针对自动驾驶汽车在双向单车道下的掉头场景，采用模糊推理提出了一种安全决策方法并基于车辆空间分布关系建立掉头数学模型，确定7个关键控制点，改进粒子群算法的搜索策略，并提出一种高效舒适的掉头轨迹规划方法。安全决策方法首先将掉头时本车道和目标车道上的车辆与自车的相对距离和转向时最小安全距离的差值建立隶属关系，选择安全性更高的时刻进行掉头；轨迹规划方法结合车辆空间分布特征，改进粒子群算法的约束，提出一种新的搜索策略，使其能够快速收敛到最优极值，规划出掉头的最优路径。研究表明：所提出的决策与轨迹规划方法可以安全、高效地完成掉头。

Aiming at the U-turn scenario of autonomous vehicles in two-way single lanes, a safety decision-making method was proposed by fuzzy reasoning, and a U-turn mathematical model was established based on the spatial distribution relationship of vehicles, seven key control points were determined, the search strategy of particle swarm optimization was improved, and an efficient and comfortable U-turn trajectory planning method was proposed. The safety decision-making method firstly establishes a membership relationship between the relative distance between the vehicle and the vehicle on the target lane and the minimum safety distance during steering when making a U-turn, and selects the time with higher safety to make a U-turn. The trajectory planning method combines the spatial distribution characteristics of vehicles, improves the constraints of particle swarm optimization, and proposes a new search strategy, which can quickly converge to the optimal extreme value and plan the optimal path of U-turn. The results show that the proposed decision-making and trajectory planning methods can complete the U-turn safely and efficiently.