Research on UAV (unmanned aerial vehicle) path planning and obstacle avoidance control based on DRL (deep reinforcement learning) still faces limitations, as previous studies primarily utilized current perceptual inputs while neglecting the continuity of flight processes, resulting in low early-stage learning efficiency. To address these issues, this paper integrates DRL with the Transformer architecture to propose the GTrXL-SAC (gated Transformer-XL soft actor critic) algorithm. The algorithm performs positional embedding on multimodal data combining visual and sensor information. Leveraging the self-attention mechanism of GTrXL, it effectively focuses on different segments of multimodal data for encoding while capturing sequential relationships, significantly improving obstacle recognition accuracy and enhancing both learning efficiency and sample efficiency. Additionally, the algorithm capitalizes on GTrXL’s memory characteristics to generate current drone control decisions through the combined analysis of historical experiences and present states, effectively mitigating long-term dependency issues. Experimental results in the AirSim drone simulation environment demonstrate that compared to PPO and SAC algorithms, GTrXL-SAC achieves more precise policy exploration and optimization, enabling superior control of drone velocity and attitude for stabilized flight while accelerating convergence speed by nearly 20%.

The swift growth of the low-altitude economic ecosystem and Unmanned Aerial Vehicle (UAV) swarm applications across diverse sectors presents significant challenges for engineering managers in terms of effective performance evaluation and operational optimization. Traditional evaluation methods often struggle with the inherent complexities, dynamic nature, and multi-faceted performance criteria of UAV swarms. This study introduces a novel Bayesian Network (BN)-based multicriteria decision-making framework that systematically integrates expert intuition with real-time data. By employing variance decomposition, the framework establishes theoretically grounded, bidirectional mapping between expert-assigned weights and the network’s probabilistic parameters, creating a unified model of subjective expertise and objective data. Comprehensive validation demonstrates the framework’s efficacy in identifying critical performance drivers, including environmental awareness, communication ability, and a collaborative decision. Ultimately, our work provides engineering managers with a transparent and adaptive tool, offering actionable insights to inform resource allocation, guide technology adoption, and enhance the overall operational effectiveness of complex UAV swarm systems.

Deep reinforcement learning (DRL) is extensively applied in autonomous unmanned aerial vehicle (UAV) control yet faces critical challenges regarding adaptability and generalization in dynamic environments. To address these limitations, this paper proposes the Meta Gated Transformer-XL Soft Actor-Critic (Meta-GSAC) algorithm. This framework integrates a Gated Transformer-XL module to capture long-term temporal dependencies from multimodal inputs and incorporates the Reptile algorithm to facilitate multi-task meta-learning. Experimental results demonstrate that Meta-GSAC significantly outperforms standard baselines. Notably, it achieves optimal policy convergence with approximately 50% fewer training epochs while effectively eliminating the high-frequency control oscillations observed in the GSAC baseline. Moreover, the proposed method exhibits superior few-shot adaptation capabilities, enabling the UAV to rapidly adapt to novel task scenarios with minimal gradient updates.

The emerging low-altitude economy (LAE), which depends on autonomous Unmanned Aerial Vehicles (UAVs) operations for services from logistics to emergency response, raises a critical question: is the underlying autonomy technology mature enough to support its large-scale deployment? This review answers this question through a comprehensive synthesis of the last decade of research on UAV autonomy. Our central finding is that while individual capabilities have advanced dramatically, the primary bottleneck has shifted from isolated algorithmic performance to the challenge of achieving end-to-end system robustness, safety assurance, and integration. This review is structured along two primary dimensions: (1) the progression of individual capability, from ``Fly Controlled" stability to ``Fly Smart" cognition, and (2) the scalability of autonomy, from single-UAV operations to decentralized swarms. Covering the period from 2015 to 2025, we categorize applications into seven major mission families. Our analysis indicates that while UAV autonomy has achieved substantial algorithmic maturity, reliable large-scale deployment remains constrained by structural challenges in closed-loop robustness, scalability, and real-world variability. Progress toward unlocking the full potential of the low-altitude economy will therefore depend on system-level advances that strengthen reliability under uncertainty and scale.