Abstract: With the rapid implementation of high-level autonomous driving technology, intelligent connected vehicles (ICV) face core pain points in complex urban traffic environments, such as limited perception range of single vehicle, insufficient blind area coverage, weak prediction ability of dynamic traffic risks, and poor robustness of path decision-making in extreme scenarios, which seriously restrict the large-scale application of high-level autonomous driving. Aiming at the above problems, this paper proposes a unmanned aerial vehicle (UAV) collaborative perception and path decision-making method for intelligent connected vehicles. A complete technical system is formed through integrated environment modeling, multi-objective optimization model construction, and two-layer collaborative algorithm design, and the effectiveness of the method is verified through simulation experiments in medium-density and high-density urban traffic scenarios. The results show that in the single vehicle-single UAV collaborative scenario, compared with the traditional A* algorithm, the improved jump point search (JPS) algorithm proposed in this paper can reduce the path decision-making time by up to 28.32%, improve the global perception coverage by 19.64%, and reduce the comprehensive traffic cost by up to 6.15%. The research effectively makes up for the spatial limitation of single vehicle perception of intelligent connected vehicles, realizes the closed-loop optimization of collaborative perception and path decision-making, can provide theoretical support and technical reference for the implementation of air-ground integrated autonomous driving technology, and has important engineering application value for promoting the in-depth integration of low-altitude economy and intelligent transportation system.

Key words: intelligent connected vehicles; UAV; collaborative perception; path decision-making; improved JPS algorithm; MAPPO algorithm; two-layer optimization model

摘要： 随着高级别自动驾驶技术的快速落地，智能网联汽车（ICV）在城市复杂交通环境中面 临单车感知视距受限、盲区覆盖不足、动态交通风险预判能力弱、极端场景路径决策鲁棒性 差等核心痛点，严重制约了高级别自动驾驶的规模化应用。针对上述问题，文章提出一种面 向智能网联汽车的无人机（UAV）协同感知与路径决策方法，通过一体化环境建模、多目标 优化模型构建、双层协同算法设计形成完整技术体系，并通过中密度与高密度城市交通场景 仿真实验完成方法有效性验证。结果表明：单车-单机协同场景下，所提改进跳点搜索（JPS） 算法较传统 A*算法路径决策时间最高减少 28.32%，全域感知覆盖度提升 19.64%，综合通行 代价最高降低 6.15%。研究有效弥补了智能网联汽车单车感知的空间局限性，实现了协同感 知与路径决策的闭环优化，可为空-地一体化自动驾驶技术落地提供理论支撑与技术参考，对 推动低空经济与智慧交通体系的深度融合具有重要的工程应用价值。

关键词: 智能网联汽车；无人机；协同感知；路径决策；改进 JPS 算法；MAPPO 算法；双层 优化模型