To address cooperative path planning for multiple UAVs in complex environments, this paper proposes an improved multi-agent deep deterministic policy gradient algorithm, named Prioritized Experience Multi-Agent Deep Deterministic Policy Gradient (PE-MADDPG). An urban low-altitude inspection environment is first constructed within a reinforcement-learning framework, in which dynamic constraints, safety-separation requirements, and formation-cooperation objectives are incorporated into a partially observable Markov decision process. To improve training effectiveness, prioritized experience replay is introduced to increase the utilization of informative samples, an adaptive exploration-noise strategy is designed to regulate exploration intensity, and a multi-head attention mechanism is embedded in the Critic network to enhance the representation of inter-agent interactions. Simulation results in a three-dimensional urban inspection scenario show that PE-MADDPG outperforms the selected benchmark methods in task completion rate, formation maintenance, flight efficiency, and energy consumption. These results provide an effective solution for urban low-altitude inspection tasks.
Zhang et al. (Tue,) studied this question.