Autonomous navigation of UAV in complex environment : a deep reinforcement learning method based on temporal attention

With the increasing demand for Unmanned Aerial Vehicles (UAVs) in both military and civil applications, the ability for UAVs to automatically avoid obstacles and navigate to specific destinations has been receiving growing attention. However, most current methods focus on environments where global information is available or both destination and obstacles are static, which are not suitable for dense, dynamic, complex real-time tasks. Therefore, we propose a novel autonomous navigation method based on Deep Reinforcement Learning (DRL), which is suitable for more complex environments. Based on the Soft Actor-Critic (SAC) algorithm, this method incorporates changes of the state space into network input with a temporal attention mechanism, which allows UAVs to adaptively extract key information from historical environments while maintaining sensitivity to the current environment. We establish a visualized two-dimensional navigation task environment and design different simulation tests to evaluate its the performance and generalization. Results show that compared to baselines, our algorithm can achieve higher average rewards and more stable convergence after training in a static multi-obstacle environment, and can demonstrate better performance in environments featuring multiple obstacles of varying numbers, sizes, and speeds, thereby achieving a balance between task completion efficiency and security.