This document describes road modeling with an integrated Gaussian process. The road is modeled at a first time using at least one Gaussian process regression (GPR). A kernel function is determined based on a detected sample set received from one or more vehicle systems. Based on the kernel function, a respective average lateral position associated with the particular longitudinal position is determined for each of the at least one GPR. The respective average lateral position of each of the at least one GPR is aggregated to determine a combined lateral position associated with the particular longitudinal position. A road model including the combined lateral positions associated with the particular longitudinal position is then output. In this manner, a robust and computationally efficient road model may be determined to help improve the safety and performance of the vehicle.
本文档描述了具有集成高斯过程的道路建模。使用至少一个高斯过程回归(GPR)在第一时刻对道路进行建模。基于从一个或多个交通工具系统接收的检测的样本集来确定核函数。基于核函数,为至少一个GPR中的每一个GPR确定与特定纵向位置相关联的相应平均横向位置。聚合至少一个GPR中的每一个GPR的相应平均横向位置,以确定与特定纵向位置相关联的组合横向位置。然后输出包括与特定纵向位置相关联的组合横向位置的道路模型。以此方式,可以确定鲁棒且计算高效的道路模型,以有助于提高交通工具的安全性和性能。
Road modeling with integrated Gaussian process
具有集成高斯过程的道路建模
2023-06-27
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 / G01S RADIO DIRECTION-FINDING , Funkpeilung / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung |
AIAA-2003-6761 Gaussian Process Meta-Modeling: Comparison of Gaussian Process Training Methods
British Library Conference Proceedings | 2003
|