Reinforcement Learning-Based Bezier Airship Hull Optimization: A Data-Driven Framework for Shape Adaptation Under Aerodynamic Constraints
Qian ZHAO, Carlo Emanuele Dionigi RIBOLDI
Abstract. This paper proposes a data-driven reinforcement learning framework for aerodynamic optimization of airship hulls. It combines Deep Deterministic Policy Gradient (DDPG) with Bezier curve parameterization to adjust the shape of the classic airship ”Lotte” [1,2,3]. A volume-preserving constraint ensures buoyancy consistency. Different from previous studies focused solely on drag minimization, we target lift-to-drag ratio (L/D) and robustness [4,5]. Simulations in SILCROAD [6,7,8,9] demonstrate significant improvement in L/D while preserving volume and smoothness. The approach offers a modular, scalable framework for future multi-objective extensions..
Keywords
Airship Design, Bezier Curves, Reinforcement Learning, DDPG, Lift-to-Drag Ratio Optimization, Robust Design, Aerodynamic Efficiency, Data-Driven Optimization
Published online 7/20/2026, 4 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Qian ZHAO, Carlo Emanuele Dionigi RIBOLDI, Reinforcement Learning-Based Bezier Airship Hull Optimization: A Data-Driven Framework for Shape Adaptation Under Aerodynamic Constraints, Materials Research Proceedings, Vol. 69, pp 846-849, 2026
DOI: https://doi.org/10.21741/9781644904251-149
The article was published as article 149 of the book CEAS – AIDAA Conference 2025
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] A. K. Shakya, G. Pillai, and S. Chakrabarty, “Reinforcement learning algorithms: A brief survey,” Expert Systems with Applications, vol. 231, 2023, Art. no. 120495. https://doi.org/10.1016/j.eswa.2023.120495.
[2] P. Alfeld, M. Neamtu, and L. L. Schumaker, “Circular Bernstein–Bezier polynomials,” in Mathematical Methods for Curves and Surfaces, 1995, pp. 11–20.
[3] T. P. Lillicrap et al., “Continuous control with deep reinforcement learning,” arXivpreprint arXiv:1509.02971, 2015
[4] R. T. Jones, Classical Aerodynamic Theory. National Aeronautics and Space Administration, 1979.
[5] S. P. Jones and J. D. DeLaurier, “Aerodynamic estimation techniques for aerostats and airships,” Journal of Aircraft, vol. 20, no. 2, pp. 120–126, 1982.
[6] C. E. D. Riboldi, M. Belan, S. Cacciola, R. Terenzi, S. Trovato, D. Usuelli, and G.Familiari, “Preliminary sizing of a low-altitude airship including ion-plasma thrusters,”in Proc. 34th Congress of the International Council of the Aeronautical Sciences (ICAS),Florence, Italy, Sept. 9–13, 2024.
[7] C. E. D. Riboldi and A. Rolando, “Layout analysis and optimization of airships with thrust-based stability augmentation,” Aerospace, vol. 9, p. 393, 2022.
[8] C. E. D. Riboldi and A. Rolando, “Thrust-based stabilization and guidance for airships without thrust-vectoring,” Aerospace, vol. 10, 2023.
[9] C. E. D. Riboldi, A. Rolando, and G. Regazzoni, “On the feasibility of a launcher- deployable high-altitude airship: Effects of design constraints in an optimal sizing framework,” Aerospace, vol. 9, pp. 1–37, 2022.
[10] A. Kornienko, System Identification Approach for Determining Flight Dynamical Characteristics of an Airship from Flight Data. Ph.D. dissertation, University of Stuttgart, 2006
[11] T. Lutz and S. Wagner, “Drag reduction and shape optimization of airship bodies,”Journal of Aircraft, vol. 35, no. 3, pp. 345–351, 1998.
[12] C. E. D. Riboldi and L. Fanchini, “Assessing the Technical–Economic Feasibility of Low-
Altitude Unmanned Airships: Methodology and Comparative Case Studies,” Aerospace,vol. 12, no. 3, p. 244, 2025.
[13] C. E. D. Riboldi and M. Tomasoni, “Formation Flight of Fixed-Wing UAVs: Dynamic Modeling, Guidance Design, and Testing in Realistic Scenarios,” Aerospace, vol. 12, no. 3, pp. 1–49, 2025.
