Epigenetic regulation for dynamic UAV-swarm optimization—EpiSwarm
-
Jordi Vallverdú
Department of Philosophy, Universitat Autònoma de Barcelona (UAB), 08193 Cerdanyola del Vallès, Spain
Abstract
Evolutionary algorithms adapt mainly through selection, recombination, and mutation, which in changing environments forces costly re-optimization and slow recovery after disruption. We present EpiSwarm, an evolutionary algorithm for dynamic industrial UAV-swarm inspection in which each candidate solution carries a persistent genotype and a fast-changing, partially heritable epigenotype. The genotype encodes mission structure; the epigenotype is a decaying memory of recent environmental stress that modulates task activation, route repair, operator intensity, and energy-aware reassignment. On a UAV-swarm inspection benchmark (8 UAVs, 45 tasks, three volatility regimes, n = 10 replications) EpiSwarm reduces mean replanning churn by about 60% (from 12–15 to 5–6 changes per epoch) and improves mission utility by 10.7–14.2% over the best of four baselines—including a memory-archive GA—with this advantage robust across four objective-weight specifications (p between 0.009 and 0.052). A matched paired ablation (n = 20) shows that the benefit of transgenerational inheritance is regime-dependent: it is significant at low volatility (p = 0.025) and vanishes as disruptions accelerate. We show that this crossover is not incidental but follows a closed-form memory-horizon condition, τepi ≲ τenv/g, that predicts a priori the regime in which inherited memory ceases to be informative—a computational instance of the established evolutionary-biology result that the value of transgenerational information is set by environmental autocorrelation. The stress-driven update is directionally positive but not statistically separable at this sample size, and is reported as such. EpiSwarm therefore contributes a quantitatively predictable, low-churn regulatory mechanism for dynamic swarm optimization rather than a universally beneficial add-on.
Copyright (c) 2026 Jordi Vallverdú
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[1]Branke J. Evolutionary Optimization in Dynamic Environments. Springer; 2002. doi: 10.1007/978-1-4615-0911-0
[2]Nguyen TT, Yang S, Branke J. Evolutionary dynamic optimization: A survey of the state of the art. Swarm and Evolutionary Computation. 2012; 6: 1–24. doi: 10.1016/j.swevo.2012.05.001
[3]Bäck THW, Kononova AV, Van Stein B, et al. Evolutionary Algorithms for Parameter Optimization—Thirty Years Later. Evolutionary Computation. 2023; 31(2): 81–122. doi: 10.1162/evco_a_00325
[4]Alqefari S, Menai MEB. Multi-UAV Task Assignment in Dynamic Environments: Current Trends and Future Directions. Drones. 2025; 9(1): 75. doi: 10.3390/drones9010075
[5]Wu H, Peng Q, Shi M, et al. A Survey of UAV Swarm Task Allocation Based on the Perspective of Coalition Formation: International Journal of Swarm Intelligence Research. 2022; 13(1): 1–22. doi: 10.4018/IJSIR.311499
[6]Li M, Li N, Shao X, et al. Survey on Collaborative Task Assignment for Heterogeneous UAVs Based on Artificial Intelligence Methods. CAAI Artificial Intelligence Research. 2024; 3: 9150033. doi: 10.26599/AIR.2024.9150033
[7]Zhang C, Xu C, Li G, et al. A distributed task allocation approach for multi-UAV persistent monitoring in dynamic environments. Scientific Reports. 2025; 15(1): 6437. doi: 10.1038/s41598-025-89787-3
[8]Wang G, Lv X, Yan X. A Two-Stage Distributed Task Assignment Algorithm Based on Contract Net Protocol for Multi-UAV Cooperative Reconnaissance Task Reassignment in Dynamic Environments. Sensors. 2023; 23(18): 7980. doi: 10.3390/s23187980
[9]Phadke A, Medrano FA. Examining application-specific resiliency implementations in UAV swarm scenarios. Intelligence & Robotics. 2023; 3(3): 453–478. doi: 10.20517/ir.2023.27
[10]Laland KN, Uller T, Feldman MW, et al. The extended evolutionary synthesis: its structure, assumptions and predictions. Proceedings of the Royal Society B: Biological Sciences. 2015; 282(1813): 20151019. doi: 10.1098/rspb.2015.1019
[11]Pigliucci M, Müller GB (editors). Evolution, the Extended Synthesis. The MIT Press; 2010. doi: 10.7551/mitpress/9780262513678.001.0001
[12]Yuen S, Ezard THG, Sobey AJ. Epigenetic opportunities for evolutionary computation. Royal Society Open Science. 2023; 10(5): 221256. doi: 10.1098/rsos.221256
[13]Yuen S, Ezard THG, Sobey AJ. The effect of epigenetic blocking on dynamic multi-objective optimisation problems. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion; 9-13 July 2022; Boston, MA, USA. pp. 379–382. doi: 10.1145/3520304.3529022
[14]Stolfi DH, Alba E. Epigenetic algorithms: A New way of building GAs based on epigenetics. Information Sciences. 2018; 424: 250–272. doi: 10.1016/j.ins.2017.10.005
[15]Yazdani D, Yazdani D, Branke J, et al. Robust Optimization Over Time by Estimating Robustness of Promising Regions. IEEE Transactions on Evolutionary Computation. 2023; 27(3): 657–670. doi: 10.1109/TEVC.2022.3180590
[16]Ong YS, Keane AJ. Meta-Lamarckian Learning in Memetic Algorithms. IEEE Transactions on Evolutionary Computation. 2004; 8(2): 99–110. doi: 10.1109/TEVC.2003.819944
[17]Neri F, Cotta C. Memetic algorithms and memetic computing optimization: A literature review. Swarm and Evolutionary Computation. 2012; 2: 1–14. doi: 10.1016/j.swevo.2011.11.003
[18]Wu F, Wang W, Chen J, et al. A dynamic multi-objective optimization method based on classification strategies. Scientific Reports. 2023; 13(1): 15221. doi: 10.1038/s41598-023-41855-2
[19]Peng H, Xiong J, Pi C, et al. A dynamic multi-objective optimization evolutionary algorithm with adaptive boosting. Swarm and Evolutionary Computation. 2024; 89: 101621. doi: 10.1016/j.swevo.2024.101621
[20]Jiang S, Yang S. A Strength Pareto Evolutionary Algorithm Based on Reference Direction for Multiobjective and Many-Objective Optimization. IEEE Transactions on Evolutionary Computation. 2017; 21(3): 329–346. doi: 10.1109/TEVC.2016.2592479
[21]Gašperov B, Đurasević M, Jakobovic D. Leveraging More of Biology in Evolutionary Reinforcement Learning. In: Smith S, Correia J, Cintrano C (editors). Applications of Evolutionary Computation. Springer Nature; 2024. pp. 91–114. doi: 10.1007/978-3-031-56855-8_6
[22]Jablonka E, Lamb MJ. Evolution in Four Dimensions: Genetic, Epigenetic, Behavioral, and Symbolic Variation in the History of Life. MIT Press; 2014.
[23]Shan Y. The extended evolutionary synthesis: An integrated historical and philosophical examination. Philosophy Compass. 2024; 19(6): e13002. doi: 10.1111/phc3.13002
[24]Zhang Z, Jiang J, Xu H, et al. Distributed dynamic task allocation for unmanned aerial vehicle swarm systems: A networked evolutionary game-theoretic approach. Chinese Journal of Aeronautics. 2024; 37(6): 182–204. doi: 10.1016/j.cja.2023.12.027
[25]Wang P, Ma Y. A dynamic multiobjective evolutionary algorithm based on fine prediction strategy and nondominated solutions-guided evolution. Applied Intelligence. 2023; 53(15): 18398–18419. doi: 10.1007/s10489-022-04429-9
[26]Eiben AE, Hinterding R, Michalewicz Z. Parameter control in evolutionary algorithms. IEEE Transactions on Evolutionary Computation. 1999; 3(2): 124–141. doi: 10.1109/4235.771166
[27]Leimar O, McNamara JM. The Evolution of Transgenerational Integration of Information in Heterogeneous Environments. The American Naturalist. 2015; 185(3): E55–E69. doi: 10.1086/679575
[28]McNamara JM, Dall SRX, Hammerstein P, et al. Detection vs. selection: integration of genetic, epigenetic and environmental cues in fluctuating environments. Ecology Letters. 2016; 19(10): 1267–1276. doi: 10.1111/ele.12663
