Biomimetics

In recent years, active inference has gained attention in robot control owing to its adaptability to environmental changes. However, its reliance on gradient descent of variational free energy offers no guarantee of convergence to an optimal solution. In this study, we propose an approach that applies a smoothing filter to a pixel-based active inference controller to mitigate the risk of local minima. By smoothing the observed, predicted, and target values, the free energy function becomes smoother, yielding a broader distribution of gradients toward the target, thereby reducing the risk of being trapped in the local minima. In addition, in order to prevent excessive smoothing from eliminating the gradient of the free energy function, we also proposed a method for dynamically adjusting the intensity of smoothing based on prediction and target errors. To evaluate the effectiveness of our method, we applied it to two simulation environments: a simple object-tracking task using a 3-degrees-of-freedom camera, and a robot control task using a 2-degrees-of-freedom robotic arm, and compared it with the conventional active inference controller as a baseline. The experimental results demonstrate that the proposed approach achieves improved convergence performance over the conventional method.

A key limitation of existing swarm intelligence (SI) algorithms for Node Coverage Optimization (NCO) is their inadequate solution accuracy. A novel chaotic quantum-inspired leader honey badger algorithm (CQLHBA) is proposed in this study. To enhance the performance of the basic HBA and better solve the numerical optimization and NCO problem, an adjustment strategy for parameter ${\alpha }_1$ to balance the optimization process of the follower position is used to improve the exploration ability. Moreover, the chaotic dynamic strategy, quantum rotation strategy, and Lévy flight strategy are employed to enhance the overall performance of the designed CQLHBA, especially for the exploitation ability of individuals. The performance of the proposed CQLHBA is verified using twenty-one benchmark functions and compared to that of other state-of-the-art (SOTA) SI algorithms, including the Honey Badger Algorithm (HBA), Chaotic Sea-Horse Optimizer (CSHO), Sine–Cosine Quantum Salp Swarm Algorithm (SCQSSA), Golden Jackal Optimization (GJO), Aquila Optimizer (AO), Butterfly Optimization Algorithm (BOA), Salp Swarm Algorithm (SSA), Grey Wolf Optimizer (GWO), and Randomised Particle Swarm Optimizer (RPSO). The experimental results demonstrate that the proposed CQLHBA exhibits superior performance, characterized by enhanced global search capability and robust stability. This advantage is further validated through its application to the NCO problem in wireless sensor networks (WSNs), where it achieves commendable outcomes in terms of both coverage rate and network connectivity, confirming its practical efficacy in real-world deployment scenarios.

This work presents a first-iteration bio-faithful dragonfly-inspired wing designed for future flapping micro air vehicle (MAV) applications. Using high-resolution imaging, the natural venation pattern of fore- and hindwings was reconstructed in CAD and reproduced through high-precision stereolithography at 1:1 and 3:1 scale. The printed polymeric wings successfully preserved the anisotropic stiffness distribution of the biological structure, enabling realistic bending and torsional responses. Modal analysis and dynamic testing confirmed that the lightweight designs operate within the biologically relevant 20–40 Hz range and that geometry and material choices allow predictable tuning of natural frequencies. Preliminary aerodynamic estimates captured the characteristic anti-phase lift behavior of four-wing flapping, while schlieren and infrared thermography demonstrated that heat dispersion and flow features follow the vein-driven structural pathways of the printed wings. Together, these results validate the feasibility and functional relevance of bio-faithful venation architectures and establish a solid foundation for future iterations incorporating membranes, full kinematic actuation, and higher-fidelity aeroelastic modeling.