Comparative analysis reveals that no single technical route can fully address the coupled challenges of uncertainty, accuracy, and real-time performance, underscoring that hybrid frameworks are essential for balancing these competing requirements.
Abstract
High-speed Unmanned Aerial Vehicles (UAVs), characterized by high velocity and maneuverability, represent critical strategic threats within the aerospace security domain. Accurate trajectory prediction is a fundamental prerequisite for effective early warning and decision-making in defense. Despite increasing research in the domain, model-, data-, and hybrid-driven methods have not yet been comprehensively examined under a unified framework, limiting the understanding of their relative strengths and applicability. To address this gap, this paper systematically reviews the evolution and current technical status of these paradigms, categorized by the core logic underlying prediction methods. The principles and applicability limits of physical process modeling and state estimation algorithms are analyzed, along with emerging applications of machine learning and deep learning for trajectory feature extraction and pattern recognition. State-of-the-art architectures involving the integration of physical constraints and data-driven learning are discussed. Standard evaluation metrics are introduced to facilitate performance benchmarking of existing methods. Comparative analysis reveals that no single technical route can fully address the coupled challenges of uncertainty, accuracy, and real-time performance, underscoring that hybrid frameworks are essential for balancing these competing requirements. Lastly, key challenges are summarized, and future research directions are outlined to advance trajectory prediction methodologies. The provided insights can inform method selection and promote the development of high-accuracy prediction systems.
Reliable and accurate trajectory prediction is critical for the safe and efficient operation of unmanned aerial vehicles (UAVs) in complex urban environments, where flight dynamics are subject to wind disturbances, dense obstacle fields, and strongly phase-dependent behavior. Conventional physics-based approaches are limited by parameter uncertainty, simplifying assumptions, and unmodeled disturbances, while data-driven models may lack physical plausibility and robustness across different flight phases. To address these limitations, this paper proposes a physics-guided hybrid residual-correction framework for UAV trajectory prediction. The approach combines a physics-based model with a data-driven sequence model and learns a residual correction that compensates for the deviation between analytical prediction and observed flight behavior. In addition, the model is trained with physics-guided feasibility regularization to promote realistic speed, acceleration, jerk, and landing descent behavior. Experimental evaluation on a real-world test set shows that the proposed method yields improved results relative to the stand-alone physics model, the LSTM model, and an MLP-based fusion model across all major metrics, including RMSE, MAE, ADE, and FDE. Phase-wise analysis further demonstrates strong improvements in cruise and landing, while highlighting takeoff as the most challenging phase. The results indicate that combining physical structure with learned residual correction provides a more accurate, physically consistent, and operationally interpretable approach for UAV trajectory forecasting.
Md Ashraful Islam, Stanley Förster, Tianxiong Zhang et al.· Scientific Reports· 0 citations
Flight safety is undoubtedly the core consideration in the trajectory planning of unmanned aerial vehicles (UAVs) during military missions. In light of this, how to comprehensively integrate flight data such as trajectory and flight speed, as well as the characteristics and performance of detectors in the mission environment, to accurately quantify the flight safety of UAVs has become an urgent, fundamental, and critical issue to be addressed. This study innovatively proposes the concept of "flight exposure risk". Based on an in-depth analysis of the potential risk sources during UAV flight, this study constructs a mathematical model for UAV flight exposure risk assessment by combining key parameters such as detection angles and distances in directed sensor networks. Subsequently, this study employs curve integral techniques to provide a clear mathematical definition of UAV flight exposure risk from the perspective of trajectory and flight speed. Finally, from the perspective of numerical calculation and algorithm implementation, this study puts forward a set of specific methods for UAV flight exposure risk assessment. The research results indicate that this method can effectively evaluate the risk of UAVs being detected or interfered with by the enemy during mission execution, providing solid and precise data support for trajectory planning in military missions such as low-altitude reconnaissance and high-value supply delivery. Notably, the proposed flight exposure risk index is designed for relative comparison of UAV detectability across different trajectories, rather than representing an exact enemy detection probability; it also differs from traditional minimum exposure-path models and low-altitude risk assessment models by integrating both trajectory spatial features and flight speed.
Yuan-Wen Chen, Wei Xu, Shuang-Chao Xu et al.· International Conference on...· 0 citations
With the rapid advancement of autonomous flight technology, there is an increasing demand for higher precision and advanced navigation techniques, with permissible distance errors often restricted to a few meters. Furthermore, the ubiquitous deployment of Unmanned Aerial Vehicles (UAVs) necessitates the integration of novel technologies to ensure operational continuity under adverse conditions, such as environmental signal interference, hostile attacks, or traversal through zones of complete signal loss. This study presents a methodology to address these challenges, enabling themaintenance of coordinates and navigation for UAVs to traverse jammed or completely out-of-coverage zones, thereby avoiding the need for emergency landings or Return-to-Home (RTH) protocols common in current UAV systems. The proposed approach leverages the TransGAN model, a framework typically employed for data analysis comprising a Generator and a Discriminator. In this context, the model processes sequential real-world coordinate data. Under normal GNSS operation, TransGAN is trained as a high-precision prediction model utilizing velocity and coordinate data as inputs. Conversely, during GNSS outages or interference, the trained TransGAN model is utilized to generate coordinates, thereby maintaining navigation capabilities for the UAV.
Nga Vu Quynh, P. N. Huu, Thanh Han-Trong· IEEE International Conferenc...· 0 citations
Unmanned Aerial Vehicles (UAVs) demonstrated improved response times and safety in life-saving missions. This paper presents a Model Predictive Control (MPC) framework for autonomous UAV search missions in maritime environments, where the UAV must locate multiple castaways floating on the sea surface after a maritime incident. The approach uses receding horizon optimization to plan trajectories that balance two competing objectives: achieving rapid area coverage at high altitudes versus maintaining reliable target detection at lower altitudes. Target detection relies on Convolutional Neural Networks (CNNs), with detection performance characterized through field experiments that measure True Positive (TP) rates and False Positive (FP) rates across multiple flight altitudes. The MPC framework dynamically adjusts the UAV’s altitude and trajectory based on these altitude dependent detection statistics, enabling mission adaptive behavior that outperforms constant-altitude search patterns. Simulation results demonstrate improved search performance compared to conventional constant-altitude missions. Real-world flight experiments validate the practical applicability of the proposed framework and confirm its effectiveness in realistic maritime search scenarios.
Andreas Anastasiou, Savvas Papaioannou, P. Kolios et al.· Journal of Intelligent &...· 0 citations
Unmanned Air Vehicles (UAVs) are becoming increasingly popular and widely used in a variety of industries such as agriculture, construction, delivery, surveillance, rescue operations, mapping, wildlife tracking and many more. With the advancements in technology, UAVs are becoming more autonomous and able to perform tasks with minimal human intervention, rendering their use indispensable for military and law enforcement purposes. In terms of control surfaces, V-tail configurations are commonly used on UAVs due to their advantages in control and stability performance, as well as their ability to reduce drag and improve overall efficiency. However, research on V-tail design and sizing is limited, particularly for Class I mini-UAVs. The objective of this paper is to identify a methodology for the Conceptual and Preliminary sizing and design of a V-tail of a Class I Mini UAV (NATO classification). The methodology follows the design of a V-tail from the characteristics of the conventional tail of the UAV. Once the characteristics of the conventional tail are extracted, V-tail geometric characteristics are computed. The stability derivatives of the V-tail are then calculated. The methodology for the analytical aerodynamic characteristics and stability derivatives is a combination of two existing methodologies: one methodology for V-tail stability and control derivatives, which refers to the Preliminary or Detailed Design of an aircraft, and one methodology for a conventional tail design, which refers to the Conceptual and Preliminary design of an aircraft. With this combination, a V-tail Preliminary design methodology was achieved. Furthermore, the aerodynamic characteristics and stability derivatives of the designed V-tail were verified by Low Fidelity Aerodynamics simulation, and then by High Fidelity Aerodynamics by means of Computational Fluid Dynamics (CFD).
Eleftherios Nikolaou, S. Kilimtzidis, V. Lappas et al.· Aerospace· 0 citations
Unmanned Aerial Vehicle applications are expanding into dense urban airspace, and path planning needs to meet the needs of safe, efficient, and autonomous flight in complex dynamic environments. Traditional path planning methods have high computational complexity, poor real-time performance, and are difficult to deal with uncertainties such as noise and disturbance. Machine learning has become a core research direction. This article builds a three-layer framework of environmental modeling -single-machine decision-making, multi-machine collaboration, and systematically sorts out the key technologies of Unmanned Aerial Vehicle (UAV) path planning-- analytical three-dimensional grid, cylindrical coordinate system spatial modeling, and four-dimensional risk cost model; reviews improved A*, swarm intelligence, biologically inspired neural networks, and other algorithms, and compares performance differences through multi-dimensional matrices. Research shows that third-party risk modeling is the core of low-altitude safety planning, and the integration of biologically inspired neural networks and swarm intelligence can effectively solve complex obstacle avoidance problems. This article points out challenges such as multi-aircraft collaborative obstacle avoidance and distributed low-altitude intelligent connectivity, and looks forward to trends such as synaesthesia and computing integration, embodied intelligence integration, and green energy efficiency optimization, providing technical reference for the safety and engineering implementation of autonomous UAV flight.
Xingran Du, Xi Hong, Min-Rui Li· MATEC Web of Conferences· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
