To address the challenges of low integration in sensing systems and the difficulties in acquiring high-sensitivity signals for bio-inspired flapping-wing aerial vehicles in complex sensing tasks, this study proposes a coordinated approach of “origami encoding-dielectric liquid sensing-neural-network decoding” and constructs an intelligent sensing system based on Peano‑HASEL and an origami substrate. The system encodes aerodynamic and collision loads into local deformations through the origami structure, which are then converted into capacitance signals by the Peano‑HASEL units, and further processed via a one‑dimensional convolutional neural network (1D‑CNN) for feature extraction and recognition. The results show that the system achieves recognition accuracies of 98.15%, 98.38%, and 100% for 8 wind directions, 6 pitch‑angle states, and 7 wind‑speed levels, respectively. In collision experiments, the classification accuracy for 7 types of obstacles reaches 97.96%, and the accuracy for collision‑location identification attains 98.21%. The study demonstrates that the proposed sensing mechanism exhibits high sensitivity and multi‑modal signal‑decoding capability, providing a key technological foundation for environmental perception and autonomous adaptation in flapping‑wing aerial vehicles.
此单元与仿生折纸基底的关键柔性铰链(翼根处)集成后,当铰链因外部载荷(如气动力)发生转动时,会挤压或拉伸集成的Peano-HASEL液袋,导致其内部不可压缩的硅油发生迁移,从而改变传感电极区域的局部几何形态,如图4所示。铰链向一个方向弯曲可使液袋在电极区鼓胀,增大 d 并可能略微减小 A;反向弯曲则使液袋压扁,减小 d 并增大 A,这种几何变化直接、灵敏地调制了电容 C。因此,折纸铰链的机械形变被直接编码为传感单元电容的连续、单调变化信号。
ZhangJun, ChenLei, GaoZhijie, et al. Low-altitude unmanned aerial vehicle technology: current status and prospects[J]. Strategic Study of CAE, 2025, 27(2): 73-85.
ChengCheng, ChenLong, ZhangYanlai, et al. A review of aerodynamic design for hover-capable flapping-wing micro air vehicles[J]. Acta Aerodynamica Sinica, 2025, 43(2): 1-26.
[5]
NeckerR. Observations on the function of a slowly-adapting mechanoreceptor associated with filoplumes in the feathered skin of pigeons[J]. Journal of Comparative Physiology A, 1985, 156(3): 391-394.
[6]
GaedeA H, WuP H, LeitchD B. Variations in touch representation in the hummingbird and zebra finch forebrain[J]. Current Biology, 2024, 34(12): 2739-2747.
[7]
XiongW N, ZhuC, GuoD L, et al. Bio-inspired, intelligent flexible sensing skin for multifunctional flying perception[J]. Nano Energy, 2021, 90: 106550.
[8]
KimT, HongI, ImS, et al. Wing-strain-based flight control of flapping-wing drones through reinforcement learning[J]. Nature Machine Intelligence, 2024, 6(9): 992-1005.
[9]
HouK Y, TanT, WangZ M, et al. Scarab beetle-inspired embodied-energy membranous-wing robot with flapping-collision piezo-mechanoreception and mobile environmental monitoring[J]. Advanced Functional Materials, 2024, 34(10): 2303745.
[10]
TanT, HouK Y, XuY M, et al. Embodied flight perception via forewing-hindwing integration in lepidopteran-inspired aerial robotics[J]. Advanced Functional Materials, 2026, 36(28): e21940.
[11]
LiQ, TanT, WangB L, et al. Avian-inspired embodied perception in biohybrid flapping-wing robotics[J]. Nature Communications, 2024, 15: 9099.
[12]
KellarisN, Gopaluni VenkataV, SmithG M, et al. Peano-HASEL actuators: muscle-mimetic, electrohydraulic transducers that linearly contract on activation[J]. Science Robotics, 2018, 3(14): eaar3276.
[13]
GravertS D, VariniE, KazemipourA, et al. Low-voltage electrohydraulic actuators for untethered robotics[J]. Science Advances, 2024, 10: eadi9319.
[14]
RumleyE H, PreningerD, Shagan ShomronA, et al. Biodegradable electrohydraulic actuators for sustainable soft robots[J]. Science Advances, 2023, 9(12): eadf5551.
[15]
KellarisN, RothemundP, ZengY, et al. Spider-inspired electrohydraulic actuators for fast, soft-actuated joints[J]. Advanced Science, 2021, 8(14): 2100916.
[16]
WangT L, JooH J, SongS Y, et al. A versatile jellyfish-like robotic platform for effective underwater propulsion and manipulation[J]. Science Advances, 2023, 9(15): eadg0292.
[17]
BuchnerT J K, FukushimaT, KazemipourA, et al. Electrohydraulic musculoskeletal robotic leg for agile, adaptive, yet energy-efficient locomotion[J]. Nature Communications, 2024, 15: 7634.
[18]
BrackenburyJ H. Wing folding and free-flight kinematics in Coleoptera (Insecta): a comparative study[J]. Journal of Zoology, 1994, 232(2): 253-283.
[19]
YangJ Y, YouZ. Folding miura-ori of uniform thickness with one degree-of-freedom[J]. Journal of Mechanisms and Robotics, 2024, 16(11): 111004.
[20]
SchenkM, GuestS D. Geometry of miura-folded metamaterials[J]. Proceedings of the National Academy of Sciences of the United States of America, 2013, 110(9): 3276-3281.
[21]
GradinaruL M, VladS, SpiridonI, et al. Durability of polyurethane membranes in artificial weathering environment[J]. Polymer Testing, 2019, 80: 106144.
[22]
SinghS, BhargawH N, JadhavM, et al. A comparative analysis between deep neural network-based 1D-CNN and LSTM models to harness the self-sensing property of the shape memory alloy wire actuator for position estimation[J]. Smart Materials and Structures, 2024, 33(8): 085045.
[23]
LecunY, BottouL, BengioY, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[24]
KiranyazS, InceT, GabboujM. Real-time patient-specific ECG classification by 1-D convolutional neural networks[J]. IEEE Transactions on Biomedical Engineering, 2016, 63(3): 664-675.
[25]
TayeM M. Theoretical understanding of convolutional neural network: concepts, architectures, applications, future directions[J]. Computation, 2023, 11(3): 52.
[26]
KrichenM. Convolutional neural networks: a survey[J]. Computers, 2023, 12(8): 151.
[27]
DasD, SadiqA S, MirjaliliS. Optimization Algorithms in Machine Learning: A Meta-Heuristics Perspective[M]. Singapore: Springer Nature Singapore, 2025.
[28]
GoelR, BansalS, GuptaK. Improved feature reduction framework for sign language recognition using autoencoders and adaptive Grey Wolf Optimization[J]. Scientific Reports, 2025, 15: 2300.
[29]
HoY, WookeyS. The real-world-weight cross-entropy loss function: modeling the costs of mislabeling[J]. IEEE Access, 2020, 8: 4806-4813.