Consensus-based path planning for UAV swarms under multiple constraints: A review

Abstract

UAV swarms are essential for emergency response, logistics, reconnaissance, and environmental monitoring, yet achieving safe and scalable path planning under dynamic conditions and complex constraints remains challenging. Unlike existing surveys that categorize algorithms by theoretical foundations, this paper systematically reviews UAV swarm path planning through the lens of spatial, temporal, and task-level consistency constraints. We classify recent advances into classical path search, intelligent optimization, and deep reinforcement learning, emphasizing how each addresses geometric continuity, behavioral coordination, and full-chain perception–decision–planning consistency under multi-constraint coupling. We further identify critical limitations in scalability, dynamic adaptability, and heterogeneous swarm cooperation, and outline future directions, including distributed control, multi-source perception fusion, cross‑platform collaboration, and robust autonomous decision-making. This review provides a unique, application‑centric taxonomy based on consensus constraints, offering actionable insights for developing consistency-aware UAV swarm path planning technologies.