The invention relates to a method (100) for training a behavioral planner (3) for an at least partially automated driving target vehicle (2) on the basis of kinematic and/or dynamic observation data (4), said observation data being recorded during at least one test travel performed with a test vehicle (1). The method comprises the following steps: identifying (110) at least one driving maneuver (5) from the observation data (4), the driving maneuver (5) switching the test vehicle (1) from an initial state (5a) to a final state (5b); determining (120) a maneuver termination time (6) when the test vehicle (1) reaches the final state (5b); invoking (130) a maneuver duration (8) required by the target vehicle (2) for performing the identified driving maneuver (5) from a kinetic model (7) of the target vehicle (2); marking (140) observation data (4) with the identified driving maneuver (5) from a time interval, the end of which is given by a maneuver end time (6) and the start of which is earlier than the maneuver end time (6) by the maneuver duration (8); the behavioral planner (3) is trained (150) with the marked observation data (4) in view of mapping observation data (4) indicative of a state of the target vehicle (2) to at least one driving maneuver (5) to be performed.
一种基于运动学和/或动力学的观察数据(4)训练针对至少部分自动化行驶的目标车辆(2)的行为规划器(3)的方法(100),其中所述观察数据是在以测试车辆(1)进行的至少一次测试行驶的期间所记录的,所述方法具有如下步骤:从所述观察数据(4)中标识出(110)至少一个驾驶机动动作(5),所述驾驶机动动作(5)将所述测试车辆(1)从初始状态(5a)转换到最终状态(5b);确定(120)所述测试车辆(1)达到所述最终状态(5b)时的机动动作终止时间点(6);从所述目标车辆(2)的动力学模型(7)中调用(130)所述目标车辆(2)为了执行所标识的驾驶机动动作(5)所需的机动动作持续时间(8);以所标识的驾驶机动动作(5)来标记(140)来自如下时间间隔的观察数据(4),所述时间间隔的结束由机动动作终止时间点(6)给出并且其开始比所述机动动作终止时间点(6)要早出所述机动动作持续时间(8)那么长;用经标记的观察数据(4)鉴于如下方面训练(150)所述行为规划器(3):将指示所述目标车辆(2)的状态的观察数据(4)映射到要执行的至少一个驾驶机动动作(5)。
Dynamically dependent behavioral planning for at least partially automated driving vehicle
针对至少部分自动化行驶的车辆的与动力学有关的行为规划
2023-08-04
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 |
Dynamics-Dependent Behavioral Planning for at least Partially Self-Driving Vehicles
European Patent Office | 2024
|Selecting driving maneuver for at least partially automated driving vehicle
European Patent Office | 2023
|European Patent Office | 2024
|European Patent Office | 2024
|Method for at least partially automated driving in a vehicle
European Patent Office | 2019
|