In one embodiment, a system/method generates a driving trajectory for an autonomous driving vehicle (ADV). The system perceives an environment of an autonomous driving vehicle (ADV). The system determines one or more defined conditions based on the perceived environment. The system generates a first trajectory using a neural network model, wherein the neural network model is trained to generate a driving trajectory. The system evaluates/determines whether the first trajectory satisfies one or more defined conditions. If the first trajectory satisfies one or more defined conditions, the system automatically controls the ADV according to the first trajectory. Otherwise, the system automatically controls the ADV according to a second trajectory, where the second trajectory is generated based on an objective function, where the objective function is determined based on at least one or more defined conditions.
在一个实施方式中,系统/方法生成自动驾驶车辆(ADV)的驾驶轨迹。该系统感知自动驾驶车辆(ADV)的环境。该系统基于所感知的环境来确定一个或多个界定条件。该系统使用神经网络模型生成第一轨迹,其中神经网络模型被训练以生成驾驶轨迹。系统评估/确定第一轨迹是否满足一个或多个界定条件。如果第一轨迹满足一个或多个界定条件,则系统根据第一轨迹自动地控制ADV。否则,系统根据第二轨迹自动地控制ADV,其中第二轨迹是基于目标函数生成的,其中目标函数是基于至少一个或多个界定条件确定的。
Hybrid planning system for autonomous vehicle
自动驾驶车辆的混合规划系统
2021-05-25
Patent
Elektronische Ressource
Chinesisch
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |