In recent decades, deep learning (DL) has become a rapidly growing research direction, redefining the state-of-the-art performances in a wide range of techniques, such as object detection and speech recognition. In the aircraft design, dynamics, and control field, many works hinge on the information-rich data-driven approach, which includes the fusion-based prognostic and health management, the airliner's flight safety monitoring, intelligent sensing, and flight control systems development. While DL provides great potentials to solve these data-driven problems, a systematic review and discussion as to how the DL has been/can be used for these problems are still missing in relation to the rapidly developing and widely used DL techniques. In this article, we aim to address this urgent issue to provide a timely overview of the state-of-the-art for applying DL to the aircraft design, dynamics, and control field. In particular, we briefly introduce five representative DL methods, i.e., deep neural network, deep autoencoder, deep belief network, convolutional neural network, and recurrent neural network. Mathematical definitions for each method are presented, and illustrative applications are also discussed. We then review the existing DL-based works that have appeared in the aircraft design, dynamics, and control field. The review efforts are divided into two major groups, i.e., the own-ship aircraft modeling, wherein the works have been/can be implemented online for the aircraft design/dynamics/control, and other airplanes research works, wherein DL-based schemes provide offline monitoring of the aircraft operation. We then summarize the data sources and DL architectures. Referring to the experiences of DL research works/techniques development in other related fields, future opportunities, challenges, and potential solutions for implementing DL in the aircraft design, dynamics, and control field are also discussed.

In recent years, unmanned aerial vehicles (UAV) have been increasingly used in power line inspections. Birds often nest on transmission line towers, which threatens safe power line operation. The existing research on bird’s nest inspection using UAVs mainly stays at the level of image postprocessing detection, which has poor real-time performance and cannot obtain timely bird’s nest detection results. Considering the above shortcomings, we designed a power inspection UAV system based on deep learning technology for autonomous flight, positioning and photography, real-time bird nest detection, and result export. In this research, 2000 bird’s nest images in the actual power inspection environment were shot and collected to create the dataset. The parameter optimization and test comparison for bird’s nest detection are based on the three target detection models of YOLOv3, YOLOv5-s, and YOLOX-s. A YOLOv5-s bird’s nest detection model optimized for bird’s nest real-time detection is proposed, and it is deployed to the onboard computer for real-time detection and verification during flight. The DJI M300 RTK UAV was used to conduct a test flight in a natural power inspection environment. The test results show that the mAP of the UAV system designed in this paper for bird’s nest detection is 92.1%, and the real-time detection frame rate is 33.9 FPS. Compared with the previous research results, this paper proposes a new practice of using drones for bird’s nest detection, dramatically improving the real-time accuracy of bird’s nest detection. The UAV system can efficiently complete the task of bird’s nest detection in the process of electric power inspection, which can significantly reduce manpower consumption in the power inspection process.

Compared with traditional model-based fault detection and classification (FDC) methods, deep neural networks (DNN) prove to be more accurate for the aerospace sensors FDC problems. A concept known as imagefication-based intelligent FDC has been studied in recent years. This concept advocates to stack the sensors measurement data into an image format, the sensors FDC issue is transformed to abnormal regions detection problems on the stacked image. Although promising advances have been claimed, due to low size of the stacked image, small convolutional kernels and shallow DNN layers were used, the FDC performances were hindered. In this paper, we propose a data augmentation method which inflates the stacked image to a larger size (corresponding to the VGG16 object detection net in the machine vision realm). The FDC neural network is then trained via fine-tuning the VGG16. To compress the net size, layered channel pruning algorithm evaluates the importance of the convolutional filters enclosed in the net, channel pruning with knowledge distillation algorithm is then implemented, which yields a more lightweight FDC neural network. The fusion of Gradient-weighted Class Activation Mapping (Grad-CAM) and SHapley Additive exPlanations (SHAP) methods are adopted for explainability analysis of the FDC net, which clarifies its internal mathematical operations both locally (e.g. convolutions) and globally (e.g. deep Shaley values). Via data augmentation, fine-tuning from VGG16, and pruning, the FDC net developed in this paper claims an accuracy of 98.99% across 4 aircraft at 5 flight conditions. We also deploy the FDC net on real data from the flight of a model airplane, which claims an accuracy of 98.44%. Both high accuracy and explainability analysis presented in this paper justifies the efficacy of the proposed scheme.

The Autonomous Air Combat technique has been a lasting research topic for decades. However, no complete solutions seem to have appeared because of the highly dynamic and complex nature of the Autonomous Air Combat problem. In devising the Autonomous Air Combat solutions, we follow similar methodologies in the robotics community, and divide the overall scheme into two folds: the perception of other (enemy/friendly) aircraft, and the guidance/control for own aircraft. While the perception in the first fold serves as a foundation, this paper is mainly focused on the second one. Based on our survey, a review of own aircraft guidance/control in the (primarily one-to-one) Autonomous Air Combat solutions is presented. We divide different Autonomous Air Combat solutions into three groups, i.e. mathematics-based, knowledge-encoded, and learning-driven. In each group, we present the representative methods first; problem definition, solution, and a brief overview of the historical development are illustrated. We also comment on both weakness and strengths for each group/method. We point out certain technical paths/challenges that need to be addressed in the future Autonomous Air Combat development, i.e. to abstract and emulate the human pilot experiences, and to develop the online learning capabilites. Inspired by the state-of-art techniques in other similar fields (robotics, autonomous driving), we also propose potential solutions, i.e. traditional approaches enhanced by the novel data-driven technique. Via this paper, we hope to deliver an in-depth analysis of past experiences and potential challenges/solutions for the Autonomous Air Combat technique. We also advocate referring to the approaches/techniques that are utilized in other similar fields in devising the Autonomous Air Combat solutions.

We consider automated vehicles operation in constrained environments, i.e. the automated parking (AP). The core of AP is formulated as a path planning problem, and Rapidly-exploring Randomized Tree (RRT) algorithm is adopted. To improve the baseline RRT, we propose several algorithmic tweaks, i.e. reversed RRT tree growth, direct tree branch connection using Reeds-Shepp curves, and RRT seeds biasing via regulated parking space/vehicle knowledge. We prove that under these tweaks the algorithm is complete and feasible. We then examine its performance (time, success rate, convergence to the optimal path) and scalability (to different parking spaces/vehicles) via batched simulations. We also test it using a real vehicle in a realistic parking environment. The proposed solution presents itself more applicable when compared with other baseline algorithms.

In this paper, we consider the fault-tolerant control problem for aerial vehicles with redundant actuators. The redundant actuator brings difficulty in fault identification and isolation. Active fault-tolerant control is adopted in this paper as it can detect actuator fault. The entire proposed fault-tolerant control algorithm contains a baseline controller, the fault detection and isolation scheme, and the controller reconstruction module. A robust parameter identification method is designed to identify the torque and thrust generated by the actuators. The feasibility of isolating the fault for the redundant actuators is analyzed through mathematical proof. Through the analysis, the practical fault isolation algorithm is also proposed. Two typical aerial vehicles with redundant actuators, an eight-rotor aircraft and a hexa-rotor aircraft, are adopted in numerical simulations to verify the effectiveness of the proposed fault-tolerant control approach.