A Bibliometric Analysis of Deep Reinforcement Learning in UAV Path Planning

Deep reinforcement learning (DRL) has become an important method in Unmanned Aerial Vehicle(UAV) path planning, but the field still lacks a dedicated bibliometric review that summarizes its publication patterns, intellectual structure, and thematic evolution. This study analyzes 1402 Web of Science publications from 2010 to 2025 using CiteSpace, VOSviewer, and the Bibliometrix R package. Three main findings are reported. First, the bibliometric evidence suggests a four-phase evolution of the field—foundational exploration (2015–2016), continuous-control breakthrough (2017–2019), multi-agent collaborative coordination (2020–2022), and complex-scenario integration (2023–2025)—as reflected in publication trends, keyword bursts, and co-citation clusters. Second, co-citation and keyword analyses indicate a gradual shift from geometric navigation toward the joint consideration of communication, energy, and mission objectives, a pattern also reflected in the prominence of Internet of Things (IoT) and vehicular-technology journals. Third, burst and clustering results highlight several active research directions, including multi-objective cooperative decision-making, hierarchical planning architectures that combine global perception with local control, and communication–energy co-design. Rather than offering prescriptive conclusions, these results provide descriptive bibliometric evidence that may help researchers understand the development and emerging priorities of DRL-based UAV path planning.