Abstract
Swarm behavior emerges from the local interaction of agents and their environment often encoded as simple rules. Extracting the rules by watching a video of the overall swarm behavior could help us study and control swarm behavior in nature, or artificial swarms that have been designed by external actors. It could also serve as a new source of inspiration for swarm robotics. Yet extracting such rules is challenging as there is often no visible link between the emergent properties of the swarm and their local interactions. To this end, we develop a method to automatically extract understandable swarm controllers from video demonstrations. The method uses evolutionary algorithms driven by a fitness function that compares eight high-level swarm metrics. The method is able to extract many controllers (behavior trees) in a simple collective movement task. We then provide a qualitative analysis of behaviors that resulted in different trees, but similar behaviors. This provides the first steps toward automatic extraction of swarm controllers based on observations.
Z. S. Abdallah and S. Hauert—Both authors have contributed equally to the work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amornbunchornvej, C., Berger-Wolf, T.: Framework for inferring following strategies from time series of movement data. ACM Trans. Knowl. Discov. Data 14(3), 35:1–35:22 (2020)
Bonnet, F., et al.: Robots mediating interactions between animals for interspecies collective behaviors. Sci. Robot. 4(28), eaau7897 (2019)
Brambilla, M., Ferrante, E., Birattari, M., Dorigo, M.: Swarm robotics: a review from the swarm engineering perspective. Swarm Intell. 7(1), 1–41 (2013)
Carrillo-Zapata, D., et al.: Mutual shaping in swarm robotics: user studies in fire and rescue, storage organization, and bridge inspection. Front. Robot. AI 7, 53 (2020)
Chatty, A., Gaussier, P., Kallel, I., Laroque, P., Alimi, A.M.: Learning by imitation for the improvement of the individual and the social behaviors of self-organized autonomous agents. In: Tan, Y., Shi, Y., Mo, H. (eds.) ICSI 2013. LNCS, vol. 7929, pp. 44–52. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38715-9_6
Chung, N., Miasojedow, B., Michał, S., Gambin1, A.: Jaccard/Tanimoto similarity test and estimation methods for biological presence-absence data. BMC Bioinform. 20 (2019)
Erbas, M.D., Bull, L., Winfield, A.F.T.: On the evolution of behaviors through embodied imitation. Artif. Life 21(2), 141–165 (2015)
Eriksson, A., Nilsson Jacobi, M., Nyström, J., Tunstrøm, K.: Determining interaction rules in animal swarms. Behav. Ecol. 21(5), 1106–1111 (2010)
Ferguson, E.A., Matthiopoulos, J., Insall, R.H., Husmeier, D.: Inference of the drivers of collective movement in two cell types: dictyostelium and melanoma. J. R. Soc. Interface 13(123), 20160695 (2016)
Francesca, G., Birattari, M.: Automatic design of robot swarms: achievements and challenges. Front. Robot. AI 3, 29 (2016)
Harriott, C., Seiffert, A., Hayes, S., Adams, J.: Biologically-inspired human-swarm interaction metrics. Proc. Hum. Factors Ergon. Soc. Ann. Meeting 58, 1471–1475 (2014)
Herbert-Read, J.E., Perna, A., Mann, R.P., Schaerf, T.M., Sumpter, D.J.T., Ward, A.J.W.: Inferring the rules of interaction of shoaling fish. Proc. Natl. Acad. Sci. 108(46), 18726–18731 (2011)
Hogg, E., Hauert, S., Harvey, D., Richards, A.: Evolving behaviour trees for supervisory control of robot swarms. Artif. Life Robot. 25(4), 569–577 (2020). https://doi.org/10.1007/s10015-020-00650-2
Hu, T.K., Gama, F., Chen, T., Wang, Z., Ribeiro, A., Sadler, B.: VGAI: end-to-end learning of vision-based decentralized controllers for robot swarms, pp. 4900–4904 (2021)
Jones, S., Studley, M., Hauert, S., Winfield, A.: Evolving behaviour trees for swarm robotics. In: Groß, R., et al. (eds.) Distributed Autonomous Robotic Systems. SPAR, vol. 6, pp. 487–501. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-73008-0_34
Li, J., Tan, Y.: A two-stage imitation learning framework for the multi-target search problem in swarm robotics. Neurocomputing 334, 249–264 (2019)
Li, W., Gauci, M., Groß, R.: Turing learning: a metric-free approach to inferring behavior and its application to swarms. Swarm Intell. 10(3), 211–243 (2016). https://doi.org/10.1007/s11721-016-0126-1
Mann, R.P.: Bayesian inference for identifying interaction rules in moving animal groups. PLoS ONE 6(8), e22827 (2011)
Manning, M.D., Harriott, C.E., Hayes, S.T., Adams, J.A., Seiffert, A.E.: Heuristic evaluation of swarm metrics’ effectiveness. In: Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts, p. 17–18 (2015)
Maxeiner, H.: Imitation learning of fish and swarm behavior with Recurrent Neural Networks. Master’s thesis, Dahlem Center for Machine Learning and Robotics (2019)
Nedjah, N., Junior, L.S.: Review of methodologies and tasks in swarm robotics towards standardization. Swarm Evol. Comput. 50, 100565 (2019)
Peyer, K.E., Zhang, L., Nelson, B.J.: Bio-inspired magnetic swimming microrobots for biomedical applications (2012)
Prorok, A., Blumenkamp, J., Li, Q., Kortvelesy, R., Liu, Z., Stump, E.: The holy grail of multi-robot planning: learning to generate online-scalable solutions from offline-optimal experts. arXiv abs/2107.12254 (2021)
Ruangdech, S., Hauert, S., Homer, M.: Inferring swarm models using a single monitoring robot. In: Artificial Life Conference Proceedings, no. 31, pp. 278–279 (2019)
Şahin, E.: Swarm robotics: from sources of inspiration to domains of application. In: Şahin, E., Spears, W.M. (eds.) SR 2004. LNCS, vol. 3342, pp. 10–20. Springer, Heidelberg (2005). https://doi.org/10.1007/978-3-540-30552-1_2
Schaerf, T.M., Herbert-Read, J.E., Ward, A.J.W.: A statistical method for identifying different rules of interaction between individuals in moving animal groups. J. R. Soc. Interface 18(176), rsif.2020.0925, 20200925 (2021)
Schilling, F., Lecoeur, J., Schiano, F., Floreano, D.: Learning vision-based flight in drone swarms by imitation. IEEE Robot. Autom. Lett. 4(4), 4523–4530 (2019)
Yu, X., Wu, W., Feng, P., Tian, Y.: Swarm inverse reinforcement learning for biological systems. In: 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 274–279 (2021)
Zhou, S., Phielipp, M.J., Sefair, J.A., Walker, S.I., Amor, H.B.: Clone swarms: learning to predict and control multi-robot systems by imitation. In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4092–4099 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Alharthi, K., Abdallah, Z.S., Hauert, S. (2022). Automatic Extraction of Understandable Controllers from Video Observations of Swarm Behaviors. In: Dorigo, M., et al. Swarm Intelligence. ANTS 2022. Lecture Notes in Computer Science, vol 13491. Springer, Cham. https://doi.org/10.1007/978-3-031-20176-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-20176-9_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20175-2
Online ISBN: 978-3-031-20176-9
eBook Packages: Computer ScienceComputer Science (R0)