PPO Based Deep Reinforcement Learning Control of Unmanned Aerial Vehicles

To enhance the autonomous target tracking and control capability of unmanned aerial vehicles (UAVs) in complex dynamic environments, this paper proposes a control strategy based on deep reinforcement learning. The target tracking task is modeled as a Markov Decision Process (MDP), in which the state space, action space, and reward function are carefully designed. A deep reinforcement learning algorithm is employed to train the control policy, and its performance is validated in a simulation environment. Experimental results demonstrate that the proposed method can achieve stable target tracking and obstacle avoidance under different initial positions and target motion patterns, while exhibiting good generalization capability.