Abstract
Behaviour trees (BTs) are commonly used as controllers in robotic swarms due their modular composition and to the fact that they can be easily interpreted by humans. From an algorithmic perspective, an additional advantage is that extra modules can easily be introduced and incorporated into new trees. Genetic Programming (GP) has already been shown to be capable of evolving BTs to achieve a variety of sub-tasks (primitives) of a higher-level goal. In this work we show that a hierarchical controller can be evolved that first uses GP to evolve a repertoire of primitives expressed as BTs, and then to evolve a high-level BT controller that leverages the evolved repertoire for a foraging task. We show that the hierarchical approach that uses BTs at two levels outperforms a baseline in which the BTs are evolved using only low-level nodes. In addition, we propose a method to improve the quality of the primitive repertoire, which in turn results in improved high-level BTs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
Obviously objectives such as increase density and decrease density are mutually exclusive and therefore are never considered together.
- 4.
Experiments in Sect. 4.1 showed that the performance of MTGP using compatible objectives was often better than using incompatible objectives.
- 5.
Further work should increase the number of runs from the 10 performed to ascertain whether we should be confident in this result.
- 6.
All experiments were run for the same amount of computational time taking into account the time taken to evolve the primitives: thus the baseline experiments are run for more generations than the arbitrator.
References
Bonani, M., et al.: The marxbot, a miniature mobile robot opening new perspectives for the collective-robotic research. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4187–4193 (2010). https://doi.org/10.1109/IROS.2010.5649153
Bossens, D.M., Mouret, J.B., Tarapore, D.: Learning behaviour-performance maps with meta-evolution. In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference, pp. 49–57. GECCO ’20, Association for Computing Machinery, New York, NY, USA (2020). https://doi.org/10.1145/3377930.3390181
Cambier, N., Ferrante, E.: AutoMoDe-pomodoro: an evolutionary class of modular designs, pp. 100–103 (2022). https://doi.org/10.1145/3520304.3529031
Colledanchise, M., Ögren, P.: How behavior trees modularize hybrid control systems and generalize sequential behavior compositions, the subsumption architecture, and decision trees. IEEE Trans. Rob. 33(2), 372–389 (2017). https://doi.org/10.1109/TRO.2016.2633567
Colledanchise, M., Ögren, P.: Behavior trees in robotics and AI: an introduction. CoRR abs/1709.00084 (2017). http://arxiv.org/abs/1709.00084
Cully, A., Clune, J., Tarapore, D., Mouret, J.B.: Robots that can adapt like animals. Nature 521(7553), 503–507 (2015)
Duarte, M., Gomes, J., Oliveira, S., Christensen, A.: EvoRBC: evolutionary repertoire-based control for robots with arbitrary locomotion complexity (2016). https://doi.org/10.1145/2908812.2908855
Duarte, M., Gomes, J., Oliveira, S.M., Christensen, A.L.: Evolution of repertoire-based control for robots with complex locomotor systems. IEEE Trans. Evol. Comput. 22(2), 314–328 (2018). https://doi.org/10.1109/TEVC.2017.2722101
Fortin, F.A., De Rainville, F.M., Gardner, M., Parizeau, M., Gagné, C.: DEAP: evolutionary algorithms made easy. J. Mach. Learn. Res. Mach. Learn. Open Source Softw. 13, 2171–2175 (2012)
Francesca, G., et al.: AutoMoDe-chocolate: automatic design of control software for robot swarms. Swarm Intell. 9 (2015)
Francesca, G., Brambilla, M., Brutschy, A., Trianni, V., Birattari, M.: AutoMoDe: a novel approach to the automatic design of control software for robot swarms. Swarm Intell. 8, 1–24 (2014). https://doi.org/10.1007/s11721-014-0092-4
Francesca, G., Brambilla, M., Brutschy, A., Trianni, V., Birattari, M.: Automode: a novel approach to the automatic design of control software for robot swarms. Swarm Intell. 8, 89–112 (2014). https://doi.org/10.1007/s11721-014-0092-4
Gomes, J., Christensen, A.L.: Task-agnostic evolution of diverse repertoires of swarm behaviours. In: Dorigo, M., Birattari, M., Blum, C., Christensen, A.L., Reina, A., Trianni, V. (eds.) Swarm Intelligence, pp. 225–238. Springer International Publishing, Cham (2018). https://doi.org/10.1007/978-3-030-00533-7_18
Gomes, J., Oliveira, S.M., Christensen, A.L.: An approach to evolve and exploit repertoires of general robot behaviours. Swarm Evol. Comput. 43, 265–283 (2018)
Hasselmann, K., Ligot, A., Birattari, M.: Automatic modular design of robot swarms based on repertoires of behaviors generated via novelty search. Swarm Evol. Comput. 83, 101395 (2023). https://doi.org/10.1016/j.swevo.2023.101395
Hogg, E., Hauert, S., Harvey, D., Richards, A.: Evolving behaviour trees for supervisory control of robot swarms. Artif. Life Robot. 25, 569–577 (2020)
Kuckling, J., Ligot, A., Bozhinoski, D., Birattari, M.: Behavior trees as a control architecture in the automatic modular design of robot swarms. In: Dorigo, M., Birattari, M., Blum, C., Christensen, A.L., Reina, A., Trianni, V. (eds.) Swarm Intelligence, pp. 30–43. Springer International Publishing, Cham (2018). https://doi.org/10.1007/978-3-030-00533-7_3
Kuckling, J., Ligot, A., Bozhinoski, D., Birattari, M.: Behavior trees as a control architecture in the automatic modular design of robot swarms. In: Dorigo, M., Birattari, M., Blum, C., Christensen, A.L., Reina, A., Trianni, V. (eds.) ANTS 2018. LNCS, vol. 11172, pp. 30–43. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00533-7_3
Kuckling, J., van Pelt, V., Birattari, M.: Automatic modular design of behavior trees for robot swarms with communication capabilites. In: Castillo, P.A., Jiménez Laredo, J.L. (eds.) Applications of Evolutionary Computation, pp. 130–145. Springer International Publishing, Cham (2021). https://doi.org/10.1007/978-3-030-72699-7_9
Kuckling, J., Ubeda Arriaza, K., Birattari, M.: AutoMoDe-icepop: automatic modular design of control software for robot swarms using simulated annealing. In: Bogaerts, B., et al. (eds.) Artificial Intelligence and Machine Learning, pp. 3–17. Springer International Publishing, Cham (2020). https://doi.org/10.1007/978-3-030-65154-1_1
Kuckling, J., Van Pelt, V., Birattari, M.: AutoMoDe-cedrata: automatic design of behavior trees for controlling a swarm of robots with communication capabilities. SN Comput. Sci. 3(2), 136 (2022). https://doi.org/10.1007/s42979-021-00988-9
Ligot, A., Hasselmann, K., Birattari, M.: AutoMoDe-arlequin: neural networks as behavioral modules for the automatic design of probabilistic finite-state machines. In: Dorigo, M., et al. (eds.) Swarm Intelligence, pp. 271–281. Springer International Publishing, Cham (2020)
López-Ibáñez, M., Dubois-Lacoste, J., Pérez Cáceres, L., Birattari, M., Stützle, T.: The irace package: iterated racing for automatic algorithm configuration. Oper. Res. Perspect. 3, 43–58 (2016). https://doi.org/10.1016/j.orp.2016.09.002, https://www.sciencedirect.com/science/article/pii/S2214716015300270
Montague, K., Hart, E., Nitschke, G., Paechter, B.: A quality-diversity approach to evolving a repertoire of diverse behaviour-trees in robot swarms. In: Correia, J., Smith, S., Qaddoura, R. (eds.) Applications of Evolutionary Computation, pp. 145–160. Springer Nature Switzerland, Cham (2023). https://doi.org/10.1007/978-3-031-30229-9_10
Pinciroli, C., et al.: ARGoS: a modular, parallel, multi-engine simulator for multi-robot systems. Swarm Intell. 6, 271–295 (2012). https://doi.org/10.1007/s11721-012-0072-5
Wei, T., Wang, S., Zhong, J., Liu, D., Zhang, J.: A review on evolutionary multi-task optimization: trends and challenges. IEEE Trans. Evol. Comput. (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Montague, K., Hart, E., Paechter, B. (2024). A Hierarchical Approach to Evolving Behaviour-Trees for Swarm Control. In: Smith, S., Correia, J., Cintrano, C. (eds) Applications of Evolutionary Computation. EvoApplications 2024. Lecture Notes in Computer Science, vol 14634. Springer, Cham. https://doi.org/10.1007/978-3-031-56852-7_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-56852-7_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-56851-0
Online ISBN: 978-3-031-56852-7
eBook Packages: Computer ScienceComputer Science (R0)