Aug 2026· Scientific Reports· Vol 16· 0 citations· 111 references
Medicine
TL;DR
Results indicate that combining physical structure with learned residual correction provides a more accurate, physically consistent, and operationally interpretable approach for UAV trajectory forecasting.
Abstract
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.
WA-TD3 is introduced, a data-driven control framework that enables real-time wind disturbance perception and adaptive compensation without dedicated wind sensors, and consistently outperforms state-of-the-art methods on tracking accuracy under strong winds.
Hui-Dong Liu, Jia-Rui Dou, Jiang-Shan Ai et al.· Proceedings of the Thirty-Fi...· 0 citations
Aiming at the difficulties of autonomous trajectory planning for unmanned aerial vehicles (UAVs) in unknown and dynamically uncertain environments, such as insufficient prediction ability, easy falling into local optimum, poor environmental adaptability, and information scarcity caused by passive obstacle avoidance, traditional single-model predictive control is difficult to balance computational efficiency and uncertainty compensation. Therefore, this paper proposes a UAV trajectory planning method based on Model Predictive Control dual-model cooperative control, which organically integrates model predictive control with the exploration-exploitation strategy. The method adopts a dual architecture of nominal model + online learning model: the simplified nominal model ensures real-time solution efficiency, and the online learning model dynamically compensates for unmodeled dynamics and environmental disturbances. By introducing information gain and uncertainty attenuation indicators into the MPC optimization objective, the UAV is guided to actively explore unknown areas, avoid local optimum traps, and achieve a dynamic balance between exploration and exploitation. Simulation verification based on MATLAB and CasAdi toolbox shows that the proposed method can significantly reduce environmental uncertainty, improve trajectory tracking accuracy and active obstacle avoidance ability, and exhibit stronger robustness, decision-making intelligence and flight efficiency in complex unstructured environments.
Yi-Tong Zhang· European Conference on Elect...· 0 citations
Vision-based Unmanned Aerial Vehicles (UAVs) often suffer from navigation failures in dead ends due to limited sensing accuracy and range. To address this challenge, this paper proposes a systematic solution for efficient dead-end prediction and avoidance. The proposed method introduces a lightweight neural network to predict the relative distance and bearing of potential dead ends within the current field of view using RGB-D inputs. These predictions prune a predefined, compact trajectory library, enabling the planner to proactively avoid dead ends while maintaining navigational smoothness. Notably, our approach transfers across real-world scenarios without manual annotation or fine-tuning on real-world data. The system achieves high-frequency replanning at 50 Hz onboard. Extensive simulation benchmarks demonstrate superior performance in success rate, flight time, and trajectory length, and real-world experiments further validate its effectiveness in complex scenarios.
Rui-Bin Zhang, Lun Pan, Zelong Xia et al.· 0 citations
A dynamic path planning method for low-altitude Unmanned Aerial Vehicles (UAVs) tailored for urban inspection missions and constrains the average response latency for high-priority emergency tasks to within 40 s even under 50 concurrent dynamic tasks is proposed.
Changqi Yang, Hongjie Hu, Yi Ai· Drones· 0 citations
We present a learning-based approach to kinodynamic online motion planning for an Unmanned Aerial Vehicle (UAV) operating at a fixed altitude in unknown dynamic environments, where real-time avoidance of both static and dynamic obstacles must be achieved under conditions of extreme partial observability. The UAV is controlled with a single degree of freedom (yaw only), resulting in constrained, nonholonomic motion similar to fixed-wing platforms. The proposed framework integrates a behavior grid map representation with Deep Reinforcement Learning (DRL), using Proximal Policy Optimization (PPO) for stable policy learning in continuous control. The key idea is the co-design of a state representation and control policy that enables reliable navigation using only three low-cost directional range sensors, without reliance on dense sensing modalities such as LiDAR or vision-based systems. The behavior grid map dynamically aggregates sparse measurements into a structured local representation that supports real-time decision-making for obstacle avoidance and target reaching. Extensive simulations across environments of varying sizes and obstacle densities demonstrate that the proposed standard and enhanced methods achieve higher success rates than PPO variants and Model Predictive Control (MPC) (94\% vs. 79--90\% in small-scale high-congestion scenarios, and 83\% vs. 62--71\% in large-scale high-congestion scenarios), while maintaining real-time performance. Real-world experiments across four scenarios further confirm practical feasibility, with consistent target-reaching behaviour and no collisions under the tested conditions.
Mohammad Reza Ranjbar Divkoti, A. Aguiar· 0 citations
Predicting the future trajectories of surrounding vehicles in autonomous driving is important for collision risk assessment and safe ego-vehicle path planning. Conventional neural network-based trajectory predictors typically achieve strong prediction performance by exploiting agent history, dynamic scene graphs, and semantic maps. However, in specific motion regimes such as acceleration, deceleration, and turning, these predictors may fail to reflect physically feasible trajectories. To address this issue, this study proposes a framework that fuses the output of Trajectron++, a neural network-based trajectory predictor, with extended Kalman filter (EKF)-based multiple trajectory candidates at a late stage. On the nuScenes dataset, the proposed method reduces the average displacement error and final displacement error of the Trajectron++ robot baseline by 13.7% and 14.6%, respectively, without modifying the baseline architecture. These results indicate that EKF-based trajectory candidates can effectively complement neural trajectory prediction through learned fusion.
Seong-Jun Kim, Seung-Hyun Kong· Journal of Institute of Cont...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
