Abstract
Recent work has developed value functions that can recognize emergent swarming behaviour and distinguish it from random behaviour. To date, this work has been done in point-mass swarm simulations. This paper proposes a transfer learning approach that can improve the performance of a value system for recognising swarming in simulated and real robots from limited data without replicating the training. A source value function is trained on human-labelled point-mass boid data. A target tree is trained on a small amount of new domain specific data. It can recognise swarm behaviour of diverse agents not used in the original training. We test the value function on homogeneous swarms of simulated and real robots. Results show that this value function can detect swarming in at least 89% of cases.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kolling, A., et al.: human interaction with robot swarms: a survey. IEEE Trans. Hum. Mach. Syst. 46(1), 9–26 (2016)
Reynolds, C.W.: Flocks, herds, and schools: a distributed behavioral model. Comput. Graph. 21(4), 25–34 (1987)
Clark, J.B., Jacques, D.R.: Flight test results for UAVs using boid guidance algorithms. Conf. Syst. Eng. Res. 8, 232–238 (2012)
Kasmarik, K., Abpeikar, S., Khan, M.M., Khattab, N., Barlow, M., Garratt, M.: Autonomous recognition of collective behaviour in robot swarms. In: Gallagher, M., Moustafa, N., Lakshika, E. (eds.) AI 2020. LNCS (LNAI), vol. 12576, pp. 281–293. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-64984-5_22
Khan, M.M., Kasmarik, K., Barlow, M.: Autonomous detection of collective behaviours in swarms. Swarm Evol. Comput. 57, 100715 (2020)
Elgibreen, H., Aksoy, M.S.: RULES-IT: incremental transfer learning with RULES family. Front. Comp. Sci. 8(4), 537–562 (2014). https://doi.org/10.1007/s11704-014-3297-1
Lu, J., et al.: Transfer learning using computational intelligence: a survey. Knowl.-Based Syst. 80, 14–23 (2015)
Weiss, K., Khoshgoftaar, T.M., Wang, D.: A survey of transfer learning. J. Big Data 3(1), 1–40 (2016). https://doi.org/10.1186/s40537-016-0043-6
Degrave, J., et al.: Transfer learning of gaits on a quadrupedal robot. Adapt. Behav. 23(2), 69–82 (2015)
Atyabi, A., Powers, D.M.: Cooperative area extension of PSO-transfer learning vs. uncertainty in a simulated swarm robotics. In: International Conference on Informatics in Control, Automation and Robotics. SCITEPRESS (2013)
Venturini, F., et al.: Distributed reinforcement learning for flexible UAV swarm control with transfer learning capabilities. In: Proceedings of the 6th ACM Workshop on Micro Aerial Vehicle Networks, Systems, and Applications. Association for Computing Machinery: Toronto, Ontario, Canada. p. Article 10 (2020)
Iuzzolino, M.L., Walker, M.E., Szafir, D.: Virtual-to-real-world transfer learning for robots on wilderness trails. In: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2018)
Nguyen, T.T., Hatua, A., Sung, A.H.: Cumulative training and transfer learning for multi-robots collision-free navigation problems. In: 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) (2019)
won Lee, J., Giraud-Carrier, C.: Transfer learning in decision trees. In: 2007 International Joint Conference on Neural Networks. IEEE (2007)
Minvielle, L., et al.: Transfer learning on decision tree with class imbalance. In: 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI). IEEE (2019)
Hlynsson, H.: Transfer learning using the minimum description length principle with a decision tree application (2007)
Parvin, H., MirnabiBaboli, M., Alinejad-Rokny, H.: Proposing a classifier ensemble framework based on classifier selection and decision tree. Eng. Appl. Artif. Intell. 37, 34–42 (2015)
Kuncheva, L.I.: On the optimality of Naive Bayes with dependent binary features. Pattern Recogn. Lett. 27(7), 830–837 (2006)
Abe, S.: Support Vector Machines for Pattern Classification, Second Edition. Support Vector Machines for Pattern Classification, Second Edition, pp. 1–471 (2010)
Mukherjee, I., Routroy, S.: Comparing the performance of neural networks developed by using Levenberg-Marquardt and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process. Expert Syst. Appl. 39(3), 2397–2407 (2012)
Abpeikar, S., et al.: Swarm Behaviour Dataset on UCI Data Repository. UCI Data Repository: UCI Data Repository (2020)
Utgoff, P.E., Berkman, N.C., Clouse, J.A.: Decision tree induction based on efficient tree restructuring. Mach. Learn. 29(1), 5–44 (1997)
Segev, N., et al.: Learn on source, refine on target: a model transfer learning framework with random forests. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1811–1824 (2017)
Abpeikar, S., et al.: Human Perception of Swarming (Online Survey) (2019). https://unsw-swarm-survey.netlify.com/
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
Abpeikar, S., Kasmarik, K., Tran, P.V., Garratt, M. (2022). Transfer Learning for Autonomous Recognition of Swarm Behaviour in UGVs. In: Long, G., Yu, X., Wang, S. (eds) AI 2021: Advances in Artificial Intelligence. AI 2022. Lecture Notes in Computer Science(), vol 13151. Springer, Cham. https://doi.org/10.1007/978-3-030-97546-3_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-97546-3_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-97545-6
Online ISBN: 978-3-030-97546-3
eBook Packages: Computer ScienceComputer Science (R0)