Two main factors, including regression accuracy and adversarial attack robustness, of six trajectory prediction models are measured in this paper using the traffic flow management system (TFMS) public dataset of fixed-wing aircraft trajectories in a specific route provided by the Federal Aviation Administration. Six data-driven regressors with their desired architectures, from basic conventional to advanced deep learning, are explored in terms of the accuracy and reliability of their predicted trajectories. The main contribution of the paper is that the existence of adversarial samples was characterized for an aircraft trajectory problem, which is recast as a regression task in this paper. In other words, although data-driven algorithms are currently the best regressors, it is shown that they can be attacked by adversarial samples. Adversarial samples are similar to training samples; however, they can cause finely trained regressors to make incorrect predictions, which poses a security concern for learning-based trajectory prediction algorithms. It is shown that although deep-learning-based algorithms (e.g., long short-term memory (LSTM)) have higher regression accuracy with respect to conventional classifiers (e.g., support vector regression (SVR)), they are more sensitive to crafted states, which can be carefully manipulated even to redirect their predicted states towards incorrect states. This fact poses a real security issue for aircraft as adversarial attacks can result in intentional and purposely designed collisions of built-in systems that can include any type of learning-based trajectory predictor.

Accurate aircraft trajectory prediction is fundamental for enhancing air traffic control systems, ensuring a safe and efficient aviation transportation environment. This research presents a detailed study on the efficacy of the Random Forest (RF) methodology for predicting aircraft trajectories. The study compares the RF approach with two established data-driven models, specifically Long Short-Term Memory (LSTM) and Logistic Regression (LR). The investigation utilizes a significant dataset comprising aircraft trajectory time history data, obtained from a UAS-S4 simulator. Experimental results indicate that within a short-term prediction horizon, the RF methodology surpasses both LSTM and LR in trajectory prediction accuracy and also its robustness to overfitting. The research further fine-tunes the performance of the RF methodology by optimizing various hyperparameters, including the number of estimators, features, depth, split, and leaf. Consequently, these results underscore the viability of the RF methodology as a proven alternative to LSTM and LR models for short-term aircraft trajectory prediction.

In tandem with the fast-growing demand for Unmanned Aerial Vehicles (UAVs) for surveillance and reconnaissance, advanced controllers for these critical systems are needed. This paper proposes a flight dynamics controller design that considers various uncertainties for the Hydra Technologies UAS-S4 Ehécatl. In order to be realistic, in addition to flight dynamics nonlinearities, three main sources of uncertainties are considered, as those caused by unknown controller’s parameters, modeling errors, and external disturbances. A Robust adaptive fuzzy logic controller is designed, in charge of nonlinear flight dynamics in presence of a variety of uncertainties. The nonlinear flight dynamics is modeled based on the Takagi-Sugeno method relying on the soft association of local linear models. Since this controller is model-based, an optimal reference model is defined, which is stabilised by the Linear Quadratic Regulator procedure. A fuzzy logic controller is then designed for the nonlinear model. Lastly, with the aim to handle the uncertainties, the gains of the fuzzy controller are reconfigured, and are continuously adjusted by Lyapunov-based robust adaptive laws. The performance of the UAS-S4 Robust adaptive fuzzy logic controller is evaluated in terms of lateral and longitudinal flight dynamics stabilisation, and the reference model state variables tracking under various uncertainties.

The rapid advancement of unmanned aerial systems in various civilian roles necessitates improved safety measures during their operation. A key aspect of enhancing safety is effective collision avoidance, which is based on conflict detection and is greatly aided by accurate trajectory prediction. This paper represents a novel data-driven trajectory prediction methodology based on applying the Long Short-Term Memory (LSTM) prediction algorithm to the UAS-S4 Ehécatl. An LSTM model was designed as the baseline and then developed into a Staked LSTM to better capture complex and hierarchical temporal trajectory patterns. Next, the Bidirectional LSTM was developed for a better understanding of the contextual trajectories from both its past and future data points, and to provide a more comprehensive temporal perspective that could enhance its accuracy. LSTM-based models were evaluated in terms of mean absolute percentage errors. The results reveal the superiority of the Bidirectional LSTM, as it could predict UAS-S4 trajectories more accurately than the Stacked LSTM. Moreover, the developed Bidirectional LSTM was compared with other state-of-the-art deep neural networks aimed at aircraft trajectory prediction. Promising results confirmed that Bidirectional LSTM exhibits the most stable MAPE across all prediction horizons.

This paper presents a methodology for designing a highly reliable Air Traffic Management and Control (ATMC) methodology using Neural Networks and Peer-to-Peer (P2P) blockchain. A novel data-driven algorithm was designed for Aircraft Trajectory Prediction (ATP) based on an Autoencoder architecture. The Autoencoder was considered in this study due to its excellent fault-tolerant ability when the input data provided by the GPS is deficient. After conflict detection, P2P blockchain was used for securely decentralized decision-making. A meta-controller composed of this Autoencoder, and P2P blockchain performed the ATMC task very well. A comprehensive database of trajectories constructed using our UAS-S4 Ehécatl was used for algorithms validation. The accuracy of the ATP was evaluated for a variety of data failures, and the high-performance index confirmed the excellent efficiency of the autoencoder. Aircraft were considered in several local encounter scenarios, and their trajectories were securely managed and controlled using our in-house Smart Contract software developed on the Ethereum platform. The Sharding approach improved the P2P blockchain performance in terms of computational complexity and processing time in real-time operations. Therefore, the probability of conflicts among aircraft in a swarm environment was significantly reduced using our new methodology and algorithm.

This paper introduces a novel and robust data-driven algorithm designed for Aircraft Trajectory Prediction (ATP). The approach employs a Neural Network architecture to predict future aircraft trajectories, utilizing input variables such as latitude, longitude, altitude, heading, speed, and time. The model’s foundation is rooted in the Generative Adversarial Network (GAN) framework, known for its inherent generative capabilities, rendering it remarkably resilient against Adversarial Attacks. To enhance its credibility, the Blockchain is employed as a Ledger Technology (LT) to securely store legitimate predicted values utilized in subsequent trajectory predictions. The Blockchain ensures that only authorized and non-adversarial samples are stored in the blocks, rejecting any adversarial predictions. In the validation process, trajectory data for training the GAN model were generated through the UAS-S4 Ehécatl simulation model. The performance evaluation relies on the model’s resistance to adversarial attacks, measured by fooling rates. The results acquired affirm the excellent efficacy of the GAN model, Secured by Blockchain, approaching against adversarial attacks.