Traversing through a tilted narrow gap is previously an intractable task for reinforcement learning mainly due to two challenges. First, searching feasible trajectories is not trivial because the goal behind the gap is difficult to reach. Second, the error tolerance after Sim2Real is low due to the relatively high speed in comparison to the gap's narrow dimensions. This problem is aggravated by the intractability of collecting real-world data due to the risk of collision damage. In this brief, we propose an end-to-end reinforcement learning framework that solves this task successfully by addressing both problems. To search for dynamically feasible flight trajectories, we use a curriculum learning to guide the agent toward the sparse reward behind the obstacle. To tackle the Sim2Real problem, we propose a Sim2Real framework that can transfer control commands to a real quadrotor without using real flight data. To the best of our knowledge, our brief is the first work that accomplishes successful gap traversing task purely using deep reinforcement learning.

The under-canopy environment, which is inherently inaccessible to humans, necessitates the use of unmanned aerial vehicles (UAVs) for data collection. The implementation of UAV autonomous navigation in such environments faces challenges, including dense obstacles, GNSS signal interference, and varying lighting conditions. This paper introduces a UAV autonomous navigation method specifically designed for under-canopy environments. Initially, image enhancement techniques are integrated with neural network-based visual feature extraction. Subsequently, employs a high-dimensional error-state optimizer coupled with a low-dimensional height filter to achieve high-precision localization of the UAV in under-canopy environments. Furthermore, proposes a boundary sampling autonomous exploration algorithm and an advanced Rapidly exploring Random Tree (RRT) path planning algorithm. The objective is to enhance the reliability and safety of UAV operations beneath the forest canopy, thereby establishing a technical foundation for surveying vertically stratified natural resources.

Structural damage induces extensive parameter changes of an aircraft, which leads to the mismatch problem between the offline model and a flying aircraft. Due to extensive parameter changes, motion of a damaged aircraft is difficultly described with a mathematical model. This article uses disturbances in accelerations and angular accelerations to quantify the effects of extensive parameter changes, and derives a mathematical model for a damaged aircraft. Provided that the flight controller of a damaged aircraft has a fixed structure, the mismatch problem may cause the aircraft unstable. Based on the proposed mathematical model, this article proposed a reconfigurable nonlinear dynamic inversion (RNDI) controller for attitude control of a structurally damaged aircraft, which synthesizes a nonlinear disturbance observer (NDO) with a modified nonlinear dynamic inversion (NDI) controller. The NDO is explored to estimate the disturbances in angular accelerations. Afterwards, the estimations are fed into the modified NDI controller realizes control structure reconfiguration. Conventional NDI control law and model reference adaptive control (MRAC) law are compared, and simulation results demonstrate that the proposed RNDI control law is robust to structural damage and possesses satisfactory control performance.

In the field of aviation industry, flush air data sensing (FADS) is an advanced sensor for hypersonic aircraft. However, since the sensor has not been used in engineering practice for a long time, there is still much room for improvement. The main purpose of this paper is to improve the measurement accuracy of FADS from the perspective of fuzzy theory. First, the aerodynamic model of FADS is established based on the knowledge of aerodynamics under supersonic and subsonic conditions. Further, to describe the uncertainty and randomness of redundant signals, normal cloud model, a significant concept in fuzzy theory, is employed. Meanwhile, to reduce the influence of abnormal data on the final measurement accuracy, 3En principle is adopted to preprocess the data. In the process of data fusion using the aggregation operate, a new method of calculating the objective weight vector is derived based on Lagrange multiplier method and simplex evolutionary method of multi-objective programming (MOP). To illustrate the feasibility and validity of the proposed method, two FADS systems with six measurement taps and thirteen taps are adopted, respectively. The experimental results show that for the FADS with six measurement taps, the proposed method can improve the measurement accuracy by 4.55% and reduce the dispersion of data by 61.38%. For the latter, the proposed method can improve the measurement accuracy by 3.43% and reduce the dispersion of data by 50.14%. To further demonstrate the superiority of the proposed method, a detailed comparison with other six widely used methods is carried out.