The invention provides a method and device for controlling a vehicle, electronic equipment, a computer readable storage medium, a computer program product and an unmanned vehicle, relates to the technical field of artificial intelligence such as data processing, trajectory planning and automatic driving, and can be applied to an automatic driving scene. According to one specific embodiment, the method comprises the steps that based on current state information between a target vehicle and traffic participants of the target vehicle, the interaction process between the target vehicle and the traffic participants is simulated and deduced, an initial part of a cooperative game tree is obtained, and a root node in the initial part corresponds to the current state information; in response to existence of a target leaf node capable of expanding a target child node in the initial part, updating each node on a deduction path from the root node to the child node on the basis of path parameters of an updated prediction trajectory obtained by processing the prediction trajectory from the root node to the target child node by using an iterative linear quadratic regulator algorithm, a complete cooperative game tree composed of the initial part and the target child nodes is obtained; and determining a first control instruction of the target vehicle by using the complete cooperative game tree so as to control the target vehicle by using the first control instruction. Therefore, not only can the decision-making efficiency in the vehicle control process be improved, but also the trajectory planning can be carried out in a smoother and more quality manner, and the control quality of the vehicle is improved.
本公开提供了控制车辆的方法、装置、电子设备、计算机可读存储介质、计算机程序产品和无人车,涉及数据处理、轨迹规划、自动驾驶等人工智能技术领域,可应用于自动驾驶场景下。该方法的一具体实施方式包括:基于目标车辆和目标车辆的交通参与者之间的当前状态信息,模拟推演目标车辆和交通参与者之间的交互过程,得到合作博弈树的初始部分,初始部分中的根节点对应于当前状态信息;响应于初始部分中存在能够扩展出目标子节点的目标叶节点,基于利用迭代线性二次调节器算法处理从根节点至目标子节点的预测轨迹得到的更新预测轨迹的路径参数,更新根节点至子节点的推演路径上的各个节点,得到由初始部分和目标子节点组成完整的合作博弈树;利用完整的合作博弈树,确定目标车辆的第一控制指令,以利用第一控制指令控制目标车辆。由此,不仅能够提升车辆控制过程中的决策效率,还能够更为平滑、更有质量地进行轨迹规划,提升车辆的控制质量。
METHOD FOR CONTROLLING A VEHICLE, RELATED DEVICE, COMPUTER PROGRAM PRODUCT AND UNMANNED VEHICLE
控制车辆的方法、相关装置、计算机程序产品及无人车
2024-10-22
Patent
Electronic Resource
Chinese
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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
European Patent Office | 2021
|European Patent Office | 2019
|METHOD FOR CONTROLLING A VEHICLE, CONTROL DEVICE, COMPUTER PROGRAM PRODUCT AND VEHICLE
European Patent Office | 2024
|METHOD FOR CONTROLLING A VEHICLE, CONTROL DEVICE, COMPUTER PROGRAM PRODUCT, AND VEHICLE
European Patent Office | 2024
|UNMANNED VEHICLE, SYSTEM OF CONTROLLING UNMANNED VEHICLE, AND METHOD OF CONTROLLING UNMANNED VEHICLE
European Patent Office | 2023
|