j.jcp.2022.111302
Cozad, A., Sahinidis, N.V., Miller, D.C.: Learning surrogate models for simulation-based optimization. AIChE J. 60(6), 2211–2227 (2014). https://doi.org/10.1002/aic.14418
Deb, K.: Multi-Objective Optimization Using Evolutionary Algorithms. John Wiley & Sons Inc., USA (2001)
Fritsch, S., Guenther, F., Wright, M.N., Suling, M., Mueller, S.M.: neuralnet: training of neural networks (2022). https://CRAN.R-project.org/package=neuralnet. Accessed 8 Dec 2022
Goldberg, D.E., Deb, K.: A comparative analysis of selection schemes used in genetic algorithms. Found. Genet. Algorithms 1, 69–93 (1991). https://doi.org/10. 1016/B978-0-08-050684-5.50008-2
Lopes, H.J., Lima, D.A.: Evolutionary Tabu inverted ant cellular automata with elitist inertia for swarm robotics as surrogate method in surveillance task using e-puck architecture. Robot. Auton. Syst. 144, 103840 (2021). https://doi.org/10. 1016/j.robot.2021.103840
do Nascimento, R.G., Fricke, K., Viana, F.: Quadcopter control optimization through machine learning. In: AIAA Scitech 2020 Forum. No. 0 in AIAA SciTech Forum, American Institute of Aeronautics and Astronautics, January 2020. https://doi.org/10.2514/6.2020-1148
Piironen, J.: gplite: General purpose gaussian process modelling (2022). https://cran.r-project.org/package=gplite. Accessed 8 Dec 2022
Pinciroli, C., et al.: ARGoS: a modular, parallel, multi-engine simulator for multi-robot systems. Swarm Intell. 6(4), 271–295 (2012). https://doi.org/10.1007/s11721-012-0072-5
Poggi, C., et al.: Surrogate models for predicting noise emission and aerodynamic performance of propellers. Aerosp. Sci. Technol. 125, 107016 (2022). https://doi. org/10.1016/j.ast.2021.107016, sI: DICUAM 2021
Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: the rprop algorithm. In: IEEE International Conference on Neural Networks, vol. 1, pp. 586–591 (1993). https://doi.org/10.1109/ICNN.1993.298623
Rosalie, M., Kieffer, E., Brust, M.R., Danoy, G., Bouvry, P.: Bayesian optimisation to select Rössler system parameters used in chaotic ant colony optimisation for coverage. J. Comput. Sci. 41, 101047 (2020). https://doi.org/10.1016/j.jocs.2019. 101047
Seeger, M.: Gaussian processes for machine learning. Int. J. Neural Syst.14(02), 69–106 (2004). https://doi.org/10.1142/s0129065704001899
Spiri Robotics: Spiri mu (2022). https://spirirobotics.com/. Accessed 26 Sep 2022
Stolfi, D.H., Danoy, G.: Optimising autonomous robot swarm parameters for stable formation design. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 1281–1289. GECCO 2022, Association for Computing Machinery, New York, NY, USA (2022). https://doi.org/10.1145/3512290.3528709
Stolfi, D.H., Danoy, G.: An evolutionary algorithm to Optimise a distributed UAV swarm formation system. Appl. Sci. 12(20) (2022). https://doi.org/10.3390/app122010218
Syswerda, G.: Uniform crossover in genetic algorithms. In: Proceedings of the 3rd International Conference on Genetic Algorithms, pp. 2–9. Morgan Kaufmann Publishers Inc. (1989)
Varrette, S., Cartiaux, H., Peter, S., Kieffer, E., Valette, T., Olloh, A.: Management of an academic HPC & research computing facility: the ULHPC experience 2.0. In: Proceedings of the 6th ACM High Performance Computing and Cluster Technologies Conference (HPCCT 2022). Association for Computing Machinery (ACM), Fuzhou, China, July 2022
Westermann, P., Evins, R.: Surrogate modelling for sustainable building design-a review. Energy Build. 198, 170–186 (2019). https://doi.org/10.1016/j.enbuild. 2019.05.057
Yelten, M.B., Zhu, T., Koziel, S., Franzon, P.D., Steer, M.B.: Demystifying surrogate modeling for circuits and systems. IEEE Circuits Syst. Mag. 12(1), 45–63 (2012). https://doi.org/10.1109/MCAS.2011.2181095
Yue, H., Medromi, H., Ding, H., Bassir, D.: A novel hybrid drone for multi-propose aerial transportation and its conceptual optimization based on surrogate approach. J. Phys. Conf. Ser. 1972(1), 012103 (2021). https://doi.org/10.1088/1742-6596/1972/1/012103