An Integrated Strategy for Intelligent Evasion and Navigation of Unmanned Aerial Vehicles in Multi-Obstacle Environments

To enhance the navigation accuracy and obstacle avoidance capability of Unmanned Aerial Vehicles (UAVs) operating in dynamic multi-obstacle environments, this paper proposes an intelligent navigation and avoidance strategy based on deep reinforcement learning. First, a performance index is formulated by integrating miss distances from multiple obstacles with energy consumption. An optimal avoidance strategy is then derived as an expert policy through a solution of the Riccati equation. Subsequently, a Markov Decision Process (MDP) model is constructed for UAV navigation and obstacle avoidance, incorporating a multi-objective reward function that simultaneously optimizes avoidance success rate, navigation accuracy, and energy efficiency. Furthermore, a hybrid learning architecture combining Generative Adversarial Imitation Learning (GAIL) with Proximal Policy Optimization (PPO) is designed and trained. Simulation results demonstrate that the proposed method achieves high training efficiency and enables robust decision-making in complex navigation scenarios.