Due to the uncertain nonlinear dynamics and the coupling motions of the longitudinal and lateral axes, the attitude control of flying-wing vehicles presents significant challenges. Proportional-Integral-Derivative (PID) control with gain scheduling relies on small disturbance linearization theory, which limits control performance under substantial nonlinear behavior. Nonlinear control techniques, such as Model Predictive Control (MPC) and Nonlinear Dynamic Inversion (NDI), are heavily dependent on accurate models, and their robustness diminishes when aerodynamic models are mismatched. To address these limitations, this paper proposes an attitude control algorithm based on Deep Reinforcement Learning (DRL), which considers the coupling of lateral and longitudinal motions as well as airspeed. The algorithm establishes a clear mapping between ’State-Action-Reward’ by utilizing an error-related state space. The proposed algorithm significantly enhances training efficiency and test success rates compared to DRL algorithms that incorporate attitude angle. Furthermore, it introduces physical constraints on the control surface deflection and an additional loss function term, resulting in smooth actuation signals and attitude responses. In simulated environments, the algorithm was compared with other state-of-the-art algorithms, and the results demonstrate its strong robustness in the presence of severe turbulence disturbances and model uncertainties. The algorithm is also assessed through real vehicle experiments, which fully corroborate its effectiveness.

Robotic micromanipulation technology plays a fundamental supporting role in biomedical engineering field. However, it is still a challenge for robotic manipulators to meet the puncture performance requirements for complex cells and curved vessels with different sizes, because they are difficult to achieve a comprehensive characteristic of multi-DOF, long stroke, high displacement resolution, large puncture force, and high force resolution for limitations of structures, driving elements, and actuation methods. To addresses this challenge, this article proposes the conceptual design of a piezoelectric robotic manipulator (PERM) driven by a single piezoelectric actuator. A configuration design idea and a new actuation method are elaborated to achieve 2-DOF cross-scale manipulation and adjustable puncture force. Theoretical analyses and simulations are carried out to investigate the influence of key structural parameters on displacement response and puncture force, as well as to determine the parameters. A prototype is fabricated, a dedicated handheld controller is developed, and a robotic micropuncture system is constructed to conduct characteristic testing and application research. Experimental results reveal that the manipulator achieves linear and rotary strokes of 38.5 mm and 360°, displacement resolutions of 48 nm and 0.38μrad, a puncture force range from 1.70 to 301.34 mN, and a force resolution of 0.13 mN. Additionally, the manipulator successfully performs delicate puncture of silicone capillaries with different sizes and a curved silicone capillary under collaborative manipulation of the piezoelectric platform. This article exhibits a high-performance PERM and verifies its feasibility in micropuncture of tiny and complex-shaped organisms.